MilaWang commited on
Commit
6cb998b
·
verified ·
1 Parent(s): ee3884e

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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/README.md +202 -0
  3. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/adapter_config.json +29 -0
  4. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/adapter_model.safetensors +3 -0
  5. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/README.md +202 -0
  6. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/adapter_config.json +29 -0
  7. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/adapter_model.safetensors +3 -0
  8. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/optimizer.pt +3 -0
  9. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/rng_state.pth +3 -0
  10. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/scheduler.pt +3 -0
  11. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/special_tokens_map.json +17 -0
  12. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/tokenizer.json +3 -0
  13. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/tokenizer_config.json +2063 -0
  14. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/trainer_state.json +0 -0
  15. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/training_args.bin +3 -0
  16. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/README.md +202 -0
  17. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/adapter_config.json +29 -0
  18. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/adapter_model.safetensors +3 -0
  19. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/optimizer.pt +3 -0
  20. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/rng_state.pth +3 -0
  21. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/scheduler.pt +3 -0
  22. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/special_tokens_map.json +17 -0
  23. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/tokenizer.json +3 -0
  24. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/tokenizer_config.json +2063 -0
  25. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/trainer_state.json +972 -0
  26. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/training_args.bin +3 -0
  27. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/README.md +202 -0
  28. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/adapter_config.json +29 -0
  29. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/adapter_model.safetensors +3 -0
  30. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/optimizer.pt +3 -0
  31. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/rng_state.pth +3 -0
  32. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/scheduler.pt +3 -0
  33. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/special_tokens_map.json +17 -0
  34. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/tokenizer.json +3 -0
  35. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/tokenizer_config.json +2063 -0
  36. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/trainer_state.json +1918 -0
  37. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/training_args.bin +3 -0
  38. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/README.md +202 -0
  39. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/adapter_config.json +29 -0
  40. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/adapter_model.safetensors +3 -0
  41. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/optimizer.pt +3 -0
  42. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/rng_state.pth +3 -0
  43. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/scheduler.pt +3 -0
  44. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/special_tokens_map.json +17 -0
  45. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/tokenizer.json +3 -0
  46. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/tokenizer_config.json +2063 -0
  47. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/trainer_state.json +2864 -0
  48. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/training_args.bin +3 -0
  49. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-5354/README.md +202 -0
  50. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-5354/adapter_config.json +29 -0
.gitattributes CHANGED
@@ -938,3 +938,12 @@ gemma-2b-it_int4_arc_challenge-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32
938
  gemma-2b-it_int4_arc_challenge-routerbench-0shot_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-308-sd-42/checkpoint-64/tokenizer.json filter=lfs diff=lfs merge=lfs -text
939
  gemma-2b-it_int4_arc_challenge-routerbench-0shot_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-308-sd-42/checkpoint-96/tokenizer.json filter=lfs diff=lfs merge=lfs -text
940
  gemma-2b-it_int4_arc_challenge-routerbench-0shot_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-308-sd-42/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
938
  gemma-2b-it_int4_arc_challenge-routerbench-0shot_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-308-sd-42/checkpoint-64/tokenizer.json filter=lfs diff=lfs merge=lfs -text
939
  gemma-2b-it_int4_arc_challenge-routerbench-0shot_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-308-sd-42/checkpoint-96/tokenizer.json filter=lfs diff=lfs merge=lfs -text
940
  gemma-2b-it_int4_arc_challenge-routerbench-0shot_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-308-sd-42/tokenizer.json filter=lfs diff=lfs merge=lfs -text
941
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/tokenizer.json filter=lfs diff=lfs merge=lfs -text
942
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/tokenizer.json filter=lfs diff=lfs merge=lfs -text
943
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/tokenizer.json filter=lfs diff=lfs merge=lfs -text
944
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/tokenizer.json filter=lfs diff=lfs merge=lfs -text
945
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-5354/tokenizer.json filter=lfs diff=lfs merge=lfs -text
946
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-6692/tokenizer.json filter=lfs diff=lfs merge=lfs -text
947
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-8031/tokenizer.json filter=lfs diff=lfs merge=lfs -text
948
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-9369/tokenizer.json filter=lfs diff=lfs merge=lfs -text
949
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8767e0d0604ccff5925fd06b1ebf5a468436644640dabefecdff8b512facf8aa
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abcdfcac6f09b8d04b847f0786435c773d18d77630561c9d325f90ae90a09178
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4baeb9cc32972d690c5b7a9b98b0eb28c6b8afd2ce9c908058754805719d6dd
3
+ size 55532666
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f3421092a5ba4c2db1ce51d3b93698e8a2c6e0239127b2a377690d0d1f4cc1
3
+ size 14244
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9340a5bf0cf4c7a2611e19a4b084d5b6085acada4269b8e0cfcdade92431d60d
3
+ size 1064
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-10704/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fc87da605e94ff0ecd8f5b371302a2d5f8727b77984707a2185ddb447fc3796
3
+ size 5560
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ea4fc35757651c7c3a6bde3cbe3a29f159b4d024130edde539538989c54f675
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4d3550f9d0c229652556a63f6a1db40a586e6c5c4c6a62b3dda5721a65c6553
3
+ size 55532666
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4da1ccefac00163faaeff70f727c5f6340a85466e9e936f079a69b938730bb96
3
+ size 14244
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392d8ed6255678b167709c169ac1b7830ba060af79331ac91cf29c25699c5e20
3
+ size 1064
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/trainer_state.json ADDED
@@ -0,0 +1,972 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.8051470518112183,
3
+ "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338",
4
+ "epoch": 0.9996264475158759,
5
+ "eval_steps": 10,
6
+ "global_step": 1338,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.007471049682480389,
13
+ "grad_norm": 0.4912872612476349,
14
+ "learning_rate": 0.0002,
15
+ "loss": 2.6181,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.014942099364960777,
20
+ "grad_norm": 0.4856316149234772,
21
+ "learning_rate": 0.0002,
22
+ "loss": 2.2606,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.022413149047441166,
27
+ "grad_norm": 0.47683125734329224,
28
+ "learning_rate": 0.0002,
29
+ "loss": 2.0957,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.029884198729921554,
34
+ "grad_norm": 0.515082597732544,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.8908,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.03735524841240194,
41
+ "grad_norm": 0.5299215316772461,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.9704,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.04482629809488233,
48
+ "grad_norm": 0.4951399862766266,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.9225,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.05229734777736272,
55
+ "grad_norm": 0.48079821467399597,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.9742,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.05976839745984311,
62
+ "grad_norm": 0.49402132630348206,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.9466,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.0672394471423235,
69
+ "grad_norm": 0.4778193235397339,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.8691,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.07471049682480388,
76
+ "grad_norm": 0.42472657561302185,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.8455,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.08218154650728428,
83
+ "grad_norm": 0.4433092474937439,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.8744,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.08965259618976466,
90
+ "grad_norm": 0.4472862780094147,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.865,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.09712364587224505,
97
+ "grad_norm": 0.42596298456192017,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.9256,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.10459469555472543,
104
+ "grad_norm": 0.46645811200141907,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.8015,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.11206574523720583,
111
+ "grad_norm": 0.41041234135627747,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.8307,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.11953679491968622,
118
+ "grad_norm": 0.5329819917678833,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.8276,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.1270078446021666,
125
+ "grad_norm": 0.4065922200679779,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.8118,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.134478894284647,
132
+ "grad_norm": 0.38406994938850403,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.8559,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.14194994396712737,
139
+ "grad_norm": 0.4246881306171417,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.8647,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.14942099364960776,
146
+ "grad_norm": 0.35136649012565613,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.8054,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.15689204333208817,
153
+ "grad_norm": 0.43252742290496826,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.802,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.16436309301456856,
160
+ "grad_norm": 0.39236941933631897,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.7823,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.17183414269704894,
167
+ "grad_norm": 0.3748249113559723,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.818,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.17930519237952933,
174
+ "grad_norm": 0.6432855725288391,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.866,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.1867762420620097,
181
+ "grad_norm": 0.34874802827835083,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.8397,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.1942472917444901,
188
+ "grad_norm": 0.3721984326839447,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.79,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.20171834142697048,
195
+ "grad_norm": 0.4339311420917511,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.8464,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.20918939110945087,
202
+ "grad_norm": 0.4018215537071228,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.8665,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.21666044079193125,
209
+ "grad_norm": 0.3278839886188507,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.8048,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.22413149047441167,
216
+ "grad_norm": 0.36146077513694763,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.7395,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.23160254015689205,
223
+ "grad_norm": 0.38175010681152344,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.7916,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.23907358983937244,
230
+ "grad_norm": 0.44776618480682373,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.8593,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.24654463952185282,
237
+ "grad_norm": 0.3933652937412262,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.7824,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.2540156892043332,
244
+ "grad_norm": 0.3515005111694336,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.8393,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.2614867388868136,
251
+ "grad_norm": 0.6683304309844971,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.8653,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.268957788569294,
258
+ "grad_norm": 0.37093454599380493,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.8797,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.2764288382517744,
265
+ "grad_norm": 0.3450651168823242,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.8251,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.28389988793425475,
272
+ "grad_norm": 0.5140917301177979,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.7435,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.29137093761673516,
279
+ "grad_norm": 0.32885563373565674,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.8026,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.2988419872992155,
286
+ "grad_norm": 0.33962297439575195,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.8174,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.30631303698169593,
293
+ "grad_norm": 0.3723141849040985,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.7467,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.31378408666417634,
300
+ "grad_norm": 0.37173134088516235,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.8459,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.3212551363466567,
307
+ "grad_norm": 0.33736956119537354,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.8876,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.3287261860291371,
314
+ "grad_norm": 0.3602448105812073,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.8367,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.33619723571161747,
321
+ "grad_norm": 0.3569699227809906,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.8058,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.3436682853940979,
328
+ "grad_norm": 0.31009167432785034,
329
+ "learning_rate": 0.0002,
330
+ "loss": 1.8086,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.35113933507657824,
335
+ "grad_norm": 0.5278693437576294,
336
+ "learning_rate": 0.0002,
337
+ "loss": 1.8876,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.35861038475905865,
342
+ "grad_norm": 0.3587537109851837,
343
+ "learning_rate": 0.0002,
344
+ "loss": 1.8534,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.366081434441539,
349
+ "grad_norm": 0.3859670162200928,
350
+ "learning_rate": 0.0002,
351
+ "loss": 1.8046,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.3735524841240194,
356
+ "grad_norm": 0.395913690328598,
357
+ "learning_rate": 0.0002,
358
+ "loss": 1.8287,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.38102353380649984,
363
+ "grad_norm": 0.35052940249443054,
364
+ "learning_rate": 0.0002,
365
+ "loss": 1.7619,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.3884945834889802,
370
+ "grad_norm": 0.2979494333267212,
371
+ "learning_rate": 0.0002,
372
+ "loss": 1.7824,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.3959656331714606,
377
+ "grad_norm": 0.3062683343887329,
378
+ "learning_rate": 0.0002,
379
+ "loss": 1.8641,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.40343668285394096,
384
+ "grad_norm": 0.3172847330570221,
385
+ "learning_rate": 0.0002,
386
+ "loss": 1.7651,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.4109077325364214,
391
+ "grad_norm": 0.360435426235199,
392
+ "learning_rate": 0.0002,
393
+ "loss": 1.806,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.41837878221890173,
398
+ "grad_norm": 0.3427872359752655,
399
+ "learning_rate": 0.0002,
400
+ "loss": 1.9054,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.42584983190138215,
405
+ "grad_norm": 0.34036558866500854,
406
+ "learning_rate": 0.0002,
407
+ "loss": 1.7562,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.4333208815838625,
412
+ "grad_norm": 0.3365345299243927,
413
+ "learning_rate": 0.0002,
414
+ "loss": 1.7254,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.4407919312663429,
419
+ "grad_norm": 0.35619041323661804,
420
+ "learning_rate": 0.0002,
421
+ "loss": 1.8328,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.44826298094882333,
426
+ "grad_norm": 0.3569088280200958,
427
+ "learning_rate": 0.0002,
428
+ "loss": 1.8114,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.4557340306313037,
433
+ "grad_norm": 0.3581278622150421,
434
+ "learning_rate": 0.0002,
435
+ "loss": 1.8599,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.4632050803137841,
440
+ "grad_norm": 0.43197110295295715,
441
+ "learning_rate": 0.0002,
442
+ "loss": 1.7078,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.47067612999626446,
447
+ "grad_norm": 0.33966198563575745,
448
+ "learning_rate": 0.0002,
449
+ "loss": 1.8257,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.47814717967874487,
454
+ "grad_norm": 0.3343866467475891,
455
+ "learning_rate": 0.0002,
456
+ "loss": 1.7528,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.48561822936122523,
461
+ "grad_norm": 0.33878564834594727,
462
+ "learning_rate": 0.0002,
463
+ "loss": 1.8191,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.49308927904370564,
468
+ "grad_norm": 0.387195885181427,
469
+ "learning_rate": 0.0002,
470
+ "loss": 1.8801,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.500560328726186,
475
+ "grad_norm": 0.3755440413951874,
476
+ "learning_rate": 0.0002,
477
+ "loss": 1.7559,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.5080313784086664,
482
+ "grad_norm": 0.3272816836833954,
483
+ "learning_rate": 0.0002,
484
+ "loss": 1.8057,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.5155024280911468,
489
+ "grad_norm": 0.36063864827156067,
490
+ "learning_rate": 0.0002,
491
+ "loss": 1.8156,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.5229734777736272,
496
+ "grad_norm": 0.35317373275756836,
497
+ "learning_rate": 0.0002,
498
+ "loss": 1.8397,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.5304445274561076,
503
+ "grad_norm": 0.3561195433139801,
504
+ "learning_rate": 0.0002,
505
+ "loss": 1.7603,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.537915577138588,
510
+ "grad_norm": 0.31124624609947205,
511
+ "learning_rate": 0.0002,
512
+ "loss": 1.8149,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.5453866268210683,
517
+ "grad_norm": 0.3294544517993927,
518
+ "learning_rate": 0.0002,
519
+ "loss": 1.7434,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.5528576765035488,
524
+ "grad_norm": 0.31933900713920593,
525
+ "learning_rate": 0.0002,
526
+ "loss": 1.8027,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.5603287261860291,
531
+ "grad_norm": 0.3226020634174347,
532
+ "learning_rate": 0.0002,
533
+ "loss": 1.7601,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.5677997758685095,
538
+ "grad_norm": 0.3147525489330292,
539
+ "learning_rate": 0.0002,
540
+ "loss": 1.7862,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.57527082555099,
545
+ "grad_norm": 0.32234328985214233,
546
+ "learning_rate": 0.0002,
547
+ "loss": 1.9028,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.5827418752334703,
552
+ "grad_norm": 0.3258664309978485,
553
+ "learning_rate": 0.0002,
554
+ "loss": 1.7623,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.5902129249159507,
559
+ "grad_norm": 0.3166961967945099,
560
+ "learning_rate": 0.0002,
561
+ "loss": 1.7384,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.597683974598431,
566
+ "grad_norm": 0.35621458292007446,
567
+ "learning_rate": 0.0002,
568
+ "loss": 1.8799,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.6051550242809115,
573
+ "grad_norm": 0.3236999213695526,
574
+ "learning_rate": 0.0002,
575
+ "loss": 1.8313,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.6126260739633919,
580
+ "grad_norm": 0.2892923653125763,
581
+ "learning_rate": 0.0002,
582
+ "loss": 1.7132,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.6200971236458722,
587
+ "grad_norm": 0.4098321497440338,
588
+ "learning_rate": 0.0002,
589
+ "loss": 1.8709,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.6275681733283527,
594
+ "grad_norm": 0.3337118923664093,
595
+ "learning_rate": 0.0002,
596
+ "loss": 1.7637,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.635039223010833,
601
+ "grad_norm": 0.30416029691696167,
602
+ "learning_rate": 0.0002,
603
+ "loss": 1.7375,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.6425102726933134,
608
+ "grad_norm": 0.3361026346683502,
609
+ "learning_rate": 0.0002,
610
+ "loss": 1.7419,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.6499813223757938,
615
+ "grad_norm": 0.3537365198135376,
616
+ "learning_rate": 0.0002,
617
+ "loss": 1.732,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.6574523720582742,
622
+ "grad_norm": 0.33854469656944275,
623
+ "learning_rate": 0.0002,
624
+ "loss": 1.7825,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.6649234217407546,
629
+ "grad_norm": 0.3332272469997406,
630
+ "learning_rate": 0.0002,
631
+ "loss": 1.7561,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.6723944714232349,
636
+ "grad_norm": 0.34954726696014404,
637
+ "learning_rate": 0.0002,
638
+ "loss": 1.7247,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.6798655211057153,
643
+ "grad_norm": 0.2921750247478485,
644
+ "learning_rate": 0.0002,
645
+ "loss": 1.7917,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.6873365707881958,
650
+ "grad_norm": 0.30508682131767273,
651
+ "learning_rate": 0.0002,
652
+ "loss": 1.7807,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.6948076204706761,
657
+ "grad_norm": 0.32268425822257996,
658
+ "learning_rate": 0.0002,
659
+ "loss": 1.8082,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.7022786701531565,
664
+ "grad_norm": 0.2844390869140625,
665
+ "learning_rate": 0.0002,
666
+ "loss": 1.8283,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.709749719835637,
671
+ "grad_norm": 0.31263890862464905,
672
+ "learning_rate": 0.0002,
673
+ "loss": 1.7363,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.7172207695181173,
678
+ "grad_norm": 0.3626808822154999,
679
+ "learning_rate": 0.0002,
680
+ "loss": 1.8081,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.7246918192005977,
685
+ "grad_norm": 0.3322749733924866,
686
+ "learning_rate": 0.0002,
687
+ "loss": 1.853,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.732162868883078,
692
+ "grad_norm": 0.29177871346473694,
693
+ "learning_rate": 0.0002,
694
+ "loss": 1.7912,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.7396339185655585,
699
+ "grad_norm": 0.35405513644218445,
700
+ "learning_rate": 0.0002,
701
+ "loss": 1.8447,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.7471049682480388,
706
+ "grad_norm": 0.39318400621414185,
707
+ "learning_rate": 0.0002,
708
+ "loss": 1.7008,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.7545760179305192,
713
+ "grad_norm": 0.29401418566703796,
714
+ "learning_rate": 0.0002,
715
+ "loss": 1.7803,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 0.7620470676129997,
720
+ "grad_norm": 0.3271748721599579,
721
+ "learning_rate": 0.0002,
722
+ "loss": 1.7649,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 0.76951811729548,
727
+ "grad_norm": 0.30883970856666565,
728
+ "learning_rate": 0.0002,
729
+ "loss": 1.7266,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 0.7769891669779604,
734
+ "grad_norm": 0.3411838412284851,
735
+ "learning_rate": 0.0002,
736
+ "loss": 1.7722,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 0.7844602166604407,
741
+ "grad_norm": 0.30608129501342773,
742
+ "learning_rate": 0.0002,
743
+ "loss": 1.829,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 0.7919312663429212,
748
+ "grad_norm": 0.30899080634117126,
749
+ "learning_rate": 0.0002,
750
+ "loss": 1.7815,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 0.7994023160254016,
755
+ "grad_norm": 0.3160453140735626,
756
+ "learning_rate": 0.0002,
757
+ "loss": 1.7625,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 0.8068733657078819,
762
+ "grad_norm": 0.30947187542915344,
763
+ "learning_rate": 0.0002,
764
+ "loss": 1.8452,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 0.8143444153903624,
769
+ "grad_norm": 0.3103134036064148,
770
+ "learning_rate": 0.0002,
771
+ "loss": 1.7418,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 0.8218154650728428,
776
+ "grad_norm": 0.31771138310432434,
777
+ "learning_rate": 0.0002,
778
+ "loss": 1.842,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 0.8292865147553231,
783
+ "grad_norm": 0.5860997438430786,
784
+ "learning_rate": 0.0002,
785
+ "loss": 1.7918,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 0.8367575644378035,
790
+ "grad_norm": 0.3230148255825043,
791
+ "learning_rate": 0.0002,
792
+ "loss": 1.8443,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 0.8442286141202839,
797
+ "grad_norm": 0.29611510038375854,
798
+ "learning_rate": 0.0002,
799
+ "loss": 1.8478,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 0.8516996638027643,
804
+ "grad_norm": 0.3373654782772064,
805
+ "learning_rate": 0.0002,
806
+ "loss": 1.7673,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 0.8591707134852447,
811
+ "grad_norm": 0.3474279046058655,
812
+ "learning_rate": 0.0002,
813
+ "loss": 1.7997,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 0.866641763167725,
818
+ "grad_norm": 0.35057875514030457,
819
+ "learning_rate": 0.0002,
820
+ "loss": 1.75,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 0.8741128128502055,
825
+ "grad_norm": 0.39537495374679565,
826
+ "learning_rate": 0.0002,
827
+ "loss": 1.8273,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 0.8815838625326858,
832
+ "grad_norm": 0.3714233636856079,
833
+ "learning_rate": 0.0002,
834
+ "loss": 1.7682,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 0.8890549122151662,
839
+ "grad_norm": 0.2950296998023987,
840
+ "learning_rate": 0.0002,
841
+ "loss": 1.7549,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 0.8965259618976467,
846
+ "grad_norm": 0.38182979822158813,
847
+ "learning_rate": 0.0002,
848
+ "loss": 1.7612,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 0.903997011580127,
853
+ "grad_norm": 0.27883678674697876,
854
+ "learning_rate": 0.0002,
855
+ "loss": 1.827,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 0.9114680612626074,
860
+ "grad_norm": 0.33874374628067017,
861
+ "learning_rate": 0.0002,
862
+ "loss": 1.7623,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 0.9189391109450877,
867
+ "grad_norm": 0.3014272153377533,
868
+ "learning_rate": 0.0002,
869
+ "loss": 1.7334,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 0.9264101606275682,
874
+ "grad_norm": 0.3194271922111511,
875
+ "learning_rate": 0.0002,
876
+ "loss": 1.8235,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 0.9338812103100486,
881
+ "grad_norm": 0.3049403429031372,
882
+ "learning_rate": 0.0002,
883
+ "loss": 1.7924,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 0.9413522599925289,
888
+ "grad_norm": 0.30621254444122314,
889
+ "learning_rate": 0.0002,
890
+ "loss": 1.7535,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 0.9488233096750094,
895
+ "grad_norm": 0.28675132989883423,
896
+ "learning_rate": 0.0002,
897
+ "loss": 1.8287,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 0.9562943593574897,
902
+ "grad_norm": 0.3322032690048218,
903
+ "learning_rate": 0.0002,
904
+ "loss": 1.7586,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 0.9637654090399701,
909
+ "grad_norm": 0.35408294200897217,
910
+ "learning_rate": 0.0002,
911
+ "loss": 1.8054,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 0.9712364587224505,
916
+ "grad_norm": 0.36386919021606445,
917
+ "learning_rate": 0.0002,
918
+ "loss": 1.7343,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 0.9787075084049309,
923
+ "grad_norm": 0.32338324189186096,
924
+ "learning_rate": 0.0002,
925
+ "loss": 1.8633,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 0.9861785580874113,
930
+ "grad_norm": 0.3714013993740082,
931
+ "learning_rate": 0.0002,
932
+ "loss": 1.7724,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 0.9936496077698916,
937
+ "grad_norm": 0.3133082389831543,
938
+ "learning_rate": 0.0002,
939
+ "loss": 1.7766,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 0.9996264475158759,
944
+ "eval_loss": 1.8051470518112183,
945
+ "eval_runtime": 38.6332,
946
+ "eval_samples_per_second": 13.331,
947
+ "eval_steps_per_second": 1.682,
948
+ "step": 1338
949
+ }
950
+ ],
951
+ "logging_steps": 10,
952
+ "max_steps": 10704,
953
+ "num_input_tokens_seen": 0,
954
+ "num_train_epochs": 8,
955
+ "save_steps": 200,
956
+ "stateful_callbacks": {
957
+ "TrainerControl": {
958
+ "args": {
959
+ "should_epoch_stop": false,
960
+ "should_evaluate": false,
961
+ "should_log": false,
962
+ "should_save": true,
963
+ "should_training_stop": false
964
+ },
965
+ "attributes": {}
966
+ }
967
+ },
968
+ "total_flos": 6.194278297711411e+16,
969
+ "train_batch_size": 1,
970
+ "trial_name": null,
971
+ "trial_params": null
972
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-1338/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fc87da605e94ff0ecd8f5b371302a2d5f8727b77984707a2185ddb447fc3796
3
+ size 5560
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8767e0d0604ccff5925fd06b1ebf5a468436644640dabefecdff8b512facf8aa
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7853c5f0c85c20e1969da93901ceeec41a9e7e3c7cdea7b0086247ba5bce952
3
+ size 55532666
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd7a777006d9d84e8e167a92deaa029dbda5c325805a5aee24ceddb0c3465d4a
3
+ size 14244
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5948bcf2b8a11466457f31ca0ea8be19b105a5e0386ed276110793dbcdcaaf44
3
+ size 1064
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/trainer_state.json ADDED
@@ -0,0 +1,1918 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.8046749830245972,
3
+ "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677",
4
+ "epoch": 2.0,
5
+ "eval_steps": 10,
6
+ "global_step": 2677,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.007471049682480389,
13
+ "grad_norm": 0.4912872612476349,
14
+ "learning_rate": 0.0002,
15
+ "loss": 2.6181,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.014942099364960777,
20
+ "grad_norm": 0.4856316149234772,
21
+ "learning_rate": 0.0002,
22
+ "loss": 2.2606,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.022413149047441166,
27
+ "grad_norm": 0.47683125734329224,
28
+ "learning_rate": 0.0002,
29
+ "loss": 2.0957,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.029884198729921554,
34
+ "grad_norm": 0.515082597732544,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.8908,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.03735524841240194,
41
+ "grad_norm": 0.5299215316772461,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.9704,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.04482629809488233,
48
+ "grad_norm": 0.4951399862766266,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.9225,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.05229734777736272,
55
+ "grad_norm": 0.48079821467399597,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.9742,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.05976839745984311,
62
+ "grad_norm": 0.49402132630348206,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.9466,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.0672394471423235,
69
+ "grad_norm": 0.4778193235397339,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.8691,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.07471049682480388,
76
+ "grad_norm": 0.42472657561302185,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.8455,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.08218154650728428,
83
+ "grad_norm": 0.4433092474937439,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.8744,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.08965259618976466,
90
+ "grad_norm": 0.4472862780094147,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.865,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.09712364587224505,
97
+ "grad_norm": 0.42596298456192017,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.9256,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.10459469555472543,
104
+ "grad_norm": 0.46645811200141907,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.8015,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.11206574523720583,
111
+ "grad_norm": 0.41041234135627747,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.8307,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.11953679491968622,
118
+ "grad_norm": 0.5329819917678833,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.8276,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.1270078446021666,
125
+ "grad_norm": 0.4065922200679779,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.8118,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.134478894284647,
132
+ "grad_norm": 0.38406994938850403,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.8559,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.14194994396712737,
139
+ "grad_norm": 0.4246881306171417,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.8647,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.14942099364960776,
146
+ "grad_norm": 0.35136649012565613,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.8054,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.15689204333208817,
153
+ "grad_norm": 0.43252742290496826,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.802,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.16436309301456856,
160
+ "grad_norm": 0.39236941933631897,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.7823,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.17183414269704894,
167
+ "grad_norm": 0.3748249113559723,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.818,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.17930519237952933,
174
+ "grad_norm": 0.6432855725288391,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.866,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.1867762420620097,
181
+ "grad_norm": 0.34874802827835083,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.8397,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.1942472917444901,
188
+ "grad_norm": 0.3721984326839447,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.79,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.20171834142697048,
195
+ "grad_norm": 0.4339311420917511,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.8464,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.20918939110945087,
202
+ "grad_norm": 0.4018215537071228,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.8665,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.21666044079193125,
209
+ "grad_norm": 0.3278839886188507,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.8048,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.22413149047441167,
216
+ "grad_norm": 0.36146077513694763,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.7395,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.23160254015689205,
223
+ "grad_norm": 0.38175010681152344,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.7916,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.23907358983937244,
230
+ "grad_norm": 0.44776618480682373,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.8593,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.24654463952185282,
237
+ "grad_norm": 0.3933652937412262,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.7824,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.2540156892043332,
244
+ "grad_norm": 0.3515005111694336,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.8393,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.2614867388868136,
251
+ "grad_norm": 0.6683304309844971,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.8653,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.268957788569294,
258
+ "grad_norm": 0.37093454599380493,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.8797,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.2764288382517744,
265
+ "grad_norm": 0.3450651168823242,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.8251,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.28389988793425475,
272
+ "grad_norm": 0.5140917301177979,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.7435,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.29137093761673516,
279
+ "grad_norm": 0.32885563373565674,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.8026,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.2988419872992155,
286
+ "grad_norm": 0.33962297439575195,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.8174,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.30631303698169593,
293
+ "grad_norm": 0.3723141849040985,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.7467,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.31378408666417634,
300
+ "grad_norm": 0.37173134088516235,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.8459,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.3212551363466567,
307
+ "grad_norm": 0.33736956119537354,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.8876,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.3287261860291371,
314
+ "grad_norm": 0.3602448105812073,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.8367,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.33619723571161747,
321
+ "grad_norm": 0.3569699227809906,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.8058,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.3436682853940979,
328
+ "grad_norm": 0.31009167432785034,
329
+ "learning_rate": 0.0002,
330
+ "loss": 1.8086,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.35113933507657824,
335
+ "grad_norm": 0.5278693437576294,
336
+ "learning_rate": 0.0002,
337
+ "loss": 1.8876,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.35861038475905865,
342
+ "grad_norm": 0.3587537109851837,
343
+ "learning_rate": 0.0002,
344
+ "loss": 1.8534,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.366081434441539,
349
+ "grad_norm": 0.3859670162200928,
350
+ "learning_rate": 0.0002,
351
+ "loss": 1.8046,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.3735524841240194,
356
+ "grad_norm": 0.395913690328598,
357
+ "learning_rate": 0.0002,
358
+ "loss": 1.8287,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.38102353380649984,
363
+ "grad_norm": 0.35052940249443054,
364
+ "learning_rate": 0.0002,
365
+ "loss": 1.7619,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.3884945834889802,
370
+ "grad_norm": 0.2979494333267212,
371
+ "learning_rate": 0.0002,
372
+ "loss": 1.7824,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.3959656331714606,
377
+ "grad_norm": 0.3062683343887329,
378
+ "learning_rate": 0.0002,
379
+ "loss": 1.8641,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.40343668285394096,
384
+ "grad_norm": 0.3172847330570221,
385
+ "learning_rate": 0.0002,
386
+ "loss": 1.7651,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.4109077325364214,
391
+ "grad_norm": 0.360435426235199,
392
+ "learning_rate": 0.0002,
393
+ "loss": 1.806,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.41837878221890173,
398
+ "grad_norm": 0.3427872359752655,
399
+ "learning_rate": 0.0002,
400
+ "loss": 1.9054,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.42584983190138215,
405
+ "grad_norm": 0.34036558866500854,
406
+ "learning_rate": 0.0002,
407
+ "loss": 1.7562,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.4333208815838625,
412
+ "grad_norm": 0.3365345299243927,
413
+ "learning_rate": 0.0002,
414
+ "loss": 1.7254,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.4407919312663429,
419
+ "grad_norm": 0.35619041323661804,
420
+ "learning_rate": 0.0002,
421
+ "loss": 1.8328,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.44826298094882333,
426
+ "grad_norm": 0.3569088280200958,
427
+ "learning_rate": 0.0002,
428
+ "loss": 1.8114,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.4557340306313037,
433
+ "grad_norm": 0.3581278622150421,
434
+ "learning_rate": 0.0002,
435
+ "loss": 1.8599,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.4632050803137841,
440
+ "grad_norm": 0.43197110295295715,
441
+ "learning_rate": 0.0002,
442
+ "loss": 1.7078,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.47067612999626446,
447
+ "grad_norm": 0.33966198563575745,
448
+ "learning_rate": 0.0002,
449
+ "loss": 1.8257,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.47814717967874487,
454
+ "grad_norm": 0.3343866467475891,
455
+ "learning_rate": 0.0002,
456
+ "loss": 1.7528,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.48561822936122523,
461
+ "grad_norm": 0.33878564834594727,
462
+ "learning_rate": 0.0002,
463
+ "loss": 1.8191,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.49308927904370564,
468
+ "grad_norm": 0.387195885181427,
469
+ "learning_rate": 0.0002,
470
+ "loss": 1.8801,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.500560328726186,
475
+ "grad_norm": 0.3755440413951874,
476
+ "learning_rate": 0.0002,
477
+ "loss": 1.7559,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.5080313784086664,
482
+ "grad_norm": 0.3272816836833954,
483
+ "learning_rate": 0.0002,
484
+ "loss": 1.8057,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.5155024280911468,
489
+ "grad_norm": 0.36063864827156067,
490
+ "learning_rate": 0.0002,
491
+ "loss": 1.8156,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.5229734777736272,
496
+ "grad_norm": 0.35317373275756836,
497
+ "learning_rate": 0.0002,
498
+ "loss": 1.8397,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.5304445274561076,
503
+ "grad_norm": 0.3561195433139801,
504
+ "learning_rate": 0.0002,
505
+ "loss": 1.7603,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.537915577138588,
510
+ "grad_norm": 0.31124624609947205,
511
+ "learning_rate": 0.0002,
512
+ "loss": 1.8149,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.5453866268210683,
517
+ "grad_norm": 0.3294544517993927,
518
+ "learning_rate": 0.0002,
519
+ "loss": 1.7434,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.5528576765035488,
524
+ "grad_norm": 0.31933900713920593,
525
+ "learning_rate": 0.0002,
526
+ "loss": 1.8027,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.5603287261860291,
531
+ "grad_norm": 0.3226020634174347,
532
+ "learning_rate": 0.0002,
533
+ "loss": 1.7601,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.5677997758685095,
538
+ "grad_norm": 0.3147525489330292,
539
+ "learning_rate": 0.0002,
540
+ "loss": 1.7862,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.57527082555099,
545
+ "grad_norm": 0.32234328985214233,
546
+ "learning_rate": 0.0002,
547
+ "loss": 1.9028,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.5827418752334703,
552
+ "grad_norm": 0.3258664309978485,
553
+ "learning_rate": 0.0002,
554
+ "loss": 1.7623,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.5902129249159507,
559
+ "grad_norm": 0.3166961967945099,
560
+ "learning_rate": 0.0002,
561
+ "loss": 1.7384,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.597683974598431,
566
+ "grad_norm": 0.35621458292007446,
567
+ "learning_rate": 0.0002,
568
+ "loss": 1.8799,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.6051550242809115,
573
+ "grad_norm": 0.3236999213695526,
574
+ "learning_rate": 0.0002,
575
+ "loss": 1.8313,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.6126260739633919,
580
+ "grad_norm": 0.2892923653125763,
581
+ "learning_rate": 0.0002,
582
+ "loss": 1.7132,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.6200971236458722,
587
+ "grad_norm": 0.4098321497440338,
588
+ "learning_rate": 0.0002,
589
+ "loss": 1.8709,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.6275681733283527,
594
+ "grad_norm": 0.3337118923664093,
595
+ "learning_rate": 0.0002,
596
+ "loss": 1.7637,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.635039223010833,
601
+ "grad_norm": 0.30416029691696167,
602
+ "learning_rate": 0.0002,
603
+ "loss": 1.7375,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.6425102726933134,
608
+ "grad_norm": 0.3361026346683502,
609
+ "learning_rate": 0.0002,
610
+ "loss": 1.7419,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.6499813223757938,
615
+ "grad_norm": 0.3537365198135376,
616
+ "learning_rate": 0.0002,
617
+ "loss": 1.732,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.6574523720582742,
622
+ "grad_norm": 0.33854469656944275,
623
+ "learning_rate": 0.0002,
624
+ "loss": 1.7825,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.6649234217407546,
629
+ "grad_norm": 0.3332272469997406,
630
+ "learning_rate": 0.0002,
631
+ "loss": 1.7561,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.6723944714232349,
636
+ "grad_norm": 0.34954726696014404,
637
+ "learning_rate": 0.0002,
638
+ "loss": 1.7247,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.6798655211057153,
643
+ "grad_norm": 0.2921750247478485,
644
+ "learning_rate": 0.0002,
645
+ "loss": 1.7917,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.6873365707881958,
650
+ "grad_norm": 0.30508682131767273,
651
+ "learning_rate": 0.0002,
652
+ "loss": 1.7807,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.6948076204706761,
657
+ "grad_norm": 0.32268425822257996,
658
+ "learning_rate": 0.0002,
659
+ "loss": 1.8082,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.7022786701531565,
664
+ "grad_norm": 0.2844390869140625,
665
+ "learning_rate": 0.0002,
666
+ "loss": 1.8283,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.709749719835637,
671
+ "grad_norm": 0.31263890862464905,
672
+ "learning_rate": 0.0002,
673
+ "loss": 1.7363,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.7172207695181173,
678
+ "grad_norm": 0.3626808822154999,
679
+ "learning_rate": 0.0002,
680
+ "loss": 1.8081,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.7246918192005977,
685
+ "grad_norm": 0.3322749733924866,
686
+ "learning_rate": 0.0002,
687
+ "loss": 1.853,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.732162868883078,
692
+ "grad_norm": 0.29177871346473694,
693
+ "learning_rate": 0.0002,
694
+ "loss": 1.7912,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.7396339185655585,
699
+ "grad_norm": 0.35405513644218445,
700
+ "learning_rate": 0.0002,
701
+ "loss": 1.8447,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.7471049682480388,
706
+ "grad_norm": 0.39318400621414185,
707
+ "learning_rate": 0.0002,
708
+ "loss": 1.7008,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.7545760179305192,
713
+ "grad_norm": 0.29401418566703796,
714
+ "learning_rate": 0.0002,
715
+ "loss": 1.7803,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 0.7620470676129997,
720
+ "grad_norm": 0.3271748721599579,
721
+ "learning_rate": 0.0002,
722
+ "loss": 1.7649,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 0.76951811729548,
727
+ "grad_norm": 0.30883970856666565,
728
+ "learning_rate": 0.0002,
729
+ "loss": 1.7266,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 0.7769891669779604,
734
+ "grad_norm": 0.3411838412284851,
735
+ "learning_rate": 0.0002,
736
+ "loss": 1.7722,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 0.7844602166604407,
741
+ "grad_norm": 0.30608129501342773,
742
+ "learning_rate": 0.0002,
743
+ "loss": 1.829,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 0.7919312663429212,
748
+ "grad_norm": 0.30899080634117126,
749
+ "learning_rate": 0.0002,
750
+ "loss": 1.7815,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 0.7994023160254016,
755
+ "grad_norm": 0.3160453140735626,
756
+ "learning_rate": 0.0002,
757
+ "loss": 1.7625,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 0.8068733657078819,
762
+ "grad_norm": 0.30947187542915344,
763
+ "learning_rate": 0.0002,
764
+ "loss": 1.8452,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 0.8143444153903624,
769
+ "grad_norm": 0.3103134036064148,
770
+ "learning_rate": 0.0002,
771
+ "loss": 1.7418,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 0.8218154650728428,
776
+ "grad_norm": 0.31771138310432434,
777
+ "learning_rate": 0.0002,
778
+ "loss": 1.842,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 0.8292865147553231,
783
+ "grad_norm": 0.5860997438430786,
784
+ "learning_rate": 0.0002,
785
+ "loss": 1.7918,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 0.8367575644378035,
790
+ "grad_norm": 0.3230148255825043,
791
+ "learning_rate": 0.0002,
792
+ "loss": 1.8443,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 0.8442286141202839,
797
+ "grad_norm": 0.29611510038375854,
798
+ "learning_rate": 0.0002,
799
+ "loss": 1.8478,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 0.8516996638027643,
804
+ "grad_norm": 0.3373654782772064,
805
+ "learning_rate": 0.0002,
806
+ "loss": 1.7673,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 0.8591707134852447,
811
+ "grad_norm": 0.3474279046058655,
812
+ "learning_rate": 0.0002,
813
+ "loss": 1.7997,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 0.866641763167725,
818
+ "grad_norm": 0.35057875514030457,
819
+ "learning_rate": 0.0002,
820
+ "loss": 1.75,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 0.8741128128502055,
825
+ "grad_norm": 0.39537495374679565,
826
+ "learning_rate": 0.0002,
827
+ "loss": 1.8273,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 0.8815838625326858,
832
+ "grad_norm": 0.3714233636856079,
833
+ "learning_rate": 0.0002,
834
+ "loss": 1.7682,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 0.8890549122151662,
839
+ "grad_norm": 0.2950296998023987,
840
+ "learning_rate": 0.0002,
841
+ "loss": 1.7549,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 0.8965259618976467,
846
+ "grad_norm": 0.38182979822158813,
847
+ "learning_rate": 0.0002,
848
+ "loss": 1.7612,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 0.903997011580127,
853
+ "grad_norm": 0.27883678674697876,
854
+ "learning_rate": 0.0002,
855
+ "loss": 1.827,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 0.9114680612626074,
860
+ "grad_norm": 0.33874374628067017,
861
+ "learning_rate": 0.0002,
862
+ "loss": 1.7623,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 0.9189391109450877,
867
+ "grad_norm": 0.3014272153377533,
868
+ "learning_rate": 0.0002,
869
+ "loss": 1.7334,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 0.9264101606275682,
874
+ "grad_norm": 0.3194271922111511,
875
+ "learning_rate": 0.0002,
876
+ "loss": 1.8235,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 0.9338812103100486,
881
+ "grad_norm": 0.3049403429031372,
882
+ "learning_rate": 0.0002,
883
+ "loss": 1.7924,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 0.9413522599925289,
888
+ "grad_norm": 0.30621254444122314,
889
+ "learning_rate": 0.0002,
890
+ "loss": 1.7535,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 0.9488233096750094,
895
+ "grad_norm": 0.28675132989883423,
896
+ "learning_rate": 0.0002,
897
+ "loss": 1.8287,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 0.9562943593574897,
902
+ "grad_norm": 0.3322032690048218,
903
+ "learning_rate": 0.0002,
904
+ "loss": 1.7586,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 0.9637654090399701,
909
+ "grad_norm": 0.35408294200897217,
910
+ "learning_rate": 0.0002,
911
+ "loss": 1.8054,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 0.9712364587224505,
916
+ "grad_norm": 0.36386919021606445,
917
+ "learning_rate": 0.0002,
918
+ "loss": 1.7343,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 0.9787075084049309,
923
+ "grad_norm": 0.32338324189186096,
924
+ "learning_rate": 0.0002,
925
+ "loss": 1.8633,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 0.9861785580874113,
930
+ "grad_norm": 0.3714013993740082,
931
+ "learning_rate": 0.0002,
932
+ "loss": 1.7724,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 0.9936496077698916,
937
+ "grad_norm": 0.3133082389831543,
938
+ "learning_rate": 0.0002,
939
+ "loss": 1.7766,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 0.9996264475158759,
944
+ "eval_loss": 1.8051470518112183,
945
+ "eval_runtime": 38.6332,
946
+ "eval_samples_per_second": 13.331,
947
+ "eval_steps_per_second": 1.682,
948
+ "step": 1338
949
+ },
950
+ {
951
+ "epoch": 1.001120657452372,
952
+ "grad_norm": 0.31595754623413086,
953
+ "learning_rate": 0.0002,
954
+ "loss": 1.8035,
955
+ "step": 1340
956
+ },
957
+ {
958
+ "epoch": 1.0085917071348525,
959
+ "grad_norm": 0.3095700144767761,
960
+ "learning_rate": 0.0002,
961
+ "loss": 1.7486,
962
+ "step": 1350
963
+ },
964
+ {
965
+ "epoch": 1.0160627568173328,
966
+ "grad_norm": 0.34677496552467346,
967
+ "learning_rate": 0.0002,
968
+ "loss": 1.6981,
969
+ "step": 1360
970
+ },
971
+ {
972
+ "epoch": 1.0235338064998132,
973
+ "grad_norm": 0.29108840227127075,
974
+ "learning_rate": 0.0002,
975
+ "loss": 1.7377,
976
+ "step": 1370
977
+ },
978
+ {
979
+ "epoch": 1.0310048561822935,
980
+ "grad_norm": 0.32356950640678406,
981
+ "learning_rate": 0.0002,
982
+ "loss": 1.7194,
983
+ "step": 1380
984
+ },
985
+ {
986
+ "epoch": 1.038475905864774,
987
+ "grad_norm": 0.4200669229030609,
988
+ "learning_rate": 0.0002,
989
+ "loss": 1.7593,
990
+ "step": 1390
991
+ },
992
+ {
993
+ "epoch": 1.0459469555472545,
994
+ "grad_norm": 0.3283711373806,
995
+ "learning_rate": 0.0002,
996
+ "loss": 1.797,
997
+ "step": 1400
998
+ },
999
+ {
1000
+ "epoch": 1.0534180052297348,
1001
+ "grad_norm": 0.32898256182670593,
1002
+ "learning_rate": 0.0002,
1003
+ "loss": 1.7163,
1004
+ "step": 1410
1005
+ },
1006
+ {
1007
+ "epoch": 1.0608890549122152,
1008
+ "grad_norm": 0.38790300488471985,
1009
+ "learning_rate": 0.0002,
1010
+ "loss": 1.7559,
1011
+ "step": 1420
1012
+ },
1013
+ {
1014
+ "epoch": 1.0683601045946955,
1015
+ "grad_norm": 0.339800089597702,
1016
+ "learning_rate": 0.0002,
1017
+ "loss": 1.6922,
1018
+ "step": 1430
1019
+ },
1020
+ {
1021
+ "epoch": 1.075831154277176,
1022
+ "grad_norm": 0.3548751175403595,
1023
+ "learning_rate": 0.0002,
1024
+ "loss": 1.7076,
1025
+ "step": 1440
1026
+ },
1027
+ {
1028
+ "epoch": 1.0833022039596563,
1029
+ "grad_norm": 0.35114359855651855,
1030
+ "learning_rate": 0.0002,
1031
+ "loss": 1.6985,
1032
+ "step": 1450
1033
+ },
1034
+ {
1035
+ "epoch": 1.0907732536421366,
1036
+ "grad_norm": 0.35226720571517944,
1037
+ "learning_rate": 0.0002,
1038
+ "loss": 1.7217,
1039
+ "step": 1460
1040
+ },
1041
+ {
1042
+ "epoch": 1.0982443033246172,
1043
+ "grad_norm": 0.33665576577186584,
1044
+ "learning_rate": 0.0002,
1045
+ "loss": 1.6822,
1046
+ "step": 1470
1047
+ },
1048
+ {
1049
+ "epoch": 1.1057153530070976,
1050
+ "grad_norm": 0.363889217376709,
1051
+ "learning_rate": 0.0002,
1052
+ "loss": 1.6699,
1053
+ "step": 1480
1054
+ },
1055
+ {
1056
+ "epoch": 1.113186402689578,
1057
+ "grad_norm": 0.3826201856136322,
1058
+ "learning_rate": 0.0002,
1059
+ "loss": 1.7933,
1060
+ "step": 1490
1061
+ },
1062
+ {
1063
+ "epoch": 1.1206574523720583,
1064
+ "grad_norm": 0.34058740735054016,
1065
+ "learning_rate": 0.0002,
1066
+ "loss": 1.7022,
1067
+ "step": 1500
1068
+ },
1069
+ {
1070
+ "epoch": 1.1281285020545386,
1071
+ "grad_norm": 0.3462134301662445,
1072
+ "learning_rate": 0.0002,
1073
+ "loss": 1.6375,
1074
+ "step": 1510
1075
+ },
1076
+ {
1077
+ "epoch": 1.135599551737019,
1078
+ "grad_norm": 0.3396756052970886,
1079
+ "learning_rate": 0.0002,
1080
+ "loss": 1.7147,
1081
+ "step": 1520
1082
+ },
1083
+ {
1084
+ "epoch": 1.1430706014194993,
1085
+ "grad_norm": 0.32004743814468384,
1086
+ "learning_rate": 0.0002,
1087
+ "loss": 1.7219,
1088
+ "step": 1530
1089
+ },
1090
+ {
1091
+ "epoch": 1.15054165110198,
1092
+ "grad_norm": 0.3397733271121979,
1093
+ "learning_rate": 0.0002,
1094
+ "loss": 1.743,
1095
+ "step": 1540
1096
+ },
1097
+ {
1098
+ "epoch": 1.1580127007844603,
1099
+ "grad_norm": 0.3783262073993683,
1100
+ "learning_rate": 0.0002,
1101
+ "loss": 1.7333,
1102
+ "step": 1550
1103
+ },
1104
+ {
1105
+ "epoch": 1.1654837504669406,
1106
+ "grad_norm": 0.35121291875839233,
1107
+ "learning_rate": 0.0002,
1108
+ "loss": 1.6075,
1109
+ "step": 1560
1110
+ },
1111
+ {
1112
+ "epoch": 1.172954800149421,
1113
+ "grad_norm": 0.35816895961761475,
1114
+ "learning_rate": 0.0002,
1115
+ "loss": 1.678,
1116
+ "step": 1570
1117
+ },
1118
+ {
1119
+ "epoch": 1.1804258498319014,
1120
+ "grad_norm": 0.33843839168548584,
1121
+ "learning_rate": 0.0002,
1122
+ "loss": 1.7143,
1123
+ "step": 1580
1124
+ },
1125
+ {
1126
+ "epoch": 1.1878968995143817,
1127
+ "grad_norm": 0.3371972143650055,
1128
+ "learning_rate": 0.0002,
1129
+ "loss": 1.7434,
1130
+ "step": 1590
1131
+ },
1132
+ {
1133
+ "epoch": 1.195367949196862,
1134
+ "grad_norm": 0.36016878485679626,
1135
+ "learning_rate": 0.0002,
1136
+ "loss": 1.7671,
1137
+ "step": 1600
1138
+ },
1139
+ {
1140
+ "epoch": 1.2028389988793426,
1141
+ "grad_norm": 0.40879473090171814,
1142
+ "learning_rate": 0.0002,
1143
+ "loss": 1.6914,
1144
+ "step": 1610
1145
+ },
1146
+ {
1147
+ "epoch": 1.210310048561823,
1148
+ "grad_norm": 0.3216715455055237,
1149
+ "learning_rate": 0.0002,
1150
+ "loss": 1.6955,
1151
+ "step": 1620
1152
+ },
1153
+ {
1154
+ "epoch": 1.2177810982443034,
1155
+ "grad_norm": 0.4482610821723938,
1156
+ "learning_rate": 0.0002,
1157
+ "loss": 1.632,
1158
+ "step": 1630
1159
+ },
1160
+ {
1161
+ "epoch": 1.2252521479267837,
1162
+ "grad_norm": 0.3257700502872467,
1163
+ "learning_rate": 0.0002,
1164
+ "loss": 1.6999,
1165
+ "step": 1640
1166
+ },
1167
+ {
1168
+ "epoch": 1.232723197609264,
1169
+ "grad_norm": 0.38646459579467773,
1170
+ "learning_rate": 0.0002,
1171
+ "loss": 1.7177,
1172
+ "step": 1650
1173
+ },
1174
+ {
1175
+ "epoch": 1.2401942472917444,
1176
+ "grad_norm": 0.4081360697746277,
1177
+ "learning_rate": 0.0002,
1178
+ "loss": 1.7081,
1179
+ "step": 1660
1180
+ },
1181
+ {
1182
+ "epoch": 1.2476652969742248,
1183
+ "grad_norm": 0.4326848089694977,
1184
+ "learning_rate": 0.0002,
1185
+ "loss": 1.7519,
1186
+ "step": 1670
1187
+ },
1188
+ {
1189
+ "epoch": 1.2551363466567054,
1190
+ "grad_norm": 0.346401572227478,
1191
+ "learning_rate": 0.0002,
1192
+ "loss": 1.6752,
1193
+ "step": 1680
1194
+ },
1195
+ {
1196
+ "epoch": 1.2626073963391857,
1197
+ "grad_norm": 0.34536251425743103,
1198
+ "learning_rate": 0.0002,
1199
+ "loss": 1.7425,
1200
+ "step": 1690
1201
+ },
1202
+ {
1203
+ "epoch": 1.270078446021666,
1204
+ "grad_norm": 0.41359591484069824,
1205
+ "learning_rate": 0.0002,
1206
+ "loss": 1.7061,
1207
+ "step": 1700
1208
+ },
1209
+ {
1210
+ "epoch": 1.2775494957041464,
1211
+ "grad_norm": 0.3530874252319336,
1212
+ "learning_rate": 0.0002,
1213
+ "loss": 1.7906,
1214
+ "step": 1710
1215
+ },
1216
+ {
1217
+ "epoch": 1.2850205453866268,
1218
+ "grad_norm": 0.3702719211578369,
1219
+ "learning_rate": 0.0002,
1220
+ "loss": 1.7357,
1221
+ "step": 1720
1222
+ },
1223
+ {
1224
+ "epoch": 1.2924915950691072,
1225
+ "grad_norm": 0.3703329563140869,
1226
+ "learning_rate": 0.0002,
1227
+ "loss": 1.766,
1228
+ "step": 1730
1229
+ },
1230
+ {
1231
+ "epoch": 1.2999626447515875,
1232
+ "grad_norm": 0.37919729948043823,
1233
+ "learning_rate": 0.0002,
1234
+ "loss": 1.7221,
1235
+ "step": 1740
1236
+ },
1237
+ {
1238
+ "epoch": 1.307433694434068,
1239
+ "grad_norm": 0.32526856660842896,
1240
+ "learning_rate": 0.0002,
1241
+ "loss": 1.7859,
1242
+ "step": 1750
1243
+ },
1244
+ {
1245
+ "epoch": 1.3149047441165485,
1246
+ "grad_norm": 0.36752620339393616,
1247
+ "learning_rate": 0.0002,
1248
+ "loss": 1.7117,
1249
+ "step": 1760
1250
+ },
1251
+ {
1252
+ "epoch": 1.3223757937990288,
1253
+ "grad_norm": 0.3398192524909973,
1254
+ "learning_rate": 0.0002,
1255
+ "loss": 1.7335,
1256
+ "step": 1770
1257
+ },
1258
+ {
1259
+ "epoch": 1.3298468434815092,
1260
+ "grad_norm": 0.37435585260391235,
1261
+ "learning_rate": 0.0002,
1262
+ "loss": 1.7492,
1263
+ "step": 1780
1264
+ },
1265
+ {
1266
+ "epoch": 1.3373178931639895,
1267
+ "grad_norm": 0.35793280601501465,
1268
+ "learning_rate": 0.0002,
1269
+ "loss": 1.7393,
1270
+ "step": 1790
1271
+ },
1272
+ {
1273
+ "epoch": 1.3447889428464699,
1274
+ "grad_norm": 0.35481882095336914,
1275
+ "learning_rate": 0.0002,
1276
+ "loss": 1.7266,
1277
+ "step": 1800
1278
+ },
1279
+ {
1280
+ "epoch": 1.3522599925289502,
1281
+ "grad_norm": 0.3786393105983734,
1282
+ "learning_rate": 0.0002,
1283
+ "loss": 1.7456,
1284
+ "step": 1810
1285
+ },
1286
+ {
1287
+ "epoch": 1.3597310422114308,
1288
+ "grad_norm": 0.33245593309402466,
1289
+ "learning_rate": 0.0002,
1290
+ "loss": 1.7169,
1291
+ "step": 1820
1292
+ },
1293
+ {
1294
+ "epoch": 1.3672020918939112,
1295
+ "grad_norm": 0.35388344526290894,
1296
+ "learning_rate": 0.0002,
1297
+ "loss": 1.7577,
1298
+ "step": 1830
1299
+ },
1300
+ {
1301
+ "epoch": 1.3746731415763915,
1302
+ "grad_norm": 0.3695325553417206,
1303
+ "learning_rate": 0.0002,
1304
+ "loss": 1.6968,
1305
+ "step": 1840
1306
+ },
1307
+ {
1308
+ "epoch": 1.382144191258872,
1309
+ "grad_norm": 0.3683604598045349,
1310
+ "learning_rate": 0.0002,
1311
+ "loss": 1.7086,
1312
+ "step": 1850
1313
+ },
1314
+ {
1315
+ "epoch": 1.3896152409413522,
1316
+ "grad_norm": 0.3753012418746948,
1317
+ "learning_rate": 0.0002,
1318
+ "loss": 1.7878,
1319
+ "step": 1860
1320
+ },
1321
+ {
1322
+ "epoch": 1.3970862906238326,
1323
+ "grad_norm": 0.3331069350242615,
1324
+ "learning_rate": 0.0002,
1325
+ "loss": 1.6969,
1326
+ "step": 1870
1327
+ },
1328
+ {
1329
+ "epoch": 1.404557340306313,
1330
+ "grad_norm": 0.3877500295639038,
1331
+ "learning_rate": 0.0002,
1332
+ "loss": 1.6644,
1333
+ "step": 1880
1334
+ },
1335
+ {
1336
+ "epoch": 1.4120283899887935,
1337
+ "grad_norm": 0.33525151014328003,
1338
+ "learning_rate": 0.0002,
1339
+ "loss": 1.7586,
1340
+ "step": 1890
1341
+ },
1342
+ {
1343
+ "epoch": 1.4194994396712737,
1344
+ "grad_norm": 0.3697299659252167,
1345
+ "learning_rate": 0.0002,
1346
+ "loss": 1.7031,
1347
+ "step": 1900
1348
+ },
1349
+ {
1350
+ "epoch": 1.4269704893537543,
1351
+ "grad_norm": 0.4029286205768585,
1352
+ "learning_rate": 0.0002,
1353
+ "loss": 1.6956,
1354
+ "step": 1910
1355
+ },
1356
+ {
1357
+ "epoch": 1.4344415390362346,
1358
+ "grad_norm": 0.3596203029155731,
1359
+ "learning_rate": 0.0002,
1360
+ "loss": 1.6897,
1361
+ "step": 1920
1362
+ },
1363
+ {
1364
+ "epoch": 1.441912588718715,
1365
+ "grad_norm": 0.450783908367157,
1366
+ "learning_rate": 0.0002,
1367
+ "loss": 1.7139,
1368
+ "step": 1930
1369
+ },
1370
+ {
1371
+ "epoch": 1.4493836384011953,
1372
+ "grad_norm": 0.3651481866836548,
1373
+ "learning_rate": 0.0002,
1374
+ "loss": 1.7243,
1375
+ "step": 1940
1376
+ },
1377
+ {
1378
+ "epoch": 1.4568546880836757,
1379
+ "grad_norm": 0.3608424663543701,
1380
+ "learning_rate": 0.0002,
1381
+ "loss": 1.6637,
1382
+ "step": 1950
1383
+ },
1384
+ {
1385
+ "epoch": 1.4643257377661563,
1386
+ "grad_norm": 0.39684420824050903,
1387
+ "learning_rate": 0.0002,
1388
+ "loss": 1.8285,
1389
+ "step": 1960
1390
+ },
1391
+ {
1392
+ "epoch": 1.4717967874486364,
1393
+ "grad_norm": 0.34618663787841797,
1394
+ "learning_rate": 0.0002,
1395
+ "loss": 1.7514,
1396
+ "step": 1970
1397
+ },
1398
+ {
1399
+ "epoch": 1.479267837131117,
1400
+ "grad_norm": 0.4150386452674866,
1401
+ "learning_rate": 0.0002,
1402
+ "loss": 1.6655,
1403
+ "step": 1980
1404
+ },
1405
+ {
1406
+ "epoch": 1.4867388868135973,
1407
+ "grad_norm": 0.35500776767730713,
1408
+ "learning_rate": 0.0002,
1409
+ "loss": 1.7021,
1410
+ "step": 1990
1411
+ },
1412
+ {
1413
+ "epoch": 1.4942099364960777,
1414
+ "grad_norm": 0.344144344329834,
1415
+ "learning_rate": 0.0002,
1416
+ "loss": 1.7322,
1417
+ "step": 2000
1418
+ },
1419
+ {
1420
+ "epoch": 1.501680986178558,
1421
+ "grad_norm": 0.3340149223804474,
1422
+ "learning_rate": 0.0002,
1423
+ "loss": 1.6998,
1424
+ "step": 2010
1425
+ },
1426
+ {
1427
+ "epoch": 1.5091520358610384,
1428
+ "grad_norm": 0.37685006856918335,
1429
+ "learning_rate": 0.0002,
1430
+ "loss": 1.7508,
1431
+ "step": 2020
1432
+ },
1433
+ {
1434
+ "epoch": 1.516623085543519,
1435
+ "grad_norm": 0.3699876368045807,
1436
+ "learning_rate": 0.0002,
1437
+ "loss": 1.8299,
1438
+ "step": 2030
1439
+ },
1440
+ {
1441
+ "epoch": 1.5240941352259991,
1442
+ "grad_norm": 0.3370307385921478,
1443
+ "learning_rate": 0.0002,
1444
+ "loss": 1.7357,
1445
+ "step": 2040
1446
+ },
1447
+ {
1448
+ "epoch": 1.5315651849084797,
1449
+ "grad_norm": 0.37780630588531494,
1450
+ "learning_rate": 0.0002,
1451
+ "loss": 1.8044,
1452
+ "step": 2050
1453
+ },
1454
+ {
1455
+ "epoch": 1.53903623459096,
1456
+ "grad_norm": 0.370259165763855,
1457
+ "learning_rate": 0.0002,
1458
+ "loss": 1.7408,
1459
+ "step": 2060
1460
+ },
1461
+ {
1462
+ "epoch": 1.5465072842734404,
1463
+ "grad_norm": 0.3440011441707611,
1464
+ "learning_rate": 0.0002,
1465
+ "loss": 1.7398,
1466
+ "step": 2070
1467
+ },
1468
+ {
1469
+ "epoch": 1.5539783339559208,
1470
+ "grad_norm": 0.40382063388824463,
1471
+ "learning_rate": 0.0002,
1472
+ "loss": 1.7105,
1473
+ "step": 2080
1474
+ },
1475
+ {
1476
+ "epoch": 1.5614493836384011,
1477
+ "grad_norm": 0.38002029061317444,
1478
+ "learning_rate": 0.0002,
1479
+ "loss": 1.7071,
1480
+ "step": 2090
1481
+ },
1482
+ {
1483
+ "epoch": 1.5689204333208817,
1484
+ "grad_norm": 0.3658451437950134,
1485
+ "learning_rate": 0.0002,
1486
+ "loss": 1.6815,
1487
+ "step": 2100
1488
+ },
1489
+ {
1490
+ "epoch": 1.5763914830033618,
1491
+ "grad_norm": 0.354842871427536,
1492
+ "learning_rate": 0.0002,
1493
+ "loss": 1.7598,
1494
+ "step": 2110
1495
+ },
1496
+ {
1497
+ "epoch": 1.5838625326858424,
1498
+ "grad_norm": 0.34735530614852905,
1499
+ "learning_rate": 0.0002,
1500
+ "loss": 1.6898,
1501
+ "step": 2120
1502
+ },
1503
+ {
1504
+ "epoch": 1.5913335823683228,
1505
+ "grad_norm": 0.377581924200058,
1506
+ "learning_rate": 0.0002,
1507
+ "loss": 1.7363,
1508
+ "step": 2130
1509
+ },
1510
+ {
1511
+ "epoch": 1.5988046320508031,
1512
+ "grad_norm": 0.41254034638404846,
1513
+ "learning_rate": 0.0002,
1514
+ "loss": 1.7789,
1515
+ "step": 2140
1516
+ },
1517
+ {
1518
+ "epoch": 1.6062756817332835,
1519
+ "grad_norm": 0.3630715310573578,
1520
+ "learning_rate": 0.0002,
1521
+ "loss": 1.6782,
1522
+ "step": 2150
1523
+ },
1524
+ {
1525
+ "epoch": 1.6137467314157639,
1526
+ "grad_norm": 0.36980143189430237,
1527
+ "learning_rate": 0.0002,
1528
+ "loss": 1.7531,
1529
+ "step": 2160
1530
+ },
1531
+ {
1532
+ "epoch": 1.6212177810982444,
1533
+ "grad_norm": 0.3634769320487976,
1534
+ "learning_rate": 0.0002,
1535
+ "loss": 1.6847,
1536
+ "step": 2170
1537
+ },
1538
+ {
1539
+ "epoch": 1.6286888307807246,
1540
+ "grad_norm": 0.3794139623641968,
1541
+ "learning_rate": 0.0002,
1542
+ "loss": 1.6367,
1543
+ "step": 2180
1544
+ },
1545
+ {
1546
+ "epoch": 1.6361598804632052,
1547
+ "grad_norm": 0.359742134809494,
1548
+ "learning_rate": 0.0002,
1549
+ "loss": 1.7064,
1550
+ "step": 2190
1551
+ },
1552
+ {
1553
+ "epoch": 1.6436309301456855,
1554
+ "grad_norm": 0.3770543932914734,
1555
+ "learning_rate": 0.0002,
1556
+ "loss": 1.7027,
1557
+ "step": 2200
1558
+ },
1559
+ {
1560
+ "epoch": 1.6511019798281659,
1561
+ "grad_norm": 0.3797036409378052,
1562
+ "learning_rate": 0.0002,
1563
+ "loss": 1.784,
1564
+ "step": 2210
1565
+ },
1566
+ {
1567
+ "epoch": 1.6585730295106462,
1568
+ "grad_norm": 0.35622093081474304,
1569
+ "learning_rate": 0.0002,
1570
+ "loss": 1.7875,
1571
+ "step": 2220
1572
+ },
1573
+ {
1574
+ "epoch": 1.6660440791931266,
1575
+ "grad_norm": 0.34552520513534546,
1576
+ "learning_rate": 0.0002,
1577
+ "loss": 1.6615,
1578
+ "step": 2230
1579
+ },
1580
+ {
1581
+ "epoch": 1.6735151288756072,
1582
+ "grad_norm": 0.379926860332489,
1583
+ "learning_rate": 0.0002,
1584
+ "loss": 1.7522,
1585
+ "step": 2240
1586
+ },
1587
+ {
1588
+ "epoch": 1.6809861785580873,
1589
+ "grad_norm": 0.37083810567855835,
1590
+ "learning_rate": 0.0002,
1591
+ "loss": 1.7953,
1592
+ "step": 2250
1593
+ },
1594
+ {
1595
+ "epoch": 1.6884572282405679,
1596
+ "grad_norm": 0.42746543884277344,
1597
+ "learning_rate": 0.0002,
1598
+ "loss": 1.7485,
1599
+ "step": 2260
1600
+ },
1601
+ {
1602
+ "epoch": 1.6959282779230482,
1603
+ "grad_norm": 0.3372884690761566,
1604
+ "learning_rate": 0.0002,
1605
+ "loss": 1.776,
1606
+ "step": 2270
1607
+ },
1608
+ {
1609
+ "epoch": 1.7033993276055286,
1610
+ "grad_norm": 0.35220256447792053,
1611
+ "learning_rate": 0.0002,
1612
+ "loss": 1.7604,
1613
+ "step": 2280
1614
+ },
1615
+ {
1616
+ "epoch": 1.710870377288009,
1617
+ "grad_norm": 0.3659130930900574,
1618
+ "learning_rate": 0.0002,
1619
+ "loss": 1.7154,
1620
+ "step": 2290
1621
+ },
1622
+ {
1623
+ "epoch": 1.7183414269704893,
1624
+ "grad_norm": 0.37629297375679016,
1625
+ "learning_rate": 0.0002,
1626
+ "loss": 1.6953,
1627
+ "step": 2300
1628
+ },
1629
+ {
1630
+ "epoch": 1.7258124766529699,
1631
+ "grad_norm": 0.36312398314476013,
1632
+ "learning_rate": 0.0002,
1633
+ "loss": 1.7212,
1634
+ "step": 2310
1635
+ },
1636
+ {
1637
+ "epoch": 1.73328352633545,
1638
+ "grad_norm": 0.467709481716156,
1639
+ "learning_rate": 0.0002,
1640
+ "loss": 1.7903,
1641
+ "step": 2320
1642
+ },
1643
+ {
1644
+ "epoch": 1.7407545760179306,
1645
+ "grad_norm": 0.38685527443885803,
1646
+ "learning_rate": 0.0002,
1647
+ "loss": 1.696,
1648
+ "step": 2330
1649
+ },
1650
+ {
1651
+ "epoch": 1.748225625700411,
1652
+ "grad_norm": 0.3578338325023651,
1653
+ "learning_rate": 0.0002,
1654
+ "loss": 1.7041,
1655
+ "step": 2340
1656
+ },
1657
+ {
1658
+ "epoch": 1.7556966753828913,
1659
+ "grad_norm": 0.36057502031326294,
1660
+ "learning_rate": 0.0002,
1661
+ "loss": 1.6456,
1662
+ "step": 2350
1663
+ },
1664
+ {
1665
+ "epoch": 1.7631677250653717,
1666
+ "grad_norm": 0.3615196645259857,
1667
+ "learning_rate": 0.0002,
1668
+ "loss": 1.6853,
1669
+ "step": 2360
1670
+ },
1671
+ {
1672
+ "epoch": 1.770638774747852,
1673
+ "grad_norm": 0.4118947684764862,
1674
+ "learning_rate": 0.0002,
1675
+ "loss": 1.7612,
1676
+ "step": 2370
1677
+ },
1678
+ {
1679
+ "epoch": 1.7781098244303326,
1680
+ "grad_norm": 0.4067276120185852,
1681
+ "learning_rate": 0.0002,
1682
+ "loss": 1.6946,
1683
+ "step": 2380
1684
+ },
1685
+ {
1686
+ "epoch": 1.7855808741128127,
1687
+ "grad_norm": 0.3979823887348175,
1688
+ "learning_rate": 0.0002,
1689
+ "loss": 1.712,
1690
+ "step": 2390
1691
+ },
1692
+ {
1693
+ "epoch": 1.7930519237952933,
1694
+ "grad_norm": 0.44045883417129517,
1695
+ "learning_rate": 0.0002,
1696
+ "loss": 1.7644,
1697
+ "step": 2400
1698
+ },
1699
+ {
1700
+ "epoch": 1.8005229734777737,
1701
+ "grad_norm": 0.3998069167137146,
1702
+ "learning_rate": 0.0002,
1703
+ "loss": 1.7251,
1704
+ "step": 2410
1705
+ },
1706
+ {
1707
+ "epoch": 1.807994023160254,
1708
+ "grad_norm": 0.3450094759464264,
1709
+ "learning_rate": 0.0002,
1710
+ "loss": 1.7354,
1711
+ "step": 2420
1712
+ },
1713
+ {
1714
+ "epoch": 1.8154650728427344,
1715
+ "grad_norm": 0.3759009838104248,
1716
+ "learning_rate": 0.0002,
1717
+ "loss": 1.6998,
1718
+ "step": 2430
1719
+ },
1720
+ {
1721
+ "epoch": 1.8229361225252148,
1722
+ "grad_norm": 0.34347015619277954,
1723
+ "learning_rate": 0.0002,
1724
+ "loss": 1.7706,
1725
+ "step": 2440
1726
+ },
1727
+ {
1728
+ "epoch": 1.8304071722076953,
1729
+ "grad_norm": 0.3511228859424591,
1730
+ "learning_rate": 0.0002,
1731
+ "loss": 1.7345,
1732
+ "step": 2450
1733
+ },
1734
+ {
1735
+ "epoch": 1.8378782218901755,
1736
+ "grad_norm": 0.36853715777397156,
1737
+ "learning_rate": 0.0002,
1738
+ "loss": 1.6909,
1739
+ "step": 2460
1740
+ },
1741
+ {
1742
+ "epoch": 1.845349271572656,
1743
+ "grad_norm": 0.40659376978874207,
1744
+ "learning_rate": 0.0002,
1745
+ "loss": 1.6931,
1746
+ "step": 2470
1747
+ },
1748
+ {
1749
+ "epoch": 1.8528203212551362,
1750
+ "grad_norm": 0.39621320366859436,
1751
+ "learning_rate": 0.0002,
1752
+ "loss": 1.7626,
1753
+ "step": 2480
1754
+ },
1755
+ {
1756
+ "epoch": 1.8602913709376168,
1757
+ "grad_norm": 0.3753979504108429,
1758
+ "learning_rate": 0.0002,
1759
+ "loss": 1.7427,
1760
+ "step": 2490
1761
+ },
1762
+ {
1763
+ "epoch": 1.8677624206200971,
1764
+ "grad_norm": 0.3811938464641571,
1765
+ "learning_rate": 0.0002,
1766
+ "loss": 1.6622,
1767
+ "step": 2500
1768
+ },
1769
+ {
1770
+ "epoch": 1.8752334703025775,
1771
+ "grad_norm": 0.3432596027851105,
1772
+ "learning_rate": 0.0002,
1773
+ "loss": 1.7718,
1774
+ "step": 2510
1775
+ },
1776
+ {
1777
+ "epoch": 1.882704519985058,
1778
+ "grad_norm": 0.3670712113380432,
1779
+ "learning_rate": 0.0002,
1780
+ "loss": 1.7488,
1781
+ "step": 2520
1782
+ },
1783
+ {
1784
+ "epoch": 1.8901755696675382,
1785
+ "grad_norm": 0.40907177329063416,
1786
+ "learning_rate": 0.0002,
1787
+ "loss": 1.705,
1788
+ "step": 2530
1789
+ },
1790
+ {
1791
+ "epoch": 1.8976466193500188,
1792
+ "grad_norm": 0.3821999728679657,
1793
+ "learning_rate": 0.0002,
1794
+ "loss": 1.7148,
1795
+ "step": 2540
1796
+ },
1797
+ {
1798
+ "epoch": 1.905117669032499,
1799
+ "grad_norm": 0.36173978447914124,
1800
+ "learning_rate": 0.0002,
1801
+ "loss": 1.7934,
1802
+ "step": 2550
1803
+ },
1804
+ {
1805
+ "epoch": 1.9125887187149795,
1806
+ "grad_norm": 0.38990336656570435,
1807
+ "learning_rate": 0.0002,
1808
+ "loss": 1.6939,
1809
+ "step": 2560
1810
+ },
1811
+ {
1812
+ "epoch": 1.9200597683974598,
1813
+ "grad_norm": 0.35242322087287903,
1814
+ "learning_rate": 0.0002,
1815
+ "loss": 1.6893,
1816
+ "step": 2570
1817
+ },
1818
+ {
1819
+ "epoch": 1.9275308180799402,
1820
+ "grad_norm": 0.3506428003311157,
1821
+ "learning_rate": 0.0002,
1822
+ "loss": 1.7268,
1823
+ "step": 2580
1824
+ },
1825
+ {
1826
+ "epoch": 1.9350018677624208,
1827
+ "grad_norm": 0.39540135860443115,
1828
+ "learning_rate": 0.0002,
1829
+ "loss": 1.6953,
1830
+ "step": 2590
1831
+ },
1832
+ {
1833
+ "epoch": 1.942472917444901,
1834
+ "grad_norm": 0.3444725573062897,
1835
+ "learning_rate": 0.0002,
1836
+ "loss": 1.6511,
1837
+ "step": 2600
1838
+ },
1839
+ {
1840
+ "epoch": 1.9499439671273815,
1841
+ "grad_norm": 0.3963521718978882,
1842
+ "learning_rate": 0.0002,
1843
+ "loss": 1.7259,
1844
+ "step": 2610
1845
+ },
1846
+ {
1847
+ "epoch": 1.9574150168098616,
1848
+ "grad_norm": 0.3689815402030945,
1849
+ "learning_rate": 0.0002,
1850
+ "loss": 1.6946,
1851
+ "step": 2620
1852
+ },
1853
+ {
1854
+ "epoch": 1.9648860664923422,
1855
+ "grad_norm": 0.3482626676559448,
1856
+ "learning_rate": 0.0002,
1857
+ "loss": 1.7384,
1858
+ "step": 2630
1859
+ },
1860
+ {
1861
+ "epoch": 1.9723571161748226,
1862
+ "grad_norm": 0.35832616686820984,
1863
+ "learning_rate": 0.0002,
1864
+ "loss": 1.7048,
1865
+ "step": 2640
1866
+ },
1867
+ {
1868
+ "epoch": 1.979828165857303,
1869
+ "grad_norm": 0.4776208996772766,
1870
+ "learning_rate": 0.0002,
1871
+ "loss": 1.6681,
1872
+ "step": 2650
1873
+ },
1874
+ {
1875
+ "epoch": 1.9872992155397835,
1876
+ "grad_norm": 0.32570165395736694,
1877
+ "learning_rate": 0.0002,
1878
+ "loss": 1.6696,
1879
+ "step": 2660
1880
+ },
1881
+ {
1882
+ "epoch": 1.9947702652222636,
1883
+ "grad_norm": 0.3380725085735321,
1884
+ "learning_rate": 0.0002,
1885
+ "loss": 1.7232,
1886
+ "step": 2670
1887
+ },
1888
+ {
1889
+ "epoch": 2.0,
1890
+ "eval_loss": 1.8046749830245972,
1891
+ "eval_runtime": 38.5096,
1892
+ "eval_samples_per_second": 13.373,
1893
+ "eval_steps_per_second": 1.688,
1894
+ "step": 2677
1895
+ }
1896
+ ],
1897
+ "logging_steps": 10,
1898
+ "max_steps": 10704,
1899
+ "num_input_tokens_seen": 0,
1900
+ "num_train_epochs": 8,
1901
+ "save_steps": 200,
1902
+ "stateful_callbacks": {
1903
+ "TrainerControl": {
1904
+ "args": {
1905
+ "should_epoch_stop": false,
1906
+ "should_evaluate": false,
1907
+ "should_log": false,
1908
+ "should_save": true,
1909
+ "should_training_stop": false
1910
+ },
1911
+ "attributes": {}
1912
+ }
1913
+ },
1914
+ "total_flos": 1.2388556595422822e+17,
1915
+ "train_batch_size": 1,
1916
+ "trial_name": null,
1917
+ "trial_params": null
1918
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fc87da605e94ff0ecd8f5b371302a2d5f8727b77984707a2185ddb447fc3796
3
+ size 5560
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d478f3d289857e8c3bac6e8f78ca8e9abcdca9a67a0f9422f335d9f204ba81c
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d177228f65938693aca16f68ff150166213b5361c99e1eb61010f54f8a11485
3
+ size 55532666
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:815e355ea07f47424238b4562e23ff869072de740aa219e0094905863e498161
3
+ size 14244
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e3229c0eb3893b4ed9dc78c51b78922835046ad4263156ec195b41cd09021c9
3
+ size 1064
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/trainer_state.json ADDED
@@ -0,0 +1,2864 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.8046749830245972,
3
+ "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-2677",
4
+ "epoch": 2.999626447515876,
5
+ "eval_steps": 10,
6
+ "global_step": 4015,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.007471049682480389,
13
+ "grad_norm": 0.4912872612476349,
14
+ "learning_rate": 0.0002,
15
+ "loss": 2.6181,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.014942099364960777,
20
+ "grad_norm": 0.4856316149234772,
21
+ "learning_rate": 0.0002,
22
+ "loss": 2.2606,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.022413149047441166,
27
+ "grad_norm": 0.47683125734329224,
28
+ "learning_rate": 0.0002,
29
+ "loss": 2.0957,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.029884198729921554,
34
+ "grad_norm": 0.515082597732544,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.8908,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.03735524841240194,
41
+ "grad_norm": 0.5299215316772461,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.9704,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.04482629809488233,
48
+ "grad_norm": 0.4951399862766266,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.9225,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.05229734777736272,
55
+ "grad_norm": 0.48079821467399597,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.9742,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.05976839745984311,
62
+ "grad_norm": 0.49402132630348206,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.9466,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.0672394471423235,
69
+ "grad_norm": 0.4778193235397339,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.8691,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.07471049682480388,
76
+ "grad_norm": 0.42472657561302185,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.8455,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.08218154650728428,
83
+ "grad_norm": 0.4433092474937439,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.8744,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.08965259618976466,
90
+ "grad_norm": 0.4472862780094147,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.865,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.09712364587224505,
97
+ "grad_norm": 0.42596298456192017,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.9256,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.10459469555472543,
104
+ "grad_norm": 0.46645811200141907,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.8015,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.11206574523720583,
111
+ "grad_norm": 0.41041234135627747,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.8307,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.11953679491968622,
118
+ "grad_norm": 0.5329819917678833,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.8276,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.1270078446021666,
125
+ "grad_norm": 0.4065922200679779,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.8118,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.134478894284647,
132
+ "grad_norm": 0.38406994938850403,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.8559,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.14194994396712737,
139
+ "grad_norm": 0.4246881306171417,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.8647,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.14942099364960776,
146
+ "grad_norm": 0.35136649012565613,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.8054,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.15689204333208817,
153
+ "grad_norm": 0.43252742290496826,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.802,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.16436309301456856,
160
+ "grad_norm": 0.39236941933631897,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.7823,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.17183414269704894,
167
+ "grad_norm": 0.3748249113559723,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.818,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.17930519237952933,
174
+ "grad_norm": 0.6432855725288391,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.866,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.1867762420620097,
181
+ "grad_norm": 0.34874802827835083,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.8397,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.1942472917444901,
188
+ "grad_norm": 0.3721984326839447,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.79,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.20171834142697048,
195
+ "grad_norm": 0.4339311420917511,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.8464,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.20918939110945087,
202
+ "grad_norm": 0.4018215537071228,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.8665,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.21666044079193125,
209
+ "grad_norm": 0.3278839886188507,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.8048,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.22413149047441167,
216
+ "grad_norm": 0.36146077513694763,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.7395,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.23160254015689205,
223
+ "grad_norm": 0.38175010681152344,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.7916,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.23907358983937244,
230
+ "grad_norm": 0.44776618480682373,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.8593,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.24654463952185282,
237
+ "grad_norm": 0.3933652937412262,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.7824,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.2540156892043332,
244
+ "grad_norm": 0.3515005111694336,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.8393,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.2614867388868136,
251
+ "grad_norm": 0.6683304309844971,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.8653,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.268957788569294,
258
+ "grad_norm": 0.37093454599380493,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.8797,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.2764288382517744,
265
+ "grad_norm": 0.3450651168823242,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.8251,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.28389988793425475,
272
+ "grad_norm": 0.5140917301177979,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.7435,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.29137093761673516,
279
+ "grad_norm": 0.32885563373565674,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.8026,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.2988419872992155,
286
+ "grad_norm": 0.33962297439575195,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.8174,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.30631303698169593,
293
+ "grad_norm": 0.3723141849040985,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.7467,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.31378408666417634,
300
+ "grad_norm": 0.37173134088516235,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.8459,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.3212551363466567,
307
+ "grad_norm": 0.33736956119537354,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.8876,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.3287261860291371,
314
+ "grad_norm": 0.3602448105812073,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.8367,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.33619723571161747,
321
+ "grad_norm": 0.3569699227809906,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.8058,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.3436682853940979,
328
+ "grad_norm": 0.31009167432785034,
329
+ "learning_rate": 0.0002,
330
+ "loss": 1.8086,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.35113933507657824,
335
+ "grad_norm": 0.5278693437576294,
336
+ "learning_rate": 0.0002,
337
+ "loss": 1.8876,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.35861038475905865,
342
+ "grad_norm": 0.3587537109851837,
343
+ "learning_rate": 0.0002,
344
+ "loss": 1.8534,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.366081434441539,
349
+ "grad_norm": 0.3859670162200928,
350
+ "learning_rate": 0.0002,
351
+ "loss": 1.8046,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.3735524841240194,
356
+ "grad_norm": 0.395913690328598,
357
+ "learning_rate": 0.0002,
358
+ "loss": 1.8287,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.38102353380649984,
363
+ "grad_norm": 0.35052940249443054,
364
+ "learning_rate": 0.0002,
365
+ "loss": 1.7619,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.3884945834889802,
370
+ "grad_norm": 0.2979494333267212,
371
+ "learning_rate": 0.0002,
372
+ "loss": 1.7824,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.3959656331714606,
377
+ "grad_norm": 0.3062683343887329,
378
+ "learning_rate": 0.0002,
379
+ "loss": 1.8641,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.40343668285394096,
384
+ "grad_norm": 0.3172847330570221,
385
+ "learning_rate": 0.0002,
386
+ "loss": 1.7651,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.4109077325364214,
391
+ "grad_norm": 0.360435426235199,
392
+ "learning_rate": 0.0002,
393
+ "loss": 1.806,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.41837878221890173,
398
+ "grad_norm": 0.3427872359752655,
399
+ "learning_rate": 0.0002,
400
+ "loss": 1.9054,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.42584983190138215,
405
+ "grad_norm": 0.34036558866500854,
406
+ "learning_rate": 0.0002,
407
+ "loss": 1.7562,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.4333208815838625,
412
+ "grad_norm": 0.3365345299243927,
413
+ "learning_rate": 0.0002,
414
+ "loss": 1.7254,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.4407919312663429,
419
+ "grad_norm": 0.35619041323661804,
420
+ "learning_rate": 0.0002,
421
+ "loss": 1.8328,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.44826298094882333,
426
+ "grad_norm": 0.3569088280200958,
427
+ "learning_rate": 0.0002,
428
+ "loss": 1.8114,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.4557340306313037,
433
+ "grad_norm": 0.3581278622150421,
434
+ "learning_rate": 0.0002,
435
+ "loss": 1.8599,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.4632050803137841,
440
+ "grad_norm": 0.43197110295295715,
441
+ "learning_rate": 0.0002,
442
+ "loss": 1.7078,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.47067612999626446,
447
+ "grad_norm": 0.33966198563575745,
448
+ "learning_rate": 0.0002,
449
+ "loss": 1.8257,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.47814717967874487,
454
+ "grad_norm": 0.3343866467475891,
455
+ "learning_rate": 0.0002,
456
+ "loss": 1.7528,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.48561822936122523,
461
+ "grad_norm": 0.33878564834594727,
462
+ "learning_rate": 0.0002,
463
+ "loss": 1.8191,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.49308927904370564,
468
+ "grad_norm": 0.387195885181427,
469
+ "learning_rate": 0.0002,
470
+ "loss": 1.8801,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.500560328726186,
475
+ "grad_norm": 0.3755440413951874,
476
+ "learning_rate": 0.0002,
477
+ "loss": 1.7559,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.5080313784086664,
482
+ "grad_norm": 0.3272816836833954,
483
+ "learning_rate": 0.0002,
484
+ "loss": 1.8057,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.5155024280911468,
489
+ "grad_norm": 0.36063864827156067,
490
+ "learning_rate": 0.0002,
491
+ "loss": 1.8156,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.5229734777736272,
496
+ "grad_norm": 0.35317373275756836,
497
+ "learning_rate": 0.0002,
498
+ "loss": 1.8397,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.5304445274561076,
503
+ "grad_norm": 0.3561195433139801,
504
+ "learning_rate": 0.0002,
505
+ "loss": 1.7603,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.537915577138588,
510
+ "grad_norm": 0.31124624609947205,
511
+ "learning_rate": 0.0002,
512
+ "loss": 1.8149,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.5453866268210683,
517
+ "grad_norm": 0.3294544517993927,
518
+ "learning_rate": 0.0002,
519
+ "loss": 1.7434,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.5528576765035488,
524
+ "grad_norm": 0.31933900713920593,
525
+ "learning_rate": 0.0002,
526
+ "loss": 1.8027,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.5603287261860291,
531
+ "grad_norm": 0.3226020634174347,
532
+ "learning_rate": 0.0002,
533
+ "loss": 1.7601,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.5677997758685095,
538
+ "grad_norm": 0.3147525489330292,
539
+ "learning_rate": 0.0002,
540
+ "loss": 1.7862,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.57527082555099,
545
+ "grad_norm": 0.32234328985214233,
546
+ "learning_rate": 0.0002,
547
+ "loss": 1.9028,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.5827418752334703,
552
+ "grad_norm": 0.3258664309978485,
553
+ "learning_rate": 0.0002,
554
+ "loss": 1.7623,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.5902129249159507,
559
+ "grad_norm": 0.3166961967945099,
560
+ "learning_rate": 0.0002,
561
+ "loss": 1.7384,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.597683974598431,
566
+ "grad_norm": 0.35621458292007446,
567
+ "learning_rate": 0.0002,
568
+ "loss": 1.8799,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.6051550242809115,
573
+ "grad_norm": 0.3236999213695526,
574
+ "learning_rate": 0.0002,
575
+ "loss": 1.8313,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.6126260739633919,
580
+ "grad_norm": 0.2892923653125763,
581
+ "learning_rate": 0.0002,
582
+ "loss": 1.7132,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.6200971236458722,
587
+ "grad_norm": 0.4098321497440338,
588
+ "learning_rate": 0.0002,
589
+ "loss": 1.8709,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.6275681733283527,
594
+ "grad_norm": 0.3337118923664093,
595
+ "learning_rate": 0.0002,
596
+ "loss": 1.7637,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.635039223010833,
601
+ "grad_norm": 0.30416029691696167,
602
+ "learning_rate": 0.0002,
603
+ "loss": 1.7375,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.6425102726933134,
608
+ "grad_norm": 0.3361026346683502,
609
+ "learning_rate": 0.0002,
610
+ "loss": 1.7419,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.6499813223757938,
615
+ "grad_norm": 0.3537365198135376,
616
+ "learning_rate": 0.0002,
617
+ "loss": 1.732,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.6574523720582742,
622
+ "grad_norm": 0.33854469656944275,
623
+ "learning_rate": 0.0002,
624
+ "loss": 1.7825,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.6649234217407546,
629
+ "grad_norm": 0.3332272469997406,
630
+ "learning_rate": 0.0002,
631
+ "loss": 1.7561,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.6723944714232349,
636
+ "grad_norm": 0.34954726696014404,
637
+ "learning_rate": 0.0002,
638
+ "loss": 1.7247,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.6798655211057153,
643
+ "grad_norm": 0.2921750247478485,
644
+ "learning_rate": 0.0002,
645
+ "loss": 1.7917,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.6873365707881958,
650
+ "grad_norm": 0.30508682131767273,
651
+ "learning_rate": 0.0002,
652
+ "loss": 1.7807,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.6948076204706761,
657
+ "grad_norm": 0.32268425822257996,
658
+ "learning_rate": 0.0002,
659
+ "loss": 1.8082,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.7022786701531565,
664
+ "grad_norm": 0.2844390869140625,
665
+ "learning_rate": 0.0002,
666
+ "loss": 1.8283,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.709749719835637,
671
+ "grad_norm": 0.31263890862464905,
672
+ "learning_rate": 0.0002,
673
+ "loss": 1.7363,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.7172207695181173,
678
+ "grad_norm": 0.3626808822154999,
679
+ "learning_rate": 0.0002,
680
+ "loss": 1.8081,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.7246918192005977,
685
+ "grad_norm": 0.3322749733924866,
686
+ "learning_rate": 0.0002,
687
+ "loss": 1.853,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.732162868883078,
692
+ "grad_norm": 0.29177871346473694,
693
+ "learning_rate": 0.0002,
694
+ "loss": 1.7912,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.7396339185655585,
699
+ "grad_norm": 0.35405513644218445,
700
+ "learning_rate": 0.0002,
701
+ "loss": 1.8447,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.7471049682480388,
706
+ "grad_norm": 0.39318400621414185,
707
+ "learning_rate": 0.0002,
708
+ "loss": 1.7008,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.7545760179305192,
713
+ "grad_norm": 0.29401418566703796,
714
+ "learning_rate": 0.0002,
715
+ "loss": 1.7803,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 0.7620470676129997,
720
+ "grad_norm": 0.3271748721599579,
721
+ "learning_rate": 0.0002,
722
+ "loss": 1.7649,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 0.76951811729548,
727
+ "grad_norm": 0.30883970856666565,
728
+ "learning_rate": 0.0002,
729
+ "loss": 1.7266,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 0.7769891669779604,
734
+ "grad_norm": 0.3411838412284851,
735
+ "learning_rate": 0.0002,
736
+ "loss": 1.7722,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 0.7844602166604407,
741
+ "grad_norm": 0.30608129501342773,
742
+ "learning_rate": 0.0002,
743
+ "loss": 1.829,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 0.7919312663429212,
748
+ "grad_norm": 0.30899080634117126,
749
+ "learning_rate": 0.0002,
750
+ "loss": 1.7815,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 0.7994023160254016,
755
+ "grad_norm": 0.3160453140735626,
756
+ "learning_rate": 0.0002,
757
+ "loss": 1.7625,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 0.8068733657078819,
762
+ "grad_norm": 0.30947187542915344,
763
+ "learning_rate": 0.0002,
764
+ "loss": 1.8452,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 0.8143444153903624,
769
+ "grad_norm": 0.3103134036064148,
770
+ "learning_rate": 0.0002,
771
+ "loss": 1.7418,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 0.8218154650728428,
776
+ "grad_norm": 0.31771138310432434,
777
+ "learning_rate": 0.0002,
778
+ "loss": 1.842,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 0.8292865147553231,
783
+ "grad_norm": 0.5860997438430786,
784
+ "learning_rate": 0.0002,
785
+ "loss": 1.7918,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 0.8367575644378035,
790
+ "grad_norm": 0.3230148255825043,
791
+ "learning_rate": 0.0002,
792
+ "loss": 1.8443,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 0.8442286141202839,
797
+ "grad_norm": 0.29611510038375854,
798
+ "learning_rate": 0.0002,
799
+ "loss": 1.8478,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 0.8516996638027643,
804
+ "grad_norm": 0.3373654782772064,
805
+ "learning_rate": 0.0002,
806
+ "loss": 1.7673,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 0.8591707134852447,
811
+ "grad_norm": 0.3474279046058655,
812
+ "learning_rate": 0.0002,
813
+ "loss": 1.7997,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 0.866641763167725,
818
+ "grad_norm": 0.35057875514030457,
819
+ "learning_rate": 0.0002,
820
+ "loss": 1.75,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 0.8741128128502055,
825
+ "grad_norm": 0.39537495374679565,
826
+ "learning_rate": 0.0002,
827
+ "loss": 1.8273,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 0.8815838625326858,
832
+ "grad_norm": 0.3714233636856079,
833
+ "learning_rate": 0.0002,
834
+ "loss": 1.7682,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 0.8890549122151662,
839
+ "grad_norm": 0.2950296998023987,
840
+ "learning_rate": 0.0002,
841
+ "loss": 1.7549,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 0.8965259618976467,
846
+ "grad_norm": 0.38182979822158813,
847
+ "learning_rate": 0.0002,
848
+ "loss": 1.7612,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 0.903997011580127,
853
+ "grad_norm": 0.27883678674697876,
854
+ "learning_rate": 0.0002,
855
+ "loss": 1.827,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 0.9114680612626074,
860
+ "grad_norm": 0.33874374628067017,
861
+ "learning_rate": 0.0002,
862
+ "loss": 1.7623,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 0.9189391109450877,
867
+ "grad_norm": 0.3014272153377533,
868
+ "learning_rate": 0.0002,
869
+ "loss": 1.7334,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 0.9264101606275682,
874
+ "grad_norm": 0.3194271922111511,
875
+ "learning_rate": 0.0002,
876
+ "loss": 1.8235,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 0.9338812103100486,
881
+ "grad_norm": 0.3049403429031372,
882
+ "learning_rate": 0.0002,
883
+ "loss": 1.7924,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 0.9413522599925289,
888
+ "grad_norm": 0.30621254444122314,
889
+ "learning_rate": 0.0002,
890
+ "loss": 1.7535,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 0.9488233096750094,
895
+ "grad_norm": 0.28675132989883423,
896
+ "learning_rate": 0.0002,
897
+ "loss": 1.8287,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 0.9562943593574897,
902
+ "grad_norm": 0.3322032690048218,
903
+ "learning_rate": 0.0002,
904
+ "loss": 1.7586,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 0.9637654090399701,
909
+ "grad_norm": 0.35408294200897217,
910
+ "learning_rate": 0.0002,
911
+ "loss": 1.8054,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 0.9712364587224505,
916
+ "grad_norm": 0.36386919021606445,
917
+ "learning_rate": 0.0002,
918
+ "loss": 1.7343,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 0.9787075084049309,
923
+ "grad_norm": 0.32338324189186096,
924
+ "learning_rate": 0.0002,
925
+ "loss": 1.8633,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 0.9861785580874113,
930
+ "grad_norm": 0.3714013993740082,
931
+ "learning_rate": 0.0002,
932
+ "loss": 1.7724,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 0.9936496077698916,
937
+ "grad_norm": 0.3133082389831543,
938
+ "learning_rate": 0.0002,
939
+ "loss": 1.7766,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 0.9996264475158759,
944
+ "eval_loss": 1.8051470518112183,
945
+ "eval_runtime": 38.6332,
946
+ "eval_samples_per_second": 13.331,
947
+ "eval_steps_per_second": 1.682,
948
+ "step": 1338
949
+ },
950
+ {
951
+ "epoch": 1.001120657452372,
952
+ "grad_norm": 0.31595754623413086,
953
+ "learning_rate": 0.0002,
954
+ "loss": 1.8035,
955
+ "step": 1340
956
+ },
957
+ {
958
+ "epoch": 1.0085917071348525,
959
+ "grad_norm": 0.3095700144767761,
960
+ "learning_rate": 0.0002,
961
+ "loss": 1.7486,
962
+ "step": 1350
963
+ },
964
+ {
965
+ "epoch": 1.0160627568173328,
966
+ "grad_norm": 0.34677496552467346,
967
+ "learning_rate": 0.0002,
968
+ "loss": 1.6981,
969
+ "step": 1360
970
+ },
971
+ {
972
+ "epoch": 1.0235338064998132,
973
+ "grad_norm": 0.29108840227127075,
974
+ "learning_rate": 0.0002,
975
+ "loss": 1.7377,
976
+ "step": 1370
977
+ },
978
+ {
979
+ "epoch": 1.0310048561822935,
980
+ "grad_norm": 0.32356950640678406,
981
+ "learning_rate": 0.0002,
982
+ "loss": 1.7194,
983
+ "step": 1380
984
+ },
985
+ {
986
+ "epoch": 1.038475905864774,
987
+ "grad_norm": 0.4200669229030609,
988
+ "learning_rate": 0.0002,
989
+ "loss": 1.7593,
990
+ "step": 1390
991
+ },
992
+ {
993
+ "epoch": 1.0459469555472545,
994
+ "grad_norm": 0.3283711373806,
995
+ "learning_rate": 0.0002,
996
+ "loss": 1.797,
997
+ "step": 1400
998
+ },
999
+ {
1000
+ "epoch": 1.0534180052297348,
1001
+ "grad_norm": 0.32898256182670593,
1002
+ "learning_rate": 0.0002,
1003
+ "loss": 1.7163,
1004
+ "step": 1410
1005
+ },
1006
+ {
1007
+ "epoch": 1.0608890549122152,
1008
+ "grad_norm": 0.38790300488471985,
1009
+ "learning_rate": 0.0002,
1010
+ "loss": 1.7559,
1011
+ "step": 1420
1012
+ },
1013
+ {
1014
+ "epoch": 1.0683601045946955,
1015
+ "grad_norm": 0.339800089597702,
1016
+ "learning_rate": 0.0002,
1017
+ "loss": 1.6922,
1018
+ "step": 1430
1019
+ },
1020
+ {
1021
+ "epoch": 1.075831154277176,
1022
+ "grad_norm": 0.3548751175403595,
1023
+ "learning_rate": 0.0002,
1024
+ "loss": 1.7076,
1025
+ "step": 1440
1026
+ },
1027
+ {
1028
+ "epoch": 1.0833022039596563,
1029
+ "grad_norm": 0.35114359855651855,
1030
+ "learning_rate": 0.0002,
1031
+ "loss": 1.6985,
1032
+ "step": 1450
1033
+ },
1034
+ {
1035
+ "epoch": 1.0907732536421366,
1036
+ "grad_norm": 0.35226720571517944,
1037
+ "learning_rate": 0.0002,
1038
+ "loss": 1.7217,
1039
+ "step": 1460
1040
+ },
1041
+ {
1042
+ "epoch": 1.0982443033246172,
1043
+ "grad_norm": 0.33665576577186584,
1044
+ "learning_rate": 0.0002,
1045
+ "loss": 1.6822,
1046
+ "step": 1470
1047
+ },
1048
+ {
1049
+ "epoch": 1.1057153530070976,
1050
+ "grad_norm": 0.363889217376709,
1051
+ "learning_rate": 0.0002,
1052
+ "loss": 1.6699,
1053
+ "step": 1480
1054
+ },
1055
+ {
1056
+ "epoch": 1.113186402689578,
1057
+ "grad_norm": 0.3826201856136322,
1058
+ "learning_rate": 0.0002,
1059
+ "loss": 1.7933,
1060
+ "step": 1490
1061
+ },
1062
+ {
1063
+ "epoch": 1.1206574523720583,
1064
+ "grad_norm": 0.34058740735054016,
1065
+ "learning_rate": 0.0002,
1066
+ "loss": 1.7022,
1067
+ "step": 1500
1068
+ },
1069
+ {
1070
+ "epoch": 1.1281285020545386,
1071
+ "grad_norm": 0.3462134301662445,
1072
+ "learning_rate": 0.0002,
1073
+ "loss": 1.6375,
1074
+ "step": 1510
1075
+ },
1076
+ {
1077
+ "epoch": 1.135599551737019,
1078
+ "grad_norm": 0.3396756052970886,
1079
+ "learning_rate": 0.0002,
1080
+ "loss": 1.7147,
1081
+ "step": 1520
1082
+ },
1083
+ {
1084
+ "epoch": 1.1430706014194993,
1085
+ "grad_norm": 0.32004743814468384,
1086
+ "learning_rate": 0.0002,
1087
+ "loss": 1.7219,
1088
+ "step": 1530
1089
+ },
1090
+ {
1091
+ "epoch": 1.15054165110198,
1092
+ "grad_norm": 0.3397733271121979,
1093
+ "learning_rate": 0.0002,
1094
+ "loss": 1.743,
1095
+ "step": 1540
1096
+ },
1097
+ {
1098
+ "epoch": 1.1580127007844603,
1099
+ "grad_norm": 0.3783262073993683,
1100
+ "learning_rate": 0.0002,
1101
+ "loss": 1.7333,
1102
+ "step": 1550
1103
+ },
1104
+ {
1105
+ "epoch": 1.1654837504669406,
1106
+ "grad_norm": 0.35121291875839233,
1107
+ "learning_rate": 0.0002,
1108
+ "loss": 1.6075,
1109
+ "step": 1560
1110
+ },
1111
+ {
1112
+ "epoch": 1.172954800149421,
1113
+ "grad_norm": 0.35816895961761475,
1114
+ "learning_rate": 0.0002,
1115
+ "loss": 1.678,
1116
+ "step": 1570
1117
+ },
1118
+ {
1119
+ "epoch": 1.1804258498319014,
1120
+ "grad_norm": 0.33843839168548584,
1121
+ "learning_rate": 0.0002,
1122
+ "loss": 1.7143,
1123
+ "step": 1580
1124
+ },
1125
+ {
1126
+ "epoch": 1.1878968995143817,
1127
+ "grad_norm": 0.3371972143650055,
1128
+ "learning_rate": 0.0002,
1129
+ "loss": 1.7434,
1130
+ "step": 1590
1131
+ },
1132
+ {
1133
+ "epoch": 1.195367949196862,
1134
+ "grad_norm": 0.36016878485679626,
1135
+ "learning_rate": 0.0002,
1136
+ "loss": 1.7671,
1137
+ "step": 1600
1138
+ },
1139
+ {
1140
+ "epoch": 1.2028389988793426,
1141
+ "grad_norm": 0.40879473090171814,
1142
+ "learning_rate": 0.0002,
1143
+ "loss": 1.6914,
1144
+ "step": 1610
1145
+ },
1146
+ {
1147
+ "epoch": 1.210310048561823,
1148
+ "grad_norm": 0.3216715455055237,
1149
+ "learning_rate": 0.0002,
1150
+ "loss": 1.6955,
1151
+ "step": 1620
1152
+ },
1153
+ {
1154
+ "epoch": 1.2177810982443034,
1155
+ "grad_norm": 0.4482610821723938,
1156
+ "learning_rate": 0.0002,
1157
+ "loss": 1.632,
1158
+ "step": 1630
1159
+ },
1160
+ {
1161
+ "epoch": 1.2252521479267837,
1162
+ "grad_norm": 0.3257700502872467,
1163
+ "learning_rate": 0.0002,
1164
+ "loss": 1.6999,
1165
+ "step": 1640
1166
+ },
1167
+ {
1168
+ "epoch": 1.232723197609264,
1169
+ "grad_norm": 0.38646459579467773,
1170
+ "learning_rate": 0.0002,
1171
+ "loss": 1.7177,
1172
+ "step": 1650
1173
+ },
1174
+ {
1175
+ "epoch": 1.2401942472917444,
1176
+ "grad_norm": 0.4081360697746277,
1177
+ "learning_rate": 0.0002,
1178
+ "loss": 1.7081,
1179
+ "step": 1660
1180
+ },
1181
+ {
1182
+ "epoch": 1.2476652969742248,
1183
+ "grad_norm": 0.4326848089694977,
1184
+ "learning_rate": 0.0002,
1185
+ "loss": 1.7519,
1186
+ "step": 1670
1187
+ },
1188
+ {
1189
+ "epoch": 1.2551363466567054,
1190
+ "grad_norm": 0.346401572227478,
1191
+ "learning_rate": 0.0002,
1192
+ "loss": 1.6752,
1193
+ "step": 1680
1194
+ },
1195
+ {
1196
+ "epoch": 1.2626073963391857,
1197
+ "grad_norm": 0.34536251425743103,
1198
+ "learning_rate": 0.0002,
1199
+ "loss": 1.7425,
1200
+ "step": 1690
1201
+ },
1202
+ {
1203
+ "epoch": 1.270078446021666,
1204
+ "grad_norm": 0.41359591484069824,
1205
+ "learning_rate": 0.0002,
1206
+ "loss": 1.7061,
1207
+ "step": 1700
1208
+ },
1209
+ {
1210
+ "epoch": 1.2775494957041464,
1211
+ "grad_norm": 0.3530874252319336,
1212
+ "learning_rate": 0.0002,
1213
+ "loss": 1.7906,
1214
+ "step": 1710
1215
+ },
1216
+ {
1217
+ "epoch": 1.2850205453866268,
1218
+ "grad_norm": 0.3702719211578369,
1219
+ "learning_rate": 0.0002,
1220
+ "loss": 1.7357,
1221
+ "step": 1720
1222
+ },
1223
+ {
1224
+ "epoch": 1.2924915950691072,
1225
+ "grad_norm": 0.3703329563140869,
1226
+ "learning_rate": 0.0002,
1227
+ "loss": 1.766,
1228
+ "step": 1730
1229
+ },
1230
+ {
1231
+ "epoch": 1.2999626447515875,
1232
+ "grad_norm": 0.37919729948043823,
1233
+ "learning_rate": 0.0002,
1234
+ "loss": 1.7221,
1235
+ "step": 1740
1236
+ },
1237
+ {
1238
+ "epoch": 1.307433694434068,
1239
+ "grad_norm": 0.32526856660842896,
1240
+ "learning_rate": 0.0002,
1241
+ "loss": 1.7859,
1242
+ "step": 1750
1243
+ },
1244
+ {
1245
+ "epoch": 1.3149047441165485,
1246
+ "grad_norm": 0.36752620339393616,
1247
+ "learning_rate": 0.0002,
1248
+ "loss": 1.7117,
1249
+ "step": 1760
1250
+ },
1251
+ {
1252
+ "epoch": 1.3223757937990288,
1253
+ "grad_norm": 0.3398192524909973,
1254
+ "learning_rate": 0.0002,
1255
+ "loss": 1.7335,
1256
+ "step": 1770
1257
+ },
1258
+ {
1259
+ "epoch": 1.3298468434815092,
1260
+ "grad_norm": 0.37435585260391235,
1261
+ "learning_rate": 0.0002,
1262
+ "loss": 1.7492,
1263
+ "step": 1780
1264
+ },
1265
+ {
1266
+ "epoch": 1.3373178931639895,
1267
+ "grad_norm": 0.35793280601501465,
1268
+ "learning_rate": 0.0002,
1269
+ "loss": 1.7393,
1270
+ "step": 1790
1271
+ },
1272
+ {
1273
+ "epoch": 1.3447889428464699,
1274
+ "grad_norm": 0.35481882095336914,
1275
+ "learning_rate": 0.0002,
1276
+ "loss": 1.7266,
1277
+ "step": 1800
1278
+ },
1279
+ {
1280
+ "epoch": 1.3522599925289502,
1281
+ "grad_norm": 0.3786393105983734,
1282
+ "learning_rate": 0.0002,
1283
+ "loss": 1.7456,
1284
+ "step": 1810
1285
+ },
1286
+ {
1287
+ "epoch": 1.3597310422114308,
1288
+ "grad_norm": 0.33245593309402466,
1289
+ "learning_rate": 0.0002,
1290
+ "loss": 1.7169,
1291
+ "step": 1820
1292
+ },
1293
+ {
1294
+ "epoch": 1.3672020918939112,
1295
+ "grad_norm": 0.35388344526290894,
1296
+ "learning_rate": 0.0002,
1297
+ "loss": 1.7577,
1298
+ "step": 1830
1299
+ },
1300
+ {
1301
+ "epoch": 1.3746731415763915,
1302
+ "grad_norm": 0.3695325553417206,
1303
+ "learning_rate": 0.0002,
1304
+ "loss": 1.6968,
1305
+ "step": 1840
1306
+ },
1307
+ {
1308
+ "epoch": 1.382144191258872,
1309
+ "grad_norm": 0.3683604598045349,
1310
+ "learning_rate": 0.0002,
1311
+ "loss": 1.7086,
1312
+ "step": 1850
1313
+ },
1314
+ {
1315
+ "epoch": 1.3896152409413522,
1316
+ "grad_norm": 0.3753012418746948,
1317
+ "learning_rate": 0.0002,
1318
+ "loss": 1.7878,
1319
+ "step": 1860
1320
+ },
1321
+ {
1322
+ "epoch": 1.3970862906238326,
1323
+ "grad_norm": 0.3331069350242615,
1324
+ "learning_rate": 0.0002,
1325
+ "loss": 1.6969,
1326
+ "step": 1870
1327
+ },
1328
+ {
1329
+ "epoch": 1.404557340306313,
1330
+ "grad_norm": 0.3877500295639038,
1331
+ "learning_rate": 0.0002,
1332
+ "loss": 1.6644,
1333
+ "step": 1880
1334
+ },
1335
+ {
1336
+ "epoch": 1.4120283899887935,
1337
+ "grad_norm": 0.33525151014328003,
1338
+ "learning_rate": 0.0002,
1339
+ "loss": 1.7586,
1340
+ "step": 1890
1341
+ },
1342
+ {
1343
+ "epoch": 1.4194994396712737,
1344
+ "grad_norm": 0.3697299659252167,
1345
+ "learning_rate": 0.0002,
1346
+ "loss": 1.7031,
1347
+ "step": 1900
1348
+ },
1349
+ {
1350
+ "epoch": 1.4269704893537543,
1351
+ "grad_norm": 0.4029286205768585,
1352
+ "learning_rate": 0.0002,
1353
+ "loss": 1.6956,
1354
+ "step": 1910
1355
+ },
1356
+ {
1357
+ "epoch": 1.4344415390362346,
1358
+ "grad_norm": 0.3596203029155731,
1359
+ "learning_rate": 0.0002,
1360
+ "loss": 1.6897,
1361
+ "step": 1920
1362
+ },
1363
+ {
1364
+ "epoch": 1.441912588718715,
1365
+ "grad_norm": 0.450783908367157,
1366
+ "learning_rate": 0.0002,
1367
+ "loss": 1.7139,
1368
+ "step": 1930
1369
+ },
1370
+ {
1371
+ "epoch": 1.4493836384011953,
1372
+ "grad_norm": 0.3651481866836548,
1373
+ "learning_rate": 0.0002,
1374
+ "loss": 1.7243,
1375
+ "step": 1940
1376
+ },
1377
+ {
1378
+ "epoch": 1.4568546880836757,
1379
+ "grad_norm": 0.3608424663543701,
1380
+ "learning_rate": 0.0002,
1381
+ "loss": 1.6637,
1382
+ "step": 1950
1383
+ },
1384
+ {
1385
+ "epoch": 1.4643257377661563,
1386
+ "grad_norm": 0.39684420824050903,
1387
+ "learning_rate": 0.0002,
1388
+ "loss": 1.8285,
1389
+ "step": 1960
1390
+ },
1391
+ {
1392
+ "epoch": 1.4717967874486364,
1393
+ "grad_norm": 0.34618663787841797,
1394
+ "learning_rate": 0.0002,
1395
+ "loss": 1.7514,
1396
+ "step": 1970
1397
+ },
1398
+ {
1399
+ "epoch": 1.479267837131117,
1400
+ "grad_norm": 0.4150386452674866,
1401
+ "learning_rate": 0.0002,
1402
+ "loss": 1.6655,
1403
+ "step": 1980
1404
+ },
1405
+ {
1406
+ "epoch": 1.4867388868135973,
1407
+ "grad_norm": 0.35500776767730713,
1408
+ "learning_rate": 0.0002,
1409
+ "loss": 1.7021,
1410
+ "step": 1990
1411
+ },
1412
+ {
1413
+ "epoch": 1.4942099364960777,
1414
+ "grad_norm": 0.344144344329834,
1415
+ "learning_rate": 0.0002,
1416
+ "loss": 1.7322,
1417
+ "step": 2000
1418
+ },
1419
+ {
1420
+ "epoch": 1.501680986178558,
1421
+ "grad_norm": 0.3340149223804474,
1422
+ "learning_rate": 0.0002,
1423
+ "loss": 1.6998,
1424
+ "step": 2010
1425
+ },
1426
+ {
1427
+ "epoch": 1.5091520358610384,
1428
+ "grad_norm": 0.37685006856918335,
1429
+ "learning_rate": 0.0002,
1430
+ "loss": 1.7508,
1431
+ "step": 2020
1432
+ },
1433
+ {
1434
+ "epoch": 1.516623085543519,
1435
+ "grad_norm": 0.3699876368045807,
1436
+ "learning_rate": 0.0002,
1437
+ "loss": 1.8299,
1438
+ "step": 2030
1439
+ },
1440
+ {
1441
+ "epoch": 1.5240941352259991,
1442
+ "grad_norm": 0.3370307385921478,
1443
+ "learning_rate": 0.0002,
1444
+ "loss": 1.7357,
1445
+ "step": 2040
1446
+ },
1447
+ {
1448
+ "epoch": 1.5315651849084797,
1449
+ "grad_norm": 0.37780630588531494,
1450
+ "learning_rate": 0.0002,
1451
+ "loss": 1.8044,
1452
+ "step": 2050
1453
+ },
1454
+ {
1455
+ "epoch": 1.53903623459096,
1456
+ "grad_norm": 0.370259165763855,
1457
+ "learning_rate": 0.0002,
1458
+ "loss": 1.7408,
1459
+ "step": 2060
1460
+ },
1461
+ {
1462
+ "epoch": 1.5465072842734404,
1463
+ "grad_norm": 0.3440011441707611,
1464
+ "learning_rate": 0.0002,
1465
+ "loss": 1.7398,
1466
+ "step": 2070
1467
+ },
1468
+ {
1469
+ "epoch": 1.5539783339559208,
1470
+ "grad_norm": 0.40382063388824463,
1471
+ "learning_rate": 0.0002,
1472
+ "loss": 1.7105,
1473
+ "step": 2080
1474
+ },
1475
+ {
1476
+ "epoch": 1.5614493836384011,
1477
+ "grad_norm": 0.38002029061317444,
1478
+ "learning_rate": 0.0002,
1479
+ "loss": 1.7071,
1480
+ "step": 2090
1481
+ },
1482
+ {
1483
+ "epoch": 1.5689204333208817,
1484
+ "grad_norm": 0.3658451437950134,
1485
+ "learning_rate": 0.0002,
1486
+ "loss": 1.6815,
1487
+ "step": 2100
1488
+ },
1489
+ {
1490
+ "epoch": 1.5763914830033618,
1491
+ "grad_norm": 0.354842871427536,
1492
+ "learning_rate": 0.0002,
1493
+ "loss": 1.7598,
1494
+ "step": 2110
1495
+ },
1496
+ {
1497
+ "epoch": 1.5838625326858424,
1498
+ "grad_norm": 0.34735530614852905,
1499
+ "learning_rate": 0.0002,
1500
+ "loss": 1.6898,
1501
+ "step": 2120
1502
+ },
1503
+ {
1504
+ "epoch": 1.5913335823683228,
1505
+ "grad_norm": 0.377581924200058,
1506
+ "learning_rate": 0.0002,
1507
+ "loss": 1.7363,
1508
+ "step": 2130
1509
+ },
1510
+ {
1511
+ "epoch": 1.5988046320508031,
1512
+ "grad_norm": 0.41254034638404846,
1513
+ "learning_rate": 0.0002,
1514
+ "loss": 1.7789,
1515
+ "step": 2140
1516
+ },
1517
+ {
1518
+ "epoch": 1.6062756817332835,
1519
+ "grad_norm": 0.3630715310573578,
1520
+ "learning_rate": 0.0002,
1521
+ "loss": 1.6782,
1522
+ "step": 2150
1523
+ },
1524
+ {
1525
+ "epoch": 1.6137467314157639,
1526
+ "grad_norm": 0.36980143189430237,
1527
+ "learning_rate": 0.0002,
1528
+ "loss": 1.7531,
1529
+ "step": 2160
1530
+ },
1531
+ {
1532
+ "epoch": 1.6212177810982444,
1533
+ "grad_norm": 0.3634769320487976,
1534
+ "learning_rate": 0.0002,
1535
+ "loss": 1.6847,
1536
+ "step": 2170
1537
+ },
1538
+ {
1539
+ "epoch": 1.6286888307807246,
1540
+ "grad_norm": 0.3794139623641968,
1541
+ "learning_rate": 0.0002,
1542
+ "loss": 1.6367,
1543
+ "step": 2180
1544
+ },
1545
+ {
1546
+ "epoch": 1.6361598804632052,
1547
+ "grad_norm": 0.359742134809494,
1548
+ "learning_rate": 0.0002,
1549
+ "loss": 1.7064,
1550
+ "step": 2190
1551
+ },
1552
+ {
1553
+ "epoch": 1.6436309301456855,
1554
+ "grad_norm": 0.3770543932914734,
1555
+ "learning_rate": 0.0002,
1556
+ "loss": 1.7027,
1557
+ "step": 2200
1558
+ },
1559
+ {
1560
+ "epoch": 1.6511019798281659,
1561
+ "grad_norm": 0.3797036409378052,
1562
+ "learning_rate": 0.0002,
1563
+ "loss": 1.784,
1564
+ "step": 2210
1565
+ },
1566
+ {
1567
+ "epoch": 1.6585730295106462,
1568
+ "grad_norm": 0.35622093081474304,
1569
+ "learning_rate": 0.0002,
1570
+ "loss": 1.7875,
1571
+ "step": 2220
1572
+ },
1573
+ {
1574
+ "epoch": 1.6660440791931266,
1575
+ "grad_norm": 0.34552520513534546,
1576
+ "learning_rate": 0.0002,
1577
+ "loss": 1.6615,
1578
+ "step": 2230
1579
+ },
1580
+ {
1581
+ "epoch": 1.6735151288756072,
1582
+ "grad_norm": 0.379926860332489,
1583
+ "learning_rate": 0.0002,
1584
+ "loss": 1.7522,
1585
+ "step": 2240
1586
+ },
1587
+ {
1588
+ "epoch": 1.6809861785580873,
1589
+ "grad_norm": 0.37083810567855835,
1590
+ "learning_rate": 0.0002,
1591
+ "loss": 1.7953,
1592
+ "step": 2250
1593
+ },
1594
+ {
1595
+ "epoch": 1.6884572282405679,
1596
+ "grad_norm": 0.42746543884277344,
1597
+ "learning_rate": 0.0002,
1598
+ "loss": 1.7485,
1599
+ "step": 2260
1600
+ },
1601
+ {
1602
+ "epoch": 1.6959282779230482,
1603
+ "grad_norm": 0.3372884690761566,
1604
+ "learning_rate": 0.0002,
1605
+ "loss": 1.776,
1606
+ "step": 2270
1607
+ },
1608
+ {
1609
+ "epoch": 1.7033993276055286,
1610
+ "grad_norm": 0.35220256447792053,
1611
+ "learning_rate": 0.0002,
1612
+ "loss": 1.7604,
1613
+ "step": 2280
1614
+ },
1615
+ {
1616
+ "epoch": 1.710870377288009,
1617
+ "grad_norm": 0.3659130930900574,
1618
+ "learning_rate": 0.0002,
1619
+ "loss": 1.7154,
1620
+ "step": 2290
1621
+ },
1622
+ {
1623
+ "epoch": 1.7183414269704893,
1624
+ "grad_norm": 0.37629297375679016,
1625
+ "learning_rate": 0.0002,
1626
+ "loss": 1.6953,
1627
+ "step": 2300
1628
+ },
1629
+ {
1630
+ "epoch": 1.7258124766529699,
1631
+ "grad_norm": 0.36312398314476013,
1632
+ "learning_rate": 0.0002,
1633
+ "loss": 1.7212,
1634
+ "step": 2310
1635
+ },
1636
+ {
1637
+ "epoch": 1.73328352633545,
1638
+ "grad_norm": 0.467709481716156,
1639
+ "learning_rate": 0.0002,
1640
+ "loss": 1.7903,
1641
+ "step": 2320
1642
+ },
1643
+ {
1644
+ "epoch": 1.7407545760179306,
1645
+ "grad_norm": 0.38685527443885803,
1646
+ "learning_rate": 0.0002,
1647
+ "loss": 1.696,
1648
+ "step": 2330
1649
+ },
1650
+ {
1651
+ "epoch": 1.748225625700411,
1652
+ "grad_norm": 0.3578338325023651,
1653
+ "learning_rate": 0.0002,
1654
+ "loss": 1.7041,
1655
+ "step": 2340
1656
+ },
1657
+ {
1658
+ "epoch": 1.7556966753828913,
1659
+ "grad_norm": 0.36057502031326294,
1660
+ "learning_rate": 0.0002,
1661
+ "loss": 1.6456,
1662
+ "step": 2350
1663
+ },
1664
+ {
1665
+ "epoch": 1.7631677250653717,
1666
+ "grad_norm": 0.3615196645259857,
1667
+ "learning_rate": 0.0002,
1668
+ "loss": 1.6853,
1669
+ "step": 2360
1670
+ },
1671
+ {
1672
+ "epoch": 1.770638774747852,
1673
+ "grad_norm": 0.4118947684764862,
1674
+ "learning_rate": 0.0002,
1675
+ "loss": 1.7612,
1676
+ "step": 2370
1677
+ },
1678
+ {
1679
+ "epoch": 1.7781098244303326,
1680
+ "grad_norm": 0.4067276120185852,
1681
+ "learning_rate": 0.0002,
1682
+ "loss": 1.6946,
1683
+ "step": 2380
1684
+ },
1685
+ {
1686
+ "epoch": 1.7855808741128127,
1687
+ "grad_norm": 0.3979823887348175,
1688
+ "learning_rate": 0.0002,
1689
+ "loss": 1.712,
1690
+ "step": 2390
1691
+ },
1692
+ {
1693
+ "epoch": 1.7930519237952933,
1694
+ "grad_norm": 0.44045883417129517,
1695
+ "learning_rate": 0.0002,
1696
+ "loss": 1.7644,
1697
+ "step": 2400
1698
+ },
1699
+ {
1700
+ "epoch": 1.8005229734777737,
1701
+ "grad_norm": 0.3998069167137146,
1702
+ "learning_rate": 0.0002,
1703
+ "loss": 1.7251,
1704
+ "step": 2410
1705
+ },
1706
+ {
1707
+ "epoch": 1.807994023160254,
1708
+ "grad_norm": 0.3450094759464264,
1709
+ "learning_rate": 0.0002,
1710
+ "loss": 1.7354,
1711
+ "step": 2420
1712
+ },
1713
+ {
1714
+ "epoch": 1.8154650728427344,
1715
+ "grad_norm": 0.3759009838104248,
1716
+ "learning_rate": 0.0002,
1717
+ "loss": 1.6998,
1718
+ "step": 2430
1719
+ },
1720
+ {
1721
+ "epoch": 1.8229361225252148,
1722
+ "grad_norm": 0.34347015619277954,
1723
+ "learning_rate": 0.0002,
1724
+ "loss": 1.7706,
1725
+ "step": 2440
1726
+ },
1727
+ {
1728
+ "epoch": 1.8304071722076953,
1729
+ "grad_norm": 0.3511228859424591,
1730
+ "learning_rate": 0.0002,
1731
+ "loss": 1.7345,
1732
+ "step": 2450
1733
+ },
1734
+ {
1735
+ "epoch": 1.8378782218901755,
1736
+ "grad_norm": 0.36853715777397156,
1737
+ "learning_rate": 0.0002,
1738
+ "loss": 1.6909,
1739
+ "step": 2460
1740
+ },
1741
+ {
1742
+ "epoch": 1.845349271572656,
1743
+ "grad_norm": 0.40659376978874207,
1744
+ "learning_rate": 0.0002,
1745
+ "loss": 1.6931,
1746
+ "step": 2470
1747
+ },
1748
+ {
1749
+ "epoch": 1.8528203212551362,
1750
+ "grad_norm": 0.39621320366859436,
1751
+ "learning_rate": 0.0002,
1752
+ "loss": 1.7626,
1753
+ "step": 2480
1754
+ },
1755
+ {
1756
+ "epoch": 1.8602913709376168,
1757
+ "grad_norm": 0.3753979504108429,
1758
+ "learning_rate": 0.0002,
1759
+ "loss": 1.7427,
1760
+ "step": 2490
1761
+ },
1762
+ {
1763
+ "epoch": 1.8677624206200971,
1764
+ "grad_norm": 0.3811938464641571,
1765
+ "learning_rate": 0.0002,
1766
+ "loss": 1.6622,
1767
+ "step": 2500
1768
+ },
1769
+ {
1770
+ "epoch": 1.8752334703025775,
1771
+ "grad_norm": 0.3432596027851105,
1772
+ "learning_rate": 0.0002,
1773
+ "loss": 1.7718,
1774
+ "step": 2510
1775
+ },
1776
+ {
1777
+ "epoch": 1.882704519985058,
1778
+ "grad_norm": 0.3670712113380432,
1779
+ "learning_rate": 0.0002,
1780
+ "loss": 1.7488,
1781
+ "step": 2520
1782
+ },
1783
+ {
1784
+ "epoch": 1.8901755696675382,
1785
+ "grad_norm": 0.40907177329063416,
1786
+ "learning_rate": 0.0002,
1787
+ "loss": 1.705,
1788
+ "step": 2530
1789
+ },
1790
+ {
1791
+ "epoch": 1.8976466193500188,
1792
+ "grad_norm": 0.3821999728679657,
1793
+ "learning_rate": 0.0002,
1794
+ "loss": 1.7148,
1795
+ "step": 2540
1796
+ },
1797
+ {
1798
+ "epoch": 1.905117669032499,
1799
+ "grad_norm": 0.36173978447914124,
1800
+ "learning_rate": 0.0002,
1801
+ "loss": 1.7934,
1802
+ "step": 2550
1803
+ },
1804
+ {
1805
+ "epoch": 1.9125887187149795,
1806
+ "grad_norm": 0.38990336656570435,
1807
+ "learning_rate": 0.0002,
1808
+ "loss": 1.6939,
1809
+ "step": 2560
1810
+ },
1811
+ {
1812
+ "epoch": 1.9200597683974598,
1813
+ "grad_norm": 0.35242322087287903,
1814
+ "learning_rate": 0.0002,
1815
+ "loss": 1.6893,
1816
+ "step": 2570
1817
+ },
1818
+ {
1819
+ "epoch": 1.9275308180799402,
1820
+ "grad_norm": 0.3506428003311157,
1821
+ "learning_rate": 0.0002,
1822
+ "loss": 1.7268,
1823
+ "step": 2580
1824
+ },
1825
+ {
1826
+ "epoch": 1.9350018677624208,
1827
+ "grad_norm": 0.39540135860443115,
1828
+ "learning_rate": 0.0002,
1829
+ "loss": 1.6953,
1830
+ "step": 2590
1831
+ },
1832
+ {
1833
+ "epoch": 1.942472917444901,
1834
+ "grad_norm": 0.3444725573062897,
1835
+ "learning_rate": 0.0002,
1836
+ "loss": 1.6511,
1837
+ "step": 2600
1838
+ },
1839
+ {
1840
+ "epoch": 1.9499439671273815,
1841
+ "grad_norm": 0.3963521718978882,
1842
+ "learning_rate": 0.0002,
1843
+ "loss": 1.7259,
1844
+ "step": 2610
1845
+ },
1846
+ {
1847
+ "epoch": 1.9574150168098616,
1848
+ "grad_norm": 0.3689815402030945,
1849
+ "learning_rate": 0.0002,
1850
+ "loss": 1.6946,
1851
+ "step": 2620
1852
+ },
1853
+ {
1854
+ "epoch": 1.9648860664923422,
1855
+ "grad_norm": 0.3482626676559448,
1856
+ "learning_rate": 0.0002,
1857
+ "loss": 1.7384,
1858
+ "step": 2630
1859
+ },
1860
+ {
1861
+ "epoch": 1.9723571161748226,
1862
+ "grad_norm": 0.35832616686820984,
1863
+ "learning_rate": 0.0002,
1864
+ "loss": 1.7048,
1865
+ "step": 2640
1866
+ },
1867
+ {
1868
+ "epoch": 1.979828165857303,
1869
+ "grad_norm": 0.4776208996772766,
1870
+ "learning_rate": 0.0002,
1871
+ "loss": 1.6681,
1872
+ "step": 2650
1873
+ },
1874
+ {
1875
+ "epoch": 1.9872992155397835,
1876
+ "grad_norm": 0.32570165395736694,
1877
+ "learning_rate": 0.0002,
1878
+ "loss": 1.6696,
1879
+ "step": 2660
1880
+ },
1881
+ {
1882
+ "epoch": 1.9947702652222636,
1883
+ "grad_norm": 0.3380725085735321,
1884
+ "learning_rate": 0.0002,
1885
+ "loss": 1.7232,
1886
+ "step": 2670
1887
+ },
1888
+ {
1889
+ "epoch": 2.0,
1890
+ "eval_loss": 1.8046749830245972,
1891
+ "eval_runtime": 38.5096,
1892
+ "eval_samples_per_second": 13.373,
1893
+ "eval_steps_per_second": 1.688,
1894
+ "step": 2677
1895
+ },
1896
+ {
1897
+ "epoch": 2.002241314904744,
1898
+ "grad_norm": 0.36817631125450134,
1899
+ "learning_rate": 0.0002,
1900
+ "loss": 1.7265,
1901
+ "step": 2680
1902
+ },
1903
+ {
1904
+ "epoch": 2.0097123645872244,
1905
+ "grad_norm": 0.4056456685066223,
1906
+ "learning_rate": 0.0002,
1907
+ "loss": 1.548,
1908
+ "step": 2690
1909
+ },
1910
+ {
1911
+ "epoch": 2.017183414269705,
1912
+ "grad_norm": 0.37416863441467285,
1913
+ "learning_rate": 0.0002,
1914
+ "loss": 1.5515,
1915
+ "step": 2700
1916
+ },
1917
+ {
1918
+ "epoch": 2.024654463952185,
1919
+ "grad_norm": 0.4273638427257538,
1920
+ "learning_rate": 0.0002,
1921
+ "loss": 1.5895,
1922
+ "step": 2710
1923
+ },
1924
+ {
1925
+ "epoch": 2.0321255136346656,
1926
+ "grad_norm": 0.36497923731803894,
1927
+ "learning_rate": 0.0002,
1928
+ "loss": 1.5884,
1929
+ "step": 2720
1930
+ },
1931
+ {
1932
+ "epoch": 2.0395965633171462,
1933
+ "grad_norm": 0.5021994113922119,
1934
+ "learning_rate": 0.0002,
1935
+ "loss": 1.6999,
1936
+ "step": 2730
1937
+ },
1938
+ {
1939
+ "epoch": 2.0470676129996264,
1940
+ "grad_norm": 0.45896220207214355,
1941
+ "learning_rate": 0.0002,
1942
+ "loss": 1.6655,
1943
+ "step": 2740
1944
+ },
1945
+ {
1946
+ "epoch": 2.054538662682107,
1947
+ "grad_norm": 0.3973815143108368,
1948
+ "learning_rate": 0.0002,
1949
+ "loss": 1.6305,
1950
+ "step": 2750
1951
+ },
1952
+ {
1953
+ "epoch": 2.062009712364587,
1954
+ "grad_norm": 0.4521815776824951,
1955
+ "learning_rate": 0.0002,
1956
+ "loss": 1.6301,
1957
+ "step": 2760
1958
+ },
1959
+ {
1960
+ "epoch": 2.0694807620470677,
1961
+ "grad_norm": 0.42775002121925354,
1962
+ "learning_rate": 0.0002,
1963
+ "loss": 1.6189,
1964
+ "step": 2770
1965
+ },
1966
+ {
1967
+ "epoch": 2.076951811729548,
1968
+ "grad_norm": 0.48158586025238037,
1969
+ "learning_rate": 0.0002,
1970
+ "loss": 1.6491,
1971
+ "step": 2780
1972
+ },
1973
+ {
1974
+ "epoch": 2.0844228614120284,
1975
+ "grad_norm": 0.4612371623516083,
1976
+ "learning_rate": 0.0002,
1977
+ "loss": 1.6301,
1978
+ "step": 2790
1979
+ },
1980
+ {
1981
+ "epoch": 2.091893911094509,
1982
+ "grad_norm": 0.42536866664886475,
1983
+ "learning_rate": 0.0002,
1984
+ "loss": 1.6327,
1985
+ "step": 2800
1986
+ },
1987
+ {
1988
+ "epoch": 2.099364960776989,
1989
+ "grad_norm": 0.48515772819519043,
1990
+ "learning_rate": 0.0002,
1991
+ "loss": 1.651,
1992
+ "step": 2810
1993
+ },
1994
+ {
1995
+ "epoch": 2.1068360104594697,
1996
+ "grad_norm": 0.41418662667274475,
1997
+ "learning_rate": 0.0002,
1998
+ "loss": 1.6829,
1999
+ "step": 2820
2000
+ },
2001
+ {
2002
+ "epoch": 2.11430706014195,
2003
+ "grad_norm": 0.4683697819709778,
2004
+ "learning_rate": 0.0002,
2005
+ "loss": 1.6266,
2006
+ "step": 2830
2007
+ },
2008
+ {
2009
+ "epoch": 2.1217781098244304,
2010
+ "grad_norm": 0.4484657049179077,
2011
+ "learning_rate": 0.0002,
2012
+ "loss": 1.6586,
2013
+ "step": 2840
2014
+ },
2015
+ {
2016
+ "epoch": 2.1292491595069105,
2017
+ "grad_norm": 0.6621400713920593,
2018
+ "learning_rate": 0.0002,
2019
+ "loss": 1.6483,
2020
+ "step": 2850
2021
+ },
2022
+ {
2023
+ "epoch": 2.136720209189391,
2024
+ "grad_norm": 0.45074811577796936,
2025
+ "learning_rate": 0.0002,
2026
+ "loss": 1.5755,
2027
+ "step": 2860
2028
+ },
2029
+ {
2030
+ "epoch": 2.1441912588718717,
2031
+ "grad_norm": 0.3513113558292389,
2032
+ "learning_rate": 0.0002,
2033
+ "loss": 1.6456,
2034
+ "step": 2870
2035
+ },
2036
+ {
2037
+ "epoch": 2.151662308554352,
2038
+ "grad_norm": 0.40411314368247986,
2039
+ "learning_rate": 0.0002,
2040
+ "loss": 1.6081,
2041
+ "step": 2880
2042
+ },
2043
+ {
2044
+ "epoch": 2.1591333582368324,
2045
+ "grad_norm": 0.4121065139770508,
2046
+ "learning_rate": 0.0002,
2047
+ "loss": 1.6323,
2048
+ "step": 2890
2049
+ },
2050
+ {
2051
+ "epoch": 2.1666044079193125,
2052
+ "grad_norm": 0.44723689556121826,
2053
+ "learning_rate": 0.0002,
2054
+ "loss": 1.6324,
2055
+ "step": 2900
2056
+ },
2057
+ {
2058
+ "epoch": 2.174075457601793,
2059
+ "grad_norm": 0.4226122498512268,
2060
+ "learning_rate": 0.0002,
2061
+ "loss": 1.5699,
2062
+ "step": 2910
2063
+ },
2064
+ {
2065
+ "epoch": 2.1815465072842732,
2066
+ "grad_norm": 0.46617650985717773,
2067
+ "learning_rate": 0.0002,
2068
+ "loss": 1.5652,
2069
+ "step": 2920
2070
+ },
2071
+ {
2072
+ "epoch": 2.189017556966754,
2073
+ "grad_norm": 0.4506422281265259,
2074
+ "learning_rate": 0.0002,
2075
+ "loss": 1.6378,
2076
+ "step": 2930
2077
+ },
2078
+ {
2079
+ "epoch": 2.1964886066492344,
2080
+ "grad_norm": 0.4892672896385193,
2081
+ "learning_rate": 0.0002,
2082
+ "loss": 1.6112,
2083
+ "step": 2940
2084
+ },
2085
+ {
2086
+ "epoch": 2.2039596563317145,
2087
+ "grad_norm": 0.44095516204833984,
2088
+ "learning_rate": 0.0002,
2089
+ "loss": 1.6176,
2090
+ "step": 2950
2091
+ },
2092
+ {
2093
+ "epoch": 2.211430706014195,
2094
+ "grad_norm": 0.41522109508514404,
2095
+ "learning_rate": 0.0002,
2096
+ "loss": 1.6058,
2097
+ "step": 2960
2098
+ },
2099
+ {
2100
+ "epoch": 2.2189017556966752,
2101
+ "grad_norm": 0.4860858917236328,
2102
+ "learning_rate": 0.0002,
2103
+ "loss": 1.5964,
2104
+ "step": 2970
2105
+ },
2106
+ {
2107
+ "epoch": 2.226372805379156,
2108
+ "grad_norm": 0.42662516236305237,
2109
+ "learning_rate": 0.0002,
2110
+ "loss": 1.6427,
2111
+ "step": 2980
2112
+ },
2113
+ {
2114
+ "epoch": 2.233843855061636,
2115
+ "grad_norm": 0.4390648305416107,
2116
+ "learning_rate": 0.0002,
2117
+ "loss": 1.6313,
2118
+ "step": 2990
2119
+ },
2120
+ {
2121
+ "epoch": 2.2413149047441165,
2122
+ "grad_norm": 0.47515565156936646,
2123
+ "learning_rate": 0.0002,
2124
+ "loss": 1.5992,
2125
+ "step": 3000
2126
+ },
2127
+ {
2128
+ "epoch": 2.248785954426597,
2129
+ "grad_norm": 0.4104543924331665,
2130
+ "learning_rate": 0.0002,
2131
+ "loss": 1.5563,
2132
+ "step": 3010
2133
+ },
2134
+ {
2135
+ "epoch": 2.2562570041090773,
2136
+ "grad_norm": 0.4404028654098511,
2137
+ "learning_rate": 0.0002,
2138
+ "loss": 1.6895,
2139
+ "step": 3020
2140
+ },
2141
+ {
2142
+ "epoch": 2.263728053791558,
2143
+ "grad_norm": 0.4717366695404053,
2144
+ "learning_rate": 0.0002,
2145
+ "loss": 1.6088,
2146
+ "step": 3030
2147
+ },
2148
+ {
2149
+ "epoch": 2.271199103474038,
2150
+ "grad_norm": 0.48345857858657837,
2151
+ "learning_rate": 0.0002,
2152
+ "loss": 1.7287,
2153
+ "step": 3040
2154
+ },
2155
+ {
2156
+ "epoch": 2.2786701531565186,
2157
+ "grad_norm": 0.5312452912330627,
2158
+ "learning_rate": 0.0002,
2159
+ "loss": 1.681,
2160
+ "step": 3050
2161
+ },
2162
+ {
2163
+ "epoch": 2.2861412028389987,
2164
+ "grad_norm": 0.5073099732398987,
2165
+ "learning_rate": 0.0002,
2166
+ "loss": 1.5901,
2167
+ "step": 3060
2168
+ },
2169
+ {
2170
+ "epoch": 2.2936122525214793,
2171
+ "grad_norm": 0.5027463436126709,
2172
+ "learning_rate": 0.0002,
2173
+ "loss": 1.6914,
2174
+ "step": 3070
2175
+ },
2176
+ {
2177
+ "epoch": 2.30108330220396,
2178
+ "grad_norm": 0.5436304807662964,
2179
+ "learning_rate": 0.0002,
2180
+ "loss": 1.5862,
2181
+ "step": 3080
2182
+ },
2183
+ {
2184
+ "epoch": 2.30855435188644,
2185
+ "grad_norm": 0.4701065123081207,
2186
+ "learning_rate": 0.0002,
2187
+ "loss": 1.5763,
2188
+ "step": 3090
2189
+ },
2190
+ {
2191
+ "epoch": 2.3160254015689206,
2192
+ "grad_norm": 0.46988746523857117,
2193
+ "learning_rate": 0.0002,
2194
+ "loss": 1.6177,
2195
+ "step": 3100
2196
+ },
2197
+ {
2198
+ "epoch": 2.3234964512514007,
2199
+ "grad_norm": 0.45112869143486023,
2200
+ "learning_rate": 0.0002,
2201
+ "loss": 1.6502,
2202
+ "step": 3110
2203
+ },
2204
+ {
2205
+ "epoch": 2.3309675009338813,
2206
+ "grad_norm": 0.5173566937446594,
2207
+ "learning_rate": 0.0002,
2208
+ "loss": 1.6291,
2209
+ "step": 3120
2210
+ },
2211
+ {
2212
+ "epoch": 2.3384385506163614,
2213
+ "grad_norm": 0.40345850586891174,
2214
+ "learning_rate": 0.0002,
2215
+ "loss": 1.6743,
2216
+ "step": 3130
2217
+ },
2218
+ {
2219
+ "epoch": 2.345909600298842,
2220
+ "grad_norm": 0.4218924939632416,
2221
+ "learning_rate": 0.0002,
2222
+ "loss": 1.621,
2223
+ "step": 3140
2224
+ },
2225
+ {
2226
+ "epoch": 2.3533806499813226,
2227
+ "grad_norm": 0.41857317090034485,
2228
+ "learning_rate": 0.0002,
2229
+ "loss": 1.6341,
2230
+ "step": 3150
2231
+ },
2232
+ {
2233
+ "epoch": 2.3608516996638027,
2234
+ "grad_norm": 0.4197218418121338,
2235
+ "learning_rate": 0.0002,
2236
+ "loss": 1.6087,
2237
+ "step": 3160
2238
+ },
2239
+ {
2240
+ "epoch": 2.3683227493462833,
2241
+ "grad_norm": 0.4260677397251129,
2242
+ "learning_rate": 0.0002,
2243
+ "loss": 1.6572,
2244
+ "step": 3170
2245
+ },
2246
+ {
2247
+ "epoch": 2.3757937990287634,
2248
+ "grad_norm": 0.4209042191505432,
2249
+ "learning_rate": 0.0002,
2250
+ "loss": 1.6376,
2251
+ "step": 3180
2252
+ },
2253
+ {
2254
+ "epoch": 2.383264848711244,
2255
+ "grad_norm": 0.4092234969139099,
2256
+ "learning_rate": 0.0002,
2257
+ "loss": 1.634,
2258
+ "step": 3190
2259
+ },
2260
+ {
2261
+ "epoch": 2.390735898393724,
2262
+ "grad_norm": 0.4928431510925293,
2263
+ "learning_rate": 0.0002,
2264
+ "loss": 1.6339,
2265
+ "step": 3200
2266
+ },
2267
+ {
2268
+ "epoch": 2.3982069480762047,
2269
+ "grad_norm": 0.49252402782440186,
2270
+ "learning_rate": 0.0002,
2271
+ "loss": 1.6015,
2272
+ "step": 3210
2273
+ },
2274
+ {
2275
+ "epoch": 2.4056779977586853,
2276
+ "grad_norm": 0.4368397295475006,
2277
+ "learning_rate": 0.0002,
2278
+ "loss": 1.5773,
2279
+ "step": 3220
2280
+ },
2281
+ {
2282
+ "epoch": 2.4131490474411654,
2283
+ "grad_norm": 0.46122390031814575,
2284
+ "learning_rate": 0.0002,
2285
+ "loss": 1.6629,
2286
+ "step": 3230
2287
+ },
2288
+ {
2289
+ "epoch": 2.420620097123646,
2290
+ "grad_norm": 0.4272301197052002,
2291
+ "learning_rate": 0.0002,
2292
+ "loss": 1.6224,
2293
+ "step": 3240
2294
+ },
2295
+ {
2296
+ "epoch": 2.428091146806126,
2297
+ "grad_norm": 0.41480937600135803,
2298
+ "learning_rate": 0.0002,
2299
+ "loss": 1.5961,
2300
+ "step": 3250
2301
+ },
2302
+ {
2303
+ "epoch": 2.4355621964886067,
2304
+ "grad_norm": 0.48911941051483154,
2305
+ "learning_rate": 0.0002,
2306
+ "loss": 1.6281,
2307
+ "step": 3260
2308
+ },
2309
+ {
2310
+ "epoch": 2.443033246171087,
2311
+ "grad_norm": 0.4444098472595215,
2312
+ "learning_rate": 0.0002,
2313
+ "loss": 1.6846,
2314
+ "step": 3270
2315
+ },
2316
+ {
2317
+ "epoch": 2.4505042958535674,
2318
+ "grad_norm": 0.5111684799194336,
2319
+ "learning_rate": 0.0002,
2320
+ "loss": 1.6961,
2321
+ "step": 3280
2322
+ },
2323
+ {
2324
+ "epoch": 2.457975345536048,
2325
+ "grad_norm": 0.5058825016021729,
2326
+ "learning_rate": 0.0002,
2327
+ "loss": 1.6152,
2328
+ "step": 3290
2329
+ },
2330
+ {
2331
+ "epoch": 2.465446395218528,
2332
+ "grad_norm": 0.44173210859298706,
2333
+ "learning_rate": 0.0002,
2334
+ "loss": 1.625,
2335
+ "step": 3300
2336
+ },
2337
+ {
2338
+ "epoch": 2.4729174449010087,
2339
+ "grad_norm": 0.4659745991230011,
2340
+ "learning_rate": 0.0002,
2341
+ "loss": 1.6491,
2342
+ "step": 3310
2343
+ },
2344
+ {
2345
+ "epoch": 2.480388494583489,
2346
+ "grad_norm": 0.47237497568130493,
2347
+ "learning_rate": 0.0002,
2348
+ "loss": 1.6114,
2349
+ "step": 3320
2350
+ },
2351
+ {
2352
+ "epoch": 2.4878595442659694,
2353
+ "grad_norm": 0.47303131222724915,
2354
+ "learning_rate": 0.0002,
2355
+ "loss": 1.6193,
2356
+ "step": 3330
2357
+ },
2358
+ {
2359
+ "epoch": 2.4953305939484496,
2360
+ "grad_norm": 0.4522389769554138,
2361
+ "learning_rate": 0.0002,
2362
+ "loss": 1.7256,
2363
+ "step": 3340
2364
+ },
2365
+ {
2366
+ "epoch": 2.50280164363093,
2367
+ "grad_norm": 0.4467332363128662,
2368
+ "learning_rate": 0.0002,
2369
+ "loss": 1.6834,
2370
+ "step": 3350
2371
+ },
2372
+ {
2373
+ "epoch": 2.5102726933134107,
2374
+ "grad_norm": 0.4413762092590332,
2375
+ "learning_rate": 0.0002,
2376
+ "loss": 1.6108,
2377
+ "step": 3360
2378
+ },
2379
+ {
2380
+ "epoch": 2.517743742995891,
2381
+ "grad_norm": 0.495514452457428,
2382
+ "learning_rate": 0.0002,
2383
+ "loss": 1.537,
2384
+ "step": 3370
2385
+ },
2386
+ {
2387
+ "epoch": 2.5252147926783715,
2388
+ "grad_norm": 0.4429773986339569,
2389
+ "learning_rate": 0.0002,
2390
+ "loss": 1.5839,
2391
+ "step": 3380
2392
+ },
2393
+ {
2394
+ "epoch": 2.5326858423608516,
2395
+ "grad_norm": 0.4589079022407532,
2396
+ "learning_rate": 0.0002,
2397
+ "loss": 1.6522,
2398
+ "step": 3390
2399
+ },
2400
+ {
2401
+ "epoch": 2.540156892043332,
2402
+ "grad_norm": 0.4683997333049774,
2403
+ "learning_rate": 0.0002,
2404
+ "loss": 1.6529,
2405
+ "step": 3400
2406
+ },
2407
+ {
2408
+ "epoch": 2.5476279417258123,
2409
+ "grad_norm": 0.4651731252670288,
2410
+ "learning_rate": 0.0002,
2411
+ "loss": 1.6745,
2412
+ "step": 3410
2413
+ },
2414
+ {
2415
+ "epoch": 2.555098991408293,
2416
+ "grad_norm": 0.45818084478378296,
2417
+ "learning_rate": 0.0002,
2418
+ "loss": 1.5918,
2419
+ "step": 3420
2420
+ },
2421
+ {
2422
+ "epoch": 2.5625700410907735,
2423
+ "grad_norm": 0.45209529995918274,
2424
+ "learning_rate": 0.0002,
2425
+ "loss": 1.6326,
2426
+ "step": 3430
2427
+ },
2428
+ {
2429
+ "epoch": 2.5700410907732536,
2430
+ "grad_norm": 0.4344733655452728,
2431
+ "learning_rate": 0.0002,
2432
+ "loss": 1.5606,
2433
+ "step": 3440
2434
+ },
2435
+ {
2436
+ "epoch": 2.577512140455734,
2437
+ "grad_norm": 0.47435566782951355,
2438
+ "learning_rate": 0.0002,
2439
+ "loss": 1.6748,
2440
+ "step": 3450
2441
+ },
2442
+ {
2443
+ "epoch": 2.5849831901382143,
2444
+ "grad_norm": 0.43841999769210815,
2445
+ "learning_rate": 0.0002,
2446
+ "loss": 1.6237,
2447
+ "step": 3460
2448
+ },
2449
+ {
2450
+ "epoch": 2.592454239820695,
2451
+ "grad_norm": 0.4323869049549103,
2452
+ "learning_rate": 0.0002,
2453
+ "loss": 1.7207,
2454
+ "step": 3470
2455
+ },
2456
+ {
2457
+ "epoch": 2.599925289503175,
2458
+ "grad_norm": 0.44355881214141846,
2459
+ "learning_rate": 0.0002,
2460
+ "loss": 1.5494,
2461
+ "step": 3480
2462
+ },
2463
+ {
2464
+ "epoch": 2.6073963391856556,
2465
+ "grad_norm": 0.45847779512405396,
2466
+ "learning_rate": 0.0002,
2467
+ "loss": 1.665,
2468
+ "step": 3490
2469
+ },
2470
+ {
2471
+ "epoch": 2.614867388868136,
2472
+ "grad_norm": 0.4411061704158783,
2473
+ "learning_rate": 0.0002,
2474
+ "loss": 1.6006,
2475
+ "step": 3500
2476
+ },
2477
+ {
2478
+ "epoch": 2.6223384385506163,
2479
+ "grad_norm": 0.4446796178817749,
2480
+ "learning_rate": 0.0002,
2481
+ "loss": 1.5868,
2482
+ "step": 3510
2483
+ },
2484
+ {
2485
+ "epoch": 2.629809488233097,
2486
+ "grad_norm": 0.41969653964042664,
2487
+ "learning_rate": 0.0002,
2488
+ "loss": 1.5946,
2489
+ "step": 3520
2490
+ },
2491
+ {
2492
+ "epoch": 2.637280537915577,
2493
+ "grad_norm": 0.5263747572898865,
2494
+ "learning_rate": 0.0002,
2495
+ "loss": 1.6798,
2496
+ "step": 3530
2497
+ },
2498
+ {
2499
+ "epoch": 2.6447515875980576,
2500
+ "grad_norm": 0.47719451785087585,
2501
+ "learning_rate": 0.0002,
2502
+ "loss": 1.6309,
2503
+ "step": 3540
2504
+ },
2505
+ {
2506
+ "epoch": 2.6522226372805378,
2507
+ "grad_norm": 0.46574118733406067,
2508
+ "learning_rate": 0.0002,
2509
+ "loss": 1.7024,
2510
+ "step": 3550
2511
+ },
2512
+ {
2513
+ "epoch": 2.6596936869630183,
2514
+ "grad_norm": 0.46867135167121887,
2515
+ "learning_rate": 0.0002,
2516
+ "loss": 1.618,
2517
+ "step": 3560
2518
+ },
2519
+ {
2520
+ "epoch": 2.667164736645499,
2521
+ "grad_norm": 0.4441198706626892,
2522
+ "learning_rate": 0.0002,
2523
+ "loss": 1.5885,
2524
+ "step": 3570
2525
+ },
2526
+ {
2527
+ "epoch": 2.674635786327979,
2528
+ "grad_norm": 0.4871319830417633,
2529
+ "learning_rate": 0.0002,
2530
+ "loss": 1.6426,
2531
+ "step": 3580
2532
+ },
2533
+ {
2534
+ "epoch": 2.6821068360104596,
2535
+ "grad_norm": 0.43900373578071594,
2536
+ "learning_rate": 0.0002,
2537
+ "loss": 1.6575,
2538
+ "step": 3590
2539
+ },
2540
+ {
2541
+ "epoch": 2.6895778856929398,
2542
+ "grad_norm": 0.42509549856185913,
2543
+ "learning_rate": 0.0002,
2544
+ "loss": 1.6071,
2545
+ "step": 3600
2546
+ },
2547
+ {
2548
+ "epoch": 2.6970489353754203,
2549
+ "grad_norm": 0.4691086709499359,
2550
+ "learning_rate": 0.0002,
2551
+ "loss": 1.5651,
2552
+ "step": 3610
2553
+ },
2554
+ {
2555
+ "epoch": 2.7045199850579005,
2556
+ "grad_norm": 0.46318942308425903,
2557
+ "learning_rate": 0.0002,
2558
+ "loss": 1.5491,
2559
+ "step": 3620
2560
+ },
2561
+ {
2562
+ "epoch": 2.711991034740381,
2563
+ "grad_norm": 0.44631096720695496,
2564
+ "learning_rate": 0.0002,
2565
+ "loss": 1.5422,
2566
+ "step": 3630
2567
+ },
2568
+ {
2569
+ "epoch": 2.7194620844228616,
2570
+ "grad_norm": 0.42315489053726196,
2571
+ "learning_rate": 0.0002,
2572
+ "loss": 1.6831,
2573
+ "step": 3640
2574
+ },
2575
+ {
2576
+ "epoch": 2.7269331341053418,
2577
+ "grad_norm": 0.4971241056919098,
2578
+ "learning_rate": 0.0002,
2579
+ "loss": 1.6008,
2580
+ "step": 3650
2581
+ },
2582
+ {
2583
+ "epoch": 2.7344041837878224,
2584
+ "grad_norm": 0.4578486382961273,
2585
+ "learning_rate": 0.0002,
2586
+ "loss": 1.6042,
2587
+ "step": 3660
2588
+ },
2589
+ {
2590
+ "epoch": 2.7418752334703025,
2591
+ "grad_norm": 0.46584776043891907,
2592
+ "learning_rate": 0.0002,
2593
+ "loss": 1.6076,
2594
+ "step": 3670
2595
+ },
2596
+ {
2597
+ "epoch": 2.749346283152783,
2598
+ "grad_norm": 0.4951731264591217,
2599
+ "learning_rate": 0.0002,
2600
+ "loss": 1.6809,
2601
+ "step": 3680
2602
+ },
2603
+ {
2604
+ "epoch": 2.756817332835263,
2605
+ "grad_norm": 0.4935225546360016,
2606
+ "learning_rate": 0.0002,
2607
+ "loss": 1.6226,
2608
+ "step": 3690
2609
+ },
2610
+ {
2611
+ "epoch": 2.764288382517744,
2612
+ "grad_norm": 0.41805586218833923,
2613
+ "learning_rate": 0.0002,
2614
+ "loss": 1.5878,
2615
+ "step": 3700
2616
+ },
2617
+ {
2618
+ "epoch": 2.7717594322002244,
2619
+ "grad_norm": 0.4417555630207062,
2620
+ "learning_rate": 0.0002,
2621
+ "loss": 1.7173,
2622
+ "step": 3710
2623
+ },
2624
+ {
2625
+ "epoch": 2.7792304818827045,
2626
+ "grad_norm": 0.48229655623435974,
2627
+ "learning_rate": 0.0002,
2628
+ "loss": 1.6398,
2629
+ "step": 3720
2630
+ },
2631
+ {
2632
+ "epoch": 2.786701531565185,
2633
+ "grad_norm": 0.48562315106391907,
2634
+ "learning_rate": 0.0002,
2635
+ "loss": 1.6074,
2636
+ "step": 3730
2637
+ },
2638
+ {
2639
+ "epoch": 2.794172581247665,
2640
+ "grad_norm": 0.4473940432071686,
2641
+ "learning_rate": 0.0002,
2642
+ "loss": 1.607,
2643
+ "step": 3740
2644
+ },
2645
+ {
2646
+ "epoch": 2.801643630930146,
2647
+ "grad_norm": 0.4626813232898712,
2648
+ "learning_rate": 0.0002,
2649
+ "loss": 1.6065,
2650
+ "step": 3750
2651
+ },
2652
+ {
2653
+ "epoch": 2.809114680612626,
2654
+ "grad_norm": 0.4339792728424072,
2655
+ "learning_rate": 0.0002,
2656
+ "loss": 1.6296,
2657
+ "step": 3760
2658
+ },
2659
+ {
2660
+ "epoch": 2.8165857302951065,
2661
+ "grad_norm": 0.5250858068466187,
2662
+ "learning_rate": 0.0002,
2663
+ "loss": 1.6815,
2664
+ "step": 3770
2665
+ },
2666
+ {
2667
+ "epoch": 2.824056779977587,
2668
+ "grad_norm": 0.4537523090839386,
2669
+ "learning_rate": 0.0002,
2670
+ "loss": 1.6644,
2671
+ "step": 3780
2672
+ },
2673
+ {
2674
+ "epoch": 2.831527829660067,
2675
+ "grad_norm": 0.5646113157272339,
2676
+ "learning_rate": 0.0002,
2677
+ "loss": 1.6535,
2678
+ "step": 3790
2679
+ },
2680
+ {
2681
+ "epoch": 2.8389988793425474,
2682
+ "grad_norm": 0.44243332743644714,
2683
+ "learning_rate": 0.0002,
2684
+ "loss": 1.5712,
2685
+ "step": 3800
2686
+ },
2687
+ {
2688
+ "epoch": 2.846469929025028,
2689
+ "grad_norm": 0.4585791826248169,
2690
+ "learning_rate": 0.0002,
2691
+ "loss": 1.6478,
2692
+ "step": 3810
2693
+ },
2694
+ {
2695
+ "epoch": 2.8539409787075085,
2696
+ "grad_norm": 0.489702045917511,
2697
+ "learning_rate": 0.0002,
2698
+ "loss": 1.6854,
2699
+ "step": 3820
2700
+ },
2701
+ {
2702
+ "epoch": 2.8614120283899886,
2703
+ "grad_norm": 0.502470850944519,
2704
+ "learning_rate": 0.0002,
2705
+ "loss": 1.7066,
2706
+ "step": 3830
2707
+ },
2708
+ {
2709
+ "epoch": 2.8688830780724692,
2710
+ "grad_norm": 0.4395960867404938,
2711
+ "learning_rate": 0.0002,
2712
+ "loss": 1.5785,
2713
+ "step": 3840
2714
+ },
2715
+ {
2716
+ "epoch": 2.87635412775495,
2717
+ "grad_norm": 0.4348670244216919,
2718
+ "learning_rate": 0.0002,
2719
+ "loss": 1.6434,
2720
+ "step": 3850
2721
+ },
2722
+ {
2723
+ "epoch": 2.88382517743743,
2724
+ "grad_norm": 0.48852720856666565,
2725
+ "learning_rate": 0.0002,
2726
+ "loss": 1.6163,
2727
+ "step": 3860
2728
+ },
2729
+ {
2730
+ "epoch": 2.89129622711991,
2731
+ "grad_norm": 0.45317450165748596,
2732
+ "learning_rate": 0.0002,
2733
+ "loss": 1.5916,
2734
+ "step": 3870
2735
+ },
2736
+ {
2737
+ "epoch": 2.8987672768023907,
2738
+ "grad_norm": 0.4732758700847626,
2739
+ "learning_rate": 0.0002,
2740
+ "loss": 1.6486,
2741
+ "step": 3880
2742
+ },
2743
+ {
2744
+ "epoch": 2.9062383264848712,
2745
+ "grad_norm": 0.45238012075424194,
2746
+ "learning_rate": 0.0002,
2747
+ "loss": 1.6758,
2748
+ "step": 3890
2749
+ },
2750
+ {
2751
+ "epoch": 2.9137093761673514,
2752
+ "grad_norm": 0.48838064074516296,
2753
+ "learning_rate": 0.0002,
2754
+ "loss": 1.6228,
2755
+ "step": 3900
2756
+ },
2757
+ {
2758
+ "epoch": 2.921180425849832,
2759
+ "grad_norm": 0.43496349453926086,
2760
+ "learning_rate": 0.0002,
2761
+ "loss": 1.658,
2762
+ "step": 3910
2763
+ },
2764
+ {
2765
+ "epoch": 2.9286514755323125,
2766
+ "grad_norm": 0.47963935136795044,
2767
+ "learning_rate": 0.0002,
2768
+ "loss": 1.7063,
2769
+ "step": 3920
2770
+ },
2771
+ {
2772
+ "epoch": 2.9361225252147927,
2773
+ "grad_norm": 0.4544987976551056,
2774
+ "learning_rate": 0.0002,
2775
+ "loss": 1.6553,
2776
+ "step": 3930
2777
+ },
2778
+ {
2779
+ "epoch": 2.943593574897273,
2780
+ "grad_norm": 0.4622892141342163,
2781
+ "learning_rate": 0.0002,
2782
+ "loss": 1.6192,
2783
+ "step": 3940
2784
+ },
2785
+ {
2786
+ "epoch": 2.9510646245797534,
2787
+ "grad_norm": 0.47026222944259644,
2788
+ "learning_rate": 0.0002,
2789
+ "loss": 1.6178,
2790
+ "step": 3950
2791
+ },
2792
+ {
2793
+ "epoch": 2.958535674262234,
2794
+ "grad_norm": 0.4549552798271179,
2795
+ "learning_rate": 0.0002,
2796
+ "loss": 1.6612,
2797
+ "step": 3960
2798
+ },
2799
+ {
2800
+ "epoch": 2.966006723944714,
2801
+ "grad_norm": 0.46647515892982483,
2802
+ "learning_rate": 0.0002,
2803
+ "loss": 1.6458,
2804
+ "step": 3970
2805
+ },
2806
+ {
2807
+ "epoch": 2.9734777736271947,
2808
+ "grad_norm": 0.45095112919807434,
2809
+ "learning_rate": 0.0002,
2810
+ "loss": 1.6051,
2811
+ "step": 3980
2812
+ },
2813
+ {
2814
+ "epoch": 2.9809488233096753,
2815
+ "grad_norm": 0.4690017104148865,
2816
+ "learning_rate": 0.0002,
2817
+ "loss": 1.6471,
2818
+ "step": 3990
2819
+ },
2820
+ {
2821
+ "epoch": 2.9884198729921554,
2822
+ "grad_norm": 0.4603444039821625,
2823
+ "learning_rate": 0.0002,
2824
+ "loss": 1.6061,
2825
+ "step": 4000
2826
+ },
2827
+ {
2828
+ "epoch": 2.9958909226746355,
2829
+ "grad_norm": 0.4743294417858124,
2830
+ "learning_rate": 0.0002,
2831
+ "loss": 1.6431,
2832
+ "step": 4010
2833
+ },
2834
+ {
2835
+ "epoch": 2.999626447515876,
2836
+ "eval_loss": 1.8252571821212769,
2837
+ "eval_runtime": 38.7853,
2838
+ "eval_samples_per_second": 13.278,
2839
+ "eval_steps_per_second": 1.676,
2840
+ "step": 4015
2841
+ }
2842
+ ],
2843
+ "logging_steps": 10,
2844
+ "max_steps": 10704,
2845
+ "num_input_tokens_seen": 0,
2846
+ "num_train_epochs": 8,
2847
+ "save_steps": 200,
2848
+ "stateful_callbacks": {
2849
+ "TrainerControl": {
2850
+ "args": {
2851
+ "should_epoch_stop": false,
2852
+ "should_evaluate": false,
2853
+ "should_log": false,
2854
+ "should_save": true,
2855
+ "should_training_stop": false
2856
+ },
2857
+ "attributes": {}
2858
+ }
2859
+ },
2860
+ "total_flos": 1.8582834893134234e+17,
2861
+ "train_batch_size": 1,
2862
+ "trial_name": null,
2863
+ "trial_params": null
2864
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-4015/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fc87da605e94ff0ecd8f5b371302a2d5f8727b77984707a2185ddb447fc3796
3
+ size 5560
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-5354/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_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.9-num-6326-sd-42/checkpoint-5354/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
+ }