MilaWang commited on
Commit
ac2d3cb
·
verified ·
1 Parent(s): 1524e61

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +9 -0
  2. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/README.md +202 -0
  3. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/adapter_config.json +29 -0
  4. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/adapter_model.safetensors +3 -0
  5. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/README.md +202 -0
  6. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/adapter_config.json +29 -0
  7. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/adapter_model.safetensors +3 -0
  8. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/optimizer.pt +3 -0
  9. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/rng_state.pth +3 -0
  10. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/scheduler.pt +3 -0
  11. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/special_tokens_map.json +17 -0
  12. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/tokenizer.json +3 -0
  13. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/tokenizer_config.json +2063 -0
  14. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/trainer_state.json +1009 -0
  15. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/training_args.bin +3 -0
  16. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/README.md +202 -0
  17. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/adapter_config.json +29 -0
  18. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/adapter_model.safetensors +3 -0
  19. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/optimizer.pt +3 -0
  20. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/rng_state.pth +3 -0
  21. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/scheduler.pt +3 -0
  22. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/special_tokens_map.json +17 -0
  23. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/tokenizer.json +3 -0
  24. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/tokenizer_config.json +2063 -0
  25. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/trainer_state.json +1339 -0
  26. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/training_args.bin +3 -0
  27. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/README.md +202 -0
  28. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/adapter_config.json +29 -0
  29. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/adapter_model.safetensors +3 -0
  30. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/optimizer.pt +3 -0
  31. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/rng_state.pth +3 -0
  32. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/scheduler.pt +3 -0
  33. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/special_tokens_map.json +17 -0
  34. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/tokenizer.json +3 -0
  35. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/tokenizer_config.json +2063 -0
  36. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/trainer_state.json +1662 -0
  37. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/training_args.bin +3 -0
  38. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/README.md +202 -0
  39. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/adapter_config.json +29 -0
  40. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/adapter_model.safetensors +3 -0
  41. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/optimizer.pt +3 -0
  42. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/rng_state.pth +3 -0
  43. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/scheduler.pt +3 -0
  44. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/special_tokens_map.json +17 -0
  45. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/tokenizer.json +3 -0
  46. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/tokenizer_config.json +2063 -0
  47. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/trainer_state.json +1992 -0
  48. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/training_args.bin +3 -0
  49. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/README.md +202 -0
  50. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/adapter_config.json +29 -0
.gitattributes CHANGED
@@ -2089,3 +2089,12 @@ Qwen2-7B-Instruct_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_
2089
  Qwen2-7B-Instruct_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-225-sd-10000/checkpoint-72/tokenizer.json filter=lfs diff=lfs merge=lfs -text
2090
  Qwen2-7B-Instruct_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-225-sd-10000/checkpoint-9/tokenizer.json filter=lfs diff=lfs merge=lfs -text
2091
  Qwen2-7B-Instruct_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-225-sd-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
2089
  Qwen2-7B-Instruct_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-225-sd-10000/checkpoint-72/tokenizer.json filter=lfs diff=lfs merge=lfs -text
2090
  Qwen2-7B-Instruct_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-225-sd-10000/checkpoint-9/tokenizer.json filter=lfs diff=lfs merge=lfs -text
2091
  Qwen2-7B-Instruct_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-225-sd-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
2092
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/tokenizer.json filter=lfs diff=lfs merge=lfs -text
2093
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/tokenizer.json filter=lfs diff=lfs merge=lfs -text
2094
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/tokenizer.json filter=lfs diff=lfs merge=lfs -text
2095
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/tokenizer.json filter=lfs diff=lfs merge=lfs -text
2096
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/tokenizer.json filter=lfs diff=lfs merge=lfs -text
2097
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3640/tokenizer.json filter=lfs diff=lfs merge=lfs -text
2098
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-455/tokenizer.json filter=lfs diff=lfs merge=lfs -text
2099
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911/tokenizer.json filter=lfs diff=lfs merge=lfs -text
2100
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb322e791bb91edfa9f435335176fce66675400951366ecb3580e7f184b2e398
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0370d7b9368c6e4a44ec9a062b8e3941eb056a3ca1e9c162ce6e31a06ef002ce
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5022f748161d196f77aea55c08c5e004671a01eb1415c4334dc3875a4e0beb56
3
+ size 55532666
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c224adca03133cd86fc326156d5695c4816aff27f44c8391b4ceb4d8d12aec3
3
+ size 14244
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3516b80b38c53efbd35ab603c99be317d10840879de9946e95b7122762d87858
3
+ size 1064
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
+ size 17209961
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/trainer_state.json ADDED
@@ -0,0 +1,1009 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.205152153968811,
3
+ "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911",
4
+ "epoch": 2.9989023051591657,
5
+ "eval_steps": 10,
6
+ "global_step": 1366,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.021953896816684963,
13
+ "grad_norm": 0.6144012212753296,
14
+ "learning_rate": 0.0002,
15
+ "loss": 1.9887,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.043907793633369926,
20
+ "grad_norm": 0.5587220788002014,
21
+ "learning_rate": 0.0002,
22
+ "loss": 1.6882,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06586169045005488,
27
+ "grad_norm": 0.43262454867362976,
28
+ "learning_rate": 0.0002,
29
+ "loss": 1.399,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.08781558726673985,
34
+ "grad_norm": 0.4783053994178772,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.4675,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.10976948408342481,
41
+ "grad_norm": 0.44338956475257874,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.1771,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.13172338090010977,
48
+ "grad_norm": 0.7255092263221741,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.3706,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.15367727771679474,
55
+ "grad_norm": 0.46073833107948303,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.2601,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.1756311745334797,
62
+ "grad_norm": 0.6698123216629028,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.3049,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.19758507135016465,
69
+ "grad_norm": 0.4190150201320648,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.2975,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.21953896816684962,
76
+ "grad_norm": 0.4110015034675598,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.2797,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.2414928649835346,
83
+ "grad_norm": 0.33374306559562683,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.2896,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.26344676180021953,
90
+ "grad_norm": 0.3061307370662689,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.2268,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.2854006586169045,
97
+ "grad_norm": 0.4386885166168213,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.376,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.30735455543358947,
104
+ "grad_norm": 0.40116462111473083,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.1814,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.32930845225027444,
111
+ "grad_norm": 0.5887949466705322,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.2592,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3512623490669594,
118
+ "grad_norm": 0.3401573896408081,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.2372,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.3732162458836443,
125
+ "grad_norm": 0.3288364112377167,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.1901,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.3951701427003293,
132
+ "grad_norm": 0.4853297472000122,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.2335,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.41712403951701427,
139
+ "grad_norm": 2.6253697872161865,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.227,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.43907793633369924,
146
+ "grad_norm": 0.5598543286323547,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.2673,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.4610318331503842,
153
+ "grad_norm": 0.4046548902988434,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.3459,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.4829857299670692,
160
+ "grad_norm": 0.3686952590942383,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.265,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5049396267837541,
167
+ "grad_norm": 0.42458799481391907,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.1364,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5268935236004391,
174
+ "grad_norm": 0.5839895009994507,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.2094,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5488474204171241,
181
+ "grad_norm": 0.408288836479187,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.2073,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.570801317233809,
188
+ "grad_norm": 0.45887550711631775,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.3121,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.5927552140504939,
195
+ "grad_norm": 0.5440235733985901,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.2257,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6147091108671789,
202
+ "grad_norm": 0.3725181519985199,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.1003,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6366630076838639,
209
+ "grad_norm": 0.4309018850326538,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.1538,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6586169045005489,
216
+ "grad_norm": 0.31488674879074097,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.2097,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6805708013172338,
223
+ "grad_norm": 0.34194841980934143,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.1689,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7025246981339188,
230
+ "grad_norm": 0.3407684862613678,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.2579,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7244785949506037,
237
+ "grad_norm": 0.2985728085041046,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.1144,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7464324917672887,
244
+ "grad_norm": 0.42316871881484985,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.2056,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7683863885839737,
251
+ "grad_norm": 0.3124258816242218,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.1753,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.7903402854006586,
258
+ "grad_norm": 0.7727567553520203,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.2547,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8122941822173436,
265
+ "grad_norm": 0.363765686750412,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.124,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8342480790340285,
272
+ "grad_norm": 0.35582536458969116,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.1302,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8562019758507134,
279
+ "grad_norm": 0.31982025504112244,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.1787,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.8781558726673985,
286
+ "grad_norm": 0.34978964924812317,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.2056,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9001097694840834,
293
+ "grad_norm": 0.8346716165542603,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.3577,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9220636663007684,
300
+ "grad_norm": 0.31984028220176697,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.1029,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9440175631174533,
307
+ "grad_norm": 0.32078951597213745,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.0967,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9659714599341384,
314
+ "grad_norm": 0.3417500853538513,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.0936,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.9879253567508233,
321
+ "grad_norm": 0.42359477281570435,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.3412,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.9989023051591658,
328
+ "eval_loss": 1.2201528549194336,
329
+ "eval_runtime": 87.152,
330
+ "eval_samples_per_second": 4.945,
331
+ "eval_steps_per_second": 0.62,
332
+ "step": 455
333
+ },
334
+ {
335
+ "epoch": 1.0098792535675083,
336
+ "grad_norm": 0.37914523482322693,
337
+ "learning_rate": 0.0002,
338
+ "loss": 1.1909,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.031833150384193,
343
+ "grad_norm": 0.43655872344970703,
344
+ "learning_rate": 0.0002,
345
+ "loss": 1.0948,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.0537870472008781,
350
+ "grad_norm": 0.3673796057701111,
351
+ "learning_rate": 0.0002,
352
+ "loss": 1.0873,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.0757409440175631,
357
+ "grad_norm": 0.37673917412757874,
358
+ "learning_rate": 0.0002,
359
+ "loss": 1.0483,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.0976948408342482,
364
+ "grad_norm": 0.2893829345703125,
365
+ "learning_rate": 0.0002,
366
+ "loss": 1.0799,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.119648737650933,
371
+ "grad_norm": 0.5551970601081848,
372
+ "learning_rate": 0.0002,
373
+ "loss": 1.1847,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.141602634467618,
378
+ "grad_norm": 0.442104309797287,
379
+ "learning_rate": 0.0002,
380
+ "loss": 1.0885,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.163556531284303,
385
+ "grad_norm": 0.4035094976425171,
386
+ "learning_rate": 0.0002,
387
+ "loss": 1.1766,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.1855104281009878,
392
+ "grad_norm": 0.47009000182151794,
393
+ "learning_rate": 0.0002,
394
+ "loss": 1.0282,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.2074643249176729,
399
+ "grad_norm": 0.4118749797344208,
400
+ "learning_rate": 0.0002,
401
+ "loss": 1.2625,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.2294182217343579,
406
+ "grad_norm": 0.35173165798187256,
407
+ "learning_rate": 0.0002,
408
+ "loss": 1.0988,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.2513721185510427,
413
+ "grad_norm": 0.7024672031402588,
414
+ "learning_rate": 0.0002,
415
+ "loss": 1.0498,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.2733260153677277,
420
+ "grad_norm": 0.42657527327537537,
421
+ "learning_rate": 0.0002,
422
+ "loss": 1.1339,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.2952799121844127,
427
+ "grad_norm": 0.3815029561519623,
428
+ "learning_rate": 0.0002,
429
+ "loss": 1.0545,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.3172338090010978,
434
+ "grad_norm": 0.7031055688858032,
435
+ "learning_rate": 0.0002,
436
+ "loss": 1.1528,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.3391877058177828,
441
+ "grad_norm": 0.393911212682724,
442
+ "learning_rate": 0.0002,
443
+ "loss": 1.1347,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.3611416026344676,
448
+ "grad_norm": 0.5077702403068542,
449
+ "learning_rate": 0.0002,
450
+ "loss": 1.1901,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.3830954994511526,
455
+ "grad_norm": 2.330033302307129,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.1251,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.4050493962678376,
462
+ "grad_norm": 0.35322949290275574,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.0477,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.4270032930845225,
469
+ "grad_norm": 0.44401052594184875,
470
+ "learning_rate": 0.0002,
471
+ "loss": 1.14,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.4489571899012075,
476
+ "grad_norm": 0.35945481061935425,
477
+ "learning_rate": 0.0002,
478
+ "loss": 1.0318,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.4709110867178925,
483
+ "grad_norm": 0.3058856129646301,
484
+ "learning_rate": 0.0002,
485
+ "loss": 1.1988,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.4928649835345773,
490
+ "grad_norm": 0.7067602872848511,
491
+ "learning_rate": 0.0002,
492
+ "loss": 1.1545,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.5148188803512623,
497
+ "grad_norm": 0.4219357371330261,
498
+ "learning_rate": 0.0002,
499
+ "loss": 1.0925,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.5367727771679474,
504
+ "grad_norm": 0.5970841646194458,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.1622,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.5587266739846322,
511
+ "grad_norm": 0.4381934404373169,
512
+ "learning_rate": 0.0002,
513
+ "loss": 1.0803,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.5806805708013172,
518
+ "grad_norm": 0.4101450443267822,
519
+ "learning_rate": 0.0002,
520
+ "loss": 1.0961,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.6026344676180022,
525
+ "grad_norm": 0.3657490015029907,
526
+ "learning_rate": 0.0002,
527
+ "loss": 1.0474,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.624588364434687,
532
+ "grad_norm": 0.36240628361701965,
533
+ "learning_rate": 0.0002,
534
+ "loss": 1.0936,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.6465422612513723,
539
+ "grad_norm": 0.4103568494319916,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.0489,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.668496158068057,
546
+ "grad_norm": 0.3138505816459656,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.0919,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.690450054884742,
553
+ "grad_norm": 0.41215717792510986,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.2308,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.7124039517014271,
560
+ "grad_norm": 0.4589519202709198,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.1659,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.734357848518112,
567
+ "grad_norm": 0.4049508571624756,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.0913,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.756311745334797,
574
+ "grad_norm": 0.48557212948799133,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.1329,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.778265642151482,
581
+ "grad_norm": 0.5331754088401794,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.0729,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.8002195389681668,
588
+ "grad_norm": 0.3853185772895813,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.1452,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.8221734357848518,
595
+ "grad_norm": 0.424062579870224,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.1061,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.8441273326015368,
602
+ "grad_norm": 0.3418445289134979,
603
+ "learning_rate": 0.0002,
604
+ "loss": 1.1104,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.8660812294182216,
609
+ "grad_norm": 0.4045565128326416,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.0546,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.8880351262349067,
616
+ "grad_norm": 0.42155781388282776,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.1608,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.9099890230515917,
623
+ "grad_norm": 0.40554770827293396,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.0628,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.9319429198682765,
630
+ "grad_norm": 0.42644748091697693,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.1609,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.9538968166849617,
637
+ "grad_norm": 0.45260652899742126,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.1132,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.9758507135016465,
644
+ "grad_norm": 0.4114069938659668,
645
+ "learning_rate": 0.0002,
646
+ "loss": 1.048,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.9978046103183313,
651
+ "grad_norm": 0.375802218914032,
652
+ "learning_rate": 0.0002,
653
+ "loss": 1.1941,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 2.0,
658
+ "eval_loss": 1.205152153968811,
659
+ "eval_runtime": 86.8795,
660
+ "eval_samples_per_second": 4.961,
661
+ "eval_steps_per_second": 0.622,
662
+ "step": 911
663
+ },
664
+ {
665
+ "epoch": 2.0197585071350166,
666
+ "grad_norm": 0.47718703746795654,
667
+ "learning_rate": 0.0002,
668
+ "loss": 1.0897,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.0417124039517014,
673
+ "grad_norm": 0.45628082752227783,
674
+ "learning_rate": 0.0002,
675
+ "loss": 1.0329,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.063666300768386,
680
+ "grad_norm": 0.5933247804641724,
681
+ "learning_rate": 0.0002,
682
+ "loss": 1.0538,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.0856201975850714,
687
+ "grad_norm": 0.5355812907218933,
688
+ "learning_rate": 0.0002,
689
+ "loss": 1.0152,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.1075740944017562,
694
+ "grad_norm": 0.5860010385513306,
695
+ "learning_rate": 0.0002,
696
+ "loss": 1.0726,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.129527991218441,
701
+ "grad_norm": 0.7471673488616943,
702
+ "learning_rate": 0.0002,
703
+ "loss": 1.025,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.1514818880351263,
708
+ "grad_norm": 2.0918211936950684,
709
+ "learning_rate": 0.0002,
710
+ "loss": 1.0247,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.173435784851811,
715
+ "grad_norm": 0.4021058678627014,
716
+ "learning_rate": 0.0002,
717
+ "loss": 0.8947,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.1953896816684964,
722
+ "grad_norm": 0.564975380897522,
723
+ "learning_rate": 0.0002,
724
+ "loss": 0.8875,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.217343578485181,
729
+ "grad_norm": 0.46260079741477966,
730
+ "learning_rate": 0.0002,
731
+ "loss": 1.0264,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.239297475301866,
736
+ "grad_norm": 0.4791034460067749,
737
+ "learning_rate": 0.0002,
738
+ "loss": 0.9265,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.261251372118551,
743
+ "grad_norm": 0.5272043943405151,
744
+ "learning_rate": 0.0002,
745
+ "loss": 0.8869,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.283205268935236,
750
+ "grad_norm": 0.5221094489097595,
751
+ "learning_rate": 0.0002,
752
+ "loss": 1.0007,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.305159165751921,
757
+ "grad_norm": 0.558032751083374,
758
+ "learning_rate": 0.0002,
759
+ "loss": 0.9472,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.327113062568606,
764
+ "grad_norm": 0.5905590653419495,
765
+ "learning_rate": 0.0002,
766
+ "loss": 0.9617,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.349066959385291,
771
+ "grad_norm": 0.5308699607849121,
772
+ "learning_rate": 0.0002,
773
+ "loss": 0.9592,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.3710208562019757,
778
+ "grad_norm": 0.6375027894973755,
779
+ "learning_rate": 0.0002,
780
+ "loss": 1.0646,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.392974753018661,
785
+ "grad_norm": 0.7439115643501282,
786
+ "learning_rate": 0.0002,
787
+ "loss": 1.0354,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.4149286498353457,
792
+ "grad_norm": 0.41945117712020874,
793
+ "learning_rate": 0.0002,
794
+ "loss": 1.0212,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.436882546652031,
799
+ "grad_norm": 0.4891968369483948,
800
+ "learning_rate": 0.0002,
801
+ "loss": 0.9609,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.4588364434687158,
806
+ "grad_norm": 0.4686794579029083,
807
+ "learning_rate": 0.0002,
808
+ "loss": 0.9829,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.4807903402854006,
813
+ "grad_norm": 0.5204509496688843,
814
+ "learning_rate": 0.0002,
815
+ "loss": 0.8919,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.5027442371020854,
820
+ "grad_norm": 0.6779005527496338,
821
+ "learning_rate": 0.0002,
822
+ "loss": 0.8983,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.5246981339187706,
827
+ "grad_norm": 0.682621955871582,
828
+ "learning_rate": 0.0002,
829
+ "loss": 0.9733,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.5466520307354554,
834
+ "grad_norm": 0.5744376182556152,
835
+ "learning_rate": 0.0002,
836
+ "loss": 1.051,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.5686059275521407,
841
+ "grad_norm": 0.49954667687416077,
842
+ "learning_rate": 0.0002,
843
+ "loss": 0.8764,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.5905598243688255,
848
+ "grad_norm": 0.4761793315410614,
849
+ "learning_rate": 0.0002,
850
+ "loss": 0.9896,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.6125137211855103,
855
+ "grad_norm": 0.548299252986908,
856
+ "learning_rate": 0.0002,
857
+ "loss": 0.8593,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.6344676180021955,
862
+ "grad_norm": 0.5771360993385315,
863
+ "learning_rate": 0.0002,
864
+ "loss": 1.0017,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.6564215148188803,
869
+ "grad_norm": 0.5543120503425598,
870
+ "learning_rate": 0.0002,
871
+ "loss": 0.9858,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.6783754116355656,
876
+ "grad_norm": 0.7564870715141296,
877
+ "learning_rate": 0.0002,
878
+ "loss": 0.9565,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.7003293084522504,
883
+ "grad_norm": 0.8222362399101257,
884
+ "learning_rate": 0.0002,
885
+ "loss": 0.9753,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.722283205268935,
890
+ "grad_norm": 0.6894469857215881,
891
+ "learning_rate": 0.0002,
892
+ "loss": 1.0079,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.74423710208562,
897
+ "grad_norm": 0.6121546030044556,
898
+ "learning_rate": 0.0002,
899
+ "loss": 1.0106,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.7661909989023052,
904
+ "grad_norm": 0.521809995174408,
905
+ "learning_rate": 0.0002,
906
+ "loss": 0.9801,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.78814489571899,
911
+ "grad_norm": 0.766968309879303,
912
+ "learning_rate": 0.0002,
913
+ "loss": 1.0196,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.8100987925356753,
918
+ "grad_norm": 0.522331714630127,
919
+ "learning_rate": 0.0002,
920
+ "loss": 0.976,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.83205268935236,
925
+ "grad_norm": 0.42923519015312195,
926
+ "learning_rate": 0.0002,
927
+ "loss": 0.8866,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.854006586169045,
932
+ "grad_norm": 0.47810837626457214,
933
+ "learning_rate": 0.0002,
934
+ "loss": 0.9049,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.8759604829857297,
939
+ "grad_norm": 1.0958846807479858,
940
+ "learning_rate": 0.0002,
941
+ "loss": 1.0291,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.897914379802415,
946
+ "grad_norm": 0.4755791127681732,
947
+ "learning_rate": 0.0002,
948
+ "loss": 0.8724,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.9198682766190998,
953
+ "grad_norm": 0.5575157403945923,
954
+ "learning_rate": 0.0002,
955
+ "loss": 0.9317,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.941822173435785,
960
+ "grad_norm": 0.5938076376914978,
961
+ "learning_rate": 0.0002,
962
+ "loss": 1.0131,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.96377607025247,
967
+ "grad_norm": 0.5751763582229614,
968
+ "learning_rate": 0.0002,
969
+ "loss": 0.9857,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.9857299670691546,
974
+ "grad_norm": 0.5590175986289978,
975
+ "learning_rate": 0.0002,
976
+ "loss": 1.0212,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.9989023051591657,
981
+ "eval_loss": 1.2402944564819336,
982
+ "eval_runtime": 88.822,
983
+ "eval_samples_per_second": 4.852,
984
+ "eval_steps_per_second": 0.608,
985
+ "step": 1366
986
+ }
987
+ ],
988
+ "logging_steps": 10,
989
+ "max_steps": 3640,
990
+ "num_input_tokens_seen": 0,
991
+ "num_train_epochs": 8,
992
+ "save_steps": 200,
993
+ "stateful_callbacks": {
994
+ "TrainerControl": {
995
+ "args": {
996
+ "should_epoch_stop": false,
997
+ "should_evaluate": false,
998
+ "should_log": false,
999
+ "should_save": true,
1000
+ "should_training_stop": false
1001
+ },
1002
+ "attributes": {}
1003
+ }
1004
+ },
1005
+ "total_flos": 6.323856028257485e+16,
1006
+ "train_batch_size": 1,
1007
+ "trial_name": null,
1008
+ "trial_params": null
1009
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1366/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf90ce7dd53cc68edd44d14e30ca84a5d7431a5b99d4697b17af4b2f7ec0abab
3
+ size 5624
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdd662729c18e2ae17e0532c2a10a7225f6b690ab2f68160a3899a37c72638bf
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba4d6429e46fa1c59b2fcd4f3e7db7d2b39e1180a8368b7edf9f299b36574979
3
+ size 55532666
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28426692871cf5cf6b3fcbb7954b695d1a7612f76ad200ab9263813cf45e86d7
3
+ size 14244
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49576c0a7c5058f8291777ab40a303a807766b0e9604129e7e31f02391844f52
3
+ size 1064
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
+ size 17209961
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/trainer_state.json ADDED
@@ -0,0 +1,1339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.205152153968811,
3
+ "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911",
4
+ "epoch": 4.0,
5
+ "eval_steps": 10,
6
+ "global_step": 1822,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.021953896816684963,
13
+ "grad_norm": 0.6144012212753296,
14
+ "learning_rate": 0.0002,
15
+ "loss": 1.9887,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.043907793633369926,
20
+ "grad_norm": 0.5587220788002014,
21
+ "learning_rate": 0.0002,
22
+ "loss": 1.6882,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06586169045005488,
27
+ "grad_norm": 0.43262454867362976,
28
+ "learning_rate": 0.0002,
29
+ "loss": 1.399,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.08781558726673985,
34
+ "grad_norm": 0.4783053994178772,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.4675,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.10976948408342481,
41
+ "grad_norm": 0.44338956475257874,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.1771,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.13172338090010977,
48
+ "grad_norm": 0.7255092263221741,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.3706,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.15367727771679474,
55
+ "grad_norm": 0.46073833107948303,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.2601,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.1756311745334797,
62
+ "grad_norm": 0.6698123216629028,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.3049,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.19758507135016465,
69
+ "grad_norm": 0.4190150201320648,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.2975,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.21953896816684962,
76
+ "grad_norm": 0.4110015034675598,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.2797,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.2414928649835346,
83
+ "grad_norm": 0.33374306559562683,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.2896,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.26344676180021953,
90
+ "grad_norm": 0.3061307370662689,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.2268,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.2854006586169045,
97
+ "grad_norm": 0.4386885166168213,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.376,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.30735455543358947,
104
+ "grad_norm": 0.40116462111473083,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.1814,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.32930845225027444,
111
+ "grad_norm": 0.5887949466705322,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.2592,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3512623490669594,
118
+ "grad_norm": 0.3401573896408081,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.2372,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.3732162458836443,
125
+ "grad_norm": 0.3288364112377167,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.1901,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.3951701427003293,
132
+ "grad_norm": 0.4853297472000122,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.2335,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.41712403951701427,
139
+ "grad_norm": 2.6253697872161865,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.227,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.43907793633369924,
146
+ "grad_norm": 0.5598543286323547,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.2673,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.4610318331503842,
153
+ "grad_norm": 0.4046548902988434,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.3459,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.4829857299670692,
160
+ "grad_norm": 0.3686952590942383,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.265,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5049396267837541,
167
+ "grad_norm": 0.42458799481391907,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.1364,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5268935236004391,
174
+ "grad_norm": 0.5839895009994507,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.2094,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5488474204171241,
181
+ "grad_norm": 0.408288836479187,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.2073,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.570801317233809,
188
+ "grad_norm": 0.45887550711631775,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.3121,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.5927552140504939,
195
+ "grad_norm": 0.5440235733985901,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.2257,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6147091108671789,
202
+ "grad_norm": 0.3725181519985199,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.1003,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6366630076838639,
209
+ "grad_norm": 0.4309018850326538,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.1538,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6586169045005489,
216
+ "grad_norm": 0.31488674879074097,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.2097,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6805708013172338,
223
+ "grad_norm": 0.34194841980934143,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.1689,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7025246981339188,
230
+ "grad_norm": 0.3407684862613678,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.2579,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7244785949506037,
237
+ "grad_norm": 0.2985728085041046,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.1144,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7464324917672887,
244
+ "grad_norm": 0.42316871881484985,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.2056,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7683863885839737,
251
+ "grad_norm": 0.3124258816242218,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.1753,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.7903402854006586,
258
+ "grad_norm": 0.7727567553520203,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.2547,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8122941822173436,
265
+ "grad_norm": 0.363765686750412,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.124,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8342480790340285,
272
+ "grad_norm": 0.35582536458969116,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.1302,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8562019758507134,
279
+ "grad_norm": 0.31982025504112244,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.1787,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.8781558726673985,
286
+ "grad_norm": 0.34978964924812317,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.2056,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9001097694840834,
293
+ "grad_norm": 0.8346716165542603,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.3577,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9220636663007684,
300
+ "grad_norm": 0.31984028220176697,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.1029,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9440175631174533,
307
+ "grad_norm": 0.32078951597213745,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.0967,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9659714599341384,
314
+ "grad_norm": 0.3417500853538513,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.0936,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.9879253567508233,
321
+ "grad_norm": 0.42359477281570435,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.3412,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.9989023051591658,
328
+ "eval_loss": 1.2201528549194336,
329
+ "eval_runtime": 87.152,
330
+ "eval_samples_per_second": 4.945,
331
+ "eval_steps_per_second": 0.62,
332
+ "step": 455
333
+ },
334
+ {
335
+ "epoch": 1.0098792535675083,
336
+ "grad_norm": 0.37914523482322693,
337
+ "learning_rate": 0.0002,
338
+ "loss": 1.1909,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.031833150384193,
343
+ "grad_norm": 0.43655872344970703,
344
+ "learning_rate": 0.0002,
345
+ "loss": 1.0948,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.0537870472008781,
350
+ "grad_norm": 0.3673796057701111,
351
+ "learning_rate": 0.0002,
352
+ "loss": 1.0873,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.0757409440175631,
357
+ "grad_norm": 0.37673917412757874,
358
+ "learning_rate": 0.0002,
359
+ "loss": 1.0483,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.0976948408342482,
364
+ "grad_norm": 0.2893829345703125,
365
+ "learning_rate": 0.0002,
366
+ "loss": 1.0799,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.119648737650933,
371
+ "grad_norm": 0.5551970601081848,
372
+ "learning_rate": 0.0002,
373
+ "loss": 1.1847,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.141602634467618,
378
+ "grad_norm": 0.442104309797287,
379
+ "learning_rate": 0.0002,
380
+ "loss": 1.0885,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.163556531284303,
385
+ "grad_norm": 0.4035094976425171,
386
+ "learning_rate": 0.0002,
387
+ "loss": 1.1766,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.1855104281009878,
392
+ "grad_norm": 0.47009000182151794,
393
+ "learning_rate": 0.0002,
394
+ "loss": 1.0282,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.2074643249176729,
399
+ "grad_norm": 0.4118749797344208,
400
+ "learning_rate": 0.0002,
401
+ "loss": 1.2625,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.2294182217343579,
406
+ "grad_norm": 0.35173165798187256,
407
+ "learning_rate": 0.0002,
408
+ "loss": 1.0988,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.2513721185510427,
413
+ "grad_norm": 0.7024672031402588,
414
+ "learning_rate": 0.0002,
415
+ "loss": 1.0498,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.2733260153677277,
420
+ "grad_norm": 0.42657527327537537,
421
+ "learning_rate": 0.0002,
422
+ "loss": 1.1339,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.2952799121844127,
427
+ "grad_norm": 0.3815029561519623,
428
+ "learning_rate": 0.0002,
429
+ "loss": 1.0545,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.3172338090010978,
434
+ "grad_norm": 0.7031055688858032,
435
+ "learning_rate": 0.0002,
436
+ "loss": 1.1528,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.3391877058177828,
441
+ "grad_norm": 0.393911212682724,
442
+ "learning_rate": 0.0002,
443
+ "loss": 1.1347,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.3611416026344676,
448
+ "grad_norm": 0.5077702403068542,
449
+ "learning_rate": 0.0002,
450
+ "loss": 1.1901,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.3830954994511526,
455
+ "grad_norm": 2.330033302307129,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.1251,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.4050493962678376,
462
+ "grad_norm": 0.35322949290275574,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.0477,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.4270032930845225,
469
+ "grad_norm": 0.44401052594184875,
470
+ "learning_rate": 0.0002,
471
+ "loss": 1.14,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.4489571899012075,
476
+ "grad_norm": 0.35945481061935425,
477
+ "learning_rate": 0.0002,
478
+ "loss": 1.0318,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.4709110867178925,
483
+ "grad_norm": 0.3058856129646301,
484
+ "learning_rate": 0.0002,
485
+ "loss": 1.1988,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.4928649835345773,
490
+ "grad_norm": 0.7067602872848511,
491
+ "learning_rate": 0.0002,
492
+ "loss": 1.1545,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.5148188803512623,
497
+ "grad_norm": 0.4219357371330261,
498
+ "learning_rate": 0.0002,
499
+ "loss": 1.0925,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.5367727771679474,
504
+ "grad_norm": 0.5970841646194458,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.1622,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.5587266739846322,
511
+ "grad_norm": 0.4381934404373169,
512
+ "learning_rate": 0.0002,
513
+ "loss": 1.0803,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.5806805708013172,
518
+ "grad_norm": 0.4101450443267822,
519
+ "learning_rate": 0.0002,
520
+ "loss": 1.0961,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.6026344676180022,
525
+ "grad_norm": 0.3657490015029907,
526
+ "learning_rate": 0.0002,
527
+ "loss": 1.0474,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.624588364434687,
532
+ "grad_norm": 0.36240628361701965,
533
+ "learning_rate": 0.0002,
534
+ "loss": 1.0936,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.6465422612513723,
539
+ "grad_norm": 0.4103568494319916,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.0489,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.668496158068057,
546
+ "grad_norm": 0.3138505816459656,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.0919,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.690450054884742,
553
+ "grad_norm": 0.41215717792510986,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.2308,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.7124039517014271,
560
+ "grad_norm": 0.4589519202709198,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.1659,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.734357848518112,
567
+ "grad_norm": 0.4049508571624756,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.0913,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.756311745334797,
574
+ "grad_norm": 0.48557212948799133,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.1329,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.778265642151482,
581
+ "grad_norm": 0.5331754088401794,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.0729,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.8002195389681668,
588
+ "grad_norm": 0.3853185772895813,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.1452,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.8221734357848518,
595
+ "grad_norm": 0.424062579870224,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.1061,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.8441273326015368,
602
+ "grad_norm": 0.3418445289134979,
603
+ "learning_rate": 0.0002,
604
+ "loss": 1.1104,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.8660812294182216,
609
+ "grad_norm": 0.4045565128326416,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.0546,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.8880351262349067,
616
+ "grad_norm": 0.42155781388282776,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.1608,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.9099890230515917,
623
+ "grad_norm": 0.40554770827293396,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.0628,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.9319429198682765,
630
+ "grad_norm": 0.42644748091697693,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.1609,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.9538968166849617,
637
+ "grad_norm": 0.45260652899742126,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.1132,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.9758507135016465,
644
+ "grad_norm": 0.4114069938659668,
645
+ "learning_rate": 0.0002,
646
+ "loss": 1.048,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.9978046103183313,
651
+ "grad_norm": 0.375802218914032,
652
+ "learning_rate": 0.0002,
653
+ "loss": 1.1941,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 2.0,
658
+ "eval_loss": 1.205152153968811,
659
+ "eval_runtime": 86.8795,
660
+ "eval_samples_per_second": 4.961,
661
+ "eval_steps_per_second": 0.622,
662
+ "step": 911
663
+ },
664
+ {
665
+ "epoch": 2.0197585071350166,
666
+ "grad_norm": 0.47718703746795654,
667
+ "learning_rate": 0.0002,
668
+ "loss": 1.0897,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.0417124039517014,
673
+ "grad_norm": 0.45628082752227783,
674
+ "learning_rate": 0.0002,
675
+ "loss": 1.0329,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.063666300768386,
680
+ "grad_norm": 0.5933247804641724,
681
+ "learning_rate": 0.0002,
682
+ "loss": 1.0538,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.0856201975850714,
687
+ "grad_norm": 0.5355812907218933,
688
+ "learning_rate": 0.0002,
689
+ "loss": 1.0152,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.1075740944017562,
694
+ "grad_norm": 0.5860010385513306,
695
+ "learning_rate": 0.0002,
696
+ "loss": 1.0726,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.129527991218441,
701
+ "grad_norm": 0.7471673488616943,
702
+ "learning_rate": 0.0002,
703
+ "loss": 1.025,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.1514818880351263,
708
+ "grad_norm": 2.0918211936950684,
709
+ "learning_rate": 0.0002,
710
+ "loss": 1.0247,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.173435784851811,
715
+ "grad_norm": 0.4021058678627014,
716
+ "learning_rate": 0.0002,
717
+ "loss": 0.8947,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.1953896816684964,
722
+ "grad_norm": 0.564975380897522,
723
+ "learning_rate": 0.0002,
724
+ "loss": 0.8875,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.217343578485181,
729
+ "grad_norm": 0.46260079741477966,
730
+ "learning_rate": 0.0002,
731
+ "loss": 1.0264,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.239297475301866,
736
+ "grad_norm": 0.4791034460067749,
737
+ "learning_rate": 0.0002,
738
+ "loss": 0.9265,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.261251372118551,
743
+ "grad_norm": 0.5272043943405151,
744
+ "learning_rate": 0.0002,
745
+ "loss": 0.8869,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.283205268935236,
750
+ "grad_norm": 0.5221094489097595,
751
+ "learning_rate": 0.0002,
752
+ "loss": 1.0007,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.305159165751921,
757
+ "grad_norm": 0.558032751083374,
758
+ "learning_rate": 0.0002,
759
+ "loss": 0.9472,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.327113062568606,
764
+ "grad_norm": 0.5905590653419495,
765
+ "learning_rate": 0.0002,
766
+ "loss": 0.9617,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.349066959385291,
771
+ "grad_norm": 0.5308699607849121,
772
+ "learning_rate": 0.0002,
773
+ "loss": 0.9592,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.3710208562019757,
778
+ "grad_norm": 0.6375027894973755,
779
+ "learning_rate": 0.0002,
780
+ "loss": 1.0646,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.392974753018661,
785
+ "grad_norm": 0.7439115643501282,
786
+ "learning_rate": 0.0002,
787
+ "loss": 1.0354,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.4149286498353457,
792
+ "grad_norm": 0.41945117712020874,
793
+ "learning_rate": 0.0002,
794
+ "loss": 1.0212,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.436882546652031,
799
+ "grad_norm": 0.4891968369483948,
800
+ "learning_rate": 0.0002,
801
+ "loss": 0.9609,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.4588364434687158,
806
+ "grad_norm": 0.4686794579029083,
807
+ "learning_rate": 0.0002,
808
+ "loss": 0.9829,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.4807903402854006,
813
+ "grad_norm": 0.5204509496688843,
814
+ "learning_rate": 0.0002,
815
+ "loss": 0.8919,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.5027442371020854,
820
+ "grad_norm": 0.6779005527496338,
821
+ "learning_rate": 0.0002,
822
+ "loss": 0.8983,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.5246981339187706,
827
+ "grad_norm": 0.682621955871582,
828
+ "learning_rate": 0.0002,
829
+ "loss": 0.9733,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.5466520307354554,
834
+ "grad_norm": 0.5744376182556152,
835
+ "learning_rate": 0.0002,
836
+ "loss": 1.051,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.5686059275521407,
841
+ "grad_norm": 0.49954667687416077,
842
+ "learning_rate": 0.0002,
843
+ "loss": 0.8764,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.5905598243688255,
848
+ "grad_norm": 0.4761793315410614,
849
+ "learning_rate": 0.0002,
850
+ "loss": 0.9896,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.6125137211855103,
855
+ "grad_norm": 0.548299252986908,
856
+ "learning_rate": 0.0002,
857
+ "loss": 0.8593,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.6344676180021955,
862
+ "grad_norm": 0.5771360993385315,
863
+ "learning_rate": 0.0002,
864
+ "loss": 1.0017,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.6564215148188803,
869
+ "grad_norm": 0.5543120503425598,
870
+ "learning_rate": 0.0002,
871
+ "loss": 0.9858,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.6783754116355656,
876
+ "grad_norm": 0.7564870715141296,
877
+ "learning_rate": 0.0002,
878
+ "loss": 0.9565,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.7003293084522504,
883
+ "grad_norm": 0.8222362399101257,
884
+ "learning_rate": 0.0002,
885
+ "loss": 0.9753,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.722283205268935,
890
+ "grad_norm": 0.6894469857215881,
891
+ "learning_rate": 0.0002,
892
+ "loss": 1.0079,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.74423710208562,
897
+ "grad_norm": 0.6121546030044556,
898
+ "learning_rate": 0.0002,
899
+ "loss": 1.0106,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.7661909989023052,
904
+ "grad_norm": 0.521809995174408,
905
+ "learning_rate": 0.0002,
906
+ "loss": 0.9801,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.78814489571899,
911
+ "grad_norm": 0.766968309879303,
912
+ "learning_rate": 0.0002,
913
+ "loss": 1.0196,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.8100987925356753,
918
+ "grad_norm": 0.522331714630127,
919
+ "learning_rate": 0.0002,
920
+ "loss": 0.976,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.83205268935236,
925
+ "grad_norm": 0.42923519015312195,
926
+ "learning_rate": 0.0002,
927
+ "loss": 0.8866,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.854006586169045,
932
+ "grad_norm": 0.47810837626457214,
933
+ "learning_rate": 0.0002,
934
+ "loss": 0.9049,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.8759604829857297,
939
+ "grad_norm": 1.0958846807479858,
940
+ "learning_rate": 0.0002,
941
+ "loss": 1.0291,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.897914379802415,
946
+ "grad_norm": 0.4755791127681732,
947
+ "learning_rate": 0.0002,
948
+ "loss": 0.8724,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.9198682766190998,
953
+ "grad_norm": 0.5575157403945923,
954
+ "learning_rate": 0.0002,
955
+ "loss": 0.9317,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.941822173435785,
960
+ "grad_norm": 0.5938076376914978,
961
+ "learning_rate": 0.0002,
962
+ "loss": 1.0131,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.96377607025247,
967
+ "grad_norm": 0.5751763582229614,
968
+ "learning_rate": 0.0002,
969
+ "loss": 0.9857,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.9857299670691546,
974
+ "grad_norm": 0.5590175986289978,
975
+ "learning_rate": 0.0002,
976
+ "loss": 1.0212,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.9989023051591657,
981
+ "eval_loss": 1.2402944564819336,
982
+ "eval_runtime": 88.822,
983
+ "eval_samples_per_second": 4.852,
984
+ "eval_steps_per_second": 0.608,
985
+ "step": 1366
986
+ },
987
+ {
988
+ "epoch": 3.00768386388584,
989
+ "grad_norm": 0.463539719581604,
990
+ "learning_rate": 0.0002,
991
+ "loss": 0.844,
992
+ "step": 1370
993
+ },
994
+ {
995
+ "epoch": 3.0296377607025247,
996
+ "grad_norm": 0.6667885780334473,
997
+ "learning_rate": 0.0002,
998
+ "loss": 0.8955,
999
+ "step": 1380
1000
+ },
1001
+ {
1002
+ "epoch": 3.0515916575192095,
1003
+ "grad_norm": 0.5849342942237854,
1004
+ "learning_rate": 0.0002,
1005
+ "loss": 0.8765,
1006
+ "step": 1390
1007
+ },
1008
+ {
1009
+ "epoch": 3.0735455543358947,
1010
+ "grad_norm": 0.5571770668029785,
1011
+ "learning_rate": 0.0002,
1012
+ "loss": 0.7808,
1013
+ "step": 1400
1014
+ },
1015
+ {
1016
+ "epoch": 3.0954994511525795,
1017
+ "grad_norm": 0.5761234164237976,
1018
+ "learning_rate": 0.0002,
1019
+ "loss": 0.7448,
1020
+ "step": 1410
1021
+ },
1022
+ {
1023
+ "epoch": 3.1174533479692643,
1024
+ "grad_norm": 0.7277371883392334,
1025
+ "learning_rate": 0.0002,
1026
+ "loss": 0.7854,
1027
+ "step": 1420
1028
+ },
1029
+ {
1030
+ "epoch": 3.1394072447859496,
1031
+ "grad_norm": 0.5190334320068359,
1032
+ "learning_rate": 0.0002,
1033
+ "loss": 0.817,
1034
+ "step": 1430
1035
+ },
1036
+ {
1037
+ "epoch": 3.1613611416026344,
1038
+ "grad_norm": 0.632939875125885,
1039
+ "learning_rate": 0.0002,
1040
+ "loss": 0.7548,
1041
+ "step": 1440
1042
+ },
1043
+ {
1044
+ "epoch": 3.1833150384193196,
1045
+ "grad_norm": 0.7229540944099426,
1046
+ "learning_rate": 0.0002,
1047
+ "loss": 0.8447,
1048
+ "step": 1450
1049
+ },
1050
+ {
1051
+ "epoch": 3.2052689352360044,
1052
+ "grad_norm": 0.7584632039070129,
1053
+ "learning_rate": 0.0002,
1054
+ "loss": 0.8595,
1055
+ "step": 1460
1056
+ },
1057
+ {
1058
+ "epoch": 3.2272228320526892,
1059
+ "grad_norm": 0.6546088457107544,
1060
+ "learning_rate": 0.0002,
1061
+ "loss": 0.7456,
1062
+ "step": 1470
1063
+ },
1064
+ {
1065
+ "epoch": 3.2491767288693745,
1066
+ "grad_norm": 0.8116684556007385,
1067
+ "learning_rate": 0.0002,
1068
+ "loss": 0.8531,
1069
+ "step": 1480
1070
+ },
1071
+ {
1072
+ "epoch": 3.2711306256860593,
1073
+ "grad_norm": 0.6206557750701904,
1074
+ "learning_rate": 0.0002,
1075
+ "loss": 0.9272,
1076
+ "step": 1490
1077
+ },
1078
+ {
1079
+ "epoch": 3.293084522502744,
1080
+ "grad_norm": 0.5393369197845459,
1081
+ "learning_rate": 0.0002,
1082
+ "loss": 0.7972,
1083
+ "step": 1500
1084
+ },
1085
+ {
1086
+ "epoch": 3.3150384193194293,
1087
+ "grad_norm": 0.7006453275680542,
1088
+ "learning_rate": 0.0002,
1089
+ "loss": 0.7614,
1090
+ "step": 1510
1091
+ },
1092
+ {
1093
+ "epoch": 3.336992316136114,
1094
+ "grad_norm": 0.95253986120224,
1095
+ "learning_rate": 0.0002,
1096
+ "loss": 0.7358,
1097
+ "step": 1520
1098
+ },
1099
+ {
1100
+ "epoch": 3.358946212952799,
1101
+ "grad_norm": 0.8138132095336914,
1102
+ "learning_rate": 0.0002,
1103
+ "loss": 0.8131,
1104
+ "step": 1530
1105
+ },
1106
+ {
1107
+ "epoch": 3.380900109769484,
1108
+ "grad_norm": 0.7974302172660828,
1109
+ "learning_rate": 0.0002,
1110
+ "loss": 0.7738,
1111
+ "step": 1540
1112
+ },
1113
+ {
1114
+ "epoch": 3.402854006586169,
1115
+ "grad_norm": 0.6694685220718384,
1116
+ "learning_rate": 0.0002,
1117
+ "loss": 0.8161,
1118
+ "step": 1550
1119
+ },
1120
+ {
1121
+ "epoch": 3.4248079034028542,
1122
+ "grad_norm": 0.908634603023529,
1123
+ "learning_rate": 0.0002,
1124
+ "loss": 0.8503,
1125
+ "step": 1560
1126
+ },
1127
+ {
1128
+ "epoch": 3.446761800219539,
1129
+ "grad_norm": 0.5625193119049072,
1130
+ "learning_rate": 0.0002,
1131
+ "loss": 0.7609,
1132
+ "step": 1570
1133
+ },
1134
+ {
1135
+ "epoch": 3.468715697036224,
1136
+ "grad_norm": 0.779325544834137,
1137
+ "learning_rate": 0.0002,
1138
+ "loss": 0.7658,
1139
+ "step": 1580
1140
+ },
1141
+ {
1142
+ "epoch": 3.4906695938529086,
1143
+ "grad_norm": 0.7133058905601501,
1144
+ "learning_rate": 0.0002,
1145
+ "loss": 0.7485,
1146
+ "step": 1590
1147
+ },
1148
+ {
1149
+ "epoch": 3.512623490669594,
1150
+ "grad_norm": 0.6741108298301697,
1151
+ "learning_rate": 0.0002,
1152
+ "loss": 0.8847,
1153
+ "step": 1600
1154
+ },
1155
+ {
1156
+ "epoch": 3.5345773874862787,
1157
+ "grad_norm": 0.696982204914093,
1158
+ "learning_rate": 0.0002,
1159
+ "loss": 0.7838,
1160
+ "step": 1610
1161
+ },
1162
+ {
1163
+ "epoch": 3.556531284302964,
1164
+ "grad_norm": 0.7946001291275024,
1165
+ "learning_rate": 0.0002,
1166
+ "loss": 0.7195,
1167
+ "step": 1620
1168
+ },
1169
+ {
1170
+ "epoch": 3.5784851811196488,
1171
+ "grad_norm": 0.6313548684120178,
1172
+ "learning_rate": 0.0002,
1173
+ "loss": 0.7772,
1174
+ "step": 1630
1175
+ },
1176
+ {
1177
+ "epoch": 3.6004390779363336,
1178
+ "grad_norm": 0.9246852397918701,
1179
+ "learning_rate": 0.0002,
1180
+ "loss": 0.8267,
1181
+ "step": 1640
1182
+ },
1183
+ {
1184
+ "epoch": 3.622392974753019,
1185
+ "grad_norm": 0.6615420579910278,
1186
+ "learning_rate": 0.0002,
1187
+ "loss": 0.779,
1188
+ "step": 1650
1189
+ },
1190
+ {
1191
+ "epoch": 3.6443468715697036,
1192
+ "grad_norm": 1.5050125122070312,
1193
+ "learning_rate": 0.0002,
1194
+ "loss": 0.883,
1195
+ "step": 1660
1196
+ },
1197
+ {
1198
+ "epoch": 3.666300768386389,
1199
+ "grad_norm": 0.5023762583732605,
1200
+ "learning_rate": 0.0002,
1201
+ "loss": 0.7763,
1202
+ "step": 1670
1203
+ },
1204
+ {
1205
+ "epoch": 3.6882546652030737,
1206
+ "grad_norm": 0.6289586424827576,
1207
+ "learning_rate": 0.0002,
1208
+ "loss": 0.8173,
1209
+ "step": 1680
1210
+ },
1211
+ {
1212
+ "epoch": 3.7102085620197585,
1213
+ "grad_norm": 1.050397515296936,
1214
+ "learning_rate": 0.0002,
1215
+ "loss": 0.9028,
1216
+ "step": 1690
1217
+ },
1218
+ {
1219
+ "epoch": 3.7321624588364433,
1220
+ "grad_norm": 0.6785626411437988,
1221
+ "learning_rate": 0.0002,
1222
+ "loss": 0.7747,
1223
+ "step": 1700
1224
+ },
1225
+ {
1226
+ "epoch": 3.7541163556531285,
1227
+ "grad_norm": 0.7565035223960876,
1228
+ "learning_rate": 0.0002,
1229
+ "loss": 0.9215,
1230
+ "step": 1710
1231
+ },
1232
+ {
1233
+ "epoch": 3.7760702524698133,
1234
+ "grad_norm": 0.7775155901908875,
1235
+ "learning_rate": 0.0002,
1236
+ "loss": 0.7913,
1237
+ "step": 1720
1238
+ },
1239
+ {
1240
+ "epoch": 3.7980241492864986,
1241
+ "grad_norm": 0.765260636806488,
1242
+ "learning_rate": 0.0002,
1243
+ "loss": 0.8081,
1244
+ "step": 1730
1245
+ },
1246
+ {
1247
+ "epoch": 3.8199780461031834,
1248
+ "grad_norm": 0.7982407808303833,
1249
+ "learning_rate": 0.0002,
1250
+ "loss": 0.9231,
1251
+ "step": 1740
1252
+ },
1253
+ {
1254
+ "epoch": 3.841931942919868,
1255
+ "grad_norm": 0.7431730628013611,
1256
+ "learning_rate": 0.0002,
1257
+ "loss": 0.7755,
1258
+ "step": 1750
1259
+ },
1260
+ {
1261
+ "epoch": 3.863885839736553,
1262
+ "grad_norm": 0.9758927226066589,
1263
+ "learning_rate": 0.0002,
1264
+ "loss": 0.9236,
1265
+ "step": 1760
1266
+ },
1267
+ {
1268
+ "epoch": 3.885839736553238,
1269
+ "grad_norm": 0.8014697432518005,
1270
+ "learning_rate": 0.0002,
1271
+ "loss": 0.9118,
1272
+ "step": 1770
1273
+ },
1274
+ {
1275
+ "epoch": 3.907793633369923,
1276
+ "grad_norm": 0.7212756276130676,
1277
+ "learning_rate": 0.0002,
1278
+ "loss": 0.7503,
1279
+ "step": 1780
1280
+ },
1281
+ {
1282
+ "epoch": 3.9297475301866083,
1283
+ "grad_norm": 0.584318220615387,
1284
+ "learning_rate": 0.0002,
1285
+ "loss": 0.7978,
1286
+ "step": 1790
1287
+ },
1288
+ {
1289
+ "epoch": 3.951701427003293,
1290
+ "grad_norm": 0.7612535953521729,
1291
+ "learning_rate": 0.0002,
1292
+ "loss": 0.7894,
1293
+ "step": 1800
1294
+ },
1295
+ {
1296
+ "epoch": 3.973655323819978,
1297
+ "grad_norm": 0.735103189945221,
1298
+ "learning_rate": 0.0002,
1299
+ "loss": 0.8589,
1300
+ "step": 1810
1301
+ },
1302
+ {
1303
+ "epoch": 3.995609220636663,
1304
+ "grad_norm": 0.9074980020523071,
1305
+ "learning_rate": 0.0002,
1306
+ "loss": 0.8192,
1307
+ "step": 1820
1308
+ },
1309
+ {
1310
+ "epoch": 4.0,
1311
+ "eval_loss": 1.279890537261963,
1312
+ "eval_runtime": 88.8969,
1313
+ "eval_samples_per_second": 4.848,
1314
+ "eval_steps_per_second": 0.607,
1315
+ "step": 1822
1316
+ }
1317
+ ],
1318
+ "logging_steps": 10,
1319
+ "max_steps": 3640,
1320
+ "num_input_tokens_seen": 0,
1321
+ "num_train_epochs": 8,
1322
+ "save_steps": 200,
1323
+ "stateful_callbacks": {
1324
+ "TrainerControl": {
1325
+ "args": {
1326
+ "should_epoch_stop": false,
1327
+ "should_evaluate": false,
1328
+ "should_log": false,
1329
+ "should_save": true,
1330
+ "should_training_stop": false
1331
+ },
1332
+ "attributes": {}
1333
+ }
1334
+ },
1335
+ "total_flos": 8.431808037676646e+16,
1336
+ "train_batch_size": 1,
1337
+ "trial_name": null,
1338
+ "trial_params": null
1339
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-1822/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf90ce7dd53cc68edd44d14e30ca84a5d7431a5b99d4697b17af4b2f7ec0abab
3
+ size 5624
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c96d3d7a842c87fa06a3879c84ca1bcf04cd5da6f344179383bdd42e7dd2a2dd
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d31faef2a2b0b29f8764f5175c794426c1984ff47fb280c987b9c09f638affe
3
+ size 55532666
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28e15845f1efe266490b2686e71d5c1a896220db3dab076ec5da4eb620926599
3
+ size 14244
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc6cb40028b40235e27b0cac0a4339b75f0d188d520221f5823c28cfacfd1224
3
+ size 1064
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
+ size 17209961
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/trainer_state.json ADDED
@@ -0,0 +1,1662 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.205152153968811,
3
+ "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911",
4
+ "epoch": 4.998902305159166,
5
+ "eval_steps": 10,
6
+ "global_step": 2277,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.021953896816684963,
13
+ "grad_norm": 0.6144012212753296,
14
+ "learning_rate": 0.0002,
15
+ "loss": 1.9887,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.043907793633369926,
20
+ "grad_norm": 0.5587220788002014,
21
+ "learning_rate": 0.0002,
22
+ "loss": 1.6882,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06586169045005488,
27
+ "grad_norm": 0.43262454867362976,
28
+ "learning_rate": 0.0002,
29
+ "loss": 1.399,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.08781558726673985,
34
+ "grad_norm": 0.4783053994178772,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.4675,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.10976948408342481,
41
+ "grad_norm": 0.44338956475257874,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.1771,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.13172338090010977,
48
+ "grad_norm": 0.7255092263221741,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.3706,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.15367727771679474,
55
+ "grad_norm": 0.46073833107948303,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.2601,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.1756311745334797,
62
+ "grad_norm": 0.6698123216629028,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.3049,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.19758507135016465,
69
+ "grad_norm": 0.4190150201320648,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.2975,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.21953896816684962,
76
+ "grad_norm": 0.4110015034675598,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.2797,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.2414928649835346,
83
+ "grad_norm": 0.33374306559562683,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.2896,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.26344676180021953,
90
+ "grad_norm": 0.3061307370662689,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.2268,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.2854006586169045,
97
+ "grad_norm": 0.4386885166168213,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.376,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.30735455543358947,
104
+ "grad_norm": 0.40116462111473083,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.1814,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.32930845225027444,
111
+ "grad_norm": 0.5887949466705322,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.2592,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3512623490669594,
118
+ "grad_norm": 0.3401573896408081,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.2372,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.3732162458836443,
125
+ "grad_norm": 0.3288364112377167,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.1901,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.3951701427003293,
132
+ "grad_norm": 0.4853297472000122,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.2335,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.41712403951701427,
139
+ "grad_norm": 2.6253697872161865,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.227,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.43907793633369924,
146
+ "grad_norm": 0.5598543286323547,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.2673,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.4610318331503842,
153
+ "grad_norm": 0.4046548902988434,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.3459,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.4829857299670692,
160
+ "grad_norm": 0.3686952590942383,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.265,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5049396267837541,
167
+ "grad_norm": 0.42458799481391907,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.1364,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5268935236004391,
174
+ "grad_norm": 0.5839895009994507,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.2094,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5488474204171241,
181
+ "grad_norm": 0.408288836479187,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.2073,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.570801317233809,
188
+ "grad_norm": 0.45887550711631775,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.3121,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.5927552140504939,
195
+ "grad_norm": 0.5440235733985901,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.2257,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6147091108671789,
202
+ "grad_norm": 0.3725181519985199,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.1003,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6366630076838639,
209
+ "grad_norm": 0.4309018850326538,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.1538,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6586169045005489,
216
+ "grad_norm": 0.31488674879074097,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.2097,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6805708013172338,
223
+ "grad_norm": 0.34194841980934143,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.1689,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7025246981339188,
230
+ "grad_norm": 0.3407684862613678,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.2579,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7244785949506037,
237
+ "grad_norm": 0.2985728085041046,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.1144,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7464324917672887,
244
+ "grad_norm": 0.42316871881484985,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.2056,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7683863885839737,
251
+ "grad_norm": 0.3124258816242218,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.1753,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.7903402854006586,
258
+ "grad_norm": 0.7727567553520203,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.2547,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8122941822173436,
265
+ "grad_norm": 0.363765686750412,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.124,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8342480790340285,
272
+ "grad_norm": 0.35582536458969116,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.1302,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8562019758507134,
279
+ "grad_norm": 0.31982025504112244,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.1787,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.8781558726673985,
286
+ "grad_norm": 0.34978964924812317,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.2056,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9001097694840834,
293
+ "grad_norm": 0.8346716165542603,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.3577,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9220636663007684,
300
+ "grad_norm": 0.31984028220176697,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.1029,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9440175631174533,
307
+ "grad_norm": 0.32078951597213745,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.0967,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9659714599341384,
314
+ "grad_norm": 0.3417500853538513,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.0936,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.9879253567508233,
321
+ "grad_norm": 0.42359477281570435,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.3412,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.9989023051591658,
328
+ "eval_loss": 1.2201528549194336,
329
+ "eval_runtime": 87.152,
330
+ "eval_samples_per_second": 4.945,
331
+ "eval_steps_per_second": 0.62,
332
+ "step": 455
333
+ },
334
+ {
335
+ "epoch": 1.0098792535675083,
336
+ "grad_norm": 0.37914523482322693,
337
+ "learning_rate": 0.0002,
338
+ "loss": 1.1909,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.031833150384193,
343
+ "grad_norm": 0.43655872344970703,
344
+ "learning_rate": 0.0002,
345
+ "loss": 1.0948,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.0537870472008781,
350
+ "grad_norm": 0.3673796057701111,
351
+ "learning_rate": 0.0002,
352
+ "loss": 1.0873,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.0757409440175631,
357
+ "grad_norm": 0.37673917412757874,
358
+ "learning_rate": 0.0002,
359
+ "loss": 1.0483,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.0976948408342482,
364
+ "grad_norm": 0.2893829345703125,
365
+ "learning_rate": 0.0002,
366
+ "loss": 1.0799,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.119648737650933,
371
+ "grad_norm": 0.5551970601081848,
372
+ "learning_rate": 0.0002,
373
+ "loss": 1.1847,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.141602634467618,
378
+ "grad_norm": 0.442104309797287,
379
+ "learning_rate": 0.0002,
380
+ "loss": 1.0885,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.163556531284303,
385
+ "grad_norm": 0.4035094976425171,
386
+ "learning_rate": 0.0002,
387
+ "loss": 1.1766,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.1855104281009878,
392
+ "grad_norm": 0.47009000182151794,
393
+ "learning_rate": 0.0002,
394
+ "loss": 1.0282,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.2074643249176729,
399
+ "grad_norm": 0.4118749797344208,
400
+ "learning_rate": 0.0002,
401
+ "loss": 1.2625,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.2294182217343579,
406
+ "grad_norm": 0.35173165798187256,
407
+ "learning_rate": 0.0002,
408
+ "loss": 1.0988,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.2513721185510427,
413
+ "grad_norm": 0.7024672031402588,
414
+ "learning_rate": 0.0002,
415
+ "loss": 1.0498,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.2733260153677277,
420
+ "grad_norm": 0.42657527327537537,
421
+ "learning_rate": 0.0002,
422
+ "loss": 1.1339,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.2952799121844127,
427
+ "grad_norm": 0.3815029561519623,
428
+ "learning_rate": 0.0002,
429
+ "loss": 1.0545,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.3172338090010978,
434
+ "grad_norm": 0.7031055688858032,
435
+ "learning_rate": 0.0002,
436
+ "loss": 1.1528,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.3391877058177828,
441
+ "grad_norm": 0.393911212682724,
442
+ "learning_rate": 0.0002,
443
+ "loss": 1.1347,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.3611416026344676,
448
+ "grad_norm": 0.5077702403068542,
449
+ "learning_rate": 0.0002,
450
+ "loss": 1.1901,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.3830954994511526,
455
+ "grad_norm": 2.330033302307129,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.1251,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.4050493962678376,
462
+ "grad_norm": 0.35322949290275574,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.0477,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.4270032930845225,
469
+ "grad_norm": 0.44401052594184875,
470
+ "learning_rate": 0.0002,
471
+ "loss": 1.14,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.4489571899012075,
476
+ "grad_norm": 0.35945481061935425,
477
+ "learning_rate": 0.0002,
478
+ "loss": 1.0318,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.4709110867178925,
483
+ "grad_norm": 0.3058856129646301,
484
+ "learning_rate": 0.0002,
485
+ "loss": 1.1988,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.4928649835345773,
490
+ "grad_norm": 0.7067602872848511,
491
+ "learning_rate": 0.0002,
492
+ "loss": 1.1545,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.5148188803512623,
497
+ "grad_norm": 0.4219357371330261,
498
+ "learning_rate": 0.0002,
499
+ "loss": 1.0925,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.5367727771679474,
504
+ "grad_norm": 0.5970841646194458,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.1622,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.5587266739846322,
511
+ "grad_norm": 0.4381934404373169,
512
+ "learning_rate": 0.0002,
513
+ "loss": 1.0803,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.5806805708013172,
518
+ "grad_norm": 0.4101450443267822,
519
+ "learning_rate": 0.0002,
520
+ "loss": 1.0961,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.6026344676180022,
525
+ "grad_norm": 0.3657490015029907,
526
+ "learning_rate": 0.0002,
527
+ "loss": 1.0474,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.624588364434687,
532
+ "grad_norm": 0.36240628361701965,
533
+ "learning_rate": 0.0002,
534
+ "loss": 1.0936,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.6465422612513723,
539
+ "grad_norm": 0.4103568494319916,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.0489,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.668496158068057,
546
+ "grad_norm": 0.3138505816459656,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.0919,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.690450054884742,
553
+ "grad_norm": 0.41215717792510986,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.2308,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.7124039517014271,
560
+ "grad_norm": 0.4589519202709198,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.1659,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.734357848518112,
567
+ "grad_norm": 0.4049508571624756,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.0913,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.756311745334797,
574
+ "grad_norm": 0.48557212948799133,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.1329,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.778265642151482,
581
+ "grad_norm": 0.5331754088401794,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.0729,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.8002195389681668,
588
+ "grad_norm": 0.3853185772895813,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.1452,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.8221734357848518,
595
+ "grad_norm": 0.424062579870224,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.1061,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.8441273326015368,
602
+ "grad_norm": 0.3418445289134979,
603
+ "learning_rate": 0.0002,
604
+ "loss": 1.1104,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.8660812294182216,
609
+ "grad_norm": 0.4045565128326416,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.0546,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.8880351262349067,
616
+ "grad_norm": 0.42155781388282776,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.1608,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.9099890230515917,
623
+ "grad_norm": 0.40554770827293396,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.0628,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.9319429198682765,
630
+ "grad_norm": 0.42644748091697693,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.1609,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.9538968166849617,
637
+ "grad_norm": 0.45260652899742126,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.1132,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.9758507135016465,
644
+ "grad_norm": 0.4114069938659668,
645
+ "learning_rate": 0.0002,
646
+ "loss": 1.048,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.9978046103183313,
651
+ "grad_norm": 0.375802218914032,
652
+ "learning_rate": 0.0002,
653
+ "loss": 1.1941,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 2.0,
658
+ "eval_loss": 1.205152153968811,
659
+ "eval_runtime": 86.8795,
660
+ "eval_samples_per_second": 4.961,
661
+ "eval_steps_per_second": 0.622,
662
+ "step": 911
663
+ },
664
+ {
665
+ "epoch": 2.0197585071350166,
666
+ "grad_norm": 0.47718703746795654,
667
+ "learning_rate": 0.0002,
668
+ "loss": 1.0897,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.0417124039517014,
673
+ "grad_norm": 0.45628082752227783,
674
+ "learning_rate": 0.0002,
675
+ "loss": 1.0329,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.063666300768386,
680
+ "grad_norm": 0.5933247804641724,
681
+ "learning_rate": 0.0002,
682
+ "loss": 1.0538,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.0856201975850714,
687
+ "grad_norm": 0.5355812907218933,
688
+ "learning_rate": 0.0002,
689
+ "loss": 1.0152,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.1075740944017562,
694
+ "grad_norm": 0.5860010385513306,
695
+ "learning_rate": 0.0002,
696
+ "loss": 1.0726,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.129527991218441,
701
+ "grad_norm": 0.7471673488616943,
702
+ "learning_rate": 0.0002,
703
+ "loss": 1.025,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.1514818880351263,
708
+ "grad_norm": 2.0918211936950684,
709
+ "learning_rate": 0.0002,
710
+ "loss": 1.0247,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.173435784851811,
715
+ "grad_norm": 0.4021058678627014,
716
+ "learning_rate": 0.0002,
717
+ "loss": 0.8947,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.1953896816684964,
722
+ "grad_norm": 0.564975380897522,
723
+ "learning_rate": 0.0002,
724
+ "loss": 0.8875,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.217343578485181,
729
+ "grad_norm": 0.46260079741477966,
730
+ "learning_rate": 0.0002,
731
+ "loss": 1.0264,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.239297475301866,
736
+ "grad_norm": 0.4791034460067749,
737
+ "learning_rate": 0.0002,
738
+ "loss": 0.9265,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.261251372118551,
743
+ "grad_norm": 0.5272043943405151,
744
+ "learning_rate": 0.0002,
745
+ "loss": 0.8869,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.283205268935236,
750
+ "grad_norm": 0.5221094489097595,
751
+ "learning_rate": 0.0002,
752
+ "loss": 1.0007,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.305159165751921,
757
+ "grad_norm": 0.558032751083374,
758
+ "learning_rate": 0.0002,
759
+ "loss": 0.9472,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.327113062568606,
764
+ "grad_norm": 0.5905590653419495,
765
+ "learning_rate": 0.0002,
766
+ "loss": 0.9617,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.349066959385291,
771
+ "grad_norm": 0.5308699607849121,
772
+ "learning_rate": 0.0002,
773
+ "loss": 0.9592,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.3710208562019757,
778
+ "grad_norm": 0.6375027894973755,
779
+ "learning_rate": 0.0002,
780
+ "loss": 1.0646,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.392974753018661,
785
+ "grad_norm": 0.7439115643501282,
786
+ "learning_rate": 0.0002,
787
+ "loss": 1.0354,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.4149286498353457,
792
+ "grad_norm": 0.41945117712020874,
793
+ "learning_rate": 0.0002,
794
+ "loss": 1.0212,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.436882546652031,
799
+ "grad_norm": 0.4891968369483948,
800
+ "learning_rate": 0.0002,
801
+ "loss": 0.9609,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.4588364434687158,
806
+ "grad_norm": 0.4686794579029083,
807
+ "learning_rate": 0.0002,
808
+ "loss": 0.9829,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.4807903402854006,
813
+ "grad_norm": 0.5204509496688843,
814
+ "learning_rate": 0.0002,
815
+ "loss": 0.8919,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.5027442371020854,
820
+ "grad_norm": 0.6779005527496338,
821
+ "learning_rate": 0.0002,
822
+ "loss": 0.8983,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.5246981339187706,
827
+ "grad_norm": 0.682621955871582,
828
+ "learning_rate": 0.0002,
829
+ "loss": 0.9733,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.5466520307354554,
834
+ "grad_norm": 0.5744376182556152,
835
+ "learning_rate": 0.0002,
836
+ "loss": 1.051,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.5686059275521407,
841
+ "grad_norm": 0.49954667687416077,
842
+ "learning_rate": 0.0002,
843
+ "loss": 0.8764,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.5905598243688255,
848
+ "grad_norm": 0.4761793315410614,
849
+ "learning_rate": 0.0002,
850
+ "loss": 0.9896,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.6125137211855103,
855
+ "grad_norm": 0.548299252986908,
856
+ "learning_rate": 0.0002,
857
+ "loss": 0.8593,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.6344676180021955,
862
+ "grad_norm": 0.5771360993385315,
863
+ "learning_rate": 0.0002,
864
+ "loss": 1.0017,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.6564215148188803,
869
+ "grad_norm": 0.5543120503425598,
870
+ "learning_rate": 0.0002,
871
+ "loss": 0.9858,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.6783754116355656,
876
+ "grad_norm": 0.7564870715141296,
877
+ "learning_rate": 0.0002,
878
+ "loss": 0.9565,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.7003293084522504,
883
+ "grad_norm": 0.8222362399101257,
884
+ "learning_rate": 0.0002,
885
+ "loss": 0.9753,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.722283205268935,
890
+ "grad_norm": 0.6894469857215881,
891
+ "learning_rate": 0.0002,
892
+ "loss": 1.0079,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.74423710208562,
897
+ "grad_norm": 0.6121546030044556,
898
+ "learning_rate": 0.0002,
899
+ "loss": 1.0106,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.7661909989023052,
904
+ "grad_norm": 0.521809995174408,
905
+ "learning_rate": 0.0002,
906
+ "loss": 0.9801,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.78814489571899,
911
+ "grad_norm": 0.766968309879303,
912
+ "learning_rate": 0.0002,
913
+ "loss": 1.0196,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.8100987925356753,
918
+ "grad_norm": 0.522331714630127,
919
+ "learning_rate": 0.0002,
920
+ "loss": 0.976,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.83205268935236,
925
+ "grad_norm": 0.42923519015312195,
926
+ "learning_rate": 0.0002,
927
+ "loss": 0.8866,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.854006586169045,
932
+ "grad_norm": 0.47810837626457214,
933
+ "learning_rate": 0.0002,
934
+ "loss": 0.9049,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.8759604829857297,
939
+ "grad_norm": 1.0958846807479858,
940
+ "learning_rate": 0.0002,
941
+ "loss": 1.0291,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.897914379802415,
946
+ "grad_norm": 0.4755791127681732,
947
+ "learning_rate": 0.0002,
948
+ "loss": 0.8724,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.9198682766190998,
953
+ "grad_norm": 0.5575157403945923,
954
+ "learning_rate": 0.0002,
955
+ "loss": 0.9317,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.941822173435785,
960
+ "grad_norm": 0.5938076376914978,
961
+ "learning_rate": 0.0002,
962
+ "loss": 1.0131,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.96377607025247,
967
+ "grad_norm": 0.5751763582229614,
968
+ "learning_rate": 0.0002,
969
+ "loss": 0.9857,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.9857299670691546,
974
+ "grad_norm": 0.5590175986289978,
975
+ "learning_rate": 0.0002,
976
+ "loss": 1.0212,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.9989023051591657,
981
+ "eval_loss": 1.2402944564819336,
982
+ "eval_runtime": 88.822,
983
+ "eval_samples_per_second": 4.852,
984
+ "eval_steps_per_second": 0.608,
985
+ "step": 1366
986
+ },
987
+ {
988
+ "epoch": 3.00768386388584,
989
+ "grad_norm": 0.463539719581604,
990
+ "learning_rate": 0.0002,
991
+ "loss": 0.844,
992
+ "step": 1370
993
+ },
994
+ {
995
+ "epoch": 3.0296377607025247,
996
+ "grad_norm": 0.6667885780334473,
997
+ "learning_rate": 0.0002,
998
+ "loss": 0.8955,
999
+ "step": 1380
1000
+ },
1001
+ {
1002
+ "epoch": 3.0515916575192095,
1003
+ "grad_norm": 0.5849342942237854,
1004
+ "learning_rate": 0.0002,
1005
+ "loss": 0.8765,
1006
+ "step": 1390
1007
+ },
1008
+ {
1009
+ "epoch": 3.0735455543358947,
1010
+ "grad_norm": 0.5571770668029785,
1011
+ "learning_rate": 0.0002,
1012
+ "loss": 0.7808,
1013
+ "step": 1400
1014
+ },
1015
+ {
1016
+ "epoch": 3.0954994511525795,
1017
+ "grad_norm": 0.5761234164237976,
1018
+ "learning_rate": 0.0002,
1019
+ "loss": 0.7448,
1020
+ "step": 1410
1021
+ },
1022
+ {
1023
+ "epoch": 3.1174533479692643,
1024
+ "grad_norm": 0.7277371883392334,
1025
+ "learning_rate": 0.0002,
1026
+ "loss": 0.7854,
1027
+ "step": 1420
1028
+ },
1029
+ {
1030
+ "epoch": 3.1394072447859496,
1031
+ "grad_norm": 0.5190334320068359,
1032
+ "learning_rate": 0.0002,
1033
+ "loss": 0.817,
1034
+ "step": 1430
1035
+ },
1036
+ {
1037
+ "epoch": 3.1613611416026344,
1038
+ "grad_norm": 0.632939875125885,
1039
+ "learning_rate": 0.0002,
1040
+ "loss": 0.7548,
1041
+ "step": 1440
1042
+ },
1043
+ {
1044
+ "epoch": 3.1833150384193196,
1045
+ "grad_norm": 0.7229540944099426,
1046
+ "learning_rate": 0.0002,
1047
+ "loss": 0.8447,
1048
+ "step": 1450
1049
+ },
1050
+ {
1051
+ "epoch": 3.2052689352360044,
1052
+ "grad_norm": 0.7584632039070129,
1053
+ "learning_rate": 0.0002,
1054
+ "loss": 0.8595,
1055
+ "step": 1460
1056
+ },
1057
+ {
1058
+ "epoch": 3.2272228320526892,
1059
+ "grad_norm": 0.6546088457107544,
1060
+ "learning_rate": 0.0002,
1061
+ "loss": 0.7456,
1062
+ "step": 1470
1063
+ },
1064
+ {
1065
+ "epoch": 3.2491767288693745,
1066
+ "grad_norm": 0.8116684556007385,
1067
+ "learning_rate": 0.0002,
1068
+ "loss": 0.8531,
1069
+ "step": 1480
1070
+ },
1071
+ {
1072
+ "epoch": 3.2711306256860593,
1073
+ "grad_norm": 0.6206557750701904,
1074
+ "learning_rate": 0.0002,
1075
+ "loss": 0.9272,
1076
+ "step": 1490
1077
+ },
1078
+ {
1079
+ "epoch": 3.293084522502744,
1080
+ "grad_norm": 0.5393369197845459,
1081
+ "learning_rate": 0.0002,
1082
+ "loss": 0.7972,
1083
+ "step": 1500
1084
+ },
1085
+ {
1086
+ "epoch": 3.3150384193194293,
1087
+ "grad_norm": 0.7006453275680542,
1088
+ "learning_rate": 0.0002,
1089
+ "loss": 0.7614,
1090
+ "step": 1510
1091
+ },
1092
+ {
1093
+ "epoch": 3.336992316136114,
1094
+ "grad_norm": 0.95253986120224,
1095
+ "learning_rate": 0.0002,
1096
+ "loss": 0.7358,
1097
+ "step": 1520
1098
+ },
1099
+ {
1100
+ "epoch": 3.358946212952799,
1101
+ "grad_norm": 0.8138132095336914,
1102
+ "learning_rate": 0.0002,
1103
+ "loss": 0.8131,
1104
+ "step": 1530
1105
+ },
1106
+ {
1107
+ "epoch": 3.380900109769484,
1108
+ "grad_norm": 0.7974302172660828,
1109
+ "learning_rate": 0.0002,
1110
+ "loss": 0.7738,
1111
+ "step": 1540
1112
+ },
1113
+ {
1114
+ "epoch": 3.402854006586169,
1115
+ "grad_norm": 0.6694685220718384,
1116
+ "learning_rate": 0.0002,
1117
+ "loss": 0.8161,
1118
+ "step": 1550
1119
+ },
1120
+ {
1121
+ "epoch": 3.4248079034028542,
1122
+ "grad_norm": 0.908634603023529,
1123
+ "learning_rate": 0.0002,
1124
+ "loss": 0.8503,
1125
+ "step": 1560
1126
+ },
1127
+ {
1128
+ "epoch": 3.446761800219539,
1129
+ "grad_norm": 0.5625193119049072,
1130
+ "learning_rate": 0.0002,
1131
+ "loss": 0.7609,
1132
+ "step": 1570
1133
+ },
1134
+ {
1135
+ "epoch": 3.468715697036224,
1136
+ "grad_norm": 0.779325544834137,
1137
+ "learning_rate": 0.0002,
1138
+ "loss": 0.7658,
1139
+ "step": 1580
1140
+ },
1141
+ {
1142
+ "epoch": 3.4906695938529086,
1143
+ "grad_norm": 0.7133058905601501,
1144
+ "learning_rate": 0.0002,
1145
+ "loss": 0.7485,
1146
+ "step": 1590
1147
+ },
1148
+ {
1149
+ "epoch": 3.512623490669594,
1150
+ "grad_norm": 0.6741108298301697,
1151
+ "learning_rate": 0.0002,
1152
+ "loss": 0.8847,
1153
+ "step": 1600
1154
+ },
1155
+ {
1156
+ "epoch": 3.5345773874862787,
1157
+ "grad_norm": 0.696982204914093,
1158
+ "learning_rate": 0.0002,
1159
+ "loss": 0.7838,
1160
+ "step": 1610
1161
+ },
1162
+ {
1163
+ "epoch": 3.556531284302964,
1164
+ "grad_norm": 0.7946001291275024,
1165
+ "learning_rate": 0.0002,
1166
+ "loss": 0.7195,
1167
+ "step": 1620
1168
+ },
1169
+ {
1170
+ "epoch": 3.5784851811196488,
1171
+ "grad_norm": 0.6313548684120178,
1172
+ "learning_rate": 0.0002,
1173
+ "loss": 0.7772,
1174
+ "step": 1630
1175
+ },
1176
+ {
1177
+ "epoch": 3.6004390779363336,
1178
+ "grad_norm": 0.9246852397918701,
1179
+ "learning_rate": 0.0002,
1180
+ "loss": 0.8267,
1181
+ "step": 1640
1182
+ },
1183
+ {
1184
+ "epoch": 3.622392974753019,
1185
+ "grad_norm": 0.6615420579910278,
1186
+ "learning_rate": 0.0002,
1187
+ "loss": 0.779,
1188
+ "step": 1650
1189
+ },
1190
+ {
1191
+ "epoch": 3.6443468715697036,
1192
+ "grad_norm": 1.5050125122070312,
1193
+ "learning_rate": 0.0002,
1194
+ "loss": 0.883,
1195
+ "step": 1660
1196
+ },
1197
+ {
1198
+ "epoch": 3.666300768386389,
1199
+ "grad_norm": 0.5023762583732605,
1200
+ "learning_rate": 0.0002,
1201
+ "loss": 0.7763,
1202
+ "step": 1670
1203
+ },
1204
+ {
1205
+ "epoch": 3.6882546652030737,
1206
+ "grad_norm": 0.6289586424827576,
1207
+ "learning_rate": 0.0002,
1208
+ "loss": 0.8173,
1209
+ "step": 1680
1210
+ },
1211
+ {
1212
+ "epoch": 3.7102085620197585,
1213
+ "grad_norm": 1.050397515296936,
1214
+ "learning_rate": 0.0002,
1215
+ "loss": 0.9028,
1216
+ "step": 1690
1217
+ },
1218
+ {
1219
+ "epoch": 3.7321624588364433,
1220
+ "grad_norm": 0.6785626411437988,
1221
+ "learning_rate": 0.0002,
1222
+ "loss": 0.7747,
1223
+ "step": 1700
1224
+ },
1225
+ {
1226
+ "epoch": 3.7541163556531285,
1227
+ "grad_norm": 0.7565035223960876,
1228
+ "learning_rate": 0.0002,
1229
+ "loss": 0.9215,
1230
+ "step": 1710
1231
+ },
1232
+ {
1233
+ "epoch": 3.7760702524698133,
1234
+ "grad_norm": 0.7775155901908875,
1235
+ "learning_rate": 0.0002,
1236
+ "loss": 0.7913,
1237
+ "step": 1720
1238
+ },
1239
+ {
1240
+ "epoch": 3.7980241492864986,
1241
+ "grad_norm": 0.765260636806488,
1242
+ "learning_rate": 0.0002,
1243
+ "loss": 0.8081,
1244
+ "step": 1730
1245
+ },
1246
+ {
1247
+ "epoch": 3.8199780461031834,
1248
+ "grad_norm": 0.7982407808303833,
1249
+ "learning_rate": 0.0002,
1250
+ "loss": 0.9231,
1251
+ "step": 1740
1252
+ },
1253
+ {
1254
+ "epoch": 3.841931942919868,
1255
+ "grad_norm": 0.7431730628013611,
1256
+ "learning_rate": 0.0002,
1257
+ "loss": 0.7755,
1258
+ "step": 1750
1259
+ },
1260
+ {
1261
+ "epoch": 3.863885839736553,
1262
+ "grad_norm": 0.9758927226066589,
1263
+ "learning_rate": 0.0002,
1264
+ "loss": 0.9236,
1265
+ "step": 1760
1266
+ },
1267
+ {
1268
+ "epoch": 3.885839736553238,
1269
+ "grad_norm": 0.8014697432518005,
1270
+ "learning_rate": 0.0002,
1271
+ "loss": 0.9118,
1272
+ "step": 1770
1273
+ },
1274
+ {
1275
+ "epoch": 3.907793633369923,
1276
+ "grad_norm": 0.7212756276130676,
1277
+ "learning_rate": 0.0002,
1278
+ "loss": 0.7503,
1279
+ "step": 1780
1280
+ },
1281
+ {
1282
+ "epoch": 3.9297475301866083,
1283
+ "grad_norm": 0.584318220615387,
1284
+ "learning_rate": 0.0002,
1285
+ "loss": 0.7978,
1286
+ "step": 1790
1287
+ },
1288
+ {
1289
+ "epoch": 3.951701427003293,
1290
+ "grad_norm": 0.7612535953521729,
1291
+ "learning_rate": 0.0002,
1292
+ "loss": 0.7894,
1293
+ "step": 1800
1294
+ },
1295
+ {
1296
+ "epoch": 3.973655323819978,
1297
+ "grad_norm": 0.735103189945221,
1298
+ "learning_rate": 0.0002,
1299
+ "loss": 0.8589,
1300
+ "step": 1810
1301
+ },
1302
+ {
1303
+ "epoch": 3.995609220636663,
1304
+ "grad_norm": 0.9074980020523071,
1305
+ "learning_rate": 0.0002,
1306
+ "loss": 0.8192,
1307
+ "step": 1820
1308
+ },
1309
+ {
1310
+ "epoch": 4.0,
1311
+ "eval_loss": 1.279890537261963,
1312
+ "eval_runtime": 88.8969,
1313
+ "eval_samples_per_second": 4.848,
1314
+ "eval_steps_per_second": 0.607,
1315
+ "step": 1822
1316
+ },
1317
+ {
1318
+ "epoch": 4.017563117453348,
1319
+ "grad_norm": 0.9290254712104797,
1320
+ "learning_rate": 0.0002,
1321
+ "loss": 0.7312,
1322
+ "step": 1830
1323
+ },
1324
+ {
1325
+ "epoch": 4.039517014270033,
1326
+ "grad_norm": 0.723889946937561,
1327
+ "learning_rate": 0.0002,
1328
+ "loss": 0.6896,
1329
+ "step": 1840
1330
+ },
1331
+ {
1332
+ "epoch": 4.061470911086718,
1333
+ "grad_norm": 0.5906972289085388,
1334
+ "learning_rate": 0.0002,
1335
+ "loss": 0.632,
1336
+ "step": 1850
1337
+ },
1338
+ {
1339
+ "epoch": 4.083424807903403,
1340
+ "grad_norm": 0.8078910708427429,
1341
+ "learning_rate": 0.0002,
1342
+ "loss": 0.6594,
1343
+ "step": 1860
1344
+ },
1345
+ {
1346
+ "epoch": 4.105378704720088,
1347
+ "grad_norm": 1.0101137161254883,
1348
+ "learning_rate": 0.0002,
1349
+ "loss": 0.6242,
1350
+ "step": 1870
1351
+ },
1352
+ {
1353
+ "epoch": 4.127332601536772,
1354
+ "grad_norm": 0.8710281848907471,
1355
+ "learning_rate": 0.0002,
1356
+ "loss": 0.7259,
1357
+ "step": 1880
1358
+ },
1359
+ {
1360
+ "epoch": 4.149286498353458,
1361
+ "grad_norm": 0.9604734778404236,
1362
+ "learning_rate": 0.0002,
1363
+ "loss": 0.6993,
1364
+ "step": 1890
1365
+ },
1366
+ {
1367
+ "epoch": 4.171240395170143,
1368
+ "grad_norm": 0.9829702377319336,
1369
+ "learning_rate": 0.0002,
1370
+ "loss": 0.6706,
1371
+ "step": 1900
1372
+ },
1373
+ {
1374
+ "epoch": 4.193194291986828,
1375
+ "grad_norm": 0.6572765707969666,
1376
+ "learning_rate": 0.0002,
1377
+ "loss": 0.7013,
1378
+ "step": 1910
1379
+ },
1380
+ {
1381
+ "epoch": 4.2151481888035125,
1382
+ "grad_norm": 0.8459188938140869,
1383
+ "learning_rate": 0.0002,
1384
+ "loss": 0.5539,
1385
+ "step": 1920
1386
+ },
1387
+ {
1388
+ "epoch": 4.237102085620197,
1389
+ "grad_norm": 0.8321021795272827,
1390
+ "learning_rate": 0.0002,
1391
+ "loss": 0.6235,
1392
+ "step": 1930
1393
+ },
1394
+ {
1395
+ "epoch": 4.259055982436882,
1396
+ "grad_norm": 0.8611727356910706,
1397
+ "learning_rate": 0.0002,
1398
+ "loss": 0.6442,
1399
+ "step": 1940
1400
+ },
1401
+ {
1402
+ "epoch": 4.281009879253568,
1403
+ "grad_norm": 0.8490208387374878,
1404
+ "learning_rate": 0.0002,
1405
+ "loss": 0.6852,
1406
+ "step": 1950
1407
+ },
1408
+ {
1409
+ "epoch": 4.302963776070253,
1410
+ "grad_norm": 0.9628722667694092,
1411
+ "learning_rate": 0.0002,
1412
+ "loss": 0.6175,
1413
+ "step": 1960
1414
+ },
1415
+ {
1416
+ "epoch": 4.324917672886937,
1417
+ "grad_norm": 0.9632807374000549,
1418
+ "learning_rate": 0.0002,
1419
+ "loss": 0.5982,
1420
+ "step": 1970
1421
+ },
1422
+ {
1423
+ "epoch": 4.346871569703622,
1424
+ "grad_norm": 0.7023298740386963,
1425
+ "learning_rate": 0.0002,
1426
+ "loss": 0.6138,
1427
+ "step": 1980
1428
+ },
1429
+ {
1430
+ "epoch": 4.368825466520307,
1431
+ "grad_norm": 0.7912909388542175,
1432
+ "learning_rate": 0.0002,
1433
+ "loss": 0.6012,
1434
+ "step": 1990
1435
+ },
1436
+ {
1437
+ "epoch": 4.390779363336993,
1438
+ "grad_norm": 1.1463429927825928,
1439
+ "learning_rate": 0.0002,
1440
+ "loss": 0.6767,
1441
+ "step": 2000
1442
+ },
1443
+ {
1444
+ "epoch": 4.4127332601536775,
1445
+ "grad_norm": 1.1780626773834229,
1446
+ "learning_rate": 0.0002,
1447
+ "loss": 0.6607,
1448
+ "step": 2010
1449
+ },
1450
+ {
1451
+ "epoch": 4.434687156970362,
1452
+ "grad_norm": 0.9349206686019897,
1453
+ "learning_rate": 0.0002,
1454
+ "loss": 0.6746,
1455
+ "step": 2020
1456
+ },
1457
+ {
1458
+ "epoch": 4.456641053787047,
1459
+ "grad_norm": 0.7816639542579651,
1460
+ "learning_rate": 0.0002,
1461
+ "loss": 0.7087,
1462
+ "step": 2030
1463
+ },
1464
+ {
1465
+ "epoch": 4.478594950603732,
1466
+ "grad_norm": 0.7005311250686646,
1467
+ "learning_rate": 0.0002,
1468
+ "loss": 0.6222,
1469
+ "step": 2040
1470
+ },
1471
+ {
1472
+ "epoch": 4.500548847420417,
1473
+ "grad_norm": 0.7746558785438538,
1474
+ "learning_rate": 0.0002,
1475
+ "loss": 0.6608,
1476
+ "step": 2050
1477
+ },
1478
+ {
1479
+ "epoch": 4.522502744237102,
1480
+ "grad_norm": 0.8261151313781738,
1481
+ "learning_rate": 0.0002,
1482
+ "loss": 0.6305,
1483
+ "step": 2060
1484
+ },
1485
+ {
1486
+ "epoch": 4.544456641053787,
1487
+ "grad_norm": 1.0917805433273315,
1488
+ "learning_rate": 0.0002,
1489
+ "loss": 0.6502,
1490
+ "step": 2070
1491
+ },
1492
+ {
1493
+ "epoch": 4.566410537870472,
1494
+ "grad_norm": 1.1570647954940796,
1495
+ "learning_rate": 0.0002,
1496
+ "loss": 0.6798,
1497
+ "step": 2080
1498
+ },
1499
+ {
1500
+ "epoch": 4.588364434687157,
1501
+ "grad_norm": 0.9936433434486389,
1502
+ "learning_rate": 0.0002,
1503
+ "loss": 0.6296,
1504
+ "step": 2090
1505
+ },
1506
+ {
1507
+ "epoch": 4.610318331503842,
1508
+ "grad_norm": 0.8574427366256714,
1509
+ "learning_rate": 0.0002,
1510
+ "loss": 0.5936,
1511
+ "step": 2100
1512
+ },
1513
+ {
1514
+ "epoch": 4.632272228320527,
1515
+ "grad_norm": 0.7630168795585632,
1516
+ "learning_rate": 0.0002,
1517
+ "loss": 0.6529,
1518
+ "step": 2110
1519
+ },
1520
+ {
1521
+ "epoch": 4.654226125137212,
1522
+ "grad_norm": 0.8146462440490723,
1523
+ "learning_rate": 0.0002,
1524
+ "loss": 0.5935,
1525
+ "step": 2120
1526
+ },
1527
+ {
1528
+ "epoch": 4.676180021953897,
1529
+ "grad_norm": 0.7090407609939575,
1530
+ "learning_rate": 0.0002,
1531
+ "loss": 0.7102,
1532
+ "step": 2130
1533
+ },
1534
+ {
1535
+ "epoch": 4.698133918770582,
1536
+ "grad_norm": 0.8278160095214844,
1537
+ "learning_rate": 0.0002,
1538
+ "loss": 0.6575,
1539
+ "step": 2140
1540
+ },
1541
+ {
1542
+ "epoch": 4.7200878155872665,
1543
+ "grad_norm": 0.9415683746337891,
1544
+ "learning_rate": 0.0002,
1545
+ "loss": 0.664,
1546
+ "step": 2150
1547
+ },
1548
+ {
1549
+ "epoch": 4.742041712403951,
1550
+ "grad_norm": 1.0056205987930298,
1551
+ "learning_rate": 0.0002,
1552
+ "loss": 0.7283,
1553
+ "step": 2160
1554
+ },
1555
+ {
1556
+ "epoch": 4.763995609220637,
1557
+ "grad_norm": 0.768304705619812,
1558
+ "learning_rate": 0.0002,
1559
+ "loss": 0.6845,
1560
+ "step": 2170
1561
+ },
1562
+ {
1563
+ "epoch": 4.785949506037322,
1564
+ "grad_norm": 1.0604112148284912,
1565
+ "learning_rate": 0.0002,
1566
+ "loss": 0.6922,
1567
+ "step": 2180
1568
+ },
1569
+ {
1570
+ "epoch": 4.807903402854007,
1571
+ "grad_norm": 1.132864236831665,
1572
+ "learning_rate": 0.0002,
1573
+ "loss": 0.7092,
1574
+ "step": 2190
1575
+ },
1576
+ {
1577
+ "epoch": 4.829857299670691,
1578
+ "grad_norm": 0.7543689608573914,
1579
+ "learning_rate": 0.0002,
1580
+ "loss": 0.6936,
1581
+ "step": 2200
1582
+ },
1583
+ {
1584
+ "epoch": 4.851811196487376,
1585
+ "grad_norm": 0.8047362565994263,
1586
+ "learning_rate": 0.0002,
1587
+ "loss": 0.6921,
1588
+ "step": 2210
1589
+ },
1590
+ {
1591
+ "epoch": 4.873765093304062,
1592
+ "grad_norm": 1.135778546333313,
1593
+ "learning_rate": 0.0002,
1594
+ "loss": 0.6753,
1595
+ "step": 2220
1596
+ },
1597
+ {
1598
+ "epoch": 4.895718990120747,
1599
+ "grad_norm": 0.9068503379821777,
1600
+ "learning_rate": 0.0002,
1601
+ "loss": 0.6443,
1602
+ "step": 2230
1603
+ },
1604
+ {
1605
+ "epoch": 4.9176728869374315,
1606
+ "grad_norm": 1.822325587272644,
1607
+ "learning_rate": 0.0002,
1608
+ "loss": 0.7419,
1609
+ "step": 2240
1610
+ },
1611
+ {
1612
+ "epoch": 4.939626783754116,
1613
+ "grad_norm": 1.1124998331069946,
1614
+ "learning_rate": 0.0002,
1615
+ "loss": 0.6436,
1616
+ "step": 2250
1617
+ },
1618
+ {
1619
+ "epoch": 4.961580680570801,
1620
+ "grad_norm": 0.818484365940094,
1621
+ "learning_rate": 0.0002,
1622
+ "loss": 0.7423,
1623
+ "step": 2260
1624
+ },
1625
+ {
1626
+ "epoch": 4.983534577387486,
1627
+ "grad_norm": 1.0057194232940674,
1628
+ "learning_rate": 0.0002,
1629
+ "loss": 0.6872,
1630
+ "step": 2270
1631
+ },
1632
+ {
1633
+ "epoch": 4.998902305159166,
1634
+ "eval_loss": 1.4120490550994873,
1635
+ "eval_runtime": 87.5617,
1636
+ "eval_samples_per_second": 4.922,
1637
+ "eval_steps_per_second": 0.617,
1638
+ "step": 2277
1639
+ }
1640
+ ],
1641
+ "logging_steps": 10,
1642
+ "max_steps": 3640,
1643
+ "num_input_tokens_seen": 0,
1644
+ "num_train_epochs": 8,
1645
+ "save_steps": 200,
1646
+ "stateful_callbacks": {
1647
+ "TrainerControl": {
1648
+ "args": {
1649
+ "should_epoch_stop": false,
1650
+ "should_evaluate": false,
1651
+ "should_log": false,
1652
+ "should_save": true,
1653
+ "should_training_stop": false
1654
+ },
1655
+ "attributes": {}
1656
+ }
1657
+ },
1658
+ "total_flos": 1.0539760047095808e+17,
1659
+ "train_batch_size": 1,
1660
+ "trial_name": null,
1661
+ "trial_params": null
1662
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2277/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf90ce7dd53cc68edd44d14e30ca84a5d7431a5b99d4697b17af4b2f7ec0abab
3
+ size 5624
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:667c6b4ac631a3df51962f967def2173f4f013fddf97a06dda77a5b8b45e00ea
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f960eb6a99562ea0e9bd182ec9a173484345481d091a1a4369799782144d5793
3
+ size 55532666
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4510bdee8ebac6ee997ff7dd13f372e8fdf526e7ba9626c7c8dd9aaff07746d5
3
+ size 14244
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:945550866d1df72da91321b3e6aeb168119fb3964ab6ca020def3cdd749b589e
3
+ size 1064
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
+ size 17209961
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/trainer_state.json ADDED
@@ -0,0 +1,1992 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.205152153968811,
3
+ "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-911",
4
+ "epoch": 6.0,
5
+ "eval_steps": 10,
6
+ "global_step": 2733,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.021953896816684963,
13
+ "grad_norm": 0.6144012212753296,
14
+ "learning_rate": 0.0002,
15
+ "loss": 1.9887,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.043907793633369926,
20
+ "grad_norm": 0.5587220788002014,
21
+ "learning_rate": 0.0002,
22
+ "loss": 1.6882,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06586169045005488,
27
+ "grad_norm": 0.43262454867362976,
28
+ "learning_rate": 0.0002,
29
+ "loss": 1.399,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.08781558726673985,
34
+ "grad_norm": 0.4783053994178772,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.4675,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.10976948408342481,
41
+ "grad_norm": 0.44338956475257874,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.1771,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.13172338090010977,
48
+ "grad_norm": 0.7255092263221741,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.3706,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.15367727771679474,
55
+ "grad_norm": 0.46073833107948303,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.2601,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.1756311745334797,
62
+ "grad_norm": 0.6698123216629028,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.3049,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.19758507135016465,
69
+ "grad_norm": 0.4190150201320648,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.2975,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.21953896816684962,
76
+ "grad_norm": 0.4110015034675598,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.2797,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.2414928649835346,
83
+ "grad_norm": 0.33374306559562683,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.2896,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.26344676180021953,
90
+ "grad_norm": 0.3061307370662689,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.2268,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.2854006586169045,
97
+ "grad_norm": 0.4386885166168213,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.376,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.30735455543358947,
104
+ "grad_norm": 0.40116462111473083,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.1814,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.32930845225027444,
111
+ "grad_norm": 0.5887949466705322,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.2592,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3512623490669594,
118
+ "grad_norm": 0.3401573896408081,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.2372,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.3732162458836443,
125
+ "grad_norm": 0.3288364112377167,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.1901,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.3951701427003293,
132
+ "grad_norm": 0.4853297472000122,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.2335,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.41712403951701427,
139
+ "grad_norm": 2.6253697872161865,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.227,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.43907793633369924,
146
+ "grad_norm": 0.5598543286323547,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.2673,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.4610318331503842,
153
+ "grad_norm": 0.4046548902988434,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.3459,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.4829857299670692,
160
+ "grad_norm": 0.3686952590942383,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.265,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5049396267837541,
167
+ "grad_norm": 0.42458799481391907,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.1364,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5268935236004391,
174
+ "grad_norm": 0.5839895009994507,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.2094,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5488474204171241,
181
+ "grad_norm": 0.408288836479187,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.2073,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.570801317233809,
188
+ "grad_norm": 0.45887550711631775,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.3121,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.5927552140504939,
195
+ "grad_norm": 0.5440235733985901,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.2257,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6147091108671789,
202
+ "grad_norm": 0.3725181519985199,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.1003,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6366630076838639,
209
+ "grad_norm": 0.4309018850326538,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.1538,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6586169045005489,
216
+ "grad_norm": 0.31488674879074097,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.2097,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6805708013172338,
223
+ "grad_norm": 0.34194841980934143,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.1689,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7025246981339188,
230
+ "grad_norm": 0.3407684862613678,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.2579,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7244785949506037,
237
+ "grad_norm": 0.2985728085041046,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.1144,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7464324917672887,
244
+ "grad_norm": 0.42316871881484985,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.2056,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7683863885839737,
251
+ "grad_norm": 0.3124258816242218,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.1753,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.7903402854006586,
258
+ "grad_norm": 0.7727567553520203,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.2547,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8122941822173436,
265
+ "grad_norm": 0.363765686750412,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.124,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8342480790340285,
272
+ "grad_norm": 0.35582536458969116,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.1302,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8562019758507134,
279
+ "grad_norm": 0.31982025504112244,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.1787,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.8781558726673985,
286
+ "grad_norm": 0.34978964924812317,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.2056,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9001097694840834,
293
+ "grad_norm": 0.8346716165542603,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.3577,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9220636663007684,
300
+ "grad_norm": 0.31984028220176697,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.1029,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9440175631174533,
307
+ "grad_norm": 0.32078951597213745,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.0967,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9659714599341384,
314
+ "grad_norm": 0.3417500853538513,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.0936,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.9879253567508233,
321
+ "grad_norm": 0.42359477281570435,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.3412,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.9989023051591658,
328
+ "eval_loss": 1.2201528549194336,
329
+ "eval_runtime": 87.152,
330
+ "eval_samples_per_second": 4.945,
331
+ "eval_steps_per_second": 0.62,
332
+ "step": 455
333
+ },
334
+ {
335
+ "epoch": 1.0098792535675083,
336
+ "grad_norm": 0.37914523482322693,
337
+ "learning_rate": 0.0002,
338
+ "loss": 1.1909,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.031833150384193,
343
+ "grad_norm": 0.43655872344970703,
344
+ "learning_rate": 0.0002,
345
+ "loss": 1.0948,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.0537870472008781,
350
+ "grad_norm": 0.3673796057701111,
351
+ "learning_rate": 0.0002,
352
+ "loss": 1.0873,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.0757409440175631,
357
+ "grad_norm": 0.37673917412757874,
358
+ "learning_rate": 0.0002,
359
+ "loss": 1.0483,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.0976948408342482,
364
+ "grad_norm": 0.2893829345703125,
365
+ "learning_rate": 0.0002,
366
+ "loss": 1.0799,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.119648737650933,
371
+ "grad_norm": 0.5551970601081848,
372
+ "learning_rate": 0.0002,
373
+ "loss": 1.1847,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.141602634467618,
378
+ "grad_norm": 0.442104309797287,
379
+ "learning_rate": 0.0002,
380
+ "loss": 1.0885,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.163556531284303,
385
+ "grad_norm": 0.4035094976425171,
386
+ "learning_rate": 0.0002,
387
+ "loss": 1.1766,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.1855104281009878,
392
+ "grad_norm": 0.47009000182151794,
393
+ "learning_rate": 0.0002,
394
+ "loss": 1.0282,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.2074643249176729,
399
+ "grad_norm": 0.4118749797344208,
400
+ "learning_rate": 0.0002,
401
+ "loss": 1.2625,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.2294182217343579,
406
+ "grad_norm": 0.35173165798187256,
407
+ "learning_rate": 0.0002,
408
+ "loss": 1.0988,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.2513721185510427,
413
+ "grad_norm": 0.7024672031402588,
414
+ "learning_rate": 0.0002,
415
+ "loss": 1.0498,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.2733260153677277,
420
+ "grad_norm": 0.42657527327537537,
421
+ "learning_rate": 0.0002,
422
+ "loss": 1.1339,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.2952799121844127,
427
+ "grad_norm": 0.3815029561519623,
428
+ "learning_rate": 0.0002,
429
+ "loss": 1.0545,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.3172338090010978,
434
+ "grad_norm": 0.7031055688858032,
435
+ "learning_rate": 0.0002,
436
+ "loss": 1.1528,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.3391877058177828,
441
+ "grad_norm": 0.393911212682724,
442
+ "learning_rate": 0.0002,
443
+ "loss": 1.1347,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.3611416026344676,
448
+ "grad_norm": 0.5077702403068542,
449
+ "learning_rate": 0.0002,
450
+ "loss": 1.1901,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.3830954994511526,
455
+ "grad_norm": 2.330033302307129,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.1251,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.4050493962678376,
462
+ "grad_norm": 0.35322949290275574,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.0477,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.4270032930845225,
469
+ "grad_norm": 0.44401052594184875,
470
+ "learning_rate": 0.0002,
471
+ "loss": 1.14,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.4489571899012075,
476
+ "grad_norm": 0.35945481061935425,
477
+ "learning_rate": 0.0002,
478
+ "loss": 1.0318,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.4709110867178925,
483
+ "grad_norm": 0.3058856129646301,
484
+ "learning_rate": 0.0002,
485
+ "loss": 1.1988,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.4928649835345773,
490
+ "grad_norm": 0.7067602872848511,
491
+ "learning_rate": 0.0002,
492
+ "loss": 1.1545,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.5148188803512623,
497
+ "grad_norm": 0.4219357371330261,
498
+ "learning_rate": 0.0002,
499
+ "loss": 1.0925,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.5367727771679474,
504
+ "grad_norm": 0.5970841646194458,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.1622,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.5587266739846322,
511
+ "grad_norm": 0.4381934404373169,
512
+ "learning_rate": 0.0002,
513
+ "loss": 1.0803,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.5806805708013172,
518
+ "grad_norm": 0.4101450443267822,
519
+ "learning_rate": 0.0002,
520
+ "loss": 1.0961,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.6026344676180022,
525
+ "grad_norm": 0.3657490015029907,
526
+ "learning_rate": 0.0002,
527
+ "loss": 1.0474,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.624588364434687,
532
+ "grad_norm": 0.36240628361701965,
533
+ "learning_rate": 0.0002,
534
+ "loss": 1.0936,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.6465422612513723,
539
+ "grad_norm": 0.4103568494319916,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.0489,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.668496158068057,
546
+ "grad_norm": 0.3138505816459656,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.0919,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.690450054884742,
553
+ "grad_norm": 0.41215717792510986,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.2308,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.7124039517014271,
560
+ "grad_norm": 0.4589519202709198,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.1659,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.734357848518112,
567
+ "grad_norm": 0.4049508571624756,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.0913,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.756311745334797,
574
+ "grad_norm": 0.48557212948799133,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.1329,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.778265642151482,
581
+ "grad_norm": 0.5331754088401794,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.0729,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.8002195389681668,
588
+ "grad_norm": 0.3853185772895813,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.1452,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.8221734357848518,
595
+ "grad_norm": 0.424062579870224,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.1061,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.8441273326015368,
602
+ "grad_norm": 0.3418445289134979,
603
+ "learning_rate": 0.0002,
604
+ "loss": 1.1104,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.8660812294182216,
609
+ "grad_norm": 0.4045565128326416,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.0546,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.8880351262349067,
616
+ "grad_norm": 0.42155781388282776,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.1608,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.9099890230515917,
623
+ "grad_norm": 0.40554770827293396,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.0628,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.9319429198682765,
630
+ "grad_norm": 0.42644748091697693,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.1609,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.9538968166849617,
637
+ "grad_norm": 0.45260652899742126,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.1132,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.9758507135016465,
644
+ "grad_norm": 0.4114069938659668,
645
+ "learning_rate": 0.0002,
646
+ "loss": 1.048,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.9978046103183313,
651
+ "grad_norm": 0.375802218914032,
652
+ "learning_rate": 0.0002,
653
+ "loss": 1.1941,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 2.0,
658
+ "eval_loss": 1.205152153968811,
659
+ "eval_runtime": 86.8795,
660
+ "eval_samples_per_second": 4.961,
661
+ "eval_steps_per_second": 0.622,
662
+ "step": 911
663
+ },
664
+ {
665
+ "epoch": 2.0197585071350166,
666
+ "grad_norm": 0.47718703746795654,
667
+ "learning_rate": 0.0002,
668
+ "loss": 1.0897,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.0417124039517014,
673
+ "grad_norm": 0.45628082752227783,
674
+ "learning_rate": 0.0002,
675
+ "loss": 1.0329,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.063666300768386,
680
+ "grad_norm": 0.5933247804641724,
681
+ "learning_rate": 0.0002,
682
+ "loss": 1.0538,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.0856201975850714,
687
+ "grad_norm": 0.5355812907218933,
688
+ "learning_rate": 0.0002,
689
+ "loss": 1.0152,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.1075740944017562,
694
+ "grad_norm": 0.5860010385513306,
695
+ "learning_rate": 0.0002,
696
+ "loss": 1.0726,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.129527991218441,
701
+ "grad_norm": 0.7471673488616943,
702
+ "learning_rate": 0.0002,
703
+ "loss": 1.025,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.1514818880351263,
708
+ "grad_norm": 2.0918211936950684,
709
+ "learning_rate": 0.0002,
710
+ "loss": 1.0247,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.173435784851811,
715
+ "grad_norm": 0.4021058678627014,
716
+ "learning_rate": 0.0002,
717
+ "loss": 0.8947,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.1953896816684964,
722
+ "grad_norm": 0.564975380897522,
723
+ "learning_rate": 0.0002,
724
+ "loss": 0.8875,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.217343578485181,
729
+ "grad_norm": 0.46260079741477966,
730
+ "learning_rate": 0.0002,
731
+ "loss": 1.0264,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.239297475301866,
736
+ "grad_norm": 0.4791034460067749,
737
+ "learning_rate": 0.0002,
738
+ "loss": 0.9265,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.261251372118551,
743
+ "grad_norm": 0.5272043943405151,
744
+ "learning_rate": 0.0002,
745
+ "loss": 0.8869,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.283205268935236,
750
+ "grad_norm": 0.5221094489097595,
751
+ "learning_rate": 0.0002,
752
+ "loss": 1.0007,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.305159165751921,
757
+ "grad_norm": 0.558032751083374,
758
+ "learning_rate": 0.0002,
759
+ "loss": 0.9472,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.327113062568606,
764
+ "grad_norm": 0.5905590653419495,
765
+ "learning_rate": 0.0002,
766
+ "loss": 0.9617,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.349066959385291,
771
+ "grad_norm": 0.5308699607849121,
772
+ "learning_rate": 0.0002,
773
+ "loss": 0.9592,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.3710208562019757,
778
+ "grad_norm": 0.6375027894973755,
779
+ "learning_rate": 0.0002,
780
+ "loss": 1.0646,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.392974753018661,
785
+ "grad_norm": 0.7439115643501282,
786
+ "learning_rate": 0.0002,
787
+ "loss": 1.0354,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.4149286498353457,
792
+ "grad_norm": 0.41945117712020874,
793
+ "learning_rate": 0.0002,
794
+ "loss": 1.0212,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.436882546652031,
799
+ "grad_norm": 0.4891968369483948,
800
+ "learning_rate": 0.0002,
801
+ "loss": 0.9609,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.4588364434687158,
806
+ "grad_norm": 0.4686794579029083,
807
+ "learning_rate": 0.0002,
808
+ "loss": 0.9829,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.4807903402854006,
813
+ "grad_norm": 0.5204509496688843,
814
+ "learning_rate": 0.0002,
815
+ "loss": 0.8919,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.5027442371020854,
820
+ "grad_norm": 0.6779005527496338,
821
+ "learning_rate": 0.0002,
822
+ "loss": 0.8983,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.5246981339187706,
827
+ "grad_norm": 0.682621955871582,
828
+ "learning_rate": 0.0002,
829
+ "loss": 0.9733,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.5466520307354554,
834
+ "grad_norm": 0.5744376182556152,
835
+ "learning_rate": 0.0002,
836
+ "loss": 1.051,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.5686059275521407,
841
+ "grad_norm": 0.49954667687416077,
842
+ "learning_rate": 0.0002,
843
+ "loss": 0.8764,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.5905598243688255,
848
+ "grad_norm": 0.4761793315410614,
849
+ "learning_rate": 0.0002,
850
+ "loss": 0.9896,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.6125137211855103,
855
+ "grad_norm": 0.548299252986908,
856
+ "learning_rate": 0.0002,
857
+ "loss": 0.8593,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.6344676180021955,
862
+ "grad_norm": 0.5771360993385315,
863
+ "learning_rate": 0.0002,
864
+ "loss": 1.0017,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.6564215148188803,
869
+ "grad_norm": 0.5543120503425598,
870
+ "learning_rate": 0.0002,
871
+ "loss": 0.9858,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.6783754116355656,
876
+ "grad_norm": 0.7564870715141296,
877
+ "learning_rate": 0.0002,
878
+ "loss": 0.9565,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.7003293084522504,
883
+ "grad_norm": 0.8222362399101257,
884
+ "learning_rate": 0.0002,
885
+ "loss": 0.9753,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.722283205268935,
890
+ "grad_norm": 0.6894469857215881,
891
+ "learning_rate": 0.0002,
892
+ "loss": 1.0079,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.74423710208562,
897
+ "grad_norm": 0.6121546030044556,
898
+ "learning_rate": 0.0002,
899
+ "loss": 1.0106,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.7661909989023052,
904
+ "grad_norm": 0.521809995174408,
905
+ "learning_rate": 0.0002,
906
+ "loss": 0.9801,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.78814489571899,
911
+ "grad_norm": 0.766968309879303,
912
+ "learning_rate": 0.0002,
913
+ "loss": 1.0196,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.8100987925356753,
918
+ "grad_norm": 0.522331714630127,
919
+ "learning_rate": 0.0002,
920
+ "loss": 0.976,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.83205268935236,
925
+ "grad_norm": 0.42923519015312195,
926
+ "learning_rate": 0.0002,
927
+ "loss": 0.8866,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.854006586169045,
932
+ "grad_norm": 0.47810837626457214,
933
+ "learning_rate": 0.0002,
934
+ "loss": 0.9049,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.8759604829857297,
939
+ "grad_norm": 1.0958846807479858,
940
+ "learning_rate": 0.0002,
941
+ "loss": 1.0291,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.897914379802415,
946
+ "grad_norm": 0.4755791127681732,
947
+ "learning_rate": 0.0002,
948
+ "loss": 0.8724,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.9198682766190998,
953
+ "grad_norm": 0.5575157403945923,
954
+ "learning_rate": 0.0002,
955
+ "loss": 0.9317,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.941822173435785,
960
+ "grad_norm": 0.5938076376914978,
961
+ "learning_rate": 0.0002,
962
+ "loss": 1.0131,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.96377607025247,
967
+ "grad_norm": 0.5751763582229614,
968
+ "learning_rate": 0.0002,
969
+ "loss": 0.9857,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.9857299670691546,
974
+ "grad_norm": 0.5590175986289978,
975
+ "learning_rate": 0.0002,
976
+ "loss": 1.0212,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.9989023051591657,
981
+ "eval_loss": 1.2402944564819336,
982
+ "eval_runtime": 88.822,
983
+ "eval_samples_per_second": 4.852,
984
+ "eval_steps_per_second": 0.608,
985
+ "step": 1366
986
+ },
987
+ {
988
+ "epoch": 3.00768386388584,
989
+ "grad_norm": 0.463539719581604,
990
+ "learning_rate": 0.0002,
991
+ "loss": 0.844,
992
+ "step": 1370
993
+ },
994
+ {
995
+ "epoch": 3.0296377607025247,
996
+ "grad_norm": 0.6667885780334473,
997
+ "learning_rate": 0.0002,
998
+ "loss": 0.8955,
999
+ "step": 1380
1000
+ },
1001
+ {
1002
+ "epoch": 3.0515916575192095,
1003
+ "grad_norm": 0.5849342942237854,
1004
+ "learning_rate": 0.0002,
1005
+ "loss": 0.8765,
1006
+ "step": 1390
1007
+ },
1008
+ {
1009
+ "epoch": 3.0735455543358947,
1010
+ "grad_norm": 0.5571770668029785,
1011
+ "learning_rate": 0.0002,
1012
+ "loss": 0.7808,
1013
+ "step": 1400
1014
+ },
1015
+ {
1016
+ "epoch": 3.0954994511525795,
1017
+ "grad_norm": 0.5761234164237976,
1018
+ "learning_rate": 0.0002,
1019
+ "loss": 0.7448,
1020
+ "step": 1410
1021
+ },
1022
+ {
1023
+ "epoch": 3.1174533479692643,
1024
+ "grad_norm": 0.7277371883392334,
1025
+ "learning_rate": 0.0002,
1026
+ "loss": 0.7854,
1027
+ "step": 1420
1028
+ },
1029
+ {
1030
+ "epoch": 3.1394072447859496,
1031
+ "grad_norm": 0.5190334320068359,
1032
+ "learning_rate": 0.0002,
1033
+ "loss": 0.817,
1034
+ "step": 1430
1035
+ },
1036
+ {
1037
+ "epoch": 3.1613611416026344,
1038
+ "grad_norm": 0.632939875125885,
1039
+ "learning_rate": 0.0002,
1040
+ "loss": 0.7548,
1041
+ "step": 1440
1042
+ },
1043
+ {
1044
+ "epoch": 3.1833150384193196,
1045
+ "grad_norm": 0.7229540944099426,
1046
+ "learning_rate": 0.0002,
1047
+ "loss": 0.8447,
1048
+ "step": 1450
1049
+ },
1050
+ {
1051
+ "epoch": 3.2052689352360044,
1052
+ "grad_norm": 0.7584632039070129,
1053
+ "learning_rate": 0.0002,
1054
+ "loss": 0.8595,
1055
+ "step": 1460
1056
+ },
1057
+ {
1058
+ "epoch": 3.2272228320526892,
1059
+ "grad_norm": 0.6546088457107544,
1060
+ "learning_rate": 0.0002,
1061
+ "loss": 0.7456,
1062
+ "step": 1470
1063
+ },
1064
+ {
1065
+ "epoch": 3.2491767288693745,
1066
+ "grad_norm": 0.8116684556007385,
1067
+ "learning_rate": 0.0002,
1068
+ "loss": 0.8531,
1069
+ "step": 1480
1070
+ },
1071
+ {
1072
+ "epoch": 3.2711306256860593,
1073
+ "grad_norm": 0.6206557750701904,
1074
+ "learning_rate": 0.0002,
1075
+ "loss": 0.9272,
1076
+ "step": 1490
1077
+ },
1078
+ {
1079
+ "epoch": 3.293084522502744,
1080
+ "grad_norm": 0.5393369197845459,
1081
+ "learning_rate": 0.0002,
1082
+ "loss": 0.7972,
1083
+ "step": 1500
1084
+ },
1085
+ {
1086
+ "epoch": 3.3150384193194293,
1087
+ "grad_norm": 0.7006453275680542,
1088
+ "learning_rate": 0.0002,
1089
+ "loss": 0.7614,
1090
+ "step": 1510
1091
+ },
1092
+ {
1093
+ "epoch": 3.336992316136114,
1094
+ "grad_norm": 0.95253986120224,
1095
+ "learning_rate": 0.0002,
1096
+ "loss": 0.7358,
1097
+ "step": 1520
1098
+ },
1099
+ {
1100
+ "epoch": 3.358946212952799,
1101
+ "grad_norm": 0.8138132095336914,
1102
+ "learning_rate": 0.0002,
1103
+ "loss": 0.8131,
1104
+ "step": 1530
1105
+ },
1106
+ {
1107
+ "epoch": 3.380900109769484,
1108
+ "grad_norm": 0.7974302172660828,
1109
+ "learning_rate": 0.0002,
1110
+ "loss": 0.7738,
1111
+ "step": 1540
1112
+ },
1113
+ {
1114
+ "epoch": 3.402854006586169,
1115
+ "grad_norm": 0.6694685220718384,
1116
+ "learning_rate": 0.0002,
1117
+ "loss": 0.8161,
1118
+ "step": 1550
1119
+ },
1120
+ {
1121
+ "epoch": 3.4248079034028542,
1122
+ "grad_norm": 0.908634603023529,
1123
+ "learning_rate": 0.0002,
1124
+ "loss": 0.8503,
1125
+ "step": 1560
1126
+ },
1127
+ {
1128
+ "epoch": 3.446761800219539,
1129
+ "grad_norm": 0.5625193119049072,
1130
+ "learning_rate": 0.0002,
1131
+ "loss": 0.7609,
1132
+ "step": 1570
1133
+ },
1134
+ {
1135
+ "epoch": 3.468715697036224,
1136
+ "grad_norm": 0.779325544834137,
1137
+ "learning_rate": 0.0002,
1138
+ "loss": 0.7658,
1139
+ "step": 1580
1140
+ },
1141
+ {
1142
+ "epoch": 3.4906695938529086,
1143
+ "grad_norm": 0.7133058905601501,
1144
+ "learning_rate": 0.0002,
1145
+ "loss": 0.7485,
1146
+ "step": 1590
1147
+ },
1148
+ {
1149
+ "epoch": 3.512623490669594,
1150
+ "grad_norm": 0.6741108298301697,
1151
+ "learning_rate": 0.0002,
1152
+ "loss": 0.8847,
1153
+ "step": 1600
1154
+ },
1155
+ {
1156
+ "epoch": 3.5345773874862787,
1157
+ "grad_norm": 0.696982204914093,
1158
+ "learning_rate": 0.0002,
1159
+ "loss": 0.7838,
1160
+ "step": 1610
1161
+ },
1162
+ {
1163
+ "epoch": 3.556531284302964,
1164
+ "grad_norm": 0.7946001291275024,
1165
+ "learning_rate": 0.0002,
1166
+ "loss": 0.7195,
1167
+ "step": 1620
1168
+ },
1169
+ {
1170
+ "epoch": 3.5784851811196488,
1171
+ "grad_norm": 0.6313548684120178,
1172
+ "learning_rate": 0.0002,
1173
+ "loss": 0.7772,
1174
+ "step": 1630
1175
+ },
1176
+ {
1177
+ "epoch": 3.6004390779363336,
1178
+ "grad_norm": 0.9246852397918701,
1179
+ "learning_rate": 0.0002,
1180
+ "loss": 0.8267,
1181
+ "step": 1640
1182
+ },
1183
+ {
1184
+ "epoch": 3.622392974753019,
1185
+ "grad_norm": 0.6615420579910278,
1186
+ "learning_rate": 0.0002,
1187
+ "loss": 0.779,
1188
+ "step": 1650
1189
+ },
1190
+ {
1191
+ "epoch": 3.6443468715697036,
1192
+ "grad_norm": 1.5050125122070312,
1193
+ "learning_rate": 0.0002,
1194
+ "loss": 0.883,
1195
+ "step": 1660
1196
+ },
1197
+ {
1198
+ "epoch": 3.666300768386389,
1199
+ "grad_norm": 0.5023762583732605,
1200
+ "learning_rate": 0.0002,
1201
+ "loss": 0.7763,
1202
+ "step": 1670
1203
+ },
1204
+ {
1205
+ "epoch": 3.6882546652030737,
1206
+ "grad_norm": 0.6289586424827576,
1207
+ "learning_rate": 0.0002,
1208
+ "loss": 0.8173,
1209
+ "step": 1680
1210
+ },
1211
+ {
1212
+ "epoch": 3.7102085620197585,
1213
+ "grad_norm": 1.050397515296936,
1214
+ "learning_rate": 0.0002,
1215
+ "loss": 0.9028,
1216
+ "step": 1690
1217
+ },
1218
+ {
1219
+ "epoch": 3.7321624588364433,
1220
+ "grad_norm": 0.6785626411437988,
1221
+ "learning_rate": 0.0002,
1222
+ "loss": 0.7747,
1223
+ "step": 1700
1224
+ },
1225
+ {
1226
+ "epoch": 3.7541163556531285,
1227
+ "grad_norm": 0.7565035223960876,
1228
+ "learning_rate": 0.0002,
1229
+ "loss": 0.9215,
1230
+ "step": 1710
1231
+ },
1232
+ {
1233
+ "epoch": 3.7760702524698133,
1234
+ "grad_norm": 0.7775155901908875,
1235
+ "learning_rate": 0.0002,
1236
+ "loss": 0.7913,
1237
+ "step": 1720
1238
+ },
1239
+ {
1240
+ "epoch": 3.7980241492864986,
1241
+ "grad_norm": 0.765260636806488,
1242
+ "learning_rate": 0.0002,
1243
+ "loss": 0.8081,
1244
+ "step": 1730
1245
+ },
1246
+ {
1247
+ "epoch": 3.8199780461031834,
1248
+ "grad_norm": 0.7982407808303833,
1249
+ "learning_rate": 0.0002,
1250
+ "loss": 0.9231,
1251
+ "step": 1740
1252
+ },
1253
+ {
1254
+ "epoch": 3.841931942919868,
1255
+ "grad_norm": 0.7431730628013611,
1256
+ "learning_rate": 0.0002,
1257
+ "loss": 0.7755,
1258
+ "step": 1750
1259
+ },
1260
+ {
1261
+ "epoch": 3.863885839736553,
1262
+ "grad_norm": 0.9758927226066589,
1263
+ "learning_rate": 0.0002,
1264
+ "loss": 0.9236,
1265
+ "step": 1760
1266
+ },
1267
+ {
1268
+ "epoch": 3.885839736553238,
1269
+ "grad_norm": 0.8014697432518005,
1270
+ "learning_rate": 0.0002,
1271
+ "loss": 0.9118,
1272
+ "step": 1770
1273
+ },
1274
+ {
1275
+ "epoch": 3.907793633369923,
1276
+ "grad_norm": 0.7212756276130676,
1277
+ "learning_rate": 0.0002,
1278
+ "loss": 0.7503,
1279
+ "step": 1780
1280
+ },
1281
+ {
1282
+ "epoch": 3.9297475301866083,
1283
+ "grad_norm": 0.584318220615387,
1284
+ "learning_rate": 0.0002,
1285
+ "loss": 0.7978,
1286
+ "step": 1790
1287
+ },
1288
+ {
1289
+ "epoch": 3.951701427003293,
1290
+ "grad_norm": 0.7612535953521729,
1291
+ "learning_rate": 0.0002,
1292
+ "loss": 0.7894,
1293
+ "step": 1800
1294
+ },
1295
+ {
1296
+ "epoch": 3.973655323819978,
1297
+ "grad_norm": 0.735103189945221,
1298
+ "learning_rate": 0.0002,
1299
+ "loss": 0.8589,
1300
+ "step": 1810
1301
+ },
1302
+ {
1303
+ "epoch": 3.995609220636663,
1304
+ "grad_norm": 0.9074980020523071,
1305
+ "learning_rate": 0.0002,
1306
+ "loss": 0.8192,
1307
+ "step": 1820
1308
+ },
1309
+ {
1310
+ "epoch": 4.0,
1311
+ "eval_loss": 1.279890537261963,
1312
+ "eval_runtime": 88.8969,
1313
+ "eval_samples_per_second": 4.848,
1314
+ "eval_steps_per_second": 0.607,
1315
+ "step": 1822
1316
+ },
1317
+ {
1318
+ "epoch": 4.017563117453348,
1319
+ "grad_norm": 0.9290254712104797,
1320
+ "learning_rate": 0.0002,
1321
+ "loss": 0.7312,
1322
+ "step": 1830
1323
+ },
1324
+ {
1325
+ "epoch": 4.039517014270033,
1326
+ "grad_norm": 0.723889946937561,
1327
+ "learning_rate": 0.0002,
1328
+ "loss": 0.6896,
1329
+ "step": 1840
1330
+ },
1331
+ {
1332
+ "epoch": 4.061470911086718,
1333
+ "grad_norm": 0.5906972289085388,
1334
+ "learning_rate": 0.0002,
1335
+ "loss": 0.632,
1336
+ "step": 1850
1337
+ },
1338
+ {
1339
+ "epoch": 4.083424807903403,
1340
+ "grad_norm": 0.8078910708427429,
1341
+ "learning_rate": 0.0002,
1342
+ "loss": 0.6594,
1343
+ "step": 1860
1344
+ },
1345
+ {
1346
+ "epoch": 4.105378704720088,
1347
+ "grad_norm": 1.0101137161254883,
1348
+ "learning_rate": 0.0002,
1349
+ "loss": 0.6242,
1350
+ "step": 1870
1351
+ },
1352
+ {
1353
+ "epoch": 4.127332601536772,
1354
+ "grad_norm": 0.8710281848907471,
1355
+ "learning_rate": 0.0002,
1356
+ "loss": 0.7259,
1357
+ "step": 1880
1358
+ },
1359
+ {
1360
+ "epoch": 4.149286498353458,
1361
+ "grad_norm": 0.9604734778404236,
1362
+ "learning_rate": 0.0002,
1363
+ "loss": 0.6993,
1364
+ "step": 1890
1365
+ },
1366
+ {
1367
+ "epoch": 4.171240395170143,
1368
+ "grad_norm": 0.9829702377319336,
1369
+ "learning_rate": 0.0002,
1370
+ "loss": 0.6706,
1371
+ "step": 1900
1372
+ },
1373
+ {
1374
+ "epoch": 4.193194291986828,
1375
+ "grad_norm": 0.6572765707969666,
1376
+ "learning_rate": 0.0002,
1377
+ "loss": 0.7013,
1378
+ "step": 1910
1379
+ },
1380
+ {
1381
+ "epoch": 4.2151481888035125,
1382
+ "grad_norm": 0.8459188938140869,
1383
+ "learning_rate": 0.0002,
1384
+ "loss": 0.5539,
1385
+ "step": 1920
1386
+ },
1387
+ {
1388
+ "epoch": 4.237102085620197,
1389
+ "grad_norm": 0.8321021795272827,
1390
+ "learning_rate": 0.0002,
1391
+ "loss": 0.6235,
1392
+ "step": 1930
1393
+ },
1394
+ {
1395
+ "epoch": 4.259055982436882,
1396
+ "grad_norm": 0.8611727356910706,
1397
+ "learning_rate": 0.0002,
1398
+ "loss": 0.6442,
1399
+ "step": 1940
1400
+ },
1401
+ {
1402
+ "epoch": 4.281009879253568,
1403
+ "grad_norm": 0.8490208387374878,
1404
+ "learning_rate": 0.0002,
1405
+ "loss": 0.6852,
1406
+ "step": 1950
1407
+ },
1408
+ {
1409
+ "epoch": 4.302963776070253,
1410
+ "grad_norm": 0.9628722667694092,
1411
+ "learning_rate": 0.0002,
1412
+ "loss": 0.6175,
1413
+ "step": 1960
1414
+ },
1415
+ {
1416
+ "epoch": 4.324917672886937,
1417
+ "grad_norm": 0.9632807374000549,
1418
+ "learning_rate": 0.0002,
1419
+ "loss": 0.5982,
1420
+ "step": 1970
1421
+ },
1422
+ {
1423
+ "epoch": 4.346871569703622,
1424
+ "grad_norm": 0.7023298740386963,
1425
+ "learning_rate": 0.0002,
1426
+ "loss": 0.6138,
1427
+ "step": 1980
1428
+ },
1429
+ {
1430
+ "epoch": 4.368825466520307,
1431
+ "grad_norm": 0.7912909388542175,
1432
+ "learning_rate": 0.0002,
1433
+ "loss": 0.6012,
1434
+ "step": 1990
1435
+ },
1436
+ {
1437
+ "epoch": 4.390779363336993,
1438
+ "grad_norm": 1.1463429927825928,
1439
+ "learning_rate": 0.0002,
1440
+ "loss": 0.6767,
1441
+ "step": 2000
1442
+ },
1443
+ {
1444
+ "epoch": 4.4127332601536775,
1445
+ "grad_norm": 1.1780626773834229,
1446
+ "learning_rate": 0.0002,
1447
+ "loss": 0.6607,
1448
+ "step": 2010
1449
+ },
1450
+ {
1451
+ "epoch": 4.434687156970362,
1452
+ "grad_norm": 0.9349206686019897,
1453
+ "learning_rate": 0.0002,
1454
+ "loss": 0.6746,
1455
+ "step": 2020
1456
+ },
1457
+ {
1458
+ "epoch": 4.456641053787047,
1459
+ "grad_norm": 0.7816639542579651,
1460
+ "learning_rate": 0.0002,
1461
+ "loss": 0.7087,
1462
+ "step": 2030
1463
+ },
1464
+ {
1465
+ "epoch": 4.478594950603732,
1466
+ "grad_norm": 0.7005311250686646,
1467
+ "learning_rate": 0.0002,
1468
+ "loss": 0.6222,
1469
+ "step": 2040
1470
+ },
1471
+ {
1472
+ "epoch": 4.500548847420417,
1473
+ "grad_norm": 0.7746558785438538,
1474
+ "learning_rate": 0.0002,
1475
+ "loss": 0.6608,
1476
+ "step": 2050
1477
+ },
1478
+ {
1479
+ "epoch": 4.522502744237102,
1480
+ "grad_norm": 0.8261151313781738,
1481
+ "learning_rate": 0.0002,
1482
+ "loss": 0.6305,
1483
+ "step": 2060
1484
+ },
1485
+ {
1486
+ "epoch": 4.544456641053787,
1487
+ "grad_norm": 1.0917805433273315,
1488
+ "learning_rate": 0.0002,
1489
+ "loss": 0.6502,
1490
+ "step": 2070
1491
+ },
1492
+ {
1493
+ "epoch": 4.566410537870472,
1494
+ "grad_norm": 1.1570647954940796,
1495
+ "learning_rate": 0.0002,
1496
+ "loss": 0.6798,
1497
+ "step": 2080
1498
+ },
1499
+ {
1500
+ "epoch": 4.588364434687157,
1501
+ "grad_norm": 0.9936433434486389,
1502
+ "learning_rate": 0.0002,
1503
+ "loss": 0.6296,
1504
+ "step": 2090
1505
+ },
1506
+ {
1507
+ "epoch": 4.610318331503842,
1508
+ "grad_norm": 0.8574427366256714,
1509
+ "learning_rate": 0.0002,
1510
+ "loss": 0.5936,
1511
+ "step": 2100
1512
+ },
1513
+ {
1514
+ "epoch": 4.632272228320527,
1515
+ "grad_norm": 0.7630168795585632,
1516
+ "learning_rate": 0.0002,
1517
+ "loss": 0.6529,
1518
+ "step": 2110
1519
+ },
1520
+ {
1521
+ "epoch": 4.654226125137212,
1522
+ "grad_norm": 0.8146462440490723,
1523
+ "learning_rate": 0.0002,
1524
+ "loss": 0.5935,
1525
+ "step": 2120
1526
+ },
1527
+ {
1528
+ "epoch": 4.676180021953897,
1529
+ "grad_norm": 0.7090407609939575,
1530
+ "learning_rate": 0.0002,
1531
+ "loss": 0.7102,
1532
+ "step": 2130
1533
+ },
1534
+ {
1535
+ "epoch": 4.698133918770582,
1536
+ "grad_norm": 0.8278160095214844,
1537
+ "learning_rate": 0.0002,
1538
+ "loss": 0.6575,
1539
+ "step": 2140
1540
+ },
1541
+ {
1542
+ "epoch": 4.7200878155872665,
1543
+ "grad_norm": 0.9415683746337891,
1544
+ "learning_rate": 0.0002,
1545
+ "loss": 0.664,
1546
+ "step": 2150
1547
+ },
1548
+ {
1549
+ "epoch": 4.742041712403951,
1550
+ "grad_norm": 1.0056205987930298,
1551
+ "learning_rate": 0.0002,
1552
+ "loss": 0.7283,
1553
+ "step": 2160
1554
+ },
1555
+ {
1556
+ "epoch": 4.763995609220637,
1557
+ "grad_norm": 0.768304705619812,
1558
+ "learning_rate": 0.0002,
1559
+ "loss": 0.6845,
1560
+ "step": 2170
1561
+ },
1562
+ {
1563
+ "epoch": 4.785949506037322,
1564
+ "grad_norm": 1.0604112148284912,
1565
+ "learning_rate": 0.0002,
1566
+ "loss": 0.6922,
1567
+ "step": 2180
1568
+ },
1569
+ {
1570
+ "epoch": 4.807903402854007,
1571
+ "grad_norm": 1.132864236831665,
1572
+ "learning_rate": 0.0002,
1573
+ "loss": 0.7092,
1574
+ "step": 2190
1575
+ },
1576
+ {
1577
+ "epoch": 4.829857299670691,
1578
+ "grad_norm": 0.7543689608573914,
1579
+ "learning_rate": 0.0002,
1580
+ "loss": 0.6936,
1581
+ "step": 2200
1582
+ },
1583
+ {
1584
+ "epoch": 4.851811196487376,
1585
+ "grad_norm": 0.8047362565994263,
1586
+ "learning_rate": 0.0002,
1587
+ "loss": 0.6921,
1588
+ "step": 2210
1589
+ },
1590
+ {
1591
+ "epoch": 4.873765093304062,
1592
+ "grad_norm": 1.135778546333313,
1593
+ "learning_rate": 0.0002,
1594
+ "loss": 0.6753,
1595
+ "step": 2220
1596
+ },
1597
+ {
1598
+ "epoch": 4.895718990120747,
1599
+ "grad_norm": 0.9068503379821777,
1600
+ "learning_rate": 0.0002,
1601
+ "loss": 0.6443,
1602
+ "step": 2230
1603
+ },
1604
+ {
1605
+ "epoch": 4.9176728869374315,
1606
+ "grad_norm": 1.822325587272644,
1607
+ "learning_rate": 0.0002,
1608
+ "loss": 0.7419,
1609
+ "step": 2240
1610
+ },
1611
+ {
1612
+ "epoch": 4.939626783754116,
1613
+ "grad_norm": 1.1124998331069946,
1614
+ "learning_rate": 0.0002,
1615
+ "loss": 0.6436,
1616
+ "step": 2250
1617
+ },
1618
+ {
1619
+ "epoch": 4.961580680570801,
1620
+ "grad_norm": 0.818484365940094,
1621
+ "learning_rate": 0.0002,
1622
+ "loss": 0.7423,
1623
+ "step": 2260
1624
+ },
1625
+ {
1626
+ "epoch": 4.983534577387486,
1627
+ "grad_norm": 1.0057194232940674,
1628
+ "learning_rate": 0.0002,
1629
+ "loss": 0.6872,
1630
+ "step": 2270
1631
+ },
1632
+ {
1633
+ "epoch": 4.998902305159166,
1634
+ "eval_loss": 1.4120490550994873,
1635
+ "eval_runtime": 87.5617,
1636
+ "eval_samples_per_second": 4.922,
1637
+ "eval_steps_per_second": 0.617,
1638
+ "step": 2277
1639
+ },
1640
+ {
1641
+ "epoch": 5.005488474204172,
1642
+ "grad_norm": 0.8211547136306763,
1643
+ "learning_rate": 0.0002,
1644
+ "loss": 0.5451,
1645
+ "step": 2280
1646
+ },
1647
+ {
1648
+ "epoch": 5.0274423710208564,
1649
+ "grad_norm": 1.1704130172729492,
1650
+ "learning_rate": 0.0002,
1651
+ "loss": 0.4965,
1652
+ "step": 2290
1653
+ },
1654
+ {
1655
+ "epoch": 5.049396267837541,
1656
+ "grad_norm": 1.033539891242981,
1657
+ "learning_rate": 0.0002,
1658
+ "loss": 0.4827,
1659
+ "step": 2300
1660
+ },
1661
+ {
1662
+ "epoch": 5.071350164654226,
1663
+ "grad_norm": 0.8830313682556152,
1664
+ "learning_rate": 0.0002,
1665
+ "loss": 0.447,
1666
+ "step": 2310
1667
+ },
1668
+ {
1669
+ "epoch": 5.093304061470911,
1670
+ "grad_norm": 1.160437822341919,
1671
+ "learning_rate": 0.0002,
1672
+ "loss": 0.5502,
1673
+ "step": 2320
1674
+ },
1675
+ {
1676
+ "epoch": 5.115257958287596,
1677
+ "grad_norm": 0.919956386089325,
1678
+ "learning_rate": 0.0002,
1679
+ "loss": 0.5123,
1680
+ "step": 2330
1681
+ },
1682
+ {
1683
+ "epoch": 5.137211855104281,
1684
+ "grad_norm": 1.0099905729293823,
1685
+ "learning_rate": 0.0002,
1686
+ "loss": 0.4784,
1687
+ "step": 2340
1688
+ },
1689
+ {
1690
+ "epoch": 5.159165751920966,
1691
+ "grad_norm": 1.1484816074371338,
1692
+ "learning_rate": 0.0002,
1693
+ "loss": 0.5109,
1694
+ "step": 2350
1695
+ },
1696
+ {
1697
+ "epoch": 5.181119648737651,
1698
+ "grad_norm": 1.0373470783233643,
1699
+ "learning_rate": 0.0002,
1700
+ "loss": 0.5222,
1701
+ "step": 2360
1702
+ },
1703
+ {
1704
+ "epoch": 5.203073545554336,
1705
+ "grad_norm": 1.0824922323226929,
1706
+ "learning_rate": 0.0002,
1707
+ "loss": 0.5366,
1708
+ "step": 2370
1709
+ },
1710
+ {
1711
+ "epoch": 5.225027442371021,
1712
+ "grad_norm": 1.3817942142486572,
1713
+ "learning_rate": 0.0002,
1714
+ "loss": 0.5592,
1715
+ "step": 2380
1716
+ },
1717
+ {
1718
+ "epoch": 5.246981339187705,
1719
+ "grad_norm": 1.197035551071167,
1720
+ "learning_rate": 0.0002,
1721
+ "loss": 0.504,
1722
+ "step": 2390
1723
+ },
1724
+ {
1725
+ "epoch": 5.268935236004391,
1726
+ "grad_norm": 1.098778486251831,
1727
+ "learning_rate": 0.0002,
1728
+ "loss": 0.5326,
1729
+ "step": 2400
1730
+ },
1731
+ {
1732
+ "epoch": 5.290889132821076,
1733
+ "grad_norm": 0.9713385105133057,
1734
+ "learning_rate": 0.0002,
1735
+ "loss": 0.5039,
1736
+ "step": 2410
1737
+ },
1738
+ {
1739
+ "epoch": 5.312843029637761,
1740
+ "grad_norm": 1.321574330329895,
1741
+ "learning_rate": 0.0002,
1742
+ "loss": 0.5735,
1743
+ "step": 2420
1744
+ },
1745
+ {
1746
+ "epoch": 5.3347969264544455,
1747
+ "grad_norm": 0.9402496218681335,
1748
+ "learning_rate": 0.0002,
1749
+ "loss": 0.4777,
1750
+ "step": 2430
1751
+ },
1752
+ {
1753
+ "epoch": 5.35675082327113,
1754
+ "grad_norm": 0.8644852042198181,
1755
+ "learning_rate": 0.0002,
1756
+ "loss": 0.5604,
1757
+ "step": 2440
1758
+ },
1759
+ {
1760
+ "epoch": 5.378704720087816,
1761
+ "grad_norm": 1.060290813446045,
1762
+ "learning_rate": 0.0002,
1763
+ "loss": 0.5324,
1764
+ "step": 2450
1765
+ },
1766
+ {
1767
+ "epoch": 5.400658616904501,
1768
+ "grad_norm": 1.0725265741348267,
1769
+ "learning_rate": 0.0002,
1770
+ "loss": 0.5366,
1771
+ "step": 2460
1772
+ },
1773
+ {
1774
+ "epoch": 5.422612513721186,
1775
+ "grad_norm": 0.9409431219100952,
1776
+ "learning_rate": 0.0002,
1777
+ "loss": 0.5469,
1778
+ "step": 2470
1779
+ },
1780
+ {
1781
+ "epoch": 5.44456641053787,
1782
+ "grad_norm": 1.1108187437057495,
1783
+ "learning_rate": 0.0002,
1784
+ "loss": 0.5186,
1785
+ "step": 2480
1786
+ },
1787
+ {
1788
+ "epoch": 5.466520307354555,
1789
+ "grad_norm": 1.0210821628570557,
1790
+ "learning_rate": 0.0002,
1791
+ "loss": 0.5312,
1792
+ "step": 2490
1793
+ },
1794
+ {
1795
+ "epoch": 5.48847420417124,
1796
+ "grad_norm": 1.110597014427185,
1797
+ "learning_rate": 0.0002,
1798
+ "loss": 0.5016,
1799
+ "step": 2500
1800
+ },
1801
+ {
1802
+ "epoch": 5.510428100987926,
1803
+ "grad_norm": 1.2534265518188477,
1804
+ "learning_rate": 0.0002,
1805
+ "loss": 0.511,
1806
+ "step": 2510
1807
+ },
1808
+ {
1809
+ "epoch": 5.5323819978046105,
1810
+ "grad_norm": 1.3389744758605957,
1811
+ "learning_rate": 0.0002,
1812
+ "loss": 0.6062,
1813
+ "step": 2520
1814
+ },
1815
+ {
1816
+ "epoch": 5.554335894621295,
1817
+ "grad_norm": 0.9520368576049805,
1818
+ "learning_rate": 0.0002,
1819
+ "loss": 0.4653,
1820
+ "step": 2530
1821
+ },
1822
+ {
1823
+ "epoch": 5.57628979143798,
1824
+ "grad_norm": 1.4737157821655273,
1825
+ "learning_rate": 0.0002,
1826
+ "loss": 0.4746,
1827
+ "step": 2540
1828
+ },
1829
+ {
1830
+ "epoch": 5.598243688254665,
1831
+ "grad_norm": 1.4143685102462769,
1832
+ "learning_rate": 0.0002,
1833
+ "loss": 0.5432,
1834
+ "step": 2550
1835
+ },
1836
+ {
1837
+ "epoch": 5.620197585071351,
1838
+ "grad_norm": 1.3573999404907227,
1839
+ "learning_rate": 0.0002,
1840
+ "loss": 0.4722,
1841
+ "step": 2560
1842
+ },
1843
+ {
1844
+ "epoch": 5.642151481888035,
1845
+ "grad_norm": 0.8475444316864014,
1846
+ "learning_rate": 0.0002,
1847
+ "loss": 0.5063,
1848
+ "step": 2570
1849
+ },
1850
+ {
1851
+ "epoch": 5.66410537870472,
1852
+ "grad_norm": 1.2670329809188843,
1853
+ "learning_rate": 0.0002,
1854
+ "loss": 0.4911,
1855
+ "step": 2580
1856
+ },
1857
+ {
1858
+ "epoch": 5.686059275521405,
1859
+ "grad_norm": 0.9688172936439514,
1860
+ "learning_rate": 0.0002,
1861
+ "loss": 0.5137,
1862
+ "step": 2590
1863
+ },
1864
+ {
1865
+ "epoch": 5.70801317233809,
1866
+ "grad_norm": 1.3652743101119995,
1867
+ "learning_rate": 0.0002,
1868
+ "loss": 0.5116,
1869
+ "step": 2600
1870
+ },
1871
+ {
1872
+ "epoch": 5.729967069154775,
1873
+ "grad_norm": 1.1475377082824707,
1874
+ "learning_rate": 0.0002,
1875
+ "loss": 0.5661,
1876
+ "step": 2610
1877
+ },
1878
+ {
1879
+ "epoch": 5.75192096597146,
1880
+ "grad_norm": 1.3105946779251099,
1881
+ "learning_rate": 0.0002,
1882
+ "loss": 0.567,
1883
+ "step": 2620
1884
+ },
1885
+ {
1886
+ "epoch": 5.773874862788145,
1887
+ "grad_norm": 0.920238196849823,
1888
+ "learning_rate": 0.0002,
1889
+ "loss": 0.4964,
1890
+ "step": 2630
1891
+ },
1892
+ {
1893
+ "epoch": 5.79582875960483,
1894
+ "grad_norm": 1.0981792211532593,
1895
+ "learning_rate": 0.0002,
1896
+ "loss": 0.5473,
1897
+ "step": 2640
1898
+ },
1899
+ {
1900
+ "epoch": 5.817782656421515,
1901
+ "grad_norm": 1.0734144449234009,
1902
+ "learning_rate": 0.0002,
1903
+ "loss": 0.5132,
1904
+ "step": 2650
1905
+ },
1906
+ {
1907
+ "epoch": 5.8397365532381995,
1908
+ "grad_norm": 1.0541702508926392,
1909
+ "learning_rate": 0.0002,
1910
+ "loss": 0.5404,
1911
+ "step": 2660
1912
+ },
1913
+ {
1914
+ "epoch": 5.861690450054885,
1915
+ "grad_norm": 1.0913143157958984,
1916
+ "learning_rate": 0.0002,
1917
+ "loss": 0.5056,
1918
+ "step": 2670
1919
+ },
1920
+ {
1921
+ "epoch": 5.88364434687157,
1922
+ "grad_norm": 1.0431408882141113,
1923
+ "learning_rate": 0.0002,
1924
+ "loss": 0.5425,
1925
+ "step": 2680
1926
+ },
1927
+ {
1928
+ "epoch": 5.905598243688255,
1929
+ "grad_norm": 1.3515729904174805,
1930
+ "learning_rate": 0.0002,
1931
+ "loss": 0.5398,
1932
+ "step": 2690
1933
+ },
1934
+ {
1935
+ "epoch": 5.92755214050494,
1936
+ "grad_norm": 1.3153903484344482,
1937
+ "learning_rate": 0.0002,
1938
+ "loss": 0.5936,
1939
+ "step": 2700
1940
+ },
1941
+ {
1942
+ "epoch": 5.949506037321624,
1943
+ "grad_norm": 1.024109125137329,
1944
+ "learning_rate": 0.0002,
1945
+ "loss": 0.5643,
1946
+ "step": 2710
1947
+ },
1948
+ {
1949
+ "epoch": 5.971459934138309,
1950
+ "grad_norm": 1.0308483839035034,
1951
+ "learning_rate": 0.0002,
1952
+ "loss": 0.5143,
1953
+ "step": 2720
1954
+ },
1955
+ {
1956
+ "epoch": 5.993413830954994,
1957
+ "grad_norm": 0.8329401016235352,
1958
+ "learning_rate": 0.0002,
1959
+ "loss": 0.4835,
1960
+ "step": 2730
1961
+ },
1962
+ {
1963
+ "epoch": 6.0,
1964
+ "eval_loss": 1.510581612586975,
1965
+ "eval_runtime": 89.0047,
1966
+ "eval_samples_per_second": 4.842,
1967
+ "eval_steps_per_second": 0.607,
1968
+ "step": 2733
1969
+ }
1970
+ ],
1971
+ "logging_steps": 10,
1972
+ "max_steps": 3640,
1973
+ "num_input_tokens_seen": 0,
1974
+ "num_train_epochs": 8,
1975
+ "save_steps": 200,
1976
+ "stateful_callbacks": {
1977
+ "TrainerControl": {
1978
+ "args": {
1979
+ "should_epoch_stop": false,
1980
+ "should_evaluate": false,
1981
+ "should_log": false,
1982
+ "should_save": true,
1983
+ "should_training_stop": false
1984
+ },
1985
+ "attributes": {}
1986
+ }
1987
+ },
1988
+ "total_flos": 1.264771205651497e+17,
1989
+ "train_batch_size": 1,
1990
+ "trial_name": null,
1991
+ "trial_params": null
1992
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-2733/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf90ce7dd53cc68edd44d14e30ca84a5d7431a5b99d4697b17af4b2f7ec0abab
3
+ size 5624
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2942-sd-4/checkpoint-3188/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }