saxon commited on
Commit
9a41c71
·
verified ·
1 Parent(s): 08064a6

Upload folder using huggingface_hub

Browse files
Files changed (49) hide show
  1. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/config.json +54 -0
  2. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/generation_config.json +9 -0
  3. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  4. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  5. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  6. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  7. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
  8. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
  9. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
  10. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
  11. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  12. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  13. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  14. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  15. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/zero_pp_rank_4_mp_rank_00_model_states.pt +3 -0
  16. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/zero_pp_rank_5_mp_rank_00_model_states.pt +3 -0
  17. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/zero_pp_rank_6_mp_rank_00_model_states.pt +3 -0
  18. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/zero_pp_rank_7_mp_rank_00_model_states.pt +3 -0
  19. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/latest +1 -0
  20. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/model-00001-of-00003.safetensors +3 -0
  21. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/model-00002-of-00003.safetensors +3 -0
  22. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/model-00003-of-00003.safetensors +3 -0
  23. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/model.safetensors.index.json +727 -0
  24. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/rng_state_0.pth +3 -0
  25. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/rng_state_1.pth +3 -0
  26. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/rng_state_2.pth +3 -0
  27. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/rng_state_3.pth +3 -0
  28. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/rng_state_4.pth +3 -0
  29. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/rng_state_5.pth +3 -0
  30. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/rng_state_6.pth +3 -0
  31. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/rng_state_7.pth +3 -0
  32. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/scheduler.pt +3 -0
  33. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/special_tokens_map.json +24 -0
  34. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/tokenizer.model +3 -0
  35. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/tokenizer_config.json +43 -0
  36. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/trainer_state.json +1458 -0
  37. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/training_args.bin +3 -0
  38. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/zero_to_fp32.py +604 -0
  39. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/config.json +54 -0
  40. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/generation_config.json +9 -0
  41. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/model-00001-of-00003.safetensors +3 -0
  42. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/model-00002-of-00003.safetensors +3 -0
  43. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/model-00003-of-00003.safetensors +3 -0
  44. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/model.safetensors.index.json +727 -0
  45. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/special_tokens_map.json +24 -0
  46. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/tokenizer.model +3 -0
  47. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/tokenizer_config.json +43 -0
  48. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/trainer_state.json +1467 -0
  49. saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/training_args.bin +3 -0
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/dockerx/Local/checkpoints/TEST-multillavafinal-vicuna-siglip-PT.l0.d0.a0-S15.l1e-5.d0.a0",
3
+ "architectures": [
4
+ "MultiLlavaLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "image_aspect_ratio": "square",
13
+ "image_crop_resolution": null,
14
+ "image_grid_pinpoints": null,
15
+ "image_split_resolution": null,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 11008,
18
+ "max_position_embeddings": 4096,
19
+ "mlp_bias": false,
20
+ "mm_hidden_size": 1152,
21
+ "mm_newline_position": "one_token",
22
+ "mm_patch_merge_type": "flat",
23
+ "mm_projector_lr": null,
24
+ "mm_projector_type": "mlp2x_gelu",
25
+ "mm_resampler_type": null,
26
+ "mm_spatial_pool_mode": "bilinear",
27
+ "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
28
+ "mm_use_im_patch_token": false,
29
+ "mm_use_im_start_end": false,
30
+ "mm_vision_select_feature": "patch",
31
+ "mm_vision_select_layer": -2,
32
+ "mm_vision_tower": "google/siglip-so400m-patch14-384",
33
+ "mm_vision_tower_lr": 2e-06,
34
+ "model_type": "llama",
35
+ "num_attention_heads": 32,
36
+ "num_hidden_layers": 32,
37
+ "num_key_value_heads": 32,
38
+ "pad_token_id": 0,
39
+ "pos_skipping_range": 4096,
40
+ "pretraining_tp": 1,
41
+ "rms_norm_eps": 1e-05,
42
+ "rope_scaling": null,
43
+ "rope_theta": 10000.0,
44
+ "tie_word_embeddings": false,
45
+ "tokenizer_model_max_length": 32768,
46
+ "tokenizer_padding_side": "right",
47
+ "torch_dtype": "bfloat16",
48
+ "transformers_version": "4.44.2",
49
+ "use_cache": false,
50
+ "use_mm_proj": true,
51
+ "use_pos_skipping": false,
52
+ "vision_tower_pretrained": null,
53
+ "vocab_size": 32000
54
+ }
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 4096,
5
+ "pad_token_id": 0,
6
+ "temperature": 0.9,
7
+ "top_p": 0.6,
8
+ "transformers_version": "4.44.2"
9
+ }
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed00e5a36a9156377ba8ec7f285df74e8a905480e2e980b7b51b0ee193a2dbce
3
+ size 10786852954
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:665c190899a3ae708dac3cb852f96d22b57c24e97e45e390aff828f1eb3f4cd9
3
+ size 10786852954
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ca6b69171a8064124f4c4fb819f4f58e85635ee272e1a5a548f6102b8e52087
3
+ size 10786852954
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d068fb93e695f806e12ca33eb470b80677da8c112736b56ab6bd93e52e21cdff
3
+ size 10786852954
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37427c9cea7c9eefa18bd95389f2258a715eea0b058c85185e122e9f9931153b
3
+ size 10786852954
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02e56759fdff2900253262de4cc86d764334c464055dd75b267367ff38448fb4
3
+ size 10786852954
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ec0cdede595a271526b6f44ad35e5392c63585e35b8053dcffc59d1ccc61c37
3
+ size 10786852954
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ad168103a905341ff07c1f911716065aa33df0ed2e5f00949368611c0179c81
3
+ size 10786852954
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/zero_pp_rank_0_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f75829352bb0c13f971c4976c9cd608e67a70503e377f0cef6f5d95f914c169
3
+ size 403582
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/zero_pp_rank_1_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2edc69280c55b5e397664c87389c1cac1081e46fdc840548e8b1f43c5fa3eeb
3
+ size 403582
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/zero_pp_rank_2_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dae64b3a75494f62a5ee433d91c74a20d547935a3afc1dfeefefa832e97237c0
3
+ size 403582
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/zero_pp_rank_3_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42346b357f2a29267ca5d9f83cb35bafbfbf41c894b484f765d11eeda1992cf5
3
+ size 403582
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/zero_pp_rank_4_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffea6b490503e6fe5ec3cddeb8109c1c20df9b32be7226406d88c6b83204bf61
3
+ size 403582
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/zero_pp_rank_5_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:656a2ba6e2d5294d9a54f8c600f4a51bb91b531fda9e8bc1908602352e2fc262
3
+ size 403582
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/zero_pp_rank_6_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:969b27431851ed2f474bbc35ae6bd66c6e7193d9dfc26ba3963cb0b238e59331
3
+ size 403582
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/global_step25/zero_pp_rank_7_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e03234229c876cab566fd096ff268747eaa43cd9bf75e16a2cc58938571ca92
3
+ size 403582
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step25
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:075d8482f80d86bc9cba01cba4ebc5a042607478b2d1c5bf49d77b213fd08ce6
3
+ size 4938985352
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2de768923996d6defacb56b3d87708049d611377f1e2779ea945e0ceafc05414
3
+ size 4947390880
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24cc5abfdef95d2cdcc6c8ef2de2974777b360a95e9c420d292f8cb2a294189e
3
+ size 4496184560
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/model.safetensors.index.json ADDED
@@ -0,0 +1,727 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14382459968
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.mm_output_projector.0.bias": "model-00003-of-00003.safetensors",
297
+ "model.mm_output_projector.0.weight": "model-00003-of-00003.safetensors",
298
+ "model.mm_output_projector.2.bias": "model-00003-of-00003.safetensors",
299
+ "model.mm_output_projector.2.weight": "model-00003-of-00003.safetensors",
300
+ "model.mm_projector.0.bias": "model-00003-of-00003.safetensors",
301
+ "model.mm_projector.0.weight": "model-00003-of-00003.safetensors",
302
+ "model.mm_projector.2.bias": "model-00003-of-00003.safetensors",
303
+ "model.mm_projector.2.weight": "model-00003-of-00003.safetensors",
304
+ "model.norm.weight": "model-00003-of-00003.safetensors",
305
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00003-of-00003.safetensors",
306
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00003.safetensors",
307
+ "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00003.safetensors",
308
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00003.safetensors",
309
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00003.safetensors",
310
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00003.safetensors",
311
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00003.safetensors",
312
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00003.safetensors",
313
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00003.safetensors",
314
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00003.safetensors",
315
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00003.safetensors",
316
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
317
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
318
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
319
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
320
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
321
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
322
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
323
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
324
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00003.safetensors",
325
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00003.safetensors",
326
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00003.safetensors",
327
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00003.safetensors",
328
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00003.safetensors",
329
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00003.safetensors",
330
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00003.safetensors",
331
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00003.safetensors",
332
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
333
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
334
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
335
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
336
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
337
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
338
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
339
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
340
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00003.safetensors",
341
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00003.safetensors",
342
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00003.safetensors",
343
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00003.safetensors",
344
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00003.safetensors",
345
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00003.safetensors",
346
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00003.safetensors",
347
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00003.safetensors",
348
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
349
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
350
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
351
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
352
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
353
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
354
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
355
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
356
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00003.safetensors",
357
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00003.safetensors",
358
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00003.safetensors",
359
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00003.safetensors",
360
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00003.safetensors",
361
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00003.safetensors",
362
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00003.safetensors",
363
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00003.safetensors",
364
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
365
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
366
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
367
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
368
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
369
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
370
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
371
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
372
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00003.safetensors",
373
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00003.safetensors",
374
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00003.safetensors",
375
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00003.safetensors",
376
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00003.safetensors",
377
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00003.safetensors",
378
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00003.safetensors",
379
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00003.safetensors",
380
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
381
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
382
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
383
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
384
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
385
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
386
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
387
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
388
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00003.safetensors",
389
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00003.safetensors",
390
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00003.safetensors",
391
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00003.safetensors",
392
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00003.safetensors",
393
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00003.safetensors",
394
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00003.safetensors",
395
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00003.safetensors",
396
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
397
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
398
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
399
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
400
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
401
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
402
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
403
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
404
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00003.safetensors",
405
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00003.safetensors",
406
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00003.safetensors",
407
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00003.safetensors",
408
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00003.safetensors",
409
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00003.safetensors",
410
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00003.safetensors",
411
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00003.safetensors",
412
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
413
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
414
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
415
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
416
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
417
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
418
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
419
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
420
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00003.safetensors",
421
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00003.safetensors",
422
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00003.safetensors",
423
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00003.safetensors",
424
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00003.safetensors",
425
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00003.safetensors",
426
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00003.safetensors",
427
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00003.safetensors",
428
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
429
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
430
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
431
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
432
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
433
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
434
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
435
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
436
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00003.safetensors",
437
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00003.safetensors",
438
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00003.safetensors",
439
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00003.safetensors",
440
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00003.safetensors",
441
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00003.safetensors",
442
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00003.safetensors",
443
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00003.safetensors",
444
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
445
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
446
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
447
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
448
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
449
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
450
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
451
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
452
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00003.safetensors",
453
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00003.safetensors",
454
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00003.safetensors",
455
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00003.safetensors",
456
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00003.safetensors",
457
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00003.safetensors",
458
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00003.safetensors",
459
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00003.safetensors",
460
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
461
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
462
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
463
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
464
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
465
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
466
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
467
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
468
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00003.safetensors",
469
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00003.safetensors",
470
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00003.safetensors",
471
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00003.safetensors",
472
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00003.safetensors",
473
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00003.safetensors",
474
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00003.safetensors",
475
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00003.safetensors",
476
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
477
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
478
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
479
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
480
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
481
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
482
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
483
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
484
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00003.safetensors",
485
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00003.safetensors",
486
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00003.safetensors",
487
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00003.safetensors",
488
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00003.safetensors",
489
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00003.safetensors",
490
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00003.safetensors",
491
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00003.safetensors",
492
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
493
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
494
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
495
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
496
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
497
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
498
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
499
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
500
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00003.safetensors",
501
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00003.safetensors",
502
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00003.safetensors",
503
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00003.safetensors",
504
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00003.safetensors",
505
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00003.safetensors",
506
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00003.safetensors",
507
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00003.safetensors",
508
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
509
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
510
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
511
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
512
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
513
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
514
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
515
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
516
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00003.safetensors",
517
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00003.safetensors",
518
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00003.safetensors",
519
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00003.safetensors",
520
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00003.safetensors",
521
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00003.safetensors",
522
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00003.safetensors",
523
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00003.safetensors",
524
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
525
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
526
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
527
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
528
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
529
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
530
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
531
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
532
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00003.safetensors",
533
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00003.safetensors",
534
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00003-of-00003.safetensors",
535
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00003-of-00003.safetensors",
536
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00003.safetensors",
537
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00003.safetensors",
538
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00003-of-00003.safetensors",
539
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00003-of-00003.safetensors",
540
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
541
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
542
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
543
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
544
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
545
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
546
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
547
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
548
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00003-of-00003.safetensors",
549
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00003-of-00003.safetensors",
550
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00003-of-00003.safetensors",
551
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00003-of-00003.safetensors",
552
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00003-of-00003.safetensors",
553
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00003-of-00003.safetensors",
554
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00003-of-00003.safetensors",
555
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00003-of-00003.safetensors",
556
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
557
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
558
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
559
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
560
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
561
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
562
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
563
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
564
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00003-of-00003.safetensors",
565
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00003-of-00003.safetensors",
566
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00003-of-00003.safetensors",
567
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00003-of-00003.safetensors",
568
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00003-of-00003.safetensors",
569
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00003-of-00003.safetensors",
570
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00003-of-00003.safetensors",
571
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00003-of-00003.safetensors",
572
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
573
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
574
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
575
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
576
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
577
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
578
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
579
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
580
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00003-of-00003.safetensors",
581
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00003-of-00003.safetensors",
582
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00003-of-00003.safetensors",
583
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00003-of-00003.safetensors",
584
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00003-of-00003.safetensors",
585
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00003-of-00003.safetensors",
586
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00003-of-00003.safetensors",
587
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00003-of-00003.safetensors",
588
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
589
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
590
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
591
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
592
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
593
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
594
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
595
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
596
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00003-of-00003.safetensors",
597
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00003-of-00003.safetensors",
598
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00003-of-00003.safetensors",
599
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00003-of-00003.safetensors",
600
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00003-of-00003.safetensors",
601
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00003-of-00003.safetensors",
602
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00003-of-00003.safetensors",
603
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00003-of-00003.safetensors",
604
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
605
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
606
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
607
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
608
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
609
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
610
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
611
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
612
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00003.safetensors",
613
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00003.safetensors",
614
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00003.safetensors",
615
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00003.safetensors",
616
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00003.safetensors",
617
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00003.safetensors",
618
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00003.safetensors",
619
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00003.safetensors",
620
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
621
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
622
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
623
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
624
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
625
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
626
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
627
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
628
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00003.safetensors",
629
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00003.safetensors",
630
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00003.safetensors",
631
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00003.safetensors",
632
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00003.safetensors",
633
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00003.safetensors",
634
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00003.safetensors",
635
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00003.safetensors",
636
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
637
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
638
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
639
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
640
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
641
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
642
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
643
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
644
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00003.safetensors",
645
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00003.safetensors",
646
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00003.safetensors",
647
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00003.safetensors",
648
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00003.safetensors",
649
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00003.safetensors",
650
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00003.safetensors",
651
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00003.safetensors",
652
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
653
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
654
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
655
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
656
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
657
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
658
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
659
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
660
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00003.safetensors",
661
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00003.safetensors",
662
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00003.safetensors",
663
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00003.safetensors",
664
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00003.safetensors",
665
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00003.safetensors",
666
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00003.safetensors",
667
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00003.safetensors",
668
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
669
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
670
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
671
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
672
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
673
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
674
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
675
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
676
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00003.safetensors",
677
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00003.safetensors",
678
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00003.safetensors",
679
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00003.safetensors",
680
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00003.safetensors",
681
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00003.safetensors",
682
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00003.safetensors",
683
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00003.safetensors",
684
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
685
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
686
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
687
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
688
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
689
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
690
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
691
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
692
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00003.safetensors",
693
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00003.safetensors",
694
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00003.safetensors",
695
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00003.safetensors",
696
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00003.safetensors",
697
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00003.safetensors",
698
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00003.safetensors",
699
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00003.safetensors",
700
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
701
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
702
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
703
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
704
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
705
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
706
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
707
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
708
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00003.safetensors",
709
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00003.safetensors",
710
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00003.safetensors",
711
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00003.safetensors",
712
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00003.safetensors",
713
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00003.safetensors",
714
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00003.safetensors",
715
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00003.safetensors",
716
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
717
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
718
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
719
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
720
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
721
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
722
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
723
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
724
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00003-of-00003.safetensors",
725
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00003-of-00003.safetensors"
726
+ }
727
+ }
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8e5019c4b65b1916f7eb0565683f71336cde85bbb39e771ee2fc26cb5c1b6a1
3
+ size 15984
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8da0e36dd376071685915de7ce62eb1a1d7423e5addd07de0b21e9ec3a08d619
3
+ size 15984
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac372d8d1a6c4f2b0421593980d61461c955dc2490ce276ad0777088f2b5419
3
+ size 15984
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c26fd9b911d613e9ea7803c2c0688dea369bba644b58d074936fdc5f6f1bf5bb
3
+ size 15984
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:954666a021ff2b1465016a33464ddf2a199df162d970a19867c9d935de771a91
3
+ size 15984
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10c01b1054eff65b6328f70d74c046ae7eb3f4c0f5f0775907f3ee0cb38354a6
3
+ size 15984
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b743abbae58133a0161ea3ffaa0176502b7e4d1eafdfa04444ff0786b1f97d07
3
+ size 15984
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5be0ba3a70138d720d58261ce9eddc554e19831407876fd1eddd582b265975ac
3
+ size 15984
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dfab20a5b5ae5b4d679de41db16bdbbbb0a8814bfec938494a3da30e5fe3fa7
3
+ size 1064
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 32768,
36
+ "pad_token": "<unk>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/trainer_state.json ADDED
@@ -0,0 +1,1458 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.0018037518037518038,
5
+ "eval_steps": 500,
6
+ "global_step": 25,
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,
13
+ "lm_loss": 1.2614614963531494,
14
+ "step": 0
15
+ },
16
+ {
17
+ "epoch": 0,
18
+ "img_loss": 885.3898315429688,
19
+ "step": 0
20
+ },
21
+ {
22
+ "epoch": 0,
23
+ "img_emb_dist": 0.9766795039176941,
24
+ "step": 0
25
+ },
26
+ {
27
+ "epoch": 0,
28
+ "img_divergence_loss": 0.0,
29
+ "step": 0
30
+ },
31
+ {
32
+ "activation_proximity_loss": 0.0,
33
+ "epoch": 0,
34
+ "step": 0
35
+ },
36
+ {
37
+ "epoch": 0,
38
+ "lm_loss": 2.016381025314331,
39
+ "step": 0
40
+ },
41
+ {
42
+ "epoch": 0,
43
+ "img_loss": 773.3865966796875,
44
+ "step": 0
45
+ },
46
+ {
47
+ "epoch": 0,
48
+ "img_emb_dist": 0.9774059057235718,
49
+ "step": 0
50
+ },
51
+ {
52
+ "epoch": 0,
53
+ "img_divergence_loss": 0.0,
54
+ "step": 0
55
+ },
56
+ {
57
+ "activation_proximity_loss": 0.0,
58
+ "epoch": 0,
59
+ "step": 0
60
+ },
61
+ {
62
+ "epoch": 7.215007215007215e-05,
63
+ "grad_norm": 4.514740996315013,
64
+ "learning_rate": 1e-05,
65
+ "loss": 1.355,
66
+ "step": 1
67
+ },
68
+ {
69
+ "epoch": 7.215007215007215e-05,
70
+ "lm_loss": 0.9086955189704895,
71
+ "step": 1
72
+ },
73
+ {
74
+ "epoch": 7.215007215007215e-05,
75
+ "img_loss": 819.3310546875,
76
+ "step": 1
77
+ },
78
+ {
79
+ "epoch": 7.215007215007215e-05,
80
+ "img_emb_dist": 0.9758827686309814,
81
+ "step": 1
82
+ },
83
+ {
84
+ "epoch": 7.215007215007215e-05,
85
+ "img_divergence_loss": 0.0,
86
+ "step": 1
87
+ },
88
+ {
89
+ "activation_proximity_loss": 0.0,
90
+ "epoch": 7.215007215007215e-05,
91
+ "step": 1
92
+ },
93
+ {
94
+ "epoch": 7.215007215007215e-05,
95
+ "lm_loss": 1.5197337865829468,
96
+ "step": 1
97
+ },
98
+ {
99
+ "epoch": 7.215007215007215e-05,
100
+ "img_loss": 791.0303955078125,
101
+ "step": 1
102
+ },
103
+ {
104
+ "epoch": 7.215007215007215e-05,
105
+ "img_emb_dist": 0.977044403553009,
106
+ "step": 1
107
+ },
108
+ {
109
+ "epoch": 7.215007215007215e-05,
110
+ "img_divergence_loss": 0.0,
111
+ "step": 1
112
+ },
113
+ {
114
+ "activation_proximity_loss": 0.0,
115
+ "epoch": 7.215007215007215e-05,
116
+ "step": 1
117
+ },
118
+ {
119
+ "epoch": 0.0001443001443001443,
120
+ "grad_norm": 5.1505158383620095,
121
+ "learning_rate": 9.957224306869053e-06,
122
+ "loss": 1.3439,
123
+ "step": 2
124
+ },
125
+ {
126
+ "epoch": 0.0001443001443001443,
127
+ "lm_loss": 1.1374003887176514,
128
+ "step": 2
129
+ },
130
+ {
131
+ "epoch": 0.0001443001443001443,
132
+ "img_loss": 765.0819702148438,
133
+ "step": 2
134
+ },
135
+ {
136
+ "epoch": 0.0001443001443001443,
137
+ "img_emb_dist": 0.974839985370636,
138
+ "step": 2
139
+ },
140
+ {
141
+ "epoch": 0.0001443001443001443,
142
+ "img_divergence_loss": 0.0,
143
+ "step": 2
144
+ },
145
+ {
146
+ "activation_proximity_loss": 0.0,
147
+ "epoch": 0.0001443001443001443,
148
+ "step": 2
149
+ },
150
+ {
151
+ "epoch": 0.0001443001443001443,
152
+ "lm_loss": 1.4494811296463013,
153
+ "step": 2
154
+ },
155
+ {
156
+ "epoch": 0.0001443001443001443,
157
+ "img_loss": 896.2612915039062,
158
+ "step": 2
159
+ },
160
+ {
161
+ "epoch": 0.0001443001443001443,
162
+ "img_emb_dist": 0.9770679473876953,
163
+ "step": 2
164
+ },
165
+ {
166
+ "epoch": 0.0001443001443001443,
167
+ "img_divergence_loss": 0.0,
168
+ "step": 2
169
+ },
170
+ {
171
+ "activation_proximity_loss": 0.0,
172
+ "epoch": 0.0001443001443001443,
173
+ "step": 2
174
+ },
175
+ {
176
+ "epoch": 0.00021645021645021645,
177
+ "grad_norm": 3.2348276164051617,
178
+ "learning_rate": 9.829629131445342e-06,
179
+ "loss": 1.3423,
180
+ "step": 3
181
+ },
182
+ {
183
+ "epoch": 0.00021645021645021645,
184
+ "lm_loss": 0.6548511981964111,
185
+ "step": 3
186
+ },
187
+ {
188
+ "epoch": 0.00021645021645021645,
189
+ "img_loss": 813.9419555664062,
190
+ "step": 3
191
+ },
192
+ {
193
+ "epoch": 0.00021645021645021645,
194
+ "img_emb_dist": 0.976345956325531,
195
+ "step": 3
196
+ },
197
+ {
198
+ "epoch": 0.00021645021645021645,
199
+ "img_divergence_loss": 0.0,
200
+ "step": 3
201
+ },
202
+ {
203
+ "activation_proximity_loss": 0.0,
204
+ "epoch": 0.00021645021645021645,
205
+ "step": 3
206
+ },
207
+ {
208
+ "epoch": 0.00021645021645021645,
209
+ "lm_loss": 1.1054067611694336,
210
+ "step": 3
211
+ },
212
+ {
213
+ "epoch": 0.00021645021645021645,
214
+ "img_loss": 788.4612426757812,
215
+ "step": 3
216
+ },
217
+ {
218
+ "epoch": 0.00021645021645021645,
219
+ "img_emb_dist": 0.9759064316749573,
220
+ "step": 3
221
+ },
222
+ {
223
+ "epoch": 0.00021645021645021645,
224
+ "img_divergence_loss": 0.0,
225
+ "step": 3
226
+ },
227
+ {
228
+ "activation_proximity_loss": 0.0,
229
+ "epoch": 0.00021645021645021645,
230
+ "step": 3
231
+ },
232
+ {
233
+ "epoch": 0.0002886002886002886,
234
+ "grad_norm": 3.171434499042359,
235
+ "learning_rate": 9.619397662556434e-06,
236
+ "loss": 1.2492,
237
+ "step": 4
238
+ },
239
+ {
240
+ "epoch": 0.0002886002886002886,
241
+ "lm_loss": 0.8177642822265625,
242
+ "step": 4
243
+ },
244
+ {
245
+ "epoch": 0.0002886002886002886,
246
+ "img_loss": 861.1069946289062,
247
+ "step": 4
248
+ },
249
+ {
250
+ "epoch": 0.0002886002886002886,
251
+ "img_emb_dist": 0.9751406311988831,
252
+ "step": 4
253
+ },
254
+ {
255
+ "epoch": 0.0002886002886002886,
256
+ "img_divergence_loss": 0.0,
257
+ "step": 4
258
+ },
259
+ {
260
+ "activation_proximity_loss": 0.0,
261
+ "epoch": 0.0002886002886002886,
262
+ "step": 4
263
+ },
264
+ {
265
+ "epoch": 0.0002886002886002886,
266
+ "lm_loss": 0.9702979922294617,
267
+ "step": 4
268
+ },
269
+ {
270
+ "epoch": 0.0002886002886002886,
271
+ "img_loss": 802.642578125,
272
+ "step": 4
273
+ },
274
+ {
275
+ "epoch": 0.0002886002886002886,
276
+ "img_emb_dist": 0.9762476682662964,
277
+ "step": 4
278
+ },
279
+ {
280
+ "epoch": 0.0002886002886002886,
281
+ "img_divergence_loss": 0.0,
282
+ "step": 4
283
+ },
284
+ {
285
+ "activation_proximity_loss": 0.0,
286
+ "epoch": 0.0002886002886002886,
287
+ "step": 4
288
+ },
289
+ {
290
+ "epoch": 0.00036075036075036075,
291
+ "grad_norm": 2.949350829936257,
292
+ "learning_rate": 9.330127018922195e-06,
293
+ "loss": 1.1519,
294
+ "step": 5
295
+ },
296
+ {
297
+ "epoch": 0.00036075036075036075,
298
+ "lm_loss": 1.165309190750122,
299
+ "step": 5
300
+ },
301
+ {
302
+ "epoch": 0.00036075036075036075,
303
+ "img_loss": 825.00634765625,
304
+ "step": 5
305
+ },
306
+ {
307
+ "epoch": 0.00036075036075036075,
308
+ "img_emb_dist": 0.9722062349319458,
309
+ "step": 5
310
+ },
311
+ {
312
+ "epoch": 0.00036075036075036075,
313
+ "img_divergence_loss": 0.0,
314
+ "step": 5
315
+ },
316
+ {
317
+ "activation_proximity_loss": 0.0,
318
+ "epoch": 0.00036075036075036075,
319
+ "step": 5
320
+ },
321
+ {
322
+ "epoch": 0.00036075036075036075,
323
+ "lm_loss": 1.2138742208480835,
324
+ "step": 5
325
+ },
326
+ {
327
+ "epoch": 0.00036075036075036075,
328
+ "img_loss": 832.3601684570312,
329
+ "step": 5
330
+ },
331
+ {
332
+ "epoch": 0.00036075036075036075,
333
+ "img_emb_dist": 0.9731454253196716,
334
+ "step": 5
335
+ },
336
+ {
337
+ "epoch": 0.00036075036075036075,
338
+ "img_divergence_loss": 0.0,
339
+ "step": 5
340
+ },
341
+ {
342
+ "activation_proximity_loss": 0.0,
343
+ "epoch": 0.00036075036075036075,
344
+ "step": 5
345
+ },
346
+ {
347
+ "epoch": 0.0004329004329004329,
348
+ "grad_norm": 2.729440391060018,
349
+ "learning_rate": 8.966766701456177e-06,
350
+ "loss": 1.268,
351
+ "step": 6
352
+ },
353
+ {
354
+ "epoch": 0.0004329004329004329,
355
+ "lm_loss": 1.2445625066757202,
356
+ "step": 6
357
+ },
358
+ {
359
+ "epoch": 0.0004329004329004329,
360
+ "img_loss": 815.9379272460938,
361
+ "step": 6
362
+ },
363
+ {
364
+ "epoch": 0.0004329004329004329,
365
+ "img_emb_dist": 0.9684582948684692,
366
+ "step": 6
367
+ },
368
+ {
369
+ "epoch": 0.0004329004329004329,
370
+ "img_divergence_loss": 0.0,
371
+ "step": 6
372
+ },
373
+ {
374
+ "activation_proximity_loss": 0.0,
375
+ "epoch": 0.0004329004329004329,
376
+ "step": 6
377
+ },
378
+ {
379
+ "epoch": 0.0004329004329004329,
380
+ "lm_loss": 1.0895243883132935,
381
+ "step": 6
382
+ },
383
+ {
384
+ "epoch": 0.0004329004329004329,
385
+ "img_loss": 864.1802978515625,
386
+ "step": 6
387
+ },
388
+ {
389
+ "epoch": 0.0004329004329004329,
390
+ "img_emb_dist": 0.9722574949264526,
391
+ "step": 6
392
+ },
393
+ {
394
+ "epoch": 0.0004329004329004329,
395
+ "img_divergence_loss": 0.0,
396
+ "step": 6
397
+ },
398
+ {
399
+ "activation_proximity_loss": 0.0,
400
+ "epoch": 0.0004329004329004329,
401
+ "step": 6
402
+ },
403
+ {
404
+ "epoch": 0.000505050505050505,
405
+ "grad_norm": 2.38479609428068,
406
+ "learning_rate": 8.535533905932739e-06,
407
+ "loss": 1.1839,
408
+ "step": 7
409
+ },
410
+ {
411
+ "epoch": 0.000505050505050505,
412
+ "lm_loss": 1.0988446474075317,
413
+ "step": 7
414
+ },
415
+ {
416
+ "epoch": 0.000505050505050505,
417
+ "img_loss": 898.799072265625,
418
+ "step": 7
419
+ },
420
+ {
421
+ "epoch": 0.000505050505050505,
422
+ "img_emb_dist": 0.971565842628479,
423
+ "step": 7
424
+ },
425
+ {
426
+ "epoch": 0.000505050505050505,
427
+ "img_divergence_loss": 0.0,
428
+ "step": 7
429
+ },
430
+ {
431
+ "activation_proximity_loss": 0.0,
432
+ "epoch": 0.000505050505050505,
433
+ "step": 7
434
+ },
435
+ {
436
+ "epoch": 0.000505050505050505,
437
+ "lm_loss": 0.9859169721603394,
438
+ "step": 7
439
+ },
440
+ {
441
+ "epoch": 0.000505050505050505,
442
+ "img_loss": 845.7677001953125,
443
+ "step": 7
444
+ },
445
+ {
446
+ "epoch": 0.000505050505050505,
447
+ "img_emb_dist": 0.9704997539520264,
448
+ "step": 7
449
+ },
450
+ {
451
+ "epoch": 0.000505050505050505,
452
+ "img_divergence_loss": 0.0,
453
+ "step": 7
454
+ },
455
+ {
456
+ "activation_proximity_loss": 0.0,
457
+ "epoch": 0.000505050505050505,
458
+ "step": 7
459
+ },
460
+ {
461
+ "epoch": 0.0005772005772005772,
462
+ "grad_norm": 2.2573539550373374,
463
+ "learning_rate": 8.043807145043604e-06,
464
+ "loss": 1.1728,
465
+ "step": 8
466
+ },
467
+ {
468
+ "epoch": 0.0005772005772005772,
469
+ "lm_loss": 0.696566641330719,
470
+ "step": 8
471
+ },
472
+ {
473
+ "epoch": 0.0005772005772005772,
474
+ "img_loss": 868.515869140625,
475
+ "step": 8
476
+ },
477
+ {
478
+ "epoch": 0.0005772005772005772,
479
+ "img_emb_dist": 0.9680835604667664,
480
+ "step": 8
481
+ },
482
+ {
483
+ "epoch": 0.0005772005772005772,
484
+ "img_divergence_loss": 0.0,
485
+ "step": 8
486
+ },
487
+ {
488
+ "activation_proximity_loss": 0.0,
489
+ "epoch": 0.0005772005772005772,
490
+ "step": 8
491
+ },
492
+ {
493
+ "epoch": 0.0005772005772005772,
494
+ "lm_loss": 1.236984372138977,
495
+ "step": 8
496
+ },
497
+ {
498
+ "epoch": 0.0005772005772005772,
499
+ "img_loss": 954.5865478515625,
500
+ "step": 8
501
+ },
502
+ {
503
+ "epoch": 0.0005772005772005772,
504
+ "img_emb_dist": 0.9685915112495422,
505
+ "step": 8
506
+ },
507
+ {
508
+ "epoch": 0.0005772005772005772,
509
+ "img_divergence_loss": 0.0,
510
+ "step": 8
511
+ },
512
+ {
513
+ "activation_proximity_loss": 0.0,
514
+ "epoch": 0.0005772005772005772,
515
+ "step": 8
516
+ },
517
+ {
518
+ "epoch": 0.0006493506493506494,
519
+ "grad_norm": 2.1746889923184933,
520
+ "learning_rate": 7.500000000000001e-06,
521
+ "loss": 1.2411,
522
+ "step": 9
523
+ },
524
+ {
525
+ "epoch": 0.0006493506493506494,
526
+ "lm_loss": 0.8733236789703369,
527
+ "step": 9
528
+ },
529
+ {
530
+ "epoch": 0.0006493506493506494,
531
+ "img_loss": 889.0441284179688,
532
+ "step": 9
533
+ },
534
+ {
535
+ "epoch": 0.0006493506493506494,
536
+ "img_emb_dist": 0.9652532339096069,
537
+ "step": 9
538
+ },
539
+ {
540
+ "epoch": 0.0006493506493506494,
541
+ "img_divergence_loss": 0.0,
542
+ "step": 9
543
+ },
544
+ {
545
+ "activation_proximity_loss": 0.0,
546
+ "epoch": 0.0006493506493506494,
547
+ "step": 9
548
+ },
549
+ {
550
+ "epoch": 0.0006493506493506494,
551
+ "lm_loss": 1.2848918437957764,
552
+ "step": 9
553
+ },
554
+ {
555
+ "epoch": 0.0006493506493506494,
556
+ "img_loss": 1006.572021484375,
557
+ "step": 9
558
+ },
559
+ {
560
+ "epoch": 0.0006493506493506494,
561
+ "img_emb_dist": 0.9681165814399719,
562
+ "step": 9
563
+ },
564
+ {
565
+ "epoch": 0.0006493506493506494,
566
+ "img_divergence_loss": 0.0,
567
+ "step": 9
568
+ },
569
+ {
570
+ "activation_proximity_loss": 0.0,
571
+ "epoch": 0.0006493506493506494,
572
+ "step": 9
573
+ },
574
+ {
575
+ "epoch": 0.0007215007215007215,
576
+ "grad_norm": 2.511095764027252,
577
+ "learning_rate": 6.913417161825449e-06,
578
+ "loss": 1.0717,
579
+ "step": 10
580
+ },
581
+ {
582
+ "epoch": 0.0007215007215007215,
583
+ "lm_loss": 1.1464320421218872,
584
+ "step": 10
585
+ },
586
+ {
587
+ "epoch": 0.0007215007215007215,
588
+ "img_loss": 986.5391235351562,
589
+ "step": 10
590
+ },
591
+ {
592
+ "epoch": 0.0007215007215007215,
593
+ "img_emb_dist": 0.9634599685668945,
594
+ "step": 10
595
+ },
596
+ {
597
+ "epoch": 0.0007215007215007215,
598
+ "img_divergence_loss": 0.0,
599
+ "step": 10
600
+ },
601
+ {
602
+ "activation_proximity_loss": 0.0,
603
+ "epoch": 0.0007215007215007215,
604
+ "step": 10
605
+ },
606
+ {
607
+ "epoch": 0.0007215007215007215,
608
+ "lm_loss": 1.1133934259414673,
609
+ "step": 10
610
+ },
611
+ {
612
+ "epoch": 0.0007215007215007215,
613
+ "img_loss": 958.0040893554688,
614
+ "step": 10
615
+ },
616
+ {
617
+ "epoch": 0.0007215007215007215,
618
+ "img_emb_dist": 0.9663693308830261,
619
+ "step": 10
620
+ },
621
+ {
622
+ "epoch": 0.0007215007215007215,
623
+ "img_divergence_loss": 0.0,
624
+ "step": 10
625
+ },
626
+ {
627
+ "activation_proximity_loss": 0.0,
628
+ "epoch": 0.0007215007215007215,
629
+ "step": 10
630
+ },
631
+ {
632
+ "epoch": 0.0007936507936507937,
633
+ "grad_norm": 2.5748822553247654,
634
+ "learning_rate": 6.294095225512604e-06,
635
+ "loss": 1.167,
636
+ "step": 11
637
+ },
638
+ {
639
+ "epoch": 0.0007936507936507937,
640
+ "lm_loss": 0.33026137948036194,
641
+ "step": 11
642
+ },
643
+ {
644
+ "epoch": 0.0007936507936507937,
645
+ "img_loss": 954.0510864257812,
646
+ "step": 11
647
+ },
648
+ {
649
+ "epoch": 0.0007936507936507937,
650
+ "img_emb_dist": 0.9645818471908569,
651
+ "step": 11
652
+ },
653
+ {
654
+ "epoch": 0.0007936507936507937,
655
+ "img_divergence_loss": 0.0,
656
+ "step": 11
657
+ },
658
+ {
659
+ "activation_proximity_loss": 0.0,
660
+ "epoch": 0.0007936507936507937,
661
+ "step": 11
662
+ },
663
+ {
664
+ "epoch": 0.0007936507936507937,
665
+ "lm_loss": 0.9683809280395508,
666
+ "step": 11
667
+ },
668
+ {
669
+ "epoch": 0.0007936507936507937,
670
+ "img_loss": 965.5768432617188,
671
+ "step": 11
672
+ },
673
+ {
674
+ "epoch": 0.0007936507936507937,
675
+ "img_emb_dist": 0.9631333351135254,
676
+ "step": 11
677
+ },
678
+ {
679
+ "epoch": 0.0007936507936507937,
680
+ "img_divergence_loss": 0.0,
681
+ "step": 11
682
+ },
683
+ {
684
+ "activation_proximity_loss": 0.0,
685
+ "epoch": 0.0007936507936507937,
686
+ "step": 11
687
+ },
688
+ {
689
+ "epoch": 0.0008658008658008658,
690
+ "grad_norm": 2.3558037289964884,
691
+ "learning_rate": 5.65263096110026e-06,
692
+ "loss": 1.0099,
693
+ "step": 12
694
+ },
695
+ {
696
+ "epoch": 0.0008658008658008658,
697
+ "lm_loss": 1.2899165153503418,
698
+ "step": 12
699
+ },
700
+ {
701
+ "epoch": 0.0008658008658008658,
702
+ "img_loss": 941.6240844726562,
703
+ "step": 12
704
+ },
705
+ {
706
+ "epoch": 0.0008658008658008658,
707
+ "img_emb_dist": 0.9658195376396179,
708
+ "step": 12
709
+ },
710
+ {
711
+ "epoch": 0.0008658008658008658,
712
+ "img_divergence_loss": 0.0,
713
+ "step": 12
714
+ },
715
+ {
716
+ "activation_proximity_loss": 0.0,
717
+ "epoch": 0.0008658008658008658,
718
+ "step": 12
719
+ },
720
+ {
721
+ "epoch": 0.0008658008658008658,
722
+ "lm_loss": 1.1860413551330566,
723
+ "step": 12
724
+ },
725
+ {
726
+ "epoch": 0.0008658008658008658,
727
+ "img_loss": 924.8343505859375,
728
+ "step": 12
729
+ },
730
+ {
731
+ "epoch": 0.0008658008658008658,
732
+ "img_emb_dist": 0.9628998041152954,
733
+ "step": 12
734
+ },
735
+ {
736
+ "epoch": 0.0008658008658008658,
737
+ "img_divergence_loss": 0.0,
738
+ "step": 12
739
+ },
740
+ {
741
+ "activation_proximity_loss": 0.0,
742
+ "epoch": 0.0008658008658008658,
743
+ "step": 12
744
+ },
745
+ {
746
+ "epoch": 0.000937950937950938,
747
+ "grad_norm": 2.1202341199517596,
748
+ "learning_rate": 5e-06,
749
+ "loss": 1.1215,
750
+ "step": 13
751
+ },
752
+ {
753
+ "epoch": 0.000937950937950938,
754
+ "lm_loss": 1.0426427125930786,
755
+ "step": 13
756
+ },
757
+ {
758
+ "epoch": 0.000937950937950938,
759
+ "img_loss": 944.3718872070312,
760
+ "step": 13
761
+ },
762
+ {
763
+ "epoch": 0.000937950937950938,
764
+ "img_emb_dist": 0.9633188247680664,
765
+ "step": 13
766
+ },
767
+ {
768
+ "epoch": 0.000937950937950938,
769
+ "img_divergence_loss": 0.0,
770
+ "step": 13
771
+ },
772
+ {
773
+ "activation_proximity_loss": 0.0,
774
+ "epoch": 0.000937950937950938,
775
+ "step": 13
776
+ },
777
+ {
778
+ "epoch": 0.000937950937950938,
779
+ "lm_loss": 1.2792726755142212,
780
+ "step": 13
781
+ },
782
+ {
783
+ "epoch": 0.000937950937950938,
784
+ "img_loss": 965.3296508789062,
785
+ "step": 13
786
+ },
787
+ {
788
+ "epoch": 0.000937950937950938,
789
+ "img_emb_dist": 0.9660452604293823,
790
+ "step": 13
791
+ },
792
+ {
793
+ "epoch": 0.000937950937950938,
794
+ "img_divergence_loss": 0.0,
795
+ "step": 13
796
+ },
797
+ {
798
+ "activation_proximity_loss": 0.0,
799
+ "epoch": 0.000937950937950938,
800
+ "step": 13
801
+ },
802
+ {
803
+ "epoch": 0.00101010101010101,
804
+ "grad_norm": 2.4173231793409236,
805
+ "learning_rate": 4.347369038899744e-06,
806
+ "loss": 1.1432,
807
+ "step": 14
808
+ },
809
+ {
810
+ "epoch": 0.00101010101010101,
811
+ "lm_loss": 0.46831265091896057,
812
+ "step": 14
813
+ },
814
+ {
815
+ "epoch": 0.00101010101010101,
816
+ "img_loss": 0.0,
817
+ "step": 14
818
+ },
819
+ {
820
+ "epoch": 0.00101010101010101,
821
+ "img_emb_dist": 0.0,
822
+ "step": 14
823
+ },
824
+ {
825
+ "epoch": 0.00101010101010101,
826
+ "img_divergence_loss": 0.0,
827
+ "step": 14
828
+ },
829
+ {
830
+ "activation_proximity_loss": 0.0,
831
+ "epoch": 0.00101010101010101,
832
+ "step": 14
833
+ },
834
+ {
835
+ "epoch": 0.00101010101010101,
836
+ "lm_loss": 0.3712627589702606,
837
+ "step": 14
838
+ },
839
+ {
840
+ "epoch": 0.00101010101010101,
841
+ "img_loss": 0.0,
842
+ "step": 14
843
+ },
844
+ {
845
+ "epoch": 0.00101010101010101,
846
+ "img_emb_dist": 0.0,
847
+ "step": 14
848
+ },
849
+ {
850
+ "epoch": 0.00101010101010101,
851
+ "img_divergence_loss": 0.0,
852
+ "step": 14
853
+ },
854
+ {
855
+ "activation_proximity_loss": 0.0,
856
+ "epoch": 0.00101010101010101,
857
+ "step": 14
858
+ },
859
+ {
860
+ "epoch": 0.0010822510822510823,
861
+ "grad_norm": 1.6914646599869387,
862
+ "learning_rate": 3.705904774487396e-06,
863
+ "loss": 0.3677,
864
+ "step": 15
865
+ },
866
+ {
867
+ "epoch": 0.0010822510822510823,
868
+ "lm_loss": 0.6287497878074646,
869
+ "step": 15
870
+ },
871
+ {
872
+ "epoch": 0.0010822510822510823,
873
+ "img_loss": 0.0,
874
+ "step": 15
875
+ },
876
+ {
877
+ "epoch": 0.0010822510822510823,
878
+ "img_emb_dist": 0.0,
879
+ "step": 15
880
+ },
881
+ {
882
+ "epoch": 0.0010822510822510823,
883
+ "img_divergence_loss": 0.0,
884
+ "step": 15
885
+ },
886
+ {
887
+ "activation_proximity_loss": 0.0,
888
+ "epoch": 0.0010822510822510823,
889
+ "step": 15
890
+ },
891
+ {
892
+ "epoch": 0.0010822510822510823,
893
+ "lm_loss": 0.2971065044403076,
894
+ "step": 15
895
+ },
896
+ {
897
+ "epoch": 0.0010822510822510823,
898
+ "img_loss": 0.0,
899
+ "step": 15
900
+ },
901
+ {
902
+ "epoch": 0.0010822510822510823,
903
+ "img_emb_dist": 0.0,
904
+ "step": 15
905
+ },
906
+ {
907
+ "epoch": 0.0010822510822510823,
908
+ "img_divergence_loss": 0.0,
909
+ "step": 15
910
+ },
911
+ {
912
+ "activation_proximity_loss": 0.0,
913
+ "epoch": 0.0010822510822510823,
914
+ "step": 15
915
+ },
916
+ {
917
+ "epoch": 0.0011544011544011544,
918
+ "grad_norm": 1.757312324226043,
919
+ "learning_rate": 3.0865828381745515e-06,
920
+ "loss": 0.4001,
921
+ "step": 16
922
+ },
923
+ {
924
+ "epoch": 0.0011544011544011544,
925
+ "lm_loss": 1.188820719718933,
926
+ "step": 16
927
+ },
928
+ {
929
+ "epoch": 0.0011544011544011544,
930
+ "img_loss": 990.9677734375,
931
+ "step": 16
932
+ },
933
+ {
934
+ "epoch": 0.0011544011544011544,
935
+ "img_emb_dist": 0.9642726182937622,
936
+ "step": 16
937
+ },
938
+ {
939
+ "epoch": 0.0011544011544011544,
940
+ "img_divergence_loss": 0.0,
941
+ "step": 16
942
+ },
943
+ {
944
+ "activation_proximity_loss": 0.0,
945
+ "epoch": 0.0011544011544011544,
946
+ "step": 16
947
+ },
948
+ {
949
+ "epoch": 0.0011544011544011544,
950
+ "lm_loss": 1.2861636877059937,
951
+ "step": 16
952
+ },
953
+ {
954
+ "epoch": 0.0011544011544011544,
955
+ "img_loss": 939.5360717773438,
956
+ "step": 16
957
+ },
958
+ {
959
+ "epoch": 0.0011544011544011544,
960
+ "img_emb_dist": 0.9632103443145752,
961
+ "step": 16
962
+ },
963
+ {
964
+ "epoch": 0.0011544011544011544,
965
+ "img_divergence_loss": 0.0,
966
+ "step": 16
967
+ },
968
+ {
969
+ "activation_proximity_loss": 0.0,
970
+ "epoch": 0.0011544011544011544,
971
+ "step": 16
972
+ },
973
+ {
974
+ "epoch": 0.0012265512265512266,
975
+ "grad_norm": 2.431545947889518,
976
+ "learning_rate": 2.5000000000000015e-06,
977
+ "loss": 1.1103,
978
+ "step": 17
979
+ },
980
+ {
981
+ "epoch": 0.0012265512265512266,
982
+ "lm_loss": 1.3463515043258667,
983
+ "step": 17
984
+ },
985
+ {
986
+ "epoch": 0.0012265512265512266,
987
+ "img_loss": 1010.4727783203125,
988
+ "step": 17
989
+ },
990
+ {
991
+ "epoch": 0.0012265512265512266,
992
+ "img_emb_dist": 0.9649385213851929,
993
+ "step": 17
994
+ },
995
+ {
996
+ "epoch": 0.0012265512265512266,
997
+ "img_divergence_loss": 0.0,
998
+ "step": 17
999
+ },
1000
+ {
1001
+ "activation_proximity_loss": 0.0,
1002
+ "epoch": 0.0012265512265512266,
1003
+ "step": 17
1004
+ },
1005
+ {
1006
+ "epoch": 0.0012265512265512266,
1007
+ "lm_loss": 0.9498377442359924,
1008
+ "step": 17
1009
+ },
1010
+ {
1011
+ "epoch": 0.0012265512265512266,
1012
+ "img_loss": 1033.6485595703125,
1013
+ "step": 17
1014
+ },
1015
+ {
1016
+ "epoch": 0.0012265512265512266,
1017
+ "img_emb_dist": 0.963358461856842,
1018
+ "step": 17
1019
+ },
1020
+ {
1021
+ "epoch": 0.0012265512265512266,
1022
+ "img_divergence_loss": 0.0,
1023
+ "step": 17
1024
+ },
1025
+ {
1026
+ "activation_proximity_loss": 0.0,
1027
+ "epoch": 0.0012265512265512266,
1028
+ "step": 17
1029
+ },
1030
+ {
1031
+ "epoch": 0.0012987012987012987,
1032
+ "grad_norm": 2.426061656297513,
1033
+ "learning_rate": 1.956192854956397e-06,
1034
+ "loss": 1.166,
1035
+ "step": 18
1036
+ },
1037
+ {
1038
+ "epoch": 0.0012987012987012987,
1039
+ "lm_loss": 1.0570887327194214,
1040
+ "step": 18
1041
+ },
1042
+ {
1043
+ "epoch": 0.0012987012987012987,
1044
+ "img_loss": 934.938232421875,
1045
+ "step": 18
1046
+ },
1047
+ {
1048
+ "epoch": 0.0012987012987012987,
1049
+ "img_emb_dist": 0.9629301428794861,
1050
+ "step": 18
1051
+ },
1052
+ {
1053
+ "epoch": 0.0012987012987012987,
1054
+ "img_divergence_loss": 0.0,
1055
+ "step": 18
1056
+ },
1057
+ {
1058
+ "activation_proximity_loss": 0.0,
1059
+ "epoch": 0.0012987012987012987,
1060
+ "step": 18
1061
+ },
1062
+ {
1063
+ "epoch": 0.0012987012987012987,
1064
+ "lm_loss": 0.8632858395576477,
1065
+ "step": 18
1066
+ },
1067
+ {
1068
+ "epoch": 0.0012987012987012987,
1069
+ "img_loss": 1023.4631958007812,
1070
+ "step": 18
1071
+ },
1072
+ {
1073
+ "epoch": 0.0012987012987012987,
1074
+ "img_emb_dist": 0.9655637741088867,
1075
+ "step": 18
1076
+ },
1077
+ {
1078
+ "epoch": 0.0012987012987012987,
1079
+ "img_divergence_loss": 0.0,
1080
+ "step": 18
1081
+ },
1082
+ {
1083
+ "activation_proximity_loss": 0.0,
1084
+ "epoch": 0.0012987012987012987,
1085
+ "step": 18
1086
+ },
1087
+ {
1088
+ "epoch": 0.0013708513708513709,
1089
+ "grad_norm": 2.1054422816169414,
1090
+ "learning_rate": 1.4644660940672628e-06,
1091
+ "loss": 1.0352,
1092
+ "step": 19
1093
+ },
1094
+ {
1095
+ "epoch": 0.0013708513708513709,
1096
+ "lm_loss": 0.4083617031574249,
1097
+ "step": 19
1098
+ },
1099
+ {
1100
+ "epoch": 0.0013708513708513709,
1101
+ "img_loss": 1058.53857421875,
1102
+ "step": 19
1103
+ },
1104
+ {
1105
+ "epoch": 0.0013708513708513709,
1106
+ "img_emb_dist": 0.9631701707839966,
1107
+ "step": 19
1108
+ },
1109
+ {
1110
+ "epoch": 0.0013708513708513709,
1111
+ "img_divergence_loss": 0.0,
1112
+ "step": 19
1113
+ },
1114
+ {
1115
+ "activation_proximity_loss": 0.0,
1116
+ "epoch": 0.0013708513708513709,
1117
+ "step": 19
1118
+ },
1119
+ {
1120
+ "epoch": 0.0013708513708513709,
1121
+ "lm_loss": 0.7984881401062012,
1122
+ "step": 19
1123
+ },
1124
+ {
1125
+ "epoch": 0.0013708513708513709,
1126
+ "img_loss": 1036.539794921875,
1127
+ "step": 19
1128
+ },
1129
+ {
1130
+ "epoch": 0.0013708513708513709,
1131
+ "img_emb_dist": 0.9626760482788086,
1132
+ "step": 19
1133
+ },
1134
+ {
1135
+ "epoch": 0.0013708513708513709,
1136
+ "img_divergence_loss": 0.0,
1137
+ "step": 19
1138
+ },
1139
+ {
1140
+ "activation_proximity_loss": 0.0,
1141
+ "epoch": 0.0013708513708513709,
1142
+ "step": 19
1143
+ },
1144
+ {
1145
+ "epoch": 0.001443001443001443,
1146
+ "grad_norm": 1.9384436653640056,
1147
+ "learning_rate": 1.0332332985438248e-06,
1148
+ "loss": 0.9994,
1149
+ "step": 20
1150
+ },
1151
+ {
1152
+ "epoch": 0.001443001443001443,
1153
+ "lm_loss": 0.9373359680175781,
1154
+ "step": 20
1155
+ },
1156
+ {
1157
+ "epoch": 0.001443001443001443,
1158
+ "img_loss": 1029.9630126953125,
1159
+ "step": 20
1160
+ },
1161
+ {
1162
+ "epoch": 0.001443001443001443,
1163
+ "img_emb_dist": 0.9650158882141113,
1164
+ "step": 20
1165
+ },
1166
+ {
1167
+ "epoch": 0.001443001443001443,
1168
+ "img_divergence_loss": 0.0,
1169
+ "step": 20
1170
+ },
1171
+ {
1172
+ "activation_proximity_loss": 0.0,
1173
+ "epoch": 0.001443001443001443,
1174
+ "step": 20
1175
+ },
1176
+ {
1177
+ "epoch": 0.001443001443001443,
1178
+ "lm_loss": 1.0467417240142822,
1179
+ "step": 20
1180
+ },
1181
+ {
1182
+ "epoch": 0.001443001443001443,
1183
+ "img_loss": 972.8388061523438,
1184
+ "step": 20
1185
+ },
1186
+ {
1187
+ "epoch": 0.001443001443001443,
1188
+ "img_emb_dist": 0.9657303094863892,
1189
+ "step": 20
1190
+ },
1191
+ {
1192
+ "epoch": 0.001443001443001443,
1193
+ "img_divergence_loss": 0.0,
1194
+ "step": 20
1195
+ },
1196
+ {
1197
+ "activation_proximity_loss": 0.0,
1198
+ "epoch": 0.001443001443001443,
1199
+ "step": 20
1200
+ },
1201
+ {
1202
+ "epoch": 0.0015151515151515152,
1203
+ "grad_norm": 2.4290960365669556,
1204
+ "learning_rate": 6.698729810778065e-07,
1205
+ "loss": 1.0614,
1206
+ "step": 21
1207
+ },
1208
+ {
1209
+ "epoch": 0.0015151515151515152,
1210
+ "lm_loss": 1.1180315017700195,
1211
+ "step": 21
1212
+ },
1213
+ {
1214
+ "epoch": 0.0015151515151515152,
1215
+ "img_loss": 1042.491455078125,
1216
+ "step": 21
1217
+ },
1218
+ {
1219
+ "epoch": 0.0015151515151515152,
1220
+ "img_emb_dist": 0.9618048667907715,
1221
+ "step": 21
1222
+ },
1223
+ {
1224
+ "epoch": 0.0015151515151515152,
1225
+ "img_divergence_loss": 0.0,
1226
+ "step": 21
1227
+ },
1228
+ {
1229
+ "activation_proximity_loss": 0.0,
1230
+ "epoch": 0.0015151515151515152,
1231
+ "step": 21
1232
+ },
1233
+ {
1234
+ "epoch": 0.0015151515151515152,
1235
+ "lm_loss": 1.1421946287155151,
1236
+ "step": 21
1237
+ },
1238
+ {
1239
+ "epoch": 0.0015151515151515152,
1240
+ "img_loss": 1001.2096557617188,
1241
+ "step": 21
1242
+ },
1243
+ {
1244
+ "epoch": 0.0015151515151515152,
1245
+ "img_emb_dist": 0.9632893800735474,
1246
+ "step": 21
1247
+ },
1248
+ {
1249
+ "epoch": 0.0015151515151515152,
1250
+ "img_divergence_loss": 0.0,
1251
+ "step": 21
1252
+ },
1253
+ {
1254
+ "activation_proximity_loss": 0.0,
1255
+ "epoch": 0.0015151515151515152,
1256
+ "step": 21
1257
+ },
1258
+ {
1259
+ "epoch": 0.0015873015873015873,
1260
+ "grad_norm": 3.5959413287337085,
1261
+ "learning_rate": 3.8060233744356634e-07,
1262
+ "loss": 1.1993,
1263
+ "step": 22
1264
+ },
1265
+ {
1266
+ "epoch": 0.0015873015873015873,
1267
+ "lm_loss": 0.8462453484535217,
1268
+ "step": 22
1269
+ },
1270
+ {
1271
+ "epoch": 0.0015873015873015873,
1272
+ "img_loss": 924.993408203125,
1273
+ "step": 22
1274
+ },
1275
+ {
1276
+ "epoch": 0.0015873015873015873,
1277
+ "img_emb_dist": 0.9621605277061462,
1278
+ "step": 22
1279
+ },
1280
+ {
1281
+ "epoch": 0.0015873015873015873,
1282
+ "img_divergence_loss": 0.0,
1283
+ "step": 22
1284
+ },
1285
+ {
1286
+ "activation_proximity_loss": 0.0,
1287
+ "epoch": 0.0015873015873015873,
1288
+ "step": 22
1289
+ },
1290
+ {
1291
+ "epoch": 0.0015873015873015873,
1292
+ "lm_loss": 0.9902944564819336,
1293
+ "step": 22
1294
+ },
1295
+ {
1296
+ "epoch": 0.0015873015873015873,
1297
+ "img_loss": 977.50732421875,
1298
+ "step": 22
1299
+ },
1300
+ {
1301
+ "epoch": 0.0015873015873015873,
1302
+ "img_emb_dist": 0.9628319144248962,
1303
+ "step": 22
1304
+ },
1305
+ {
1306
+ "epoch": 0.0015873015873015873,
1307
+ "img_divergence_loss": 0.0,
1308
+ "step": 22
1309
+ },
1310
+ {
1311
+ "activation_proximity_loss": 0.0,
1312
+ "epoch": 0.0015873015873015873,
1313
+ "step": 22
1314
+ },
1315
+ {
1316
+ "epoch": 0.0016594516594516595,
1317
+ "grad_norm": 2.4828687968296954,
1318
+ "learning_rate": 1.7037086855465902e-07,
1319
+ "loss": 1.1557,
1320
+ "step": 23
1321
+ },
1322
+ {
1323
+ "epoch": 0.0016594516594516595,
1324
+ "lm_loss": 0.5318238735198975,
1325
+ "step": 23
1326
+ },
1327
+ {
1328
+ "epoch": 0.0016594516594516595,
1329
+ "img_loss": 975.1682739257812,
1330
+ "step": 23
1331
+ },
1332
+ {
1333
+ "epoch": 0.0016594516594516595,
1334
+ "img_emb_dist": 0.9615951180458069,
1335
+ "step": 23
1336
+ },
1337
+ {
1338
+ "epoch": 0.0016594516594516595,
1339
+ "img_divergence_loss": 0.0,
1340
+ "step": 23
1341
+ },
1342
+ {
1343
+ "activation_proximity_loss": 0.0,
1344
+ "epoch": 0.0016594516594516595,
1345
+ "step": 23
1346
+ },
1347
+ {
1348
+ "epoch": 0.0016594516594516595,
1349
+ "lm_loss": 1.499765157699585,
1350
+ "step": 23
1351
+ },
1352
+ {
1353
+ "epoch": 0.0016594516594516595,
1354
+ "img_loss": 952.0101928710938,
1355
+ "step": 23
1356
+ },
1357
+ {
1358
+ "epoch": 0.0016594516594516595,
1359
+ "img_emb_dist": 0.9655733704566956,
1360
+ "step": 23
1361
+ },
1362
+ {
1363
+ "epoch": 0.0016594516594516595,
1364
+ "img_divergence_loss": 0.0,
1365
+ "step": 23
1366
+ },
1367
+ {
1368
+ "activation_proximity_loss": 0.0,
1369
+ "epoch": 0.0016594516594516595,
1370
+ "step": 23
1371
+ },
1372
+ {
1373
+ "epoch": 0.0017316017316017316,
1374
+ "grad_norm": 2.1518352777637206,
1375
+ "learning_rate": 4.2775693130948094e-08,
1376
+ "loss": 1.0811,
1377
+ "step": 24
1378
+ },
1379
+ {
1380
+ "epoch": 0.0017316017316017316,
1381
+ "lm_loss": 0.42849138379096985,
1382
+ "step": 24
1383
+ },
1384
+ {
1385
+ "epoch": 0.0017316017316017316,
1386
+ "img_loss": 987.5194091796875,
1387
+ "step": 24
1388
+ },
1389
+ {
1390
+ "epoch": 0.0017316017316017316,
1391
+ "img_emb_dist": 0.9614472985267639,
1392
+ "step": 24
1393
+ },
1394
+ {
1395
+ "epoch": 0.0017316017316017316,
1396
+ "img_divergence_loss": 0.0,
1397
+ "step": 24
1398
+ },
1399
+ {
1400
+ "activation_proximity_loss": 0.0,
1401
+ "epoch": 0.0017316017316017316,
1402
+ "step": 24
1403
+ },
1404
+ {
1405
+ "epoch": 0.0017316017316017316,
1406
+ "lm_loss": 1.1963765621185303,
1407
+ "step": 24
1408
+ },
1409
+ {
1410
+ "epoch": 0.0017316017316017316,
1411
+ "img_loss": 974.4249877929688,
1412
+ "step": 24
1413
+ },
1414
+ {
1415
+ "epoch": 0.0017316017316017316,
1416
+ "img_emb_dist": 0.9614829421043396,
1417
+ "step": 24
1418
+ },
1419
+ {
1420
+ "epoch": 0.0017316017316017316,
1421
+ "img_divergence_loss": 0.0,
1422
+ "step": 24
1423
+ },
1424
+ {
1425
+ "activation_proximity_loss": 0.0,
1426
+ "epoch": 0.0017316017316017316,
1427
+ "step": 24
1428
+ },
1429
+ {
1430
+ "epoch": 0.0018037518037518038,
1431
+ "grad_norm": 2.8558883696766513,
1432
+ "learning_rate": 0.0,
1433
+ "loss": 1.1064,
1434
+ "step": 25
1435
+ }
1436
+ ],
1437
+ "logging_steps": 1.0,
1438
+ "max_steps": 25,
1439
+ "num_input_tokens_seen": 0,
1440
+ "num_train_epochs": 1,
1441
+ "save_steps": 5,
1442
+ "stateful_callbacks": {
1443
+ "TrainerControl": {
1444
+ "args": {
1445
+ "should_epoch_stop": false,
1446
+ "should_evaluate": false,
1447
+ "should_log": false,
1448
+ "should_save": true,
1449
+ "should_training_stop": true
1450
+ },
1451
+ "attributes": {}
1452
+ }
1453
+ },
1454
+ "total_flos": 4064781361152.0,
1455
+ "train_batch_size": 3,
1456
+ "trial_name": null,
1457
+ "trial_params": null
1458
+ }
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:978eef64c362f894644dc60ceb2b3d5113c620f36ce3fb32d8cf9a1c5b73be57
3
+ size 8056
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/checkpoint-25/zero_to_fp32.py ADDED
@@ -0,0 +1,604 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example: python zero_to_fp32.py . pytorch_model.bin
14
+
15
+ import argparse
16
+ import torch
17
+ import glob
18
+ import math
19
+ import os
20
+ import re
21
+ from collections import OrderedDict
22
+ from dataclasses import dataclass
23
+
24
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
25
+ # DeepSpeed data structures it has to be available in the current python environment.
26
+ from deepspeed.utils import logger
27
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
28
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
29
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
30
+
31
+
32
+ @dataclass
33
+ class zero_model_state:
34
+ buffers: dict()
35
+ param_shapes: dict()
36
+ shared_params: list
37
+ ds_version: int
38
+ frozen_param_shapes: dict()
39
+ frozen_param_fragments: dict()
40
+
41
+
42
+ debug = 0
43
+
44
+ # load to cpu
45
+ device = torch.device('cpu')
46
+
47
+
48
+ def atoi(text):
49
+ return int(text) if text.isdigit() else text
50
+
51
+
52
+ def natural_keys(text):
53
+ '''
54
+ alist.sort(key=natural_keys) sorts in human order
55
+ http://nedbatchelder.com/blog/200712/human_sorting.html
56
+ (See Toothy's implementation in the comments)
57
+ '''
58
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
59
+
60
+
61
+ def get_model_state_file(checkpoint_dir, zero_stage):
62
+ if not os.path.isdir(checkpoint_dir):
63
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
64
+
65
+ # there should be only one file
66
+ if zero_stage <= 2:
67
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
68
+ elif zero_stage == 3:
69
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
70
+
71
+ if not os.path.exists(file):
72
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
73
+
74
+ return file
75
+
76
+
77
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
78
+ # XXX: need to test that this simple glob rule works for multi-node setup too
79
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
80
+
81
+ if len(ckpt_files) == 0:
82
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
83
+
84
+ return ckpt_files
85
+
86
+
87
+ def get_optim_files(checkpoint_dir):
88
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
89
+
90
+
91
+ def get_model_state_files(checkpoint_dir):
92
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
93
+
94
+
95
+ def parse_model_states(files):
96
+ zero_model_states = []
97
+ for file in files:
98
+ state_dict = torch.load(file, map_location=device)
99
+
100
+ if BUFFER_NAMES not in state_dict:
101
+ raise ValueError(f"{file} is not a model state checkpoint")
102
+ buffer_names = state_dict[BUFFER_NAMES]
103
+ if debug:
104
+ print("Found buffers:", buffer_names)
105
+
106
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
107
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
108
+ param_shapes = state_dict[PARAM_SHAPES]
109
+
110
+ # collect parameters that are included in param_shapes
111
+ param_names = []
112
+ for s in param_shapes:
113
+ for name in s.keys():
114
+ param_names.append(name)
115
+
116
+ # update with frozen parameters
117
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
118
+ if frozen_param_shapes is not None:
119
+ if debug:
120
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
121
+ param_names += list(frozen_param_shapes.keys())
122
+
123
+ # handle shared params
124
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
125
+
126
+ ds_version = state_dict.get(DS_VERSION, None)
127
+
128
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
129
+
130
+ z_model_state = zero_model_state(buffers=buffers,
131
+ param_shapes=param_shapes,
132
+ shared_params=shared_params,
133
+ ds_version=ds_version,
134
+ frozen_param_shapes=frozen_param_shapes,
135
+ frozen_param_fragments=frozen_param_fragments)
136
+ zero_model_states.append(z_model_state)
137
+
138
+ return zero_model_states
139
+
140
+
141
+ def parse_optim_states(files, ds_checkpoint_dir):
142
+
143
+ total_files = len(files)
144
+ state_dicts = []
145
+ for f in files:
146
+ state_dict = torch.load(f, map_location=device)
147
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
148
+ # and also handle the case where it was already removed by another helper script
149
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
150
+ state_dicts.append(state_dict)
151
+
152
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
153
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
154
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
155
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
156
+
157
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
158
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
159
+ # use the max of the partition_count to get the dp world_size.
160
+
161
+ if type(world_size) is list:
162
+ world_size = max(world_size)
163
+
164
+ if world_size != total_files:
165
+ raise ValueError(
166
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
167
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
168
+ )
169
+
170
+ # the groups are named differently in each stage
171
+ if zero_stage <= 2:
172
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
173
+ elif zero_stage == 3:
174
+ fp32_groups_key = FP32_FLAT_GROUPS
175
+ else:
176
+ raise ValueError(f"unknown zero stage {zero_stage}")
177
+
178
+ if zero_stage <= 2:
179
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
180
+ elif zero_stage == 3:
181
+ # if there is more than one param group, there will be multiple flattened tensors - one
182
+ # flattened tensor per group - for simplicity merge them into a single tensor
183
+ #
184
+ # XXX: could make the script more memory efficient for when there are multiple groups - it
185
+ # will require matching the sub-lists of param_shapes for each param group flattened tensor
186
+
187
+ fp32_flat_groups = [
188
+ torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
189
+ ]
190
+
191
+ return zero_stage, world_size, fp32_flat_groups
192
+
193
+
194
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
195
+ """
196
+ Returns fp32 state_dict reconstructed from ds checkpoint
197
+
198
+ Args:
199
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
200
+
201
+ """
202
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
203
+
204
+ optim_files = get_optim_files(ds_checkpoint_dir)
205
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
206
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
207
+
208
+ model_files = get_model_state_files(ds_checkpoint_dir)
209
+
210
+ zero_model_states = parse_model_states(model_files)
211
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
212
+
213
+ if zero_stage <= 2:
214
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
215
+ exclude_frozen_parameters)
216
+ elif zero_stage == 3:
217
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
218
+ exclude_frozen_parameters)
219
+
220
+
221
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
222
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
223
+ return
224
+
225
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
226
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
227
+
228
+ if debug:
229
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
230
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
231
+
232
+ wanted_params = len(frozen_param_shapes)
233
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
234
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
235
+ print(f'Frozen params: Have {avail_numel} numels to process.')
236
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
237
+
238
+ total_params = 0
239
+ total_numel = 0
240
+ for name, shape in frozen_param_shapes.items():
241
+ total_params += 1
242
+ unpartitioned_numel = shape.numel()
243
+ total_numel += unpartitioned_numel
244
+
245
+ state_dict[name] = frozen_param_fragments[name]
246
+
247
+ if debug:
248
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
249
+
250
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
251
+
252
+
253
+ def _has_callable(obj, fn):
254
+ attr = getattr(obj, fn, None)
255
+ return callable(attr)
256
+
257
+
258
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
259
+ param_shapes = zero_model_states[0].param_shapes
260
+
261
+ # Reconstruction protocol:
262
+ #
263
+ # XXX: document this
264
+
265
+ if debug:
266
+ for i in range(world_size):
267
+ for j in range(len(fp32_flat_groups[0])):
268
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
269
+
270
+ # XXX: memory usage doubles here (zero2)
271
+ num_param_groups = len(fp32_flat_groups[0])
272
+ merged_single_partition_of_fp32_groups = []
273
+ for i in range(num_param_groups):
274
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
275
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
276
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
277
+ avail_numel = sum(
278
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
279
+
280
+ if debug:
281
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
282
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
283
+ # not asserting if there is a mismatch due to possible padding
284
+ print(f"Have {avail_numel} numels to process.")
285
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
286
+
287
+ # params
288
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
289
+ # out-of-core computing solution
290
+ total_numel = 0
291
+ total_params = 0
292
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
293
+ offset = 0
294
+ avail_numel = full_single_fp32_vector.numel()
295
+ for name, shape in shapes.items():
296
+
297
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
298
+ total_numel += unpartitioned_numel
299
+ total_params += 1
300
+
301
+ if debug:
302
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
303
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
304
+ offset += unpartitioned_numel
305
+
306
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
307
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
308
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
309
+ # live optimizer object, so we are checking that the numbers are within the right range
310
+ align_to = 2 * world_size
311
+
312
+ def zero2_align(x):
313
+ return align_to * math.ceil(x / align_to)
314
+
315
+ if debug:
316
+ print(f"original offset={offset}, avail_numel={avail_numel}")
317
+
318
+ offset = zero2_align(offset)
319
+ avail_numel = zero2_align(avail_numel)
320
+
321
+ if debug:
322
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
323
+
324
+ # Sanity check
325
+ if offset != avail_numel:
326
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
327
+
328
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
329
+
330
+
331
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
332
+ exclude_frozen_parameters):
333
+ state_dict = OrderedDict()
334
+
335
+ # buffers
336
+ buffers = zero_model_states[0].buffers
337
+ state_dict.update(buffers)
338
+ if debug:
339
+ print(f"added {len(buffers)} buffers")
340
+
341
+ if not exclude_frozen_parameters:
342
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
343
+
344
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
345
+
346
+ # recover shared parameters
347
+ for pair in zero_model_states[0].shared_params:
348
+ if pair[1] in state_dict:
349
+ state_dict[pair[0]] = state_dict[pair[1]]
350
+
351
+ return state_dict
352
+
353
+
354
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
355
+ remainder = unpartitioned_numel % world_size
356
+ padding_numel = (world_size - remainder) if remainder else 0
357
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
358
+ return partitioned_numel, padding_numel
359
+
360
+
361
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
362
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
363
+ return
364
+
365
+ if debug:
366
+ for i in range(world_size):
367
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
368
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
369
+
370
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
371
+ wanted_params = len(frozen_param_shapes)
372
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
373
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
374
+ print(f'Frozen params: Have {avail_numel} numels to process.')
375
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
376
+
377
+ total_params = 0
378
+ total_numel = 0
379
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
380
+ total_params += 1
381
+ unpartitioned_numel = shape.numel()
382
+ total_numel += unpartitioned_numel
383
+
384
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
385
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
386
+
387
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
388
+
389
+ if debug:
390
+ print(
391
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
392
+ )
393
+
394
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
395
+
396
+
397
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
398
+ param_shapes = zero_model_states[0].param_shapes
399
+ avail_numel = fp32_flat_groups[0].numel() * world_size
400
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
401
+ # param, re-consolidating each param, while dealing with padding if any
402
+
403
+ # merge list of dicts, preserving order
404
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
405
+
406
+ if debug:
407
+ for i in range(world_size):
408
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
409
+
410
+ wanted_params = len(param_shapes)
411
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
412
+ # not asserting if there is a mismatch due to possible padding
413
+ avail_numel = fp32_flat_groups[0].numel() * world_size
414
+ print(f"Trainable params: Have {avail_numel} numels to process.")
415
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
416
+
417
+ # params
418
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
419
+ # out-of-core computing solution
420
+ offset = 0
421
+ total_numel = 0
422
+ total_params = 0
423
+ for name, shape in param_shapes.items():
424
+
425
+ unpartitioned_numel = shape.numel()
426
+ total_numel += unpartitioned_numel
427
+ total_params += 1
428
+
429
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
430
+
431
+ if debug:
432
+ print(
433
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
434
+ )
435
+
436
+ # XXX: memory usage doubles here
437
+ state_dict[name] = torch.cat(
438
+ tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
439
+ 0).narrow(0, 0, unpartitioned_numel).view(shape)
440
+ offset += partitioned_numel
441
+
442
+ offset *= world_size
443
+
444
+ # Sanity check
445
+ if offset != avail_numel:
446
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
447
+
448
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
449
+
450
+
451
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
452
+ exclude_frozen_parameters):
453
+ state_dict = OrderedDict()
454
+
455
+ # buffers
456
+ buffers = zero_model_states[0].buffers
457
+ state_dict.update(buffers)
458
+ if debug:
459
+ print(f"added {len(buffers)} buffers")
460
+
461
+ if not exclude_frozen_parameters:
462
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
463
+
464
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
465
+
466
+ # recover shared parameters
467
+ for pair in zero_model_states[0].shared_params:
468
+ if pair[1] in state_dict:
469
+ state_dict[pair[0]] = state_dict[pair[1]]
470
+
471
+ return state_dict
472
+
473
+
474
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
475
+ """
476
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
477
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
478
+ via a model hub.
479
+
480
+ Args:
481
+ - ``checkpoint_dir``: path to the desired checkpoint folder
482
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
483
+ - ``exclude_frozen_parameters``: exclude frozen parameters
484
+
485
+ Returns:
486
+ - pytorch ``state_dict``
487
+
488
+ Note: this approach may not work if your application doesn't have sufficient free CPU memory and
489
+ you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
490
+ the checkpoint.
491
+
492
+ A typical usage might be ::
493
+
494
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
495
+ # do the training and checkpoint saving
496
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
497
+ model = model.cpu() # move to cpu
498
+ model.load_state_dict(state_dict)
499
+ # submit to model hub or save the model to share with others
500
+
501
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
502
+ application. i.e. you will need to re-initialize the deepspeed engine, since
503
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
504
+
505
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
506
+
507
+ """
508
+ if tag is None:
509
+ latest_path = os.path.join(checkpoint_dir, 'latest')
510
+ if os.path.isfile(latest_path):
511
+ with open(latest_path, 'r') as fd:
512
+ tag = fd.read().strip()
513
+ else:
514
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
515
+
516
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
517
+
518
+ if not os.path.isdir(ds_checkpoint_dir):
519
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
520
+
521
+ return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
522
+
523
+
524
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
525
+ """
526
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
527
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
528
+
529
+ Args:
530
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
531
+ - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
532
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
533
+ - ``exclude_frozen_parameters``: exclude frozen parameters
534
+ """
535
+
536
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
537
+ print(f"Saving fp32 state dict to {output_file}")
538
+ torch.save(state_dict, output_file)
539
+
540
+
541
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
542
+ """
543
+ 1. Put the provided model to cpu
544
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
545
+ 3. Load it into the provided model
546
+
547
+ Args:
548
+ - ``model``: the model object to update
549
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
550
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
551
+
552
+ Returns:
553
+ - ``model`: modified model
554
+
555
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
556
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
557
+ conveniently placed for you in the checkpoint folder.
558
+
559
+ A typical usage might be ::
560
+
561
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
562
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
563
+ # submit to model hub or save the model to share with others
564
+
565
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
566
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
567
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
568
+
569
+ """
570
+ logger.info(f"Extracting fp32 weights")
571
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
572
+
573
+ logger.info(f"Overwriting model with fp32 weights")
574
+ model = model.cpu()
575
+ model.load_state_dict(state_dict, strict=False)
576
+
577
+ return model
578
+
579
+
580
+ if __name__ == "__main__":
581
+
582
+ parser = argparse.ArgumentParser()
583
+ parser.add_argument("checkpoint_dir",
584
+ type=str,
585
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
586
+ parser.add_argument(
587
+ "output_file",
588
+ type=str,
589
+ help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
590
+ parser.add_argument("-t",
591
+ "--tag",
592
+ type=str,
593
+ default=None,
594
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
595
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
596
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
597
+ args = parser.parse_args()
598
+
599
+ debug = args.debug
600
+
601
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
602
+ args.output_file,
603
+ tag=args.tag,
604
+ exclude_frozen_parameters=args.exclude_frozen_parameters)
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/dockerx/Local/checkpoints/TEST-multillavafinal-vicuna-siglip-PT.l0.d0.a0-S15.l1e-5.d0.a0",
3
+ "architectures": [
4
+ "MultiLlavaLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "image_aspect_ratio": "square",
13
+ "image_crop_resolution": null,
14
+ "image_grid_pinpoints": null,
15
+ "image_split_resolution": null,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 11008,
18
+ "max_position_embeddings": 4096,
19
+ "mlp_bias": false,
20
+ "mm_hidden_size": 1152,
21
+ "mm_newline_position": "one_token",
22
+ "mm_patch_merge_type": "flat",
23
+ "mm_projector_lr": null,
24
+ "mm_projector_type": "mlp2x_gelu",
25
+ "mm_resampler_type": null,
26
+ "mm_spatial_pool_mode": "bilinear",
27
+ "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
28
+ "mm_use_im_patch_token": false,
29
+ "mm_use_im_start_end": false,
30
+ "mm_vision_select_feature": "patch",
31
+ "mm_vision_select_layer": -2,
32
+ "mm_vision_tower": "google/siglip-so400m-patch14-384",
33
+ "mm_vision_tower_lr": 2e-06,
34
+ "model_type": "llama",
35
+ "num_attention_heads": 32,
36
+ "num_hidden_layers": 32,
37
+ "num_key_value_heads": 32,
38
+ "pad_token_id": 0,
39
+ "pos_skipping_range": 4096,
40
+ "pretraining_tp": 1,
41
+ "rms_norm_eps": 1e-05,
42
+ "rope_scaling": null,
43
+ "rope_theta": 10000.0,
44
+ "tie_word_embeddings": false,
45
+ "tokenizer_model_max_length": 32768,
46
+ "tokenizer_padding_side": "right",
47
+ "torch_dtype": "bfloat16",
48
+ "transformers_version": "4.44.2",
49
+ "use_cache": true,
50
+ "use_mm_proj": true,
51
+ "use_pos_skipping": false,
52
+ "vision_tower_pretrained": null,
53
+ "vocab_size": 32000
54
+ }
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 4096,
5
+ "pad_token_id": 0,
6
+ "temperature": 0.9,
7
+ "top_p": 0.6,
8
+ "transformers_version": "4.44.2"
9
+ }
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:075d8482f80d86bc9cba01cba4ebc5a042607478b2d1c5bf49d77b213fd08ce6
3
+ size 4938985352
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2de768923996d6defacb56b3d87708049d611377f1e2779ea945e0ceafc05414
3
+ size 4947390880
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24cc5abfdef95d2cdcc6c8ef2de2974777b360a95e9c420d292f8cb2a294189e
3
+ size 4496184560
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/model.safetensors.index.json ADDED
@@ -0,0 +1,727 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14382459968
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.mm_output_projector.0.bias": "model-00003-of-00003.safetensors",
297
+ "model.mm_output_projector.0.weight": "model-00003-of-00003.safetensors",
298
+ "model.mm_output_projector.2.bias": "model-00003-of-00003.safetensors",
299
+ "model.mm_output_projector.2.weight": "model-00003-of-00003.safetensors",
300
+ "model.mm_projector.0.bias": "model-00003-of-00003.safetensors",
301
+ "model.mm_projector.0.weight": "model-00003-of-00003.safetensors",
302
+ "model.mm_projector.2.bias": "model-00003-of-00003.safetensors",
303
+ "model.mm_projector.2.weight": "model-00003-of-00003.safetensors",
304
+ "model.norm.weight": "model-00003-of-00003.safetensors",
305
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00003-of-00003.safetensors",
306
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00003.safetensors",
307
+ "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00003.safetensors",
308
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00003.safetensors",
309
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00003.safetensors",
310
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00003.safetensors",
311
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00003.safetensors",
312
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00003.safetensors",
313
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00003.safetensors",
314
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00003.safetensors",
315
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00003.safetensors",
316
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
317
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
318
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
319
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
320
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
321
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
322
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
323
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
324
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00003.safetensors",
325
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00003.safetensors",
326
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00003.safetensors",
327
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00003.safetensors",
328
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00003.safetensors",
329
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00003.safetensors",
330
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00003.safetensors",
331
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00003.safetensors",
332
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
333
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
334
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
335
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
336
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
337
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
338
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
339
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
340
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00003.safetensors",
341
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00003.safetensors",
342
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00003.safetensors",
343
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00003.safetensors",
344
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00003.safetensors",
345
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00003.safetensors",
346
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00003.safetensors",
347
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00003.safetensors",
348
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
349
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
350
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
351
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
352
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
353
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
354
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
355
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
356
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00003.safetensors",
357
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00003.safetensors",
358
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00003.safetensors",
359
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00003.safetensors",
360
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00003.safetensors",
361
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00003.safetensors",
362
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00003.safetensors",
363
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00003.safetensors",
364
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
365
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
366
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
367
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
368
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
369
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
370
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
371
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
372
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00003.safetensors",
373
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00003.safetensors",
374
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00003.safetensors",
375
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00003.safetensors",
376
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00003.safetensors",
377
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00003.safetensors",
378
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00003.safetensors",
379
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00003.safetensors",
380
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
381
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
382
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
383
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
384
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
385
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
386
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
387
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
388
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00003.safetensors",
389
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00003.safetensors",
390
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00003.safetensors",
391
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00003.safetensors",
392
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00003.safetensors",
393
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00003.safetensors",
394
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00003.safetensors",
395
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00003.safetensors",
396
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
397
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
398
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
399
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
400
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
401
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
402
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
403
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
404
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00003.safetensors",
405
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00003.safetensors",
406
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00003.safetensors",
407
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00003.safetensors",
408
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00003.safetensors",
409
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00003.safetensors",
410
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00003.safetensors",
411
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00003.safetensors",
412
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
413
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
414
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
415
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
416
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
417
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
418
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
419
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
420
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00003.safetensors",
421
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00003.safetensors",
422
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00003.safetensors",
423
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00003.safetensors",
424
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00003.safetensors",
425
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00003.safetensors",
426
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00003.safetensors",
427
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00003.safetensors",
428
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
429
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
430
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
431
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
432
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
433
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
434
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
435
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
436
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00003.safetensors",
437
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00003.safetensors",
438
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00003.safetensors",
439
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00003.safetensors",
440
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00003.safetensors",
441
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00003.safetensors",
442
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00003.safetensors",
443
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00003.safetensors",
444
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
445
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
446
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
447
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
448
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
449
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
450
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
451
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
452
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00003.safetensors",
453
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00003.safetensors",
454
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00003.safetensors",
455
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00003.safetensors",
456
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00003.safetensors",
457
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00003.safetensors",
458
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00003.safetensors",
459
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00003.safetensors",
460
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
461
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
462
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
463
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
464
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
465
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
466
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
467
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
468
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00003.safetensors",
469
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00003.safetensors",
470
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00003.safetensors",
471
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00003.safetensors",
472
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00003.safetensors",
473
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00003.safetensors",
474
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00003.safetensors",
475
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00003.safetensors",
476
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
477
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
478
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
479
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
480
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
481
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
482
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
483
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
484
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00003.safetensors",
485
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00003.safetensors",
486
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00003.safetensors",
487
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00003.safetensors",
488
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00003.safetensors",
489
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00003.safetensors",
490
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00003.safetensors",
491
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00003.safetensors",
492
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
493
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
494
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
495
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
496
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
497
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
498
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
499
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
500
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00003.safetensors",
501
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00003.safetensors",
502
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00003.safetensors",
503
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00003.safetensors",
504
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00003.safetensors",
505
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00003.safetensors",
506
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00003.safetensors",
507
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00003.safetensors",
508
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
509
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
510
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
511
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
512
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
513
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
514
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
515
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
516
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00003.safetensors",
517
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00003.safetensors",
518
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00003.safetensors",
519
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00003.safetensors",
520
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00003.safetensors",
521
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00003.safetensors",
522
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00003.safetensors",
523
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00003.safetensors",
524
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
525
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
526
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
527
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
528
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
529
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
530
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
531
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
532
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00003.safetensors",
533
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00003.safetensors",
534
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00003-of-00003.safetensors",
535
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00003-of-00003.safetensors",
536
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00003.safetensors",
537
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00003.safetensors",
538
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00003-of-00003.safetensors",
539
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00003-of-00003.safetensors",
540
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
541
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
542
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
543
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
544
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
545
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
546
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
547
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
548
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00003-of-00003.safetensors",
549
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00003-of-00003.safetensors",
550
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00003-of-00003.safetensors",
551
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00003-of-00003.safetensors",
552
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00003-of-00003.safetensors",
553
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00003-of-00003.safetensors",
554
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00003-of-00003.safetensors",
555
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00003-of-00003.safetensors",
556
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
557
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
558
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
559
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
560
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
561
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
562
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
563
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
564
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00003-of-00003.safetensors",
565
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00003-of-00003.safetensors",
566
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00003-of-00003.safetensors",
567
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00003-of-00003.safetensors",
568
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00003-of-00003.safetensors",
569
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00003-of-00003.safetensors",
570
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00003-of-00003.safetensors",
571
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00003-of-00003.safetensors",
572
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
573
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
574
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
575
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
576
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
577
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
578
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
579
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
580
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00003-of-00003.safetensors",
581
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00003-of-00003.safetensors",
582
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00003-of-00003.safetensors",
583
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00003-of-00003.safetensors",
584
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00003-of-00003.safetensors",
585
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00003-of-00003.safetensors",
586
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00003-of-00003.safetensors",
587
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00003-of-00003.safetensors",
588
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
589
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
590
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
591
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
592
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
593
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
594
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
595
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
596
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00003-of-00003.safetensors",
597
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00003-of-00003.safetensors",
598
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00003-of-00003.safetensors",
599
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00003-of-00003.safetensors",
600
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00003-of-00003.safetensors",
601
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00003-of-00003.safetensors",
602
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00003-of-00003.safetensors",
603
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00003-of-00003.safetensors",
604
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
605
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
606
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
607
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
608
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
609
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
610
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
611
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
612
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00003.safetensors",
613
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00003.safetensors",
614
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00003.safetensors",
615
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00003.safetensors",
616
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00003.safetensors",
617
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00003.safetensors",
618
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00003.safetensors",
619
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00003.safetensors",
620
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
621
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
622
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
623
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
624
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
625
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
626
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
627
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
628
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00003.safetensors",
629
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00003.safetensors",
630
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00003.safetensors",
631
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00003.safetensors",
632
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00003.safetensors",
633
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00003.safetensors",
634
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00003.safetensors",
635
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00003.safetensors",
636
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
637
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
638
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
639
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
640
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
641
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
642
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
643
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
644
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00003.safetensors",
645
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00003.safetensors",
646
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00003.safetensors",
647
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00003.safetensors",
648
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00003.safetensors",
649
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00003.safetensors",
650
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00003.safetensors",
651
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00003.safetensors",
652
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
653
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
654
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
655
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
656
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
657
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
658
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
659
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
660
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00003.safetensors",
661
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00003.safetensors",
662
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00003.safetensors",
663
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00003.safetensors",
664
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00003.safetensors",
665
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00003.safetensors",
666
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00003.safetensors",
667
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00003.safetensors",
668
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
669
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
670
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
671
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
672
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
673
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
674
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
675
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
676
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00003.safetensors",
677
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00003.safetensors",
678
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00003.safetensors",
679
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00003.safetensors",
680
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00003.safetensors",
681
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00003.safetensors",
682
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00003.safetensors",
683
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00003.safetensors",
684
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
685
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
686
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
687
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
688
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
689
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
690
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
691
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
692
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00003.safetensors",
693
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00003.safetensors",
694
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00003.safetensors",
695
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00003.safetensors",
696
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00003.safetensors",
697
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00003.safetensors",
698
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00003.safetensors",
699
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00003.safetensors",
700
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
701
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
702
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
703
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
704
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
705
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
706
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
707
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
708
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00003.safetensors",
709
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00003.safetensors",
710
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00003.safetensors",
711
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00003.safetensors",
712
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00003.safetensors",
713
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00003.safetensors",
714
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00003.safetensors",
715
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00003.safetensors",
716
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
717
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
718
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
719
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
720
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
721
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
722
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
723
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
724
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00003-of-00003.safetensors",
725
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00003-of-00003.safetensors"
726
+ }
727
+ }
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 32768,
36
+ "pad_token": "<unk>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/trainer_state.json ADDED
@@ -0,0 +1,1467 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.0018037518037518038,
5
+ "eval_steps": 500,
6
+ "global_step": 25,
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,
13
+ "lm_loss": 1.2614614963531494,
14
+ "step": 0
15
+ },
16
+ {
17
+ "epoch": 0,
18
+ "img_loss": 885.3898315429688,
19
+ "step": 0
20
+ },
21
+ {
22
+ "epoch": 0,
23
+ "img_emb_dist": 0.9766795039176941,
24
+ "step": 0
25
+ },
26
+ {
27
+ "epoch": 0,
28
+ "img_divergence_loss": 0.0,
29
+ "step": 0
30
+ },
31
+ {
32
+ "activation_proximity_loss": 0.0,
33
+ "epoch": 0,
34
+ "step": 0
35
+ },
36
+ {
37
+ "epoch": 0,
38
+ "lm_loss": 2.016381025314331,
39
+ "step": 0
40
+ },
41
+ {
42
+ "epoch": 0,
43
+ "img_loss": 773.3865966796875,
44
+ "step": 0
45
+ },
46
+ {
47
+ "epoch": 0,
48
+ "img_emb_dist": 0.9774059057235718,
49
+ "step": 0
50
+ },
51
+ {
52
+ "epoch": 0,
53
+ "img_divergence_loss": 0.0,
54
+ "step": 0
55
+ },
56
+ {
57
+ "activation_proximity_loss": 0.0,
58
+ "epoch": 0,
59
+ "step": 0
60
+ },
61
+ {
62
+ "epoch": 7.215007215007215e-05,
63
+ "grad_norm": 4.514740996315013,
64
+ "learning_rate": 1e-05,
65
+ "loss": 1.355,
66
+ "step": 1
67
+ },
68
+ {
69
+ "epoch": 7.215007215007215e-05,
70
+ "lm_loss": 0.9086955189704895,
71
+ "step": 1
72
+ },
73
+ {
74
+ "epoch": 7.215007215007215e-05,
75
+ "img_loss": 819.3310546875,
76
+ "step": 1
77
+ },
78
+ {
79
+ "epoch": 7.215007215007215e-05,
80
+ "img_emb_dist": 0.9758827686309814,
81
+ "step": 1
82
+ },
83
+ {
84
+ "epoch": 7.215007215007215e-05,
85
+ "img_divergence_loss": 0.0,
86
+ "step": 1
87
+ },
88
+ {
89
+ "activation_proximity_loss": 0.0,
90
+ "epoch": 7.215007215007215e-05,
91
+ "step": 1
92
+ },
93
+ {
94
+ "epoch": 7.215007215007215e-05,
95
+ "lm_loss": 1.5197337865829468,
96
+ "step": 1
97
+ },
98
+ {
99
+ "epoch": 7.215007215007215e-05,
100
+ "img_loss": 791.0303955078125,
101
+ "step": 1
102
+ },
103
+ {
104
+ "epoch": 7.215007215007215e-05,
105
+ "img_emb_dist": 0.977044403553009,
106
+ "step": 1
107
+ },
108
+ {
109
+ "epoch": 7.215007215007215e-05,
110
+ "img_divergence_loss": 0.0,
111
+ "step": 1
112
+ },
113
+ {
114
+ "activation_proximity_loss": 0.0,
115
+ "epoch": 7.215007215007215e-05,
116
+ "step": 1
117
+ },
118
+ {
119
+ "epoch": 0.0001443001443001443,
120
+ "grad_norm": 5.1505158383620095,
121
+ "learning_rate": 9.957224306869053e-06,
122
+ "loss": 1.3439,
123
+ "step": 2
124
+ },
125
+ {
126
+ "epoch": 0.0001443001443001443,
127
+ "lm_loss": 1.1374003887176514,
128
+ "step": 2
129
+ },
130
+ {
131
+ "epoch": 0.0001443001443001443,
132
+ "img_loss": 765.0819702148438,
133
+ "step": 2
134
+ },
135
+ {
136
+ "epoch": 0.0001443001443001443,
137
+ "img_emb_dist": 0.974839985370636,
138
+ "step": 2
139
+ },
140
+ {
141
+ "epoch": 0.0001443001443001443,
142
+ "img_divergence_loss": 0.0,
143
+ "step": 2
144
+ },
145
+ {
146
+ "activation_proximity_loss": 0.0,
147
+ "epoch": 0.0001443001443001443,
148
+ "step": 2
149
+ },
150
+ {
151
+ "epoch": 0.0001443001443001443,
152
+ "lm_loss": 1.4494811296463013,
153
+ "step": 2
154
+ },
155
+ {
156
+ "epoch": 0.0001443001443001443,
157
+ "img_loss": 896.2612915039062,
158
+ "step": 2
159
+ },
160
+ {
161
+ "epoch": 0.0001443001443001443,
162
+ "img_emb_dist": 0.9770679473876953,
163
+ "step": 2
164
+ },
165
+ {
166
+ "epoch": 0.0001443001443001443,
167
+ "img_divergence_loss": 0.0,
168
+ "step": 2
169
+ },
170
+ {
171
+ "activation_proximity_loss": 0.0,
172
+ "epoch": 0.0001443001443001443,
173
+ "step": 2
174
+ },
175
+ {
176
+ "epoch": 0.00021645021645021645,
177
+ "grad_norm": 3.2348276164051617,
178
+ "learning_rate": 9.829629131445342e-06,
179
+ "loss": 1.3423,
180
+ "step": 3
181
+ },
182
+ {
183
+ "epoch": 0.00021645021645021645,
184
+ "lm_loss": 0.6548511981964111,
185
+ "step": 3
186
+ },
187
+ {
188
+ "epoch": 0.00021645021645021645,
189
+ "img_loss": 813.9419555664062,
190
+ "step": 3
191
+ },
192
+ {
193
+ "epoch": 0.00021645021645021645,
194
+ "img_emb_dist": 0.976345956325531,
195
+ "step": 3
196
+ },
197
+ {
198
+ "epoch": 0.00021645021645021645,
199
+ "img_divergence_loss": 0.0,
200
+ "step": 3
201
+ },
202
+ {
203
+ "activation_proximity_loss": 0.0,
204
+ "epoch": 0.00021645021645021645,
205
+ "step": 3
206
+ },
207
+ {
208
+ "epoch": 0.00021645021645021645,
209
+ "lm_loss": 1.1054067611694336,
210
+ "step": 3
211
+ },
212
+ {
213
+ "epoch": 0.00021645021645021645,
214
+ "img_loss": 788.4612426757812,
215
+ "step": 3
216
+ },
217
+ {
218
+ "epoch": 0.00021645021645021645,
219
+ "img_emb_dist": 0.9759064316749573,
220
+ "step": 3
221
+ },
222
+ {
223
+ "epoch": 0.00021645021645021645,
224
+ "img_divergence_loss": 0.0,
225
+ "step": 3
226
+ },
227
+ {
228
+ "activation_proximity_loss": 0.0,
229
+ "epoch": 0.00021645021645021645,
230
+ "step": 3
231
+ },
232
+ {
233
+ "epoch": 0.0002886002886002886,
234
+ "grad_norm": 3.171434499042359,
235
+ "learning_rate": 9.619397662556434e-06,
236
+ "loss": 1.2492,
237
+ "step": 4
238
+ },
239
+ {
240
+ "epoch": 0.0002886002886002886,
241
+ "lm_loss": 0.8177642822265625,
242
+ "step": 4
243
+ },
244
+ {
245
+ "epoch": 0.0002886002886002886,
246
+ "img_loss": 861.1069946289062,
247
+ "step": 4
248
+ },
249
+ {
250
+ "epoch": 0.0002886002886002886,
251
+ "img_emb_dist": 0.9751406311988831,
252
+ "step": 4
253
+ },
254
+ {
255
+ "epoch": 0.0002886002886002886,
256
+ "img_divergence_loss": 0.0,
257
+ "step": 4
258
+ },
259
+ {
260
+ "activation_proximity_loss": 0.0,
261
+ "epoch": 0.0002886002886002886,
262
+ "step": 4
263
+ },
264
+ {
265
+ "epoch": 0.0002886002886002886,
266
+ "lm_loss": 0.9702979922294617,
267
+ "step": 4
268
+ },
269
+ {
270
+ "epoch": 0.0002886002886002886,
271
+ "img_loss": 802.642578125,
272
+ "step": 4
273
+ },
274
+ {
275
+ "epoch": 0.0002886002886002886,
276
+ "img_emb_dist": 0.9762476682662964,
277
+ "step": 4
278
+ },
279
+ {
280
+ "epoch": 0.0002886002886002886,
281
+ "img_divergence_loss": 0.0,
282
+ "step": 4
283
+ },
284
+ {
285
+ "activation_proximity_loss": 0.0,
286
+ "epoch": 0.0002886002886002886,
287
+ "step": 4
288
+ },
289
+ {
290
+ "epoch": 0.00036075036075036075,
291
+ "grad_norm": 2.949350829936257,
292
+ "learning_rate": 9.330127018922195e-06,
293
+ "loss": 1.1519,
294
+ "step": 5
295
+ },
296
+ {
297
+ "epoch": 0.00036075036075036075,
298
+ "lm_loss": 1.165309190750122,
299
+ "step": 5
300
+ },
301
+ {
302
+ "epoch": 0.00036075036075036075,
303
+ "img_loss": 825.00634765625,
304
+ "step": 5
305
+ },
306
+ {
307
+ "epoch": 0.00036075036075036075,
308
+ "img_emb_dist": 0.9722062349319458,
309
+ "step": 5
310
+ },
311
+ {
312
+ "epoch": 0.00036075036075036075,
313
+ "img_divergence_loss": 0.0,
314
+ "step": 5
315
+ },
316
+ {
317
+ "activation_proximity_loss": 0.0,
318
+ "epoch": 0.00036075036075036075,
319
+ "step": 5
320
+ },
321
+ {
322
+ "epoch": 0.00036075036075036075,
323
+ "lm_loss": 1.2138742208480835,
324
+ "step": 5
325
+ },
326
+ {
327
+ "epoch": 0.00036075036075036075,
328
+ "img_loss": 832.3601684570312,
329
+ "step": 5
330
+ },
331
+ {
332
+ "epoch": 0.00036075036075036075,
333
+ "img_emb_dist": 0.9731454253196716,
334
+ "step": 5
335
+ },
336
+ {
337
+ "epoch": 0.00036075036075036075,
338
+ "img_divergence_loss": 0.0,
339
+ "step": 5
340
+ },
341
+ {
342
+ "activation_proximity_loss": 0.0,
343
+ "epoch": 0.00036075036075036075,
344
+ "step": 5
345
+ },
346
+ {
347
+ "epoch": 0.0004329004329004329,
348
+ "grad_norm": 2.729440391060018,
349
+ "learning_rate": 8.966766701456177e-06,
350
+ "loss": 1.268,
351
+ "step": 6
352
+ },
353
+ {
354
+ "epoch": 0.0004329004329004329,
355
+ "lm_loss": 1.2445625066757202,
356
+ "step": 6
357
+ },
358
+ {
359
+ "epoch": 0.0004329004329004329,
360
+ "img_loss": 815.9379272460938,
361
+ "step": 6
362
+ },
363
+ {
364
+ "epoch": 0.0004329004329004329,
365
+ "img_emb_dist": 0.9684582948684692,
366
+ "step": 6
367
+ },
368
+ {
369
+ "epoch": 0.0004329004329004329,
370
+ "img_divergence_loss": 0.0,
371
+ "step": 6
372
+ },
373
+ {
374
+ "activation_proximity_loss": 0.0,
375
+ "epoch": 0.0004329004329004329,
376
+ "step": 6
377
+ },
378
+ {
379
+ "epoch": 0.0004329004329004329,
380
+ "lm_loss": 1.0895243883132935,
381
+ "step": 6
382
+ },
383
+ {
384
+ "epoch": 0.0004329004329004329,
385
+ "img_loss": 864.1802978515625,
386
+ "step": 6
387
+ },
388
+ {
389
+ "epoch": 0.0004329004329004329,
390
+ "img_emb_dist": 0.9722574949264526,
391
+ "step": 6
392
+ },
393
+ {
394
+ "epoch": 0.0004329004329004329,
395
+ "img_divergence_loss": 0.0,
396
+ "step": 6
397
+ },
398
+ {
399
+ "activation_proximity_loss": 0.0,
400
+ "epoch": 0.0004329004329004329,
401
+ "step": 6
402
+ },
403
+ {
404
+ "epoch": 0.000505050505050505,
405
+ "grad_norm": 2.38479609428068,
406
+ "learning_rate": 8.535533905932739e-06,
407
+ "loss": 1.1839,
408
+ "step": 7
409
+ },
410
+ {
411
+ "epoch": 0.000505050505050505,
412
+ "lm_loss": 1.0988446474075317,
413
+ "step": 7
414
+ },
415
+ {
416
+ "epoch": 0.000505050505050505,
417
+ "img_loss": 898.799072265625,
418
+ "step": 7
419
+ },
420
+ {
421
+ "epoch": 0.000505050505050505,
422
+ "img_emb_dist": 0.971565842628479,
423
+ "step": 7
424
+ },
425
+ {
426
+ "epoch": 0.000505050505050505,
427
+ "img_divergence_loss": 0.0,
428
+ "step": 7
429
+ },
430
+ {
431
+ "activation_proximity_loss": 0.0,
432
+ "epoch": 0.000505050505050505,
433
+ "step": 7
434
+ },
435
+ {
436
+ "epoch": 0.000505050505050505,
437
+ "lm_loss": 0.9859169721603394,
438
+ "step": 7
439
+ },
440
+ {
441
+ "epoch": 0.000505050505050505,
442
+ "img_loss": 845.7677001953125,
443
+ "step": 7
444
+ },
445
+ {
446
+ "epoch": 0.000505050505050505,
447
+ "img_emb_dist": 0.9704997539520264,
448
+ "step": 7
449
+ },
450
+ {
451
+ "epoch": 0.000505050505050505,
452
+ "img_divergence_loss": 0.0,
453
+ "step": 7
454
+ },
455
+ {
456
+ "activation_proximity_loss": 0.0,
457
+ "epoch": 0.000505050505050505,
458
+ "step": 7
459
+ },
460
+ {
461
+ "epoch": 0.0005772005772005772,
462
+ "grad_norm": 2.2573539550373374,
463
+ "learning_rate": 8.043807145043604e-06,
464
+ "loss": 1.1728,
465
+ "step": 8
466
+ },
467
+ {
468
+ "epoch": 0.0005772005772005772,
469
+ "lm_loss": 0.696566641330719,
470
+ "step": 8
471
+ },
472
+ {
473
+ "epoch": 0.0005772005772005772,
474
+ "img_loss": 868.515869140625,
475
+ "step": 8
476
+ },
477
+ {
478
+ "epoch": 0.0005772005772005772,
479
+ "img_emb_dist": 0.9680835604667664,
480
+ "step": 8
481
+ },
482
+ {
483
+ "epoch": 0.0005772005772005772,
484
+ "img_divergence_loss": 0.0,
485
+ "step": 8
486
+ },
487
+ {
488
+ "activation_proximity_loss": 0.0,
489
+ "epoch": 0.0005772005772005772,
490
+ "step": 8
491
+ },
492
+ {
493
+ "epoch": 0.0005772005772005772,
494
+ "lm_loss": 1.236984372138977,
495
+ "step": 8
496
+ },
497
+ {
498
+ "epoch": 0.0005772005772005772,
499
+ "img_loss": 954.5865478515625,
500
+ "step": 8
501
+ },
502
+ {
503
+ "epoch": 0.0005772005772005772,
504
+ "img_emb_dist": 0.9685915112495422,
505
+ "step": 8
506
+ },
507
+ {
508
+ "epoch": 0.0005772005772005772,
509
+ "img_divergence_loss": 0.0,
510
+ "step": 8
511
+ },
512
+ {
513
+ "activation_proximity_loss": 0.0,
514
+ "epoch": 0.0005772005772005772,
515
+ "step": 8
516
+ },
517
+ {
518
+ "epoch": 0.0006493506493506494,
519
+ "grad_norm": 2.1746889923184933,
520
+ "learning_rate": 7.500000000000001e-06,
521
+ "loss": 1.2411,
522
+ "step": 9
523
+ },
524
+ {
525
+ "epoch": 0.0006493506493506494,
526
+ "lm_loss": 0.8733236789703369,
527
+ "step": 9
528
+ },
529
+ {
530
+ "epoch": 0.0006493506493506494,
531
+ "img_loss": 889.0441284179688,
532
+ "step": 9
533
+ },
534
+ {
535
+ "epoch": 0.0006493506493506494,
536
+ "img_emb_dist": 0.9652532339096069,
537
+ "step": 9
538
+ },
539
+ {
540
+ "epoch": 0.0006493506493506494,
541
+ "img_divergence_loss": 0.0,
542
+ "step": 9
543
+ },
544
+ {
545
+ "activation_proximity_loss": 0.0,
546
+ "epoch": 0.0006493506493506494,
547
+ "step": 9
548
+ },
549
+ {
550
+ "epoch": 0.0006493506493506494,
551
+ "lm_loss": 1.2848918437957764,
552
+ "step": 9
553
+ },
554
+ {
555
+ "epoch": 0.0006493506493506494,
556
+ "img_loss": 1006.572021484375,
557
+ "step": 9
558
+ },
559
+ {
560
+ "epoch": 0.0006493506493506494,
561
+ "img_emb_dist": 0.9681165814399719,
562
+ "step": 9
563
+ },
564
+ {
565
+ "epoch": 0.0006493506493506494,
566
+ "img_divergence_loss": 0.0,
567
+ "step": 9
568
+ },
569
+ {
570
+ "activation_proximity_loss": 0.0,
571
+ "epoch": 0.0006493506493506494,
572
+ "step": 9
573
+ },
574
+ {
575
+ "epoch": 0.0007215007215007215,
576
+ "grad_norm": 2.511095764027252,
577
+ "learning_rate": 6.913417161825449e-06,
578
+ "loss": 1.0717,
579
+ "step": 10
580
+ },
581
+ {
582
+ "epoch": 0.0007215007215007215,
583
+ "lm_loss": 1.1464320421218872,
584
+ "step": 10
585
+ },
586
+ {
587
+ "epoch": 0.0007215007215007215,
588
+ "img_loss": 986.5391235351562,
589
+ "step": 10
590
+ },
591
+ {
592
+ "epoch": 0.0007215007215007215,
593
+ "img_emb_dist": 0.9634599685668945,
594
+ "step": 10
595
+ },
596
+ {
597
+ "epoch": 0.0007215007215007215,
598
+ "img_divergence_loss": 0.0,
599
+ "step": 10
600
+ },
601
+ {
602
+ "activation_proximity_loss": 0.0,
603
+ "epoch": 0.0007215007215007215,
604
+ "step": 10
605
+ },
606
+ {
607
+ "epoch": 0.0007215007215007215,
608
+ "lm_loss": 1.1133934259414673,
609
+ "step": 10
610
+ },
611
+ {
612
+ "epoch": 0.0007215007215007215,
613
+ "img_loss": 958.0040893554688,
614
+ "step": 10
615
+ },
616
+ {
617
+ "epoch": 0.0007215007215007215,
618
+ "img_emb_dist": 0.9663693308830261,
619
+ "step": 10
620
+ },
621
+ {
622
+ "epoch": 0.0007215007215007215,
623
+ "img_divergence_loss": 0.0,
624
+ "step": 10
625
+ },
626
+ {
627
+ "activation_proximity_loss": 0.0,
628
+ "epoch": 0.0007215007215007215,
629
+ "step": 10
630
+ },
631
+ {
632
+ "epoch": 0.0007936507936507937,
633
+ "grad_norm": 2.5748822553247654,
634
+ "learning_rate": 6.294095225512604e-06,
635
+ "loss": 1.167,
636
+ "step": 11
637
+ },
638
+ {
639
+ "epoch": 0.0007936507936507937,
640
+ "lm_loss": 0.33026137948036194,
641
+ "step": 11
642
+ },
643
+ {
644
+ "epoch": 0.0007936507936507937,
645
+ "img_loss": 954.0510864257812,
646
+ "step": 11
647
+ },
648
+ {
649
+ "epoch": 0.0007936507936507937,
650
+ "img_emb_dist": 0.9645818471908569,
651
+ "step": 11
652
+ },
653
+ {
654
+ "epoch": 0.0007936507936507937,
655
+ "img_divergence_loss": 0.0,
656
+ "step": 11
657
+ },
658
+ {
659
+ "activation_proximity_loss": 0.0,
660
+ "epoch": 0.0007936507936507937,
661
+ "step": 11
662
+ },
663
+ {
664
+ "epoch": 0.0007936507936507937,
665
+ "lm_loss": 0.9683809280395508,
666
+ "step": 11
667
+ },
668
+ {
669
+ "epoch": 0.0007936507936507937,
670
+ "img_loss": 965.5768432617188,
671
+ "step": 11
672
+ },
673
+ {
674
+ "epoch": 0.0007936507936507937,
675
+ "img_emb_dist": 0.9631333351135254,
676
+ "step": 11
677
+ },
678
+ {
679
+ "epoch": 0.0007936507936507937,
680
+ "img_divergence_loss": 0.0,
681
+ "step": 11
682
+ },
683
+ {
684
+ "activation_proximity_loss": 0.0,
685
+ "epoch": 0.0007936507936507937,
686
+ "step": 11
687
+ },
688
+ {
689
+ "epoch": 0.0008658008658008658,
690
+ "grad_norm": 2.3558037289964884,
691
+ "learning_rate": 5.65263096110026e-06,
692
+ "loss": 1.0099,
693
+ "step": 12
694
+ },
695
+ {
696
+ "epoch": 0.0008658008658008658,
697
+ "lm_loss": 1.2899165153503418,
698
+ "step": 12
699
+ },
700
+ {
701
+ "epoch": 0.0008658008658008658,
702
+ "img_loss": 941.6240844726562,
703
+ "step": 12
704
+ },
705
+ {
706
+ "epoch": 0.0008658008658008658,
707
+ "img_emb_dist": 0.9658195376396179,
708
+ "step": 12
709
+ },
710
+ {
711
+ "epoch": 0.0008658008658008658,
712
+ "img_divergence_loss": 0.0,
713
+ "step": 12
714
+ },
715
+ {
716
+ "activation_proximity_loss": 0.0,
717
+ "epoch": 0.0008658008658008658,
718
+ "step": 12
719
+ },
720
+ {
721
+ "epoch": 0.0008658008658008658,
722
+ "lm_loss": 1.1860413551330566,
723
+ "step": 12
724
+ },
725
+ {
726
+ "epoch": 0.0008658008658008658,
727
+ "img_loss": 924.8343505859375,
728
+ "step": 12
729
+ },
730
+ {
731
+ "epoch": 0.0008658008658008658,
732
+ "img_emb_dist": 0.9628998041152954,
733
+ "step": 12
734
+ },
735
+ {
736
+ "epoch": 0.0008658008658008658,
737
+ "img_divergence_loss": 0.0,
738
+ "step": 12
739
+ },
740
+ {
741
+ "activation_proximity_loss": 0.0,
742
+ "epoch": 0.0008658008658008658,
743
+ "step": 12
744
+ },
745
+ {
746
+ "epoch": 0.000937950937950938,
747
+ "grad_norm": 2.1202341199517596,
748
+ "learning_rate": 5e-06,
749
+ "loss": 1.1215,
750
+ "step": 13
751
+ },
752
+ {
753
+ "epoch": 0.000937950937950938,
754
+ "lm_loss": 1.0426427125930786,
755
+ "step": 13
756
+ },
757
+ {
758
+ "epoch": 0.000937950937950938,
759
+ "img_loss": 944.3718872070312,
760
+ "step": 13
761
+ },
762
+ {
763
+ "epoch": 0.000937950937950938,
764
+ "img_emb_dist": 0.9633188247680664,
765
+ "step": 13
766
+ },
767
+ {
768
+ "epoch": 0.000937950937950938,
769
+ "img_divergence_loss": 0.0,
770
+ "step": 13
771
+ },
772
+ {
773
+ "activation_proximity_loss": 0.0,
774
+ "epoch": 0.000937950937950938,
775
+ "step": 13
776
+ },
777
+ {
778
+ "epoch": 0.000937950937950938,
779
+ "lm_loss": 1.2792726755142212,
780
+ "step": 13
781
+ },
782
+ {
783
+ "epoch": 0.000937950937950938,
784
+ "img_loss": 965.3296508789062,
785
+ "step": 13
786
+ },
787
+ {
788
+ "epoch": 0.000937950937950938,
789
+ "img_emb_dist": 0.9660452604293823,
790
+ "step": 13
791
+ },
792
+ {
793
+ "epoch": 0.000937950937950938,
794
+ "img_divergence_loss": 0.0,
795
+ "step": 13
796
+ },
797
+ {
798
+ "activation_proximity_loss": 0.0,
799
+ "epoch": 0.000937950937950938,
800
+ "step": 13
801
+ },
802
+ {
803
+ "epoch": 0.00101010101010101,
804
+ "grad_norm": 2.4173231793409236,
805
+ "learning_rate": 4.347369038899744e-06,
806
+ "loss": 1.1432,
807
+ "step": 14
808
+ },
809
+ {
810
+ "epoch": 0.00101010101010101,
811
+ "lm_loss": 0.46831265091896057,
812
+ "step": 14
813
+ },
814
+ {
815
+ "epoch": 0.00101010101010101,
816
+ "img_loss": 0.0,
817
+ "step": 14
818
+ },
819
+ {
820
+ "epoch": 0.00101010101010101,
821
+ "img_emb_dist": 0.0,
822
+ "step": 14
823
+ },
824
+ {
825
+ "epoch": 0.00101010101010101,
826
+ "img_divergence_loss": 0.0,
827
+ "step": 14
828
+ },
829
+ {
830
+ "activation_proximity_loss": 0.0,
831
+ "epoch": 0.00101010101010101,
832
+ "step": 14
833
+ },
834
+ {
835
+ "epoch": 0.00101010101010101,
836
+ "lm_loss": 0.3712627589702606,
837
+ "step": 14
838
+ },
839
+ {
840
+ "epoch": 0.00101010101010101,
841
+ "img_loss": 0.0,
842
+ "step": 14
843
+ },
844
+ {
845
+ "epoch": 0.00101010101010101,
846
+ "img_emb_dist": 0.0,
847
+ "step": 14
848
+ },
849
+ {
850
+ "epoch": 0.00101010101010101,
851
+ "img_divergence_loss": 0.0,
852
+ "step": 14
853
+ },
854
+ {
855
+ "activation_proximity_loss": 0.0,
856
+ "epoch": 0.00101010101010101,
857
+ "step": 14
858
+ },
859
+ {
860
+ "epoch": 0.0010822510822510823,
861
+ "grad_norm": 1.6914646599869387,
862
+ "learning_rate": 3.705904774487396e-06,
863
+ "loss": 0.3677,
864
+ "step": 15
865
+ },
866
+ {
867
+ "epoch": 0.0010822510822510823,
868
+ "lm_loss": 0.6287497878074646,
869
+ "step": 15
870
+ },
871
+ {
872
+ "epoch": 0.0010822510822510823,
873
+ "img_loss": 0.0,
874
+ "step": 15
875
+ },
876
+ {
877
+ "epoch": 0.0010822510822510823,
878
+ "img_emb_dist": 0.0,
879
+ "step": 15
880
+ },
881
+ {
882
+ "epoch": 0.0010822510822510823,
883
+ "img_divergence_loss": 0.0,
884
+ "step": 15
885
+ },
886
+ {
887
+ "activation_proximity_loss": 0.0,
888
+ "epoch": 0.0010822510822510823,
889
+ "step": 15
890
+ },
891
+ {
892
+ "epoch": 0.0010822510822510823,
893
+ "lm_loss": 0.2971065044403076,
894
+ "step": 15
895
+ },
896
+ {
897
+ "epoch": 0.0010822510822510823,
898
+ "img_loss": 0.0,
899
+ "step": 15
900
+ },
901
+ {
902
+ "epoch": 0.0010822510822510823,
903
+ "img_emb_dist": 0.0,
904
+ "step": 15
905
+ },
906
+ {
907
+ "epoch": 0.0010822510822510823,
908
+ "img_divergence_loss": 0.0,
909
+ "step": 15
910
+ },
911
+ {
912
+ "activation_proximity_loss": 0.0,
913
+ "epoch": 0.0010822510822510823,
914
+ "step": 15
915
+ },
916
+ {
917
+ "epoch": 0.0011544011544011544,
918
+ "grad_norm": 1.757312324226043,
919
+ "learning_rate": 3.0865828381745515e-06,
920
+ "loss": 0.4001,
921
+ "step": 16
922
+ },
923
+ {
924
+ "epoch": 0.0011544011544011544,
925
+ "lm_loss": 1.188820719718933,
926
+ "step": 16
927
+ },
928
+ {
929
+ "epoch": 0.0011544011544011544,
930
+ "img_loss": 990.9677734375,
931
+ "step": 16
932
+ },
933
+ {
934
+ "epoch": 0.0011544011544011544,
935
+ "img_emb_dist": 0.9642726182937622,
936
+ "step": 16
937
+ },
938
+ {
939
+ "epoch": 0.0011544011544011544,
940
+ "img_divergence_loss": 0.0,
941
+ "step": 16
942
+ },
943
+ {
944
+ "activation_proximity_loss": 0.0,
945
+ "epoch": 0.0011544011544011544,
946
+ "step": 16
947
+ },
948
+ {
949
+ "epoch": 0.0011544011544011544,
950
+ "lm_loss": 1.2861636877059937,
951
+ "step": 16
952
+ },
953
+ {
954
+ "epoch": 0.0011544011544011544,
955
+ "img_loss": 939.5360717773438,
956
+ "step": 16
957
+ },
958
+ {
959
+ "epoch": 0.0011544011544011544,
960
+ "img_emb_dist": 0.9632103443145752,
961
+ "step": 16
962
+ },
963
+ {
964
+ "epoch": 0.0011544011544011544,
965
+ "img_divergence_loss": 0.0,
966
+ "step": 16
967
+ },
968
+ {
969
+ "activation_proximity_loss": 0.0,
970
+ "epoch": 0.0011544011544011544,
971
+ "step": 16
972
+ },
973
+ {
974
+ "epoch": 0.0012265512265512266,
975
+ "grad_norm": 2.431545947889518,
976
+ "learning_rate": 2.5000000000000015e-06,
977
+ "loss": 1.1103,
978
+ "step": 17
979
+ },
980
+ {
981
+ "epoch": 0.0012265512265512266,
982
+ "lm_loss": 1.3463515043258667,
983
+ "step": 17
984
+ },
985
+ {
986
+ "epoch": 0.0012265512265512266,
987
+ "img_loss": 1010.4727783203125,
988
+ "step": 17
989
+ },
990
+ {
991
+ "epoch": 0.0012265512265512266,
992
+ "img_emb_dist": 0.9649385213851929,
993
+ "step": 17
994
+ },
995
+ {
996
+ "epoch": 0.0012265512265512266,
997
+ "img_divergence_loss": 0.0,
998
+ "step": 17
999
+ },
1000
+ {
1001
+ "activation_proximity_loss": 0.0,
1002
+ "epoch": 0.0012265512265512266,
1003
+ "step": 17
1004
+ },
1005
+ {
1006
+ "epoch": 0.0012265512265512266,
1007
+ "lm_loss": 0.9498377442359924,
1008
+ "step": 17
1009
+ },
1010
+ {
1011
+ "epoch": 0.0012265512265512266,
1012
+ "img_loss": 1033.6485595703125,
1013
+ "step": 17
1014
+ },
1015
+ {
1016
+ "epoch": 0.0012265512265512266,
1017
+ "img_emb_dist": 0.963358461856842,
1018
+ "step": 17
1019
+ },
1020
+ {
1021
+ "epoch": 0.0012265512265512266,
1022
+ "img_divergence_loss": 0.0,
1023
+ "step": 17
1024
+ },
1025
+ {
1026
+ "activation_proximity_loss": 0.0,
1027
+ "epoch": 0.0012265512265512266,
1028
+ "step": 17
1029
+ },
1030
+ {
1031
+ "epoch": 0.0012987012987012987,
1032
+ "grad_norm": 2.426061656297513,
1033
+ "learning_rate": 1.956192854956397e-06,
1034
+ "loss": 1.166,
1035
+ "step": 18
1036
+ },
1037
+ {
1038
+ "epoch": 0.0012987012987012987,
1039
+ "lm_loss": 1.0570887327194214,
1040
+ "step": 18
1041
+ },
1042
+ {
1043
+ "epoch": 0.0012987012987012987,
1044
+ "img_loss": 934.938232421875,
1045
+ "step": 18
1046
+ },
1047
+ {
1048
+ "epoch": 0.0012987012987012987,
1049
+ "img_emb_dist": 0.9629301428794861,
1050
+ "step": 18
1051
+ },
1052
+ {
1053
+ "epoch": 0.0012987012987012987,
1054
+ "img_divergence_loss": 0.0,
1055
+ "step": 18
1056
+ },
1057
+ {
1058
+ "activation_proximity_loss": 0.0,
1059
+ "epoch": 0.0012987012987012987,
1060
+ "step": 18
1061
+ },
1062
+ {
1063
+ "epoch": 0.0012987012987012987,
1064
+ "lm_loss": 0.8632858395576477,
1065
+ "step": 18
1066
+ },
1067
+ {
1068
+ "epoch": 0.0012987012987012987,
1069
+ "img_loss": 1023.4631958007812,
1070
+ "step": 18
1071
+ },
1072
+ {
1073
+ "epoch": 0.0012987012987012987,
1074
+ "img_emb_dist": 0.9655637741088867,
1075
+ "step": 18
1076
+ },
1077
+ {
1078
+ "epoch": 0.0012987012987012987,
1079
+ "img_divergence_loss": 0.0,
1080
+ "step": 18
1081
+ },
1082
+ {
1083
+ "activation_proximity_loss": 0.0,
1084
+ "epoch": 0.0012987012987012987,
1085
+ "step": 18
1086
+ },
1087
+ {
1088
+ "epoch": 0.0013708513708513709,
1089
+ "grad_norm": 2.1054422816169414,
1090
+ "learning_rate": 1.4644660940672628e-06,
1091
+ "loss": 1.0352,
1092
+ "step": 19
1093
+ },
1094
+ {
1095
+ "epoch": 0.0013708513708513709,
1096
+ "lm_loss": 0.4083617031574249,
1097
+ "step": 19
1098
+ },
1099
+ {
1100
+ "epoch": 0.0013708513708513709,
1101
+ "img_loss": 1058.53857421875,
1102
+ "step": 19
1103
+ },
1104
+ {
1105
+ "epoch": 0.0013708513708513709,
1106
+ "img_emb_dist": 0.9631701707839966,
1107
+ "step": 19
1108
+ },
1109
+ {
1110
+ "epoch": 0.0013708513708513709,
1111
+ "img_divergence_loss": 0.0,
1112
+ "step": 19
1113
+ },
1114
+ {
1115
+ "activation_proximity_loss": 0.0,
1116
+ "epoch": 0.0013708513708513709,
1117
+ "step": 19
1118
+ },
1119
+ {
1120
+ "epoch": 0.0013708513708513709,
1121
+ "lm_loss": 0.7984881401062012,
1122
+ "step": 19
1123
+ },
1124
+ {
1125
+ "epoch": 0.0013708513708513709,
1126
+ "img_loss": 1036.539794921875,
1127
+ "step": 19
1128
+ },
1129
+ {
1130
+ "epoch": 0.0013708513708513709,
1131
+ "img_emb_dist": 0.9626760482788086,
1132
+ "step": 19
1133
+ },
1134
+ {
1135
+ "epoch": 0.0013708513708513709,
1136
+ "img_divergence_loss": 0.0,
1137
+ "step": 19
1138
+ },
1139
+ {
1140
+ "activation_proximity_loss": 0.0,
1141
+ "epoch": 0.0013708513708513709,
1142
+ "step": 19
1143
+ },
1144
+ {
1145
+ "epoch": 0.001443001443001443,
1146
+ "grad_norm": 1.9384436653640056,
1147
+ "learning_rate": 1.0332332985438248e-06,
1148
+ "loss": 0.9994,
1149
+ "step": 20
1150
+ },
1151
+ {
1152
+ "epoch": 0.001443001443001443,
1153
+ "lm_loss": 0.9373359680175781,
1154
+ "step": 20
1155
+ },
1156
+ {
1157
+ "epoch": 0.001443001443001443,
1158
+ "img_loss": 1029.9630126953125,
1159
+ "step": 20
1160
+ },
1161
+ {
1162
+ "epoch": 0.001443001443001443,
1163
+ "img_emb_dist": 0.9650158882141113,
1164
+ "step": 20
1165
+ },
1166
+ {
1167
+ "epoch": 0.001443001443001443,
1168
+ "img_divergence_loss": 0.0,
1169
+ "step": 20
1170
+ },
1171
+ {
1172
+ "activation_proximity_loss": 0.0,
1173
+ "epoch": 0.001443001443001443,
1174
+ "step": 20
1175
+ },
1176
+ {
1177
+ "epoch": 0.001443001443001443,
1178
+ "lm_loss": 1.0467417240142822,
1179
+ "step": 20
1180
+ },
1181
+ {
1182
+ "epoch": 0.001443001443001443,
1183
+ "img_loss": 972.8388061523438,
1184
+ "step": 20
1185
+ },
1186
+ {
1187
+ "epoch": 0.001443001443001443,
1188
+ "img_emb_dist": 0.9657303094863892,
1189
+ "step": 20
1190
+ },
1191
+ {
1192
+ "epoch": 0.001443001443001443,
1193
+ "img_divergence_loss": 0.0,
1194
+ "step": 20
1195
+ },
1196
+ {
1197
+ "activation_proximity_loss": 0.0,
1198
+ "epoch": 0.001443001443001443,
1199
+ "step": 20
1200
+ },
1201
+ {
1202
+ "epoch": 0.0015151515151515152,
1203
+ "grad_norm": 2.4290960365669556,
1204
+ "learning_rate": 6.698729810778065e-07,
1205
+ "loss": 1.0614,
1206
+ "step": 21
1207
+ },
1208
+ {
1209
+ "epoch": 0.0015151515151515152,
1210
+ "lm_loss": 1.1180315017700195,
1211
+ "step": 21
1212
+ },
1213
+ {
1214
+ "epoch": 0.0015151515151515152,
1215
+ "img_loss": 1042.491455078125,
1216
+ "step": 21
1217
+ },
1218
+ {
1219
+ "epoch": 0.0015151515151515152,
1220
+ "img_emb_dist": 0.9618048667907715,
1221
+ "step": 21
1222
+ },
1223
+ {
1224
+ "epoch": 0.0015151515151515152,
1225
+ "img_divergence_loss": 0.0,
1226
+ "step": 21
1227
+ },
1228
+ {
1229
+ "activation_proximity_loss": 0.0,
1230
+ "epoch": 0.0015151515151515152,
1231
+ "step": 21
1232
+ },
1233
+ {
1234
+ "epoch": 0.0015151515151515152,
1235
+ "lm_loss": 1.1421946287155151,
1236
+ "step": 21
1237
+ },
1238
+ {
1239
+ "epoch": 0.0015151515151515152,
1240
+ "img_loss": 1001.2096557617188,
1241
+ "step": 21
1242
+ },
1243
+ {
1244
+ "epoch": 0.0015151515151515152,
1245
+ "img_emb_dist": 0.9632893800735474,
1246
+ "step": 21
1247
+ },
1248
+ {
1249
+ "epoch": 0.0015151515151515152,
1250
+ "img_divergence_loss": 0.0,
1251
+ "step": 21
1252
+ },
1253
+ {
1254
+ "activation_proximity_loss": 0.0,
1255
+ "epoch": 0.0015151515151515152,
1256
+ "step": 21
1257
+ },
1258
+ {
1259
+ "epoch": 0.0015873015873015873,
1260
+ "grad_norm": 3.5959413287337085,
1261
+ "learning_rate": 3.8060233744356634e-07,
1262
+ "loss": 1.1993,
1263
+ "step": 22
1264
+ },
1265
+ {
1266
+ "epoch": 0.0015873015873015873,
1267
+ "lm_loss": 0.8462453484535217,
1268
+ "step": 22
1269
+ },
1270
+ {
1271
+ "epoch": 0.0015873015873015873,
1272
+ "img_loss": 924.993408203125,
1273
+ "step": 22
1274
+ },
1275
+ {
1276
+ "epoch": 0.0015873015873015873,
1277
+ "img_emb_dist": 0.9621605277061462,
1278
+ "step": 22
1279
+ },
1280
+ {
1281
+ "epoch": 0.0015873015873015873,
1282
+ "img_divergence_loss": 0.0,
1283
+ "step": 22
1284
+ },
1285
+ {
1286
+ "activation_proximity_loss": 0.0,
1287
+ "epoch": 0.0015873015873015873,
1288
+ "step": 22
1289
+ },
1290
+ {
1291
+ "epoch": 0.0015873015873015873,
1292
+ "lm_loss": 0.9902944564819336,
1293
+ "step": 22
1294
+ },
1295
+ {
1296
+ "epoch": 0.0015873015873015873,
1297
+ "img_loss": 977.50732421875,
1298
+ "step": 22
1299
+ },
1300
+ {
1301
+ "epoch": 0.0015873015873015873,
1302
+ "img_emb_dist": 0.9628319144248962,
1303
+ "step": 22
1304
+ },
1305
+ {
1306
+ "epoch": 0.0015873015873015873,
1307
+ "img_divergence_loss": 0.0,
1308
+ "step": 22
1309
+ },
1310
+ {
1311
+ "activation_proximity_loss": 0.0,
1312
+ "epoch": 0.0015873015873015873,
1313
+ "step": 22
1314
+ },
1315
+ {
1316
+ "epoch": 0.0016594516594516595,
1317
+ "grad_norm": 2.4828687968296954,
1318
+ "learning_rate": 1.7037086855465902e-07,
1319
+ "loss": 1.1557,
1320
+ "step": 23
1321
+ },
1322
+ {
1323
+ "epoch": 0.0016594516594516595,
1324
+ "lm_loss": 0.5318238735198975,
1325
+ "step": 23
1326
+ },
1327
+ {
1328
+ "epoch": 0.0016594516594516595,
1329
+ "img_loss": 975.1682739257812,
1330
+ "step": 23
1331
+ },
1332
+ {
1333
+ "epoch": 0.0016594516594516595,
1334
+ "img_emb_dist": 0.9615951180458069,
1335
+ "step": 23
1336
+ },
1337
+ {
1338
+ "epoch": 0.0016594516594516595,
1339
+ "img_divergence_loss": 0.0,
1340
+ "step": 23
1341
+ },
1342
+ {
1343
+ "activation_proximity_loss": 0.0,
1344
+ "epoch": 0.0016594516594516595,
1345
+ "step": 23
1346
+ },
1347
+ {
1348
+ "epoch": 0.0016594516594516595,
1349
+ "lm_loss": 1.499765157699585,
1350
+ "step": 23
1351
+ },
1352
+ {
1353
+ "epoch": 0.0016594516594516595,
1354
+ "img_loss": 952.0101928710938,
1355
+ "step": 23
1356
+ },
1357
+ {
1358
+ "epoch": 0.0016594516594516595,
1359
+ "img_emb_dist": 0.9655733704566956,
1360
+ "step": 23
1361
+ },
1362
+ {
1363
+ "epoch": 0.0016594516594516595,
1364
+ "img_divergence_loss": 0.0,
1365
+ "step": 23
1366
+ },
1367
+ {
1368
+ "activation_proximity_loss": 0.0,
1369
+ "epoch": 0.0016594516594516595,
1370
+ "step": 23
1371
+ },
1372
+ {
1373
+ "epoch": 0.0017316017316017316,
1374
+ "grad_norm": 2.1518352777637206,
1375
+ "learning_rate": 4.2775693130948094e-08,
1376
+ "loss": 1.0811,
1377
+ "step": 24
1378
+ },
1379
+ {
1380
+ "epoch": 0.0017316017316017316,
1381
+ "lm_loss": 0.42849138379096985,
1382
+ "step": 24
1383
+ },
1384
+ {
1385
+ "epoch": 0.0017316017316017316,
1386
+ "img_loss": 987.5194091796875,
1387
+ "step": 24
1388
+ },
1389
+ {
1390
+ "epoch": 0.0017316017316017316,
1391
+ "img_emb_dist": 0.9614472985267639,
1392
+ "step": 24
1393
+ },
1394
+ {
1395
+ "epoch": 0.0017316017316017316,
1396
+ "img_divergence_loss": 0.0,
1397
+ "step": 24
1398
+ },
1399
+ {
1400
+ "activation_proximity_loss": 0.0,
1401
+ "epoch": 0.0017316017316017316,
1402
+ "step": 24
1403
+ },
1404
+ {
1405
+ "epoch": 0.0017316017316017316,
1406
+ "lm_loss": 1.1963765621185303,
1407
+ "step": 24
1408
+ },
1409
+ {
1410
+ "epoch": 0.0017316017316017316,
1411
+ "img_loss": 974.4249877929688,
1412
+ "step": 24
1413
+ },
1414
+ {
1415
+ "epoch": 0.0017316017316017316,
1416
+ "img_emb_dist": 0.9614829421043396,
1417
+ "step": 24
1418
+ },
1419
+ {
1420
+ "epoch": 0.0017316017316017316,
1421
+ "img_divergence_loss": 0.0,
1422
+ "step": 24
1423
+ },
1424
+ {
1425
+ "activation_proximity_loss": 0.0,
1426
+ "epoch": 0.0017316017316017316,
1427
+ "step": 24
1428
+ },
1429
+ {
1430
+ "epoch": 0.0018037518037518038,
1431
+ "grad_norm": 2.8558883696766513,
1432
+ "learning_rate": 0.0,
1433
+ "loss": 1.1064,
1434
+ "step": 25
1435
+ },
1436
+ {
1437
+ "epoch": 0.0018037518037518038,
1438
+ "step": 25,
1439
+ "total_flos": 4064781361152.0,
1440
+ "train_loss": 1.1001608490943908,
1441
+ "train_runtime": 761.4029,
1442
+ "train_samples_per_second": 1.576,
1443
+ "train_steps_per_second": 0.033
1444
+ }
1445
+ ],
1446
+ "logging_steps": 1.0,
1447
+ "max_steps": 25,
1448
+ "num_input_tokens_seen": 0,
1449
+ "num_train_epochs": 1,
1450
+ "save_steps": 5,
1451
+ "stateful_callbacks": {
1452
+ "TrainerControl": {
1453
+ "args": {
1454
+ "should_epoch_stop": false,
1455
+ "should_evaluate": false,
1456
+ "should_log": false,
1457
+ "should_save": true,
1458
+ "should_training_stop": true
1459
+ },
1460
+ "attributes": {}
1461
+ }
1462
+ },
1463
+ "total_flos": 4064781361152.0,
1464
+ "train_batch_size": 3,
1465
+ "trial_name": null,
1466
+ "trial_params": null
1467
+ }
saxon/TEST-multillavafinal-PT.l0.d0.a0-S15.l1e-5.d0.a0-FT.l1e-5.d0.a0/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:978eef64c362f894644dc60ceb2b3d5113c620f36ce3fb32d8cf9a1c5b73be57
3
+ size 8056