SunSec commited on
Commit
737573c
·
verified ·
1 Parent(s): e4f9480

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +3 -0
  2. dpo_search/qwen7b_sft_871_mask_doc_gen_4-14_selected_data_785_formatted_seq1w/epoch_5/pytorch_model-00001-of-00004.bin +3 -0
  3. dpo_search/qwen7b_sft_871_mask_doc_gen_4-14_selected_data_785_formatted_seq1w/epoch_5/pytorch_model-00002-of-00004.bin +3 -0
  4. dpo_search/qwen7b_sft_871_mask_doc_gen_4-14_selected_data_785_formatted_seq1w/epoch_5/pytorch_model-00003-of-00004.bin +3 -0
  5. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/added_tokens.json +24 -0
  6. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/config.json +29 -0
  7. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/generation_config.json +14 -0
  8. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/model.safetensors.index.json +346 -0
  9. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/trainer_state.json +509 -0
  10. sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/vocab.json +0 -0
  11. sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-68/model-00001-of-00004.safetensors +3 -0
  12. sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-68/model-00002-of-00004.safetensors +3 -0
  13. sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-68/model-00003-of-00004.safetensors +3 -0
  14. sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-68/model-00004-of-00004.safetensors +3 -0
  15. sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-68/tokenizer.json +3 -0
  16. sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-68/training_args.bin +3 -0
  17. sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-78/model-00002-of-00004.safetensors +3 -0
  18. sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-78/model-00003-of-00004.safetensors +3 -0
  19. sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-78/model-00004-of-00004.safetensors +3 -0
  20. sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-78/tokenizer.json +3 -0
  21. sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-78/training_args.bin +3 -0
  22. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/added_tokens.json +24 -0
  23. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/config.json +29 -0
  24. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/generation_config.json +14 -0
  25. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/merges.txt +0 -0
  26. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/model.safetensors.index.json +346 -0
  27. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/special_tokens_map.json +31 -0
  28. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/tokenizer_config.json +207 -0
  29. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/trainer_state.json +950 -0
  30. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/vocab.json +0 -0
  31. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/added_tokens.json +24 -0
  32. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/config.json +29 -0
  33. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/generation_config.json +14 -0
  34. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/merges.txt +0 -0
  35. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/model.safetensors.index.json +346 -0
  36. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/special_tokens_map.json +31 -0
  37. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/tokenizer_config.json +207 -0
  38. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/trainer_state.json +1125 -0
  39. sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/vocab.json +0 -0
  40. sft_search/JOB:28315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-7B#TOKEN:DeepSeek-R1-Distill-Qwen-7B#BSZ:2#ACC:4_no_error_data_871/checkpoint-68/special_tokens_map.json +23 -0
  41. sft_search/JOB:28315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-7B#TOKEN:DeepSeek-R1-Distill-Qwen-7B#BSZ:2#ACC:4_no_error_data_871/checkpoint-68/tokenizer_config.json +194 -0
  42. sft_search/JOB:29477#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_ques_keywords_filtered_data_727_ablation/checkpoint-46/model-00001-of-00004.safetensors +3 -0
  43. sft_search/JOB:29477#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_ques_keywords_filtered_data_727_ablation/checkpoint-46/model-00002-of-00004.safetensors +3 -0
  44. sft_search/JOB:29477#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_ques_keywords_filtered_data_727_ablation/checkpoint-46/model-00003-of-00004.safetensors +3 -0
  45. sft_search/JOB:29477#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_ques_keywords_filtered_data_727_ablation/checkpoint-46/model-00004-of-00004.safetensors +3 -0
  46. sft_search/JOB:29477#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_ques_keywords_filtered_data_727_ablation/checkpoint-46/tokenizer.json +3 -0
  47. sft_search/JOB:29477#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_ques_keywords_filtered_data_727_ablation/checkpoint-46/training_args.bin +3 -0
  48. sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-55/added_tokens.json +24 -0
  49. sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-55/config.json +29 -0
  50. sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-55/generation_config.json +14 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ sft_search/JOB:29477\#LR:1e-5\#BASE:Qwen2.5-7B-Instruct\#TOKEN:Qwen2.5-7B-Instruct\#BSZ:2\#ACC:4_ablation_ques_keywords_filtered_data_727_ablation/checkpoint-46/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ sft_search/JOB:19929\#LR:1e-5\#BASE:Qwen2.5-7B-Instruct\#TOKEN:Qwen2.5-7B-Instruct\#BSZ:2\#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-68/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ sft_search/JOB:19929\#LR:1e-5\#BASE:Qwen2.5-7B-Instruct\#TOKEN:Qwen2.5-7B-Instruct\#BSZ:2\#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-78/tokenizer.json filter=lfs diff=lfs merge=lfs -text
dpo_search/qwen7b_sft_871_mask_doc_gen_4-14_selected_data_785_formatted_seq1w/epoch_5/pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1de3b3333d6a64342516a37b483520eb07be5f6ee0a7da19b1a2ed08e81a409c
3
+ size 4877684182
dpo_search/qwen7b_sft_871_mask_doc_gen_4-14_selected_data_785_formatted_seq1w/epoch_5/pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3ae94a7eb3c5bd30c13adfd46980010aec308eecec3a74c9ffe9897496f8b28
3
+ size 4932778600
dpo_search/qwen7b_sft_871_mask_doc_gen_4-14_selected_data_785_formatted_seq1w/epoch_5/pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eeb158e11bae26ebc14a8f295efd98b757734c148d8e0673ef0b9d1fb5f0a6f
3
+ size 4330890394
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/capacity/userdata/models/Qwen2.5-7B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.0",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.46.0"
14
+ }
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/model.safetensors.index.json ADDED
@@ -0,0 +1,346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15231233024
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.norm.weight": "model-00003-of-00004.safetensors"
345
+ }
346
+ }
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/trainer_state.json ADDED
@@ -0,0 +1,509 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.945454545454545,
5
+ "eval_steps": 500,
6
+ "global_step": 68,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07272727272727272,
13
+ "grad_norm": 12.863605499267578,
14
+ "learning_rate": 3.3333333333333333e-06,
15
+ "loss": 1.6066,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.14545454545454545,
20
+ "grad_norm": 12.792675018310547,
21
+ "learning_rate": 6.666666666666667e-06,
22
+ "loss": 1.6231,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.21818181818181817,
27
+ "grad_norm": 10.905281066894531,
28
+ "learning_rate": 1e-05,
29
+ "loss": 1.566,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.2909090909090909,
34
+ "grad_norm": 5.113491058349609,
35
+ "learning_rate": 9.995614150494293e-06,
36
+ "loss": 1.3752,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.36363636363636365,
41
+ "grad_norm": 5.1580986976623535,
42
+ "learning_rate": 9.982464296247523e-06,
43
+ "loss": 1.2728,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.43636363636363634,
48
+ "grad_norm": 3.579421043395996,
49
+ "learning_rate": 9.960573506572391e-06,
50
+ "loss": 1.2054,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.509090909090909,
55
+ "grad_norm": 4.449979782104492,
56
+ "learning_rate": 9.929980185352525e-06,
57
+ "loss": 1.1506,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.5818181818181818,
62
+ "grad_norm": 3.252600908279419,
63
+ "learning_rate": 9.890738003669029e-06,
64
+ "loss": 1.1002,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.6545454545454545,
69
+ "grad_norm": 2.8043909072875977,
70
+ "learning_rate": 9.842915805643156e-06,
71
+ "loss": 1.0085,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.7272727272727273,
76
+ "grad_norm": 2.5800364017486572,
77
+ "learning_rate": 9.786597487660336e-06,
78
+ "loss": 1.0024,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.8,
83
+ "grad_norm": 2.2836010456085205,
84
+ "learning_rate": 9.721881851187406e-06,
85
+ "loss": 1.0046,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.8727272727272727,
90
+ "grad_norm": 1.9768003225326538,
91
+ "learning_rate": 9.648882429441258e-06,
92
+ "loss": 0.9928,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.9454545454545454,
97
+ "grad_norm": 1.8235994577407837,
98
+ "learning_rate": 9.567727288213005e-06,
99
+ "loss": 0.9482,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 1.018181818181818,
104
+ "grad_norm": 2.2026915550231934,
105
+ "learning_rate": 9.478558801197065e-06,
106
+ "loss": 1.185,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 1.0909090909090908,
111
+ "grad_norm": 1.9497827291488647,
112
+ "learning_rate": 9.381533400219319e-06,
113
+ "loss": 0.8687,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.1636363636363636,
118
+ "grad_norm": 1.5467802286148071,
119
+ "learning_rate": 9.276821300802535e-06,
120
+ "loss": 0.8749,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 1.2363636363636363,
125
+ "grad_norm": 1.3384064435958862,
126
+ "learning_rate": 9.164606203550498e-06,
127
+ "loss": 0.8268,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 1.309090909090909,
132
+ "grad_norm": 1.3969143629074097,
133
+ "learning_rate": 9.045084971874738e-06,
134
+ "loss": 0.8037,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 1.3818181818181818,
139
+ "grad_norm": 1.3535643815994263,
140
+ "learning_rate": 8.9184672866292e-06,
141
+ "loss": 0.7878,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 1.4545454545454546,
146
+ "grad_norm": 1.332352638244629,
147
+ "learning_rate": 8.784975278258783e-06,
148
+ "loss": 0.695,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 1.5272727272727273,
153
+ "grad_norm": 1.357491135597229,
154
+ "learning_rate": 8.644843137107058e-06,
155
+ "loss": 0.8654,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 1.6,
160
+ "grad_norm": 1.2643765211105347,
161
+ "learning_rate": 8.498316702566828e-06,
162
+ "loss": 0.827,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 1.6727272727272728,
167
+ "grad_norm": 1.2994352579116821,
168
+ "learning_rate": 8.345653031794292e-06,
169
+ "loss": 0.7782,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 1.7454545454545456,
174
+ "grad_norm": 1.3649132251739502,
175
+ "learning_rate": 8.18711994874345e-06,
176
+ "loss": 0.7561,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 1.8181818181818183,
181
+ "grad_norm": 1.3455241918563843,
182
+ "learning_rate": 8.022995574311876e-06,
183
+ "loss": 0.738,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 1.8909090909090909,
188
+ "grad_norm": 1.2925300598144531,
189
+ "learning_rate": 7.85356783842216e-06,
190
+ "loss": 0.7802,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 1.9636363636363636,
195
+ "grad_norm": 1.2759337425231934,
196
+ "learning_rate": 7.679133974894984e-06,
197
+ "loss": 0.8125,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 2.036363636363636,
202
+ "grad_norm": 1.4432379007339478,
203
+ "learning_rate": 7.500000000000001e-06,
204
+ "loss": 0.8592,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 2.109090909090909,
209
+ "grad_norm": 1.3001188039779663,
210
+ "learning_rate": 7.31648017559931e-06,
211
+ "loss": 0.6461,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 2.1818181818181817,
216
+ "grad_norm": 1.1495414972305298,
217
+ "learning_rate": 7.128896457825364e-06,
218
+ "loss": 0.602,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 2.2545454545454544,
223
+ "grad_norm": 1.1932196617126465,
224
+ "learning_rate": 6.9375779322605154e-06,
225
+ "loss": 0.6197,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 2.327272727272727,
230
+ "grad_norm": 1.2582231760025024,
231
+ "learning_rate": 6.7428602366090764e-06,
232
+ "loss": 0.6266,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 2.4,
237
+ "grad_norm": 1.1398663520812988,
238
+ "learning_rate": 6.545084971874738e-06,
239
+ "loss": 0.5696,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 2.4727272727272727,
244
+ "grad_norm": 1.1774870157241821,
245
+ "learning_rate": 6.344599103076329e-06,
246
+ "loss": 0.5542,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 2.5454545454545454,
251
+ "grad_norm": 1.248750925064087,
252
+ "learning_rate": 6.141754350553279e-06,
253
+ "loss": 0.5652,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 2.618181818181818,
258
+ "grad_norm": 1.237967610359192,
259
+ "learning_rate": 5.936906572928625e-06,
260
+ "loss": 0.6002,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 2.690909090909091,
265
+ "grad_norm": 1.1738842725753784,
266
+ "learning_rate": 5.730415142812059e-06,
267
+ "loss": 0.5135,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 2.7636363636363637,
272
+ "grad_norm": 1.1954946517944336,
273
+ "learning_rate": 5.522642316338268e-06,
274
+ "loss": 0.583,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 2.8363636363636364,
279
+ "grad_norm": 1.1883139610290527,
280
+ "learning_rate": 5.3139525976465675e-06,
281
+ "loss": 0.5378,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 2.909090909090909,
286
+ "grad_norm": 1.127272367477417,
287
+ "learning_rate": 5.1047120994167855e-06,
288
+ "loss": 0.5299,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 2.981818181818182,
293
+ "grad_norm": 1.4195200204849243,
294
+ "learning_rate": 4.895287900583216e-06,
295
+ "loss": 0.6672,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 3.0545454545454547,
300
+ "grad_norm": 1.349685549736023,
301
+ "learning_rate": 4.686047402353433e-06,
302
+ "loss": 0.4949,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 3.1272727272727274,
307
+ "grad_norm": 1.1365987062454224,
308
+ "learning_rate": 4.477357683661734e-06,
309
+ "loss": 0.458,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 3.2,
314
+ "grad_norm": 1.1739717721939087,
315
+ "learning_rate": 4.269584857187942e-06,
316
+ "loss": 0.4508,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 3.2727272727272725,
321
+ "grad_norm": 1.134547472000122,
322
+ "learning_rate": 4.063093427071376e-06,
323
+ "loss": 0.4418,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 3.3454545454545457,
328
+ "grad_norm": 1.1062874794006348,
329
+ "learning_rate": 3.8582456494467214e-06,
330
+ "loss": 0.4182,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 3.418181818181818,
335
+ "grad_norm": 1.1738144159317017,
336
+ "learning_rate": 3.655400896923672e-06,
337
+ "loss": 0.4048,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 3.4909090909090907,
342
+ "grad_norm": 1.2603284120559692,
343
+ "learning_rate": 3.4549150281252635e-06,
344
+ "loss": 0.3907,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 3.5636363636363635,
349
+ "grad_norm": 1.3774771690368652,
350
+ "learning_rate": 3.2571397633909252e-06,
351
+ "loss": 0.4155,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 3.6363636363636362,
356
+ "grad_norm": 1.3849499225616455,
357
+ "learning_rate": 3.0624220677394854e-06,
358
+ "loss": 0.4615,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 3.709090909090909,
363
+ "grad_norm": 1.2040380239486694,
364
+ "learning_rate": 2.871103542174637e-06,
365
+ "loss": 0.4282,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 3.7818181818181817,
370
+ "grad_norm": 1.1185059547424316,
371
+ "learning_rate": 2.683519824400693e-06,
372
+ "loss": 0.3728,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 3.8545454545454545,
377
+ "grad_norm": 1.1320322751998901,
378
+ "learning_rate": 2.5000000000000015e-06,
379
+ "loss": 0.4147,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 3.9272727272727272,
384
+ "grad_norm": 1.1219350099563599,
385
+ "learning_rate": 2.320866025105016e-06,
386
+ "loss": 0.4436,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 4.0,
391
+ "grad_norm": 1.3520313501358032,
392
+ "learning_rate": 2.146432161577842e-06,
393
+ "loss": 0.4979,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 4.072727272727272,
398
+ "grad_norm": 1.1228889226913452,
399
+ "learning_rate": 1.977004425688126e-06,
400
+ "loss": 0.3531,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 4.1454545454545455,
405
+ "grad_norm": 1.1075667142868042,
406
+ "learning_rate": 1.8128800512565514e-06,
407
+ "loss": 0.3665,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 4.218181818181818,
412
+ "grad_norm": 1.1154788732528687,
413
+ "learning_rate": 1.6543469682057105e-06,
414
+ "loss": 0.34,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 4.290909090909091,
419
+ "grad_norm": 1.0608782768249512,
420
+ "learning_rate": 1.5016832974331725e-06,
421
+ "loss": 0.3432,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 4.363636363636363,
426
+ "grad_norm": 1.0866858959197998,
427
+ "learning_rate": 1.3551568628929434e-06,
428
+ "loss": 0.3172,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 4.4363636363636365,
433
+ "grad_norm": 1.1228256225585938,
434
+ "learning_rate": 1.2150247217412186e-06,
435
+ "loss": 0.3398,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 4.509090909090909,
440
+ "grad_norm": 0.9872593283653259,
441
+ "learning_rate": 1.0815327133708015e-06,
442
+ "loss": 0.34,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 4.581818181818182,
447
+ "grad_norm": 1.0523958206176758,
448
+ "learning_rate": 9.549150281252633e-07,
449
+ "loss": 0.3362,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 4.654545454545454,
454
+ "grad_norm": 1.1005868911743164,
455
+ "learning_rate": 8.353937964495029e-07,
456
+ "loss": 0.3271,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 4.7272727272727275,
461
+ "grad_norm": 1.120803952217102,
462
+ "learning_rate": 7.23178699197467e-07,
463
+ "loss": 0.351,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 4.8,
468
+ "grad_norm": 1.0729155540466309,
469
+ "learning_rate": 6.184665997806832e-07,
470
+ "loss": 0.3317,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 4.872727272727273,
475
+ "grad_norm": 1.1419527530670166,
476
+ "learning_rate": 5.214411988029355e-07,
477
+ "loss": 0.3292,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 4.945454545454545,
482
+ "grad_norm": 1.0432584285736084,
483
+ "learning_rate": 4.322727117869951e-07,
484
+ "loss": 0.3083,
485
+ "step": 68
486
+ }
487
+ ],
488
+ "logging_steps": 1.0,
489
+ "max_steps": 78,
490
+ "num_input_tokens_seen": 0,
491
+ "num_train_epochs": 6,
492
+ "save_steps": 500,
493
+ "stateful_callbacks": {
494
+ "TrainerControl": {
495
+ "args": {
496
+ "should_epoch_stop": false,
497
+ "should_evaluate": false,
498
+ "should_log": false,
499
+ "should_save": true,
500
+ "should_training_stop": false
501
+ },
502
+ "attributes": {}
503
+ }
504
+ },
505
+ "total_flos": 12115104407552.0,
506
+ "train_batch_size": 2,
507
+ "trial_name": null,
508
+ "trial_params": null
509
+ }
sft_search/JOB:12290#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_no_error_data_871_871_wo_mask/checkpoint-68/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-68/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8ef297b0b9e13aedc89863823eda8739ea6d7e0c35009c9468b3c958ed1b209
3
+ size 4877660776
sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-68/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c79de7604596ea211d16db48660eb9091272763611602a0f742d0d29bb80f69
3
+ size 4932751008
sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-68/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:503c6f546fded69c73195b56de32534206242839e6152d2e10340c076f7f142c
3
+ size 4330865200
sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-68/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91cadcd6607d5992493ff140616851af6768386869c01905093ee0cae18648c3
3
+ size 1089994880
sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-68/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-68/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68180edbfd9d02c083560e46b9fdafc8a06983fbf25be76183a9fd6c70e0db7f
3
+ size 7544
sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-78/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62bff665d46e509c76e7cd2b61051ca3f04ca8edb1850e4b6a067689dff1051b
3
+ size 4932751008
sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-78/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68a8569259849286b88c4f1cc604e06dc9f0c1744d3d78d39f1342518216475f
3
+ size 4330865200
sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-78/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bd301b2441698f97d41505c8067713acc427a53d345495787b2f8274dede386
3
+ size 1089994880
sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-78/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
sft_search/JOB:19929#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_random_sample_871_ablation/checkpoint-78/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68180edbfd9d02c083560e46b9fdafc8a06983fbf25be76183a9fd6c70e0db7f
3
+ size 7544
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/capacity/userdata/models/Qwen2.5-7B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.0",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.46.0"
14
+ }
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/model.safetensors.index.json ADDED
@@ -0,0 +1,346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15231233024
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.norm.weight": "model-00003-of-00004.safetensors"
345
+ }
346
+ }
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 30000,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/trainer_state.json ADDED
@@ -0,0 +1,950 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.9904761904761905,
5
+ "eval_steps": 500,
6
+ "global_step": 131,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0380952380952381,
13
+ "grad_norm": 21.086605072021484,
14
+ "learning_rate": 2.0000000000000003e-06,
15
+ "loss": 1.6062,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0761904761904762,
20
+ "grad_norm": 21.234643936157227,
21
+ "learning_rate": 4.000000000000001e-06,
22
+ "loss": 1.6228,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.11428571428571428,
27
+ "grad_norm": 18.230310440063477,
28
+ "learning_rate": 6e-06,
29
+ "loss": 1.5263,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.1523809523809524,
34
+ "grad_norm": 12.426186561584473,
35
+ "learning_rate": 8.000000000000001e-06,
36
+ "loss": 1.3336,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.19047619047619047,
41
+ "grad_norm": 7.230856418609619,
42
+ "learning_rate": 1e-05,
43
+ "loss": 1.1368,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.22857142857142856,
48
+ "grad_norm": 7.587942600250244,
49
+ "learning_rate": 9.998917893031615e-06,
50
+ "loss": 1.1043,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.26666666666666666,
55
+ "grad_norm": 5.990701198577881,
56
+ "learning_rate": 9.995672040508656e-06,
57
+ "loss": 1.0522,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.3047619047619048,
62
+ "grad_norm": 6.41215181350708,
63
+ "learning_rate": 9.990263847374976e-06,
64
+ "loss": 0.9434,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.34285714285714286,
69
+ "grad_norm": 10.395182609558105,
70
+ "learning_rate": 9.982695654527966e-06,
71
+ "loss": 0.9337,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.38095238095238093,
76
+ "grad_norm": 4.302059650421143,
77
+ "learning_rate": 9.972970737805312e-06,
78
+ "loss": 0.8775,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.41904761904761906,
83
+ "grad_norm": 3.1416573524475098,
84
+ "learning_rate": 9.961093306567076e-06,
85
+ "loss": 0.8717,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.45714285714285713,
90
+ "grad_norm": 3.363281726837158,
91
+ "learning_rate": 9.947068501873702e-06,
92
+ "loss": 0.8406,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.49523809523809526,
97
+ "grad_norm": 3.147447109222412,
98
+ "learning_rate": 9.930902394260746e-06,
99
+ "loss": 0.8112,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.5333333333333333,
104
+ "grad_norm": 2.2096691131591797,
105
+ "learning_rate": 9.912601981111287e-06,
106
+ "loss": 0.8052,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.5714285714285714,
111
+ "grad_norm": 2.240201234817505,
112
+ "learning_rate": 9.892175183627161e-06,
113
+ "loss": 0.7625,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.6095238095238096,
118
+ "grad_norm": 2.2743282318115234,
119
+ "learning_rate": 9.869630843400331e-06,
120
+ "loss": 0.7654,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.6476190476190476,
125
+ "grad_norm": 2.560012102127075,
126
+ "learning_rate": 9.844978718585855e-06,
127
+ "loss": 0.77,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.6857142857142857,
132
+ "grad_norm": 2.0251638889312744,
133
+ "learning_rate": 9.81822947967816e-06,
134
+ "loss": 0.7163,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.7238095238095238,
139
+ "grad_norm": 2.2192909717559814,
140
+ "learning_rate": 9.789394704892364e-06,
141
+ "loss": 0.7439,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.7619047619047619,
146
+ "grad_norm": 2.166140079498291,
147
+ "learning_rate": 9.758486875152766e-06,
148
+ "loss": 0.7315,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.8,
153
+ "grad_norm": 1.8339487314224243,
154
+ "learning_rate": 9.725519368690539e-06,
155
+ "loss": 0.7111,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.8380952380952381,
160
+ "grad_norm": 1.9698566198349,
161
+ "learning_rate": 9.690506455253073e-06,
162
+ "loss": 0.7116,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.8761904761904762,
167
+ "grad_norm": 1.894209384918213,
168
+ "learning_rate": 9.65346328992741e-06,
169
+ "loss": 0.7142,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.9142857142857143,
174
+ "grad_norm": 1.9018983840942383,
175
+ "learning_rate": 9.614405906580486e-06,
176
+ "loss": 0.6839,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.9523809523809523,
181
+ "grad_norm": 2.1070282459259033,
182
+ "learning_rate": 9.573351210918976e-06,
183
+ "loss": 0.684,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.9904761904761905,
188
+ "grad_norm": 2.144148588180542,
189
+ "learning_rate": 9.53031697317178e-06,
190
+ "loss": 0.6955,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 1.0285714285714285,
195
+ "grad_norm": 3.5765540599823,
196
+ "learning_rate": 9.485321820398321e-06,
197
+ "loss": 1.1087,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 1.0666666666666667,
202
+ "grad_norm": 1.9845050573349,
203
+ "learning_rate": 9.43838522842594e-06,
204
+ "loss": 0.5726,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 1.1047619047619048,
209
+ "grad_norm": 1.7918779850006104,
210
+ "learning_rate": 9.389527513419935e-06,
211
+ "loss": 0.5665,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 1.1428571428571428,
216
+ "grad_norm": 1.7818535566329956,
217
+ "learning_rate": 9.338769823089853e-06,
218
+ "loss": 0.5763,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 1.180952380952381,
223
+ "grad_norm": 1.932702660560608,
224
+ "learning_rate": 9.286134127535859e-06,
225
+ "loss": 0.5739,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 1.2190476190476192,
230
+ "grad_norm": 1.7365800142288208,
231
+ "learning_rate": 9.231643209739128e-06,
232
+ "loss": 0.5185,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 1.2571428571428571,
237
+ "grad_norm": 1.7548762559890747,
238
+ "learning_rate": 9.175320655700407e-06,
239
+ "loss": 0.5271,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 1.2952380952380953,
244
+ "grad_norm": 1.7736371755599976,
245
+ "learning_rate": 9.117190844230971e-06,
246
+ "loss": 0.5272,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 1.3333333333333333,
251
+ "grad_norm": 1.6757187843322754,
252
+ "learning_rate": 9.057278936400453e-06,
253
+ "loss": 0.5227,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 1.3714285714285714,
258
+ "grad_norm": 1.674904227256775,
259
+ "learning_rate": 8.99561086464603e-06,
260
+ "loss": 0.512,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 1.4095238095238094,
265
+ "grad_norm": 1.6835227012634277,
266
+ "learning_rate": 8.932213321547769e-06,
267
+ "loss": 0.539,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 1.4476190476190476,
272
+ "grad_norm": 1.4854499101638794,
273
+ "learning_rate": 8.86711374827494e-06,
274
+ "loss": 0.4443,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 1.4857142857142858,
279
+ "grad_norm": 1.6214417219161987,
280
+ "learning_rate": 8.800340322708291e-06,
281
+ "loss": 0.5215,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 1.5238095238095237,
286
+ "grad_norm": 1.656782865524292,
287
+ "learning_rate": 8.73192194724347e-06,
288
+ "loss": 0.4975,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 1.561904761904762,
293
+ "grad_norm": 1.6773558855056763,
294
+ "learning_rate": 8.661888236280813e-06,
295
+ "loss": 0.5078,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 1.6,
300
+ "grad_norm": 1.745010495185852,
301
+ "learning_rate": 8.590269503406986e-06,
302
+ "loss": 0.5441,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 1.638095238095238,
307
+ "grad_norm": 1.6106173992156982,
308
+ "learning_rate": 8.517096748273951e-06,
309
+ "loss": 0.4882,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 1.6761904761904762,
314
+ "grad_norm": 1.7286875247955322,
315
+ "learning_rate": 8.442401643181e-06,
316
+ "loss": 0.5173,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 1.7142857142857144,
321
+ "grad_norm": 1.8672953844070435,
322
+ "learning_rate": 8.366216519365623e-06,
323
+ "loss": 0.5069,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 1.7523809523809524,
328
+ "grad_norm": 1.5610203742980957,
329
+ "learning_rate": 8.288574353009164e-06,
330
+ "loss": 0.4731,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 1.7904761904761903,
335
+ "grad_norm": 1.6290409564971924,
336
+ "learning_rate": 8.20950875096333e-06,
337
+ "loss": 0.5199,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 1.8285714285714287,
342
+ "grad_norm": 1.6521724462509155,
343
+ "learning_rate": 8.129053936203688e-06,
344
+ "loss": 0.4945,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 1.8666666666666667,
349
+ "grad_norm": 1.7766637802124023,
350
+ "learning_rate": 8.04724473301652e-06,
351
+ "loss": 0.4932,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 1.9047619047619047,
356
+ "grad_norm": 1.795250415802002,
357
+ "learning_rate": 7.964116551925365e-06,
358
+ "loss": 0.486,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 1.9428571428571428,
363
+ "grad_norm": 1.739128828048706,
364
+ "learning_rate": 7.879705374363831e-06,
365
+ "loss": 0.4987,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 1.980952380952381,
370
+ "grad_norm": 1.6136293411254883,
371
+ "learning_rate": 7.794047737101298e-06,
372
+ "loss": 0.4677,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 2.019047619047619,
377
+ "grad_norm": 3.2642064094543457,
378
+ "learning_rate": 7.707180716428237e-06,
379
+ "loss": 0.7829,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 2.057142857142857,
384
+ "grad_norm": 1.6384414434432983,
385
+ "learning_rate": 7.619141912108008e-06,
386
+ "loss": 0.3807,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 2.0952380952380953,
391
+ "grad_norm": 1.4165798425674438,
392
+ "learning_rate": 7.529969431102063e-06,
393
+ "loss": 0.3417,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 2.1333333333333333,
398
+ "grad_norm": 1.5709658861160278,
399
+ "learning_rate": 7.4397018710756415e-06,
400
+ "loss": 0.3494,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 2.1714285714285713,
405
+ "grad_norm": 1.5351802110671997,
406
+ "learning_rate": 7.34837830369103e-06,
407
+ "loss": 0.3134,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 2.2095238095238097,
412
+ "grad_norm": 1.5011217594146729,
413
+ "learning_rate": 7.2560382576956875e-06,
414
+ "loss": 0.2998,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 2.2476190476190476,
419
+ "grad_norm": 1.7701541185379028,
420
+ "learning_rate": 7.162721701812506e-06,
421
+ "loss": 0.3141,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 2.2857142857142856,
426
+ "grad_norm": 1.7763205766677856,
427
+ "learning_rate": 7.068469027439642e-06,
428
+ "loss": 0.3266,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 2.323809523809524,
433
+ "grad_norm": 1.7018606662750244,
434
+ "learning_rate": 6.9733210311673826e-06,
435
+ "loss": 0.3105,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 2.361904761904762,
440
+ "grad_norm": 1.744608759880066,
441
+ "learning_rate": 6.8773188971196515e-06,
442
+ "loss": 0.3151,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 2.4,
447
+ "grad_norm": 1.5167615413665771,
448
+ "learning_rate": 6.780504179127735e-06,
449
+ "loss": 0.2875,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 2.4380952380952383,
454
+ "grad_norm": 1.5365079641342163,
455
+ "learning_rate": 6.682918782744033e-06,
456
+ "loss": 0.2839,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 2.4761904761904763,
461
+ "grad_norm": 1.591735601425171,
462
+ "learning_rate": 6.584604947103515e-06,
463
+ "loss": 0.3352,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 2.5142857142857142,
468
+ "grad_norm": 1.3809449672698975,
469
+ "learning_rate": 6.4856052266408375e-06,
470
+ "loss": 0.2779,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 2.552380952380952,
475
+ "grad_norm": 1.6104717254638672,
476
+ "learning_rate": 6.385962472670953e-06,
477
+ "loss": 0.3205,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 2.5904761904761906,
482
+ "grad_norm": 1.4960706233978271,
483
+ "learning_rate": 6.28571981484123e-06,
484
+ "loss": 0.285,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 2.6285714285714286,
489
+ "grad_norm": 1.5156073570251465,
490
+ "learning_rate": 6.184920642463095e-06,
491
+ "loss": 0.3103,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 2.6666666666666665,
496
+ "grad_norm": 1.4298073053359985,
497
+ "learning_rate": 6.083608585731283e-06,
498
+ "loss": 0.2942,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 2.704761904761905,
503
+ "grad_norm": 1.5675926208496094,
504
+ "learning_rate": 5.9818274968388225e-06,
505
+ "loss": 0.3243,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 2.742857142857143,
510
+ "grad_norm": 1.524753451347351,
511
+ "learning_rate": 5.879621430995927e-06,
512
+ "loss": 0.3095,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 2.780952380952381,
517
+ "grad_norm": 1.4325066804885864,
518
+ "learning_rate": 5.777034627361025e-06,
519
+ "loss": 0.2778,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 2.819047619047619,
524
+ "grad_norm": 1.4910430908203125,
525
+ "learning_rate": 5.674111489892144e-06,
526
+ "loss": 0.2991,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 2.857142857142857,
531
+ "grad_norm": 1.6505004167556763,
532
+ "learning_rate": 5.570896568126994e-06,
533
+ "loss": 0.3098,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 2.895238095238095,
538
+ "grad_norm": 1.4687055349349976,
539
+ "learning_rate": 5.4674345379e-06,
540
+ "loss": 0.3032,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 2.9333333333333336,
545
+ "grad_norm": 1.5399705171585083,
546
+ "learning_rate": 5.36377018200472e-06,
547
+ "loss": 0.2963,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 2.9714285714285715,
552
+ "grad_norm": 1.5479682683944702,
553
+ "learning_rate": 5.259948370809902e-06,
554
+ "loss": 0.321,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 3.0095238095238095,
559
+ "grad_norm": 2.8608360290527344,
560
+ "learning_rate": 5.156014042837696e-06,
561
+ "loss": 0.4516,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 3.0476190476190474,
566
+ "grad_norm": 1.3540769815444946,
567
+ "learning_rate": 5.052012185312322e-06,
568
+ "loss": 0.1911,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 3.085714285714286,
573
+ "grad_norm": 1.3209166526794434,
574
+ "learning_rate": 4.94798781468768e-06,
575
+ "loss": 0.1948,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 3.123809523809524,
580
+ "grad_norm": 1.2951992750167847,
581
+ "learning_rate": 4.843985957162304e-06,
582
+ "loss": 0.1635,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 3.1619047619047618,
587
+ "grad_norm": 1.2254530191421509,
588
+ "learning_rate": 4.740051629190099e-06,
589
+ "loss": 0.1938,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 3.2,
594
+ "grad_norm": 1.2882040739059448,
595
+ "learning_rate": 4.636229817995281e-06,
596
+ "loss": 0.1816,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 3.238095238095238,
601
+ "grad_norm": 1.570145845413208,
602
+ "learning_rate": 4.532565462099999e-06,
603
+ "loss": 0.1927,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 3.276190476190476,
608
+ "grad_norm": 1.6147277355194092,
609
+ "learning_rate": 4.429103431873009e-06,
610
+ "loss": 0.1747,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 3.314285714285714,
615
+ "grad_norm": 1.4775006771087646,
616
+ "learning_rate": 4.3258885101078565e-06,
617
+ "loss": 0.1648,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 3.3523809523809525,
622
+ "grad_norm": 1.626664161682129,
623
+ "learning_rate": 4.2229653726389765e-06,
624
+ "loss": 0.1804,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 3.3904761904761904,
629
+ "grad_norm": 1.5191929340362549,
630
+ "learning_rate": 4.120378569004074e-06,
631
+ "loss": 0.1785,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 3.4285714285714284,
636
+ "grad_norm": 1.4385101795196533,
637
+ "learning_rate": 4.018172503161179e-06,
638
+ "loss": 0.1833,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 3.466666666666667,
643
+ "grad_norm": 1.3473029136657715,
644
+ "learning_rate": 3.9163914142687185e-06,
645
+ "loss": 0.1623,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 3.5047619047619047,
650
+ "grad_norm": 1.5257320404052734,
651
+ "learning_rate": 3.815079357536907e-06,
652
+ "loss": 0.1798,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 3.5428571428571427,
657
+ "grad_norm": 1.4962753057479858,
658
+ "learning_rate": 3.714280185158771e-06,
659
+ "loss": 0.2109,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 3.580952380952381,
664
+ "grad_norm": 1.2462799549102783,
665
+ "learning_rate": 3.614037527329048e-06,
666
+ "loss": 0.1612,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 3.619047619047619,
671
+ "grad_norm": 1.3198744058609009,
672
+ "learning_rate": 3.5143947733591633e-06,
673
+ "loss": 0.178,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 3.657142857142857,
678
+ "grad_norm": 1.338419795036316,
679
+ "learning_rate": 3.4153950528964867e-06,
680
+ "loss": 0.173,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 3.6952380952380954,
685
+ "grad_norm": 1.349777102470398,
686
+ "learning_rate": 3.3170812172559695e-06,
687
+ "loss": 0.1809,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 3.7333333333333334,
692
+ "grad_norm": 1.2716152667999268,
693
+ "learning_rate": 3.2194958208722656e-06,
694
+ "loss": 0.1738,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 3.7714285714285714,
699
+ "grad_norm": 1.2132824659347534,
700
+ "learning_rate": 3.1226811028803514e-06,
701
+ "loss": 0.1483,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 3.8095238095238093,
706
+ "grad_norm": 1.4588696956634521,
707
+ "learning_rate": 3.0266789688326187e-06,
708
+ "loss": 0.1768,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 3.8476190476190477,
713
+ "grad_norm": 1.220189094543457,
714
+ "learning_rate": 2.9315309725603596e-06,
715
+ "loss": 0.1626,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 3.8857142857142857,
720
+ "grad_norm": 1.3112905025482178,
721
+ "learning_rate": 2.8372782981874964e-06,
722
+ "loss": 0.1751,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 3.923809523809524,
727
+ "grad_norm": 1.4006564617156982,
728
+ "learning_rate": 2.7439617423043146e-06,
729
+ "loss": 0.1728,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 3.961904761904762,
734
+ "grad_norm": 1.3081145286560059,
735
+ "learning_rate": 2.6516216963089698e-06,
736
+ "loss": 0.1528,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 4.0,
741
+ "grad_norm": 2.8037190437316895,
742
+ "learning_rate": 2.560298128924358e-06,
743
+ "loss": 0.2871,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 4.038095238095238,
748
+ "grad_norm": 1.069034457206726,
749
+ "learning_rate": 2.470030568897938e-06,
750
+ "loss": 0.1101,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 4.076190476190476,
755
+ "grad_norm": 1.0345056056976318,
756
+ "learning_rate": 2.3808580878919948e-06,
757
+ "loss": 0.1146,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 4.114285714285714,
762
+ "grad_norm": 1.0240198373794556,
763
+ "learning_rate": 2.2928192835717642e-06,
764
+ "loss": 0.1064,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 4.152380952380953,
769
+ "grad_norm": 1.4057704210281372,
770
+ "learning_rate": 2.205952262898704e-06,
771
+ "loss": 0.1041,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 4.190476190476191,
776
+ "grad_norm": 1.089251160621643,
777
+ "learning_rate": 2.120294625636171e-06,
778
+ "loss": 0.1048,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 4.228571428571429,
783
+ "grad_norm": 1.0048580169677734,
784
+ "learning_rate": 2.0358834480746363e-06,
785
+ "loss": 0.1026,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 4.266666666666667,
790
+ "grad_norm": 1.0335818529129028,
791
+ "learning_rate": 1.9527552669834797e-06,
792
+ "loss": 0.094,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 4.304761904761905,
797
+ "grad_norm": 1.1736409664154053,
798
+ "learning_rate": 1.8709460637963123e-06,
799
+ "loss": 0.0951,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 4.3428571428571425,
804
+ "grad_norm": 1.2718082666397095,
805
+ "learning_rate": 1.7904912490366723e-06,
806
+ "loss": 0.0957,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 4.380952380952381,
811
+ "grad_norm": 1.1848101615905762,
812
+ "learning_rate": 1.711425646990838e-06,
813
+ "loss": 0.0952,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 4.419047619047619,
818
+ "grad_norm": 1.1475728750228882,
819
+ "learning_rate": 1.6337834806343783e-06,
820
+ "loss": 0.0939,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 4.457142857142857,
825
+ "grad_norm": 1.2558069229125977,
826
+ "learning_rate": 1.557598356819e-06,
827
+ "loss": 0.0985,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 4.495238095238095,
832
+ "grad_norm": 1.310692548751831,
833
+ "learning_rate": 1.482903251726049e-06,
834
+ "loss": 0.1057,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 4.533333333333333,
839
+ "grad_norm": 1.1631875038146973,
840
+ "learning_rate": 1.409730496593016e-06,
841
+ "loss": 0.0999,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 4.571428571428571,
846
+ "grad_norm": 1.1441932916641235,
847
+ "learning_rate": 1.3381117637191887e-06,
848
+ "loss": 0.0918,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 4.609523809523809,
853
+ "grad_norm": 1.1489994525909424,
854
+ "learning_rate": 1.2680780527565313e-06,
855
+ "loss": 0.0931,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 4.647619047619048,
860
+ "grad_norm": 1.1286568641662598,
861
+ "learning_rate": 1.1996596772917091e-06,
862
+ "loss": 0.0933,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 4.685714285714286,
867
+ "grad_norm": 1.0700788497924805,
868
+ "learning_rate": 1.132886251725061e-06,
869
+ "loss": 0.0919,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 4.723809523809524,
874
+ "grad_norm": 1.1247611045837402,
875
+ "learning_rate": 1.0677866784522317e-06,
876
+ "loss": 0.0933,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 4.761904761904762,
881
+ "grad_norm": 1.1145604848861694,
882
+ "learning_rate": 1.004389135353972e-06,
883
+ "loss": 0.0989,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 4.8,
888
+ "grad_norm": 1.10590398311615,
889
+ "learning_rate": 9.427210635995482e-07,
890
+ "loss": 0.099,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 4.838095238095238,
895
+ "grad_norm": 1.0256025791168213,
896
+ "learning_rate": 8.828091557690288e-07,
897
+ "loss": 0.0876,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 4.876190476190477,
902
+ "grad_norm": 1.118198275566101,
903
+ "learning_rate": 8.246793442995954e-07,
904
+ "loss": 0.1009,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 4.914285714285715,
909
+ "grad_norm": 1.1724058389663696,
910
+ "learning_rate": 7.68356790260873e-07,
911
+ "loss": 0.0953,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 4.9523809523809526,
916
+ "grad_norm": 1.0902793407440186,
917
+ "learning_rate": 7.138658724641417e-07,
918
+ "loss": 0.0922,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 4.9904761904761905,
923
+ "grad_norm": 1.0752878189086914,
924
+ "learning_rate": 6.612301769101464e-07,
925
+ "loss": 0.0936,
926
+ "step": 131
927
+ }
928
+ ],
929
+ "logging_steps": 1.0,
930
+ "max_steps": 156,
931
+ "num_input_tokens_seen": 0,
932
+ "num_train_epochs": 6,
933
+ "save_steps": 500,
934
+ "stateful_callbacks": {
935
+ "TrainerControl": {
936
+ "args": {
937
+ "should_epoch_stop": false,
938
+ "should_evaluate": false,
939
+ "should_log": false,
940
+ "should_save": true,
941
+ "should_training_stop": false
942
+ },
943
+ "attributes": {}
944
+ }
945
+ },
946
+ "total_flos": 22640378945536.0,
947
+ "train_batch_size": 2,
948
+ "trial_name": null,
949
+ "trial_params": null
950
+ }
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-131/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/capacity/userdata/models/Qwen2.5-7B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.0",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.46.0"
14
+ }
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/model.safetensors.index.json ADDED
@@ -0,0 +1,346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15231233024
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.norm.weight": "model-00003-of-00004.safetensors"
345
+ }
346
+ }
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 30000,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/trainer_state.json ADDED
@@ -0,0 +1,1125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.942857142857143,
5
+ "eval_steps": 500,
6
+ "global_step": 156,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0380952380952381,
13
+ "grad_norm": 21.086605072021484,
14
+ "learning_rate": 2.0000000000000003e-06,
15
+ "loss": 1.6062,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0761904761904762,
20
+ "grad_norm": 21.234643936157227,
21
+ "learning_rate": 4.000000000000001e-06,
22
+ "loss": 1.6228,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.11428571428571428,
27
+ "grad_norm": 18.230310440063477,
28
+ "learning_rate": 6e-06,
29
+ "loss": 1.5263,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.1523809523809524,
34
+ "grad_norm": 12.426186561584473,
35
+ "learning_rate": 8.000000000000001e-06,
36
+ "loss": 1.3336,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.19047619047619047,
41
+ "grad_norm": 7.230856418609619,
42
+ "learning_rate": 1e-05,
43
+ "loss": 1.1368,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.22857142857142856,
48
+ "grad_norm": 7.587942600250244,
49
+ "learning_rate": 9.998917893031615e-06,
50
+ "loss": 1.1043,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.26666666666666666,
55
+ "grad_norm": 5.990701198577881,
56
+ "learning_rate": 9.995672040508656e-06,
57
+ "loss": 1.0522,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.3047619047619048,
62
+ "grad_norm": 6.41215181350708,
63
+ "learning_rate": 9.990263847374976e-06,
64
+ "loss": 0.9434,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.34285714285714286,
69
+ "grad_norm": 10.395182609558105,
70
+ "learning_rate": 9.982695654527966e-06,
71
+ "loss": 0.9337,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.38095238095238093,
76
+ "grad_norm": 4.302059650421143,
77
+ "learning_rate": 9.972970737805312e-06,
78
+ "loss": 0.8775,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.41904761904761906,
83
+ "grad_norm": 3.1416573524475098,
84
+ "learning_rate": 9.961093306567076e-06,
85
+ "loss": 0.8717,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.45714285714285713,
90
+ "grad_norm": 3.363281726837158,
91
+ "learning_rate": 9.947068501873702e-06,
92
+ "loss": 0.8406,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.49523809523809526,
97
+ "grad_norm": 3.147447109222412,
98
+ "learning_rate": 9.930902394260746e-06,
99
+ "loss": 0.8112,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.5333333333333333,
104
+ "grad_norm": 2.2096691131591797,
105
+ "learning_rate": 9.912601981111287e-06,
106
+ "loss": 0.8052,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.5714285714285714,
111
+ "grad_norm": 2.240201234817505,
112
+ "learning_rate": 9.892175183627161e-06,
113
+ "loss": 0.7625,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.6095238095238096,
118
+ "grad_norm": 2.2743282318115234,
119
+ "learning_rate": 9.869630843400331e-06,
120
+ "loss": 0.7654,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.6476190476190476,
125
+ "grad_norm": 2.560012102127075,
126
+ "learning_rate": 9.844978718585855e-06,
127
+ "loss": 0.77,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.6857142857142857,
132
+ "grad_norm": 2.0251638889312744,
133
+ "learning_rate": 9.81822947967816e-06,
134
+ "loss": 0.7163,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.7238095238095238,
139
+ "grad_norm": 2.2192909717559814,
140
+ "learning_rate": 9.789394704892364e-06,
141
+ "loss": 0.7439,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.7619047619047619,
146
+ "grad_norm": 2.166140079498291,
147
+ "learning_rate": 9.758486875152766e-06,
148
+ "loss": 0.7315,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.8,
153
+ "grad_norm": 1.8339487314224243,
154
+ "learning_rate": 9.725519368690539e-06,
155
+ "loss": 0.7111,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.8380952380952381,
160
+ "grad_norm": 1.9698566198349,
161
+ "learning_rate": 9.690506455253073e-06,
162
+ "loss": 0.7116,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.8761904761904762,
167
+ "grad_norm": 1.894209384918213,
168
+ "learning_rate": 9.65346328992741e-06,
169
+ "loss": 0.7142,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.9142857142857143,
174
+ "grad_norm": 1.9018983840942383,
175
+ "learning_rate": 9.614405906580486e-06,
176
+ "loss": 0.6839,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.9523809523809523,
181
+ "grad_norm": 2.1070282459259033,
182
+ "learning_rate": 9.573351210918976e-06,
183
+ "loss": 0.684,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.9904761904761905,
188
+ "grad_norm": 2.144148588180542,
189
+ "learning_rate": 9.53031697317178e-06,
190
+ "loss": 0.6955,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 1.0285714285714285,
195
+ "grad_norm": 3.5765540599823,
196
+ "learning_rate": 9.485321820398321e-06,
197
+ "loss": 1.1087,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 1.0666666666666667,
202
+ "grad_norm": 1.9845050573349,
203
+ "learning_rate": 9.43838522842594e-06,
204
+ "loss": 0.5726,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 1.1047619047619048,
209
+ "grad_norm": 1.7918779850006104,
210
+ "learning_rate": 9.389527513419935e-06,
211
+ "loss": 0.5665,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 1.1428571428571428,
216
+ "grad_norm": 1.7818535566329956,
217
+ "learning_rate": 9.338769823089853e-06,
218
+ "loss": 0.5763,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 1.180952380952381,
223
+ "grad_norm": 1.932702660560608,
224
+ "learning_rate": 9.286134127535859e-06,
225
+ "loss": 0.5739,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 1.2190476190476192,
230
+ "grad_norm": 1.7365800142288208,
231
+ "learning_rate": 9.231643209739128e-06,
232
+ "loss": 0.5185,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 1.2571428571428571,
237
+ "grad_norm": 1.7548762559890747,
238
+ "learning_rate": 9.175320655700407e-06,
239
+ "loss": 0.5271,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 1.2952380952380953,
244
+ "grad_norm": 1.7736371755599976,
245
+ "learning_rate": 9.117190844230971e-06,
246
+ "loss": 0.5272,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 1.3333333333333333,
251
+ "grad_norm": 1.6757187843322754,
252
+ "learning_rate": 9.057278936400453e-06,
253
+ "loss": 0.5227,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 1.3714285714285714,
258
+ "grad_norm": 1.674904227256775,
259
+ "learning_rate": 8.99561086464603e-06,
260
+ "loss": 0.512,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 1.4095238095238094,
265
+ "grad_norm": 1.6835227012634277,
266
+ "learning_rate": 8.932213321547769e-06,
267
+ "loss": 0.539,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 1.4476190476190476,
272
+ "grad_norm": 1.4854499101638794,
273
+ "learning_rate": 8.86711374827494e-06,
274
+ "loss": 0.4443,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 1.4857142857142858,
279
+ "grad_norm": 1.6214417219161987,
280
+ "learning_rate": 8.800340322708291e-06,
281
+ "loss": 0.5215,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 1.5238095238095237,
286
+ "grad_norm": 1.656782865524292,
287
+ "learning_rate": 8.73192194724347e-06,
288
+ "loss": 0.4975,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 1.561904761904762,
293
+ "grad_norm": 1.6773558855056763,
294
+ "learning_rate": 8.661888236280813e-06,
295
+ "loss": 0.5078,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 1.6,
300
+ "grad_norm": 1.745010495185852,
301
+ "learning_rate": 8.590269503406986e-06,
302
+ "loss": 0.5441,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 1.638095238095238,
307
+ "grad_norm": 1.6106173992156982,
308
+ "learning_rate": 8.517096748273951e-06,
309
+ "loss": 0.4882,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 1.6761904761904762,
314
+ "grad_norm": 1.7286875247955322,
315
+ "learning_rate": 8.442401643181e-06,
316
+ "loss": 0.5173,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 1.7142857142857144,
321
+ "grad_norm": 1.8672953844070435,
322
+ "learning_rate": 8.366216519365623e-06,
323
+ "loss": 0.5069,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 1.7523809523809524,
328
+ "grad_norm": 1.5610203742980957,
329
+ "learning_rate": 8.288574353009164e-06,
330
+ "loss": 0.4731,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 1.7904761904761903,
335
+ "grad_norm": 1.6290409564971924,
336
+ "learning_rate": 8.20950875096333e-06,
337
+ "loss": 0.5199,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 1.8285714285714287,
342
+ "grad_norm": 1.6521724462509155,
343
+ "learning_rate": 8.129053936203688e-06,
344
+ "loss": 0.4945,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 1.8666666666666667,
349
+ "grad_norm": 1.7766637802124023,
350
+ "learning_rate": 8.04724473301652e-06,
351
+ "loss": 0.4932,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 1.9047619047619047,
356
+ "grad_norm": 1.795250415802002,
357
+ "learning_rate": 7.964116551925365e-06,
358
+ "loss": 0.486,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 1.9428571428571428,
363
+ "grad_norm": 1.739128828048706,
364
+ "learning_rate": 7.879705374363831e-06,
365
+ "loss": 0.4987,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 1.980952380952381,
370
+ "grad_norm": 1.6136293411254883,
371
+ "learning_rate": 7.794047737101298e-06,
372
+ "loss": 0.4677,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 2.019047619047619,
377
+ "grad_norm": 3.2642064094543457,
378
+ "learning_rate": 7.707180716428237e-06,
379
+ "loss": 0.7829,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 2.057142857142857,
384
+ "grad_norm": 1.6384414434432983,
385
+ "learning_rate": 7.619141912108008e-06,
386
+ "loss": 0.3807,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 2.0952380952380953,
391
+ "grad_norm": 1.4165798425674438,
392
+ "learning_rate": 7.529969431102063e-06,
393
+ "loss": 0.3417,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 2.1333333333333333,
398
+ "grad_norm": 1.5709658861160278,
399
+ "learning_rate": 7.4397018710756415e-06,
400
+ "loss": 0.3494,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 2.1714285714285713,
405
+ "grad_norm": 1.5351802110671997,
406
+ "learning_rate": 7.34837830369103e-06,
407
+ "loss": 0.3134,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 2.2095238095238097,
412
+ "grad_norm": 1.5011217594146729,
413
+ "learning_rate": 7.2560382576956875e-06,
414
+ "loss": 0.2998,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 2.2476190476190476,
419
+ "grad_norm": 1.7701541185379028,
420
+ "learning_rate": 7.162721701812506e-06,
421
+ "loss": 0.3141,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 2.2857142857142856,
426
+ "grad_norm": 1.7763205766677856,
427
+ "learning_rate": 7.068469027439642e-06,
428
+ "loss": 0.3266,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 2.323809523809524,
433
+ "grad_norm": 1.7018606662750244,
434
+ "learning_rate": 6.9733210311673826e-06,
435
+ "loss": 0.3105,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 2.361904761904762,
440
+ "grad_norm": 1.744608759880066,
441
+ "learning_rate": 6.8773188971196515e-06,
442
+ "loss": 0.3151,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 2.4,
447
+ "grad_norm": 1.5167615413665771,
448
+ "learning_rate": 6.780504179127735e-06,
449
+ "loss": 0.2875,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 2.4380952380952383,
454
+ "grad_norm": 1.5365079641342163,
455
+ "learning_rate": 6.682918782744033e-06,
456
+ "loss": 0.2839,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 2.4761904761904763,
461
+ "grad_norm": 1.591735601425171,
462
+ "learning_rate": 6.584604947103515e-06,
463
+ "loss": 0.3352,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 2.5142857142857142,
468
+ "grad_norm": 1.3809449672698975,
469
+ "learning_rate": 6.4856052266408375e-06,
470
+ "loss": 0.2779,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 2.552380952380952,
475
+ "grad_norm": 1.6104717254638672,
476
+ "learning_rate": 6.385962472670953e-06,
477
+ "loss": 0.3205,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 2.5904761904761906,
482
+ "grad_norm": 1.4960706233978271,
483
+ "learning_rate": 6.28571981484123e-06,
484
+ "loss": 0.285,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 2.6285714285714286,
489
+ "grad_norm": 1.5156073570251465,
490
+ "learning_rate": 6.184920642463095e-06,
491
+ "loss": 0.3103,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 2.6666666666666665,
496
+ "grad_norm": 1.4298073053359985,
497
+ "learning_rate": 6.083608585731283e-06,
498
+ "loss": 0.2942,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 2.704761904761905,
503
+ "grad_norm": 1.5675926208496094,
504
+ "learning_rate": 5.9818274968388225e-06,
505
+ "loss": 0.3243,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 2.742857142857143,
510
+ "grad_norm": 1.524753451347351,
511
+ "learning_rate": 5.879621430995927e-06,
512
+ "loss": 0.3095,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 2.780952380952381,
517
+ "grad_norm": 1.4325066804885864,
518
+ "learning_rate": 5.777034627361025e-06,
519
+ "loss": 0.2778,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 2.819047619047619,
524
+ "grad_norm": 1.4910430908203125,
525
+ "learning_rate": 5.674111489892144e-06,
526
+ "loss": 0.2991,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 2.857142857142857,
531
+ "grad_norm": 1.6505004167556763,
532
+ "learning_rate": 5.570896568126994e-06,
533
+ "loss": 0.3098,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 2.895238095238095,
538
+ "grad_norm": 1.4687055349349976,
539
+ "learning_rate": 5.4674345379e-06,
540
+ "loss": 0.3032,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 2.9333333333333336,
545
+ "grad_norm": 1.5399705171585083,
546
+ "learning_rate": 5.36377018200472e-06,
547
+ "loss": 0.2963,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 2.9714285714285715,
552
+ "grad_norm": 1.5479682683944702,
553
+ "learning_rate": 5.259948370809902e-06,
554
+ "loss": 0.321,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 3.0095238095238095,
559
+ "grad_norm": 2.8608360290527344,
560
+ "learning_rate": 5.156014042837696e-06,
561
+ "loss": 0.4516,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 3.0476190476190474,
566
+ "grad_norm": 1.3540769815444946,
567
+ "learning_rate": 5.052012185312322e-06,
568
+ "loss": 0.1911,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 3.085714285714286,
573
+ "grad_norm": 1.3209166526794434,
574
+ "learning_rate": 4.94798781468768e-06,
575
+ "loss": 0.1948,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 3.123809523809524,
580
+ "grad_norm": 1.2951992750167847,
581
+ "learning_rate": 4.843985957162304e-06,
582
+ "loss": 0.1635,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 3.1619047619047618,
587
+ "grad_norm": 1.2254530191421509,
588
+ "learning_rate": 4.740051629190099e-06,
589
+ "loss": 0.1938,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 3.2,
594
+ "grad_norm": 1.2882040739059448,
595
+ "learning_rate": 4.636229817995281e-06,
596
+ "loss": 0.1816,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 3.238095238095238,
601
+ "grad_norm": 1.570145845413208,
602
+ "learning_rate": 4.532565462099999e-06,
603
+ "loss": 0.1927,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 3.276190476190476,
608
+ "grad_norm": 1.6147277355194092,
609
+ "learning_rate": 4.429103431873009e-06,
610
+ "loss": 0.1747,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 3.314285714285714,
615
+ "grad_norm": 1.4775006771087646,
616
+ "learning_rate": 4.3258885101078565e-06,
617
+ "loss": 0.1648,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 3.3523809523809525,
622
+ "grad_norm": 1.626664161682129,
623
+ "learning_rate": 4.2229653726389765e-06,
624
+ "loss": 0.1804,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 3.3904761904761904,
629
+ "grad_norm": 1.5191929340362549,
630
+ "learning_rate": 4.120378569004074e-06,
631
+ "loss": 0.1785,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 3.4285714285714284,
636
+ "grad_norm": 1.4385101795196533,
637
+ "learning_rate": 4.018172503161179e-06,
638
+ "loss": 0.1833,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 3.466666666666667,
643
+ "grad_norm": 1.3473029136657715,
644
+ "learning_rate": 3.9163914142687185e-06,
645
+ "loss": 0.1623,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 3.5047619047619047,
650
+ "grad_norm": 1.5257320404052734,
651
+ "learning_rate": 3.815079357536907e-06,
652
+ "loss": 0.1798,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 3.5428571428571427,
657
+ "grad_norm": 1.4962753057479858,
658
+ "learning_rate": 3.714280185158771e-06,
659
+ "loss": 0.2109,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 3.580952380952381,
664
+ "grad_norm": 1.2462799549102783,
665
+ "learning_rate": 3.614037527329048e-06,
666
+ "loss": 0.1612,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 3.619047619047619,
671
+ "grad_norm": 1.3198744058609009,
672
+ "learning_rate": 3.5143947733591633e-06,
673
+ "loss": 0.178,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 3.657142857142857,
678
+ "grad_norm": 1.338419795036316,
679
+ "learning_rate": 3.4153950528964867e-06,
680
+ "loss": 0.173,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 3.6952380952380954,
685
+ "grad_norm": 1.349777102470398,
686
+ "learning_rate": 3.3170812172559695e-06,
687
+ "loss": 0.1809,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 3.7333333333333334,
692
+ "grad_norm": 1.2716152667999268,
693
+ "learning_rate": 3.2194958208722656e-06,
694
+ "loss": 0.1738,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 3.7714285714285714,
699
+ "grad_norm": 1.2132824659347534,
700
+ "learning_rate": 3.1226811028803514e-06,
701
+ "loss": 0.1483,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 3.8095238095238093,
706
+ "grad_norm": 1.4588696956634521,
707
+ "learning_rate": 3.0266789688326187e-06,
708
+ "loss": 0.1768,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 3.8476190476190477,
713
+ "grad_norm": 1.220189094543457,
714
+ "learning_rate": 2.9315309725603596e-06,
715
+ "loss": 0.1626,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 3.8857142857142857,
720
+ "grad_norm": 1.3112905025482178,
721
+ "learning_rate": 2.8372782981874964e-06,
722
+ "loss": 0.1751,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 3.923809523809524,
727
+ "grad_norm": 1.4006564617156982,
728
+ "learning_rate": 2.7439617423043146e-06,
729
+ "loss": 0.1728,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 3.961904761904762,
734
+ "grad_norm": 1.3081145286560059,
735
+ "learning_rate": 2.6516216963089698e-06,
736
+ "loss": 0.1528,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 4.0,
741
+ "grad_norm": 2.8037190437316895,
742
+ "learning_rate": 2.560298128924358e-06,
743
+ "loss": 0.2871,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 4.038095238095238,
748
+ "grad_norm": 1.069034457206726,
749
+ "learning_rate": 2.470030568897938e-06,
750
+ "loss": 0.1101,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 4.076190476190476,
755
+ "grad_norm": 1.0345056056976318,
756
+ "learning_rate": 2.3808580878919948e-06,
757
+ "loss": 0.1146,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 4.114285714285714,
762
+ "grad_norm": 1.0240198373794556,
763
+ "learning_rate": 2.2928192835717642e-06,
764
+ "loss": 0.1064,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 4.152380952380953,
769
+ "grad_norm": 1.4057704210281372,
770
+ "learning_rate": 2.205952262898704e-06,
771
+ "loss": 0.1041,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 4.190476190476191,
776
+ "grad_norm": 1.089251160621643,
777
+ "learning_rate": 2.120294625636171e-06,
778
+ "loss": 0.1048,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 4.228571428571429,
783
+ "grad_norm": 1.0048580169677734,
784
+ "learning_rate": 2.0358834480746363e-06,
785
+ "loss": 0.1026,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 4.266666666666667,
790
+ "grad_norm": 1.0335818529129028,
791
+ "learning_rate": 1.9527552669834797e-06,
792
+ "loss": 0.094,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 4.304761904761905,
797
+ "grad_norm": 1.1736409664154053,
798
+ "learning_rate": 1.8709460637963123e-06,
799
+ "loss": 0.0951,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 4.3428571428571425,
804
+ "grad_norm": 1.2718082666397095,
805
+ "learning_rate": 1.7904912490366723e-06,
806
+ "loss": 0.0957,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 4.380952380952381,
811
+ "grad_norm": 1.1848101615905762,
812
+ "learning_rate": 1.711425646990838e-06,
813
+ "loss": 0.0952,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 4.419047619047619,
818
+ "grad_norm": 1.1475728750228882,
819
+ "learning_rate": 1.6337834806343783e-06,
820
+ "loss": 0.0939,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 4.457142857142857,
825
+ "grad_norm": 1.2558069229125977,
826
+ "learning_rate": 1.557598356819e-06,
827
+ "loss": 0.0985,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 4.495238095238095,
832
+ "grad_norm": 1.310692548751831,
833
+ "learning_rate": 1.482903251726049e-06,
834
+ "loss": 0.1057,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 4.533333333333333,
839
+ "grad_norm": 1.1631875038146973,
840
+ "learning_rate": 1.409730496593016e-06,
841
+ "loss": 0.0999,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 4.571428571428571,
846
+ "grad_norm": 1.1441932916641235,
847
+ "learning_rate": 1.3381117637191887e-06,
848
+ "loss": 0.0918,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 4.609523809523809,
853
+ "grad_norm": 1.1489994525909424,
854
+ "learning_rate": 1.2680780527565313e-06,
855
+ "loss": 0.0931,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 4.647619047619048,
860
+ "grad_norm": 1.1286568641662598,
861
+ "learning_rate": 1.1996596772917091e-06,
862
+ "loss": 0.0933,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 4.685714285714286,
867
+ "grad_norm": 1.0700788497924805,
868
+ "learning_rate": 1.132886251725061e-06,
869
+ "loss": 0.0919,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 4.723809523809524,
874
+ "grad_norm": 1.1247611045837402,
875
+ "learning_rate": 1.0677866784522317e-06,
876
+ "loss": 0.0933,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 4.761904761904762,
881
+ "grad_norm": 1.1145604848861694,
882
+ "learning_rate": 1.004389135353972e-06,
883
+ "loss": 0.0989,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 4.8,
888
+ "grad_norm": 1.10590398311615,
889
+ "learning_rate": 9.427210635995482e-07,
890
+ "loss": 0.099,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 4.838095238095238,
895
+ "grad_norm": 1.0256025791168213,
896
+ "learning_rate": 8.828091557690288e-07,
897
+ "loss": 0.0876,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 4.876190476190477,
902
+ "grad_norm": 1.118198275566101,
903
+ "learning_rate": 8.246793442995954e-07,
904
+ "loss": 0.1009,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 4.914285714285715,
909
+ "grad_norm": 1.1724058389663696,
910
+ "learning_rate": 7.68356790260873e-07,
911
+ "loss": 0.0953,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 4.9523809523809526,
916
+ "grad_norm": 1.0902793407440186,
917
+ "learning_rate": 7.138658724641417e-07,
918
+ "loss": 0.0922,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 4.9904761904761905,
923
+ "grad_norm": 1.0752878189086914,
924
+ "learning_rate": 6.612301769101464e-07,
925
+ "loss": 0.0936,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 5.0285714285714285,
930
+ "grad_norm": 2.0665369033813477,
931
+ "learning_rate": 6.104724865800665e-07,
932
+ "loss": 0.1454,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 5.066666666666666,
937
+ "grad_norm": 0.9048326015472412,
938
+ "learning_rate": 5.616147715740611e-07,
939
+ "loss": 0.0767,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 5.104761904761904,
944
+ "grad_norm": 0.7645267844200134,
945
+ "learning_rate": 5.146781796016798e-07,
946
+ "loss": 0.0593,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 5.142857142857143,
951
+ "grad_norm": 1.0063519477844238,
952
+ "learning_rate": 4.696830268282204e-07,
953
+ "loss": 0.0746,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 5.180952380952381,
958
+ "grad_norm": 0.8538525104522705,
959
+ "learning_rate": 4.2664878908102556e-07,
960
+ "loss": 0.0687,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 5.219047619047619,
965
+ "grad_norm": 0.777083158493042,
966
+ "learning_rate": 3.855940934195146e-07,
967
+ "loss": 0.0634,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 5.257142857142857,
972
+ "grad_norm": 0.8090792894363403,
973
+ "learning_rate": 3.4653671007259084e-07,
974
+ "loss": 0.0618,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 5.295238095238095,
979
+ "grad_norm": 0.7944886088371277,
980
+ "learning_rate": 3.0949354474692937e-07,
981
+ "loss": 0.0678,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 5.333333333333333,
986
+ "grad_norm": 0.8538249135017395,
987
+ "learning_rate": 2.7448063130946224e-07,
988
+ "loss": 0.0724,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 5.371428571428572,
993
+ "grad_norm": 0.8483505249023438,
994
+ "learning_rate": 2.4151312484723465e-07,
995
+ "loss": 0.073,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 5.40952380952381,
1000
+ "grad_norm": 0.8070799708366394,
1001
+ "learning_rate": 2.106052951076365e-07,
1002
+ "loss": 0.0648,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 5.447619047619048,
1007
+ "grad_norm": 0.8302094340324402,
1008
+ "learning_rate": 1.8177052032184285e-07,
1009
+ "loss": 0.0674,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 5.485714285714286,
1014
+ "grad_norm": 0.7968501448631287,
1015
+ "learning_rate": 1.5502128141414496e-07,
1016
+ "loss": 0.0607,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 5.523809523809524,
1021
+ "grad_norm": 0.8013125061988831,
1022
+ "learning_rate": 1.303691565996712e-07,
1023
+ "loss": 0.0685,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 5.561904761904762,
1028
+ "grad_norm": 0.8090999126434326,
1029
+ "learning_rate": 1.0782481637284014e-07,
1030
+ "loss": 0.0652,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 5.6,
1035
+ "grad_norm": 0.8096015453338623,
1036
+ "learning_rate": 8.739801888871468e-08,
1037
+ "loss": 0.066,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 5.638095238095238,
1042
+ "grad_norm": 0.8489735722541809,
1043
+ "learning_rate": 6.909760573925561e-08,
1044
+ "loss": 0.0701,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 5.6761904761904765,
1049
+ "grad_norm": 0.7535190582275391,
1050
+ "learning_rate": 5.2931498126298495e-08,
1051
+ "loss": 0.0636,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 5.714285714285714,
1056
+ "grad_norm": 0.753428041934967,
1057
+ "learning_rate": 3.890669343292464e-08,
1058
+ "loss": 0.0588,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 5.752380952380952,
1063
+ "grad_norm": 0.7326428890228271,
1064
+ "learning_rate": 2.702926219468882e-08,
1065
+ "loss": 0.0611,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 5.79047619047619,
1070
+ "grad_norm": 0.8159373998641968,
1071
+ "learning_rate": 1.7304345472035634e-08,
1072
+ "loss": 0.0643,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 5.828571428571428,
1077
+ "grad_norm": 0.7761690616607666,
1078
+ "learning_rate": 9.73615262502503e-09,
1079
+ "loss": 0.0633,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 5.866666666666667,
1084
+ "grad_norm": 0.7957490086555481,
1085
+ "learning_rate": 4.327959491344791e-09,
1086
+ "loss": 0.0654,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 5.904761904761905,
1091
+ "grad_norm": 0.7681158185005188,
1092
+ "learning_rate": 1.082106968385288e-09,
1093
+ "loss": 0.0605,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 5.942857142857143,
1098
+ "grad_norm": 0.8738431930541992,
1099
+ "learning_rate": 0.0,
1100
+ "loss": 0.0661,
1101
+ "step": 156
1102
+ }
1103
+ ],
1104
+ "logging_steps": 1.0,
1105
+ "max_steps": 156,
1106
+ "num_input_tokens_seen": 0,
1107
+ "num_train_epochs": 6,
1108
+ "save_steps": 500,
1109
+ "stateful_callbacks": {
1110
+ "TrainerControl": {
1111
+ "args": {
1112
+ "should_epoch_stop": false,
1113
+ "should_evaluate": false,
1114
+ "should_log": false,
1115
+ "should_save": true,
1116
+ "should_training_stop": true
1117
+ },
1118
+ "attributes": {}
1119
+ }
1120
+ },
1121
+ "total_flos": 26907733843968.0,
1122
+ "train_batch_size": 2,
1123
+ "trial_name": null,
1124
+ "trial_params": null
1125
+ }
sft_search/JOB:24815#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_resp_difficulty_1678_ablation/checkpoint-156/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
sft_search/JOB:28315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-7B#TOKEN:DeepSeek-R1-Distill-Qwen-7B#BSZ:2#ACC:4_no_error_data_871/checkpoint-68/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end▁of▁sentence|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end▁of▁sentence|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
sft_search/JOB:28315#LR:1e-5#BASE:DeepSeek-R1-Distill-Qwen-7B#TOKEN:DeepSeek-R1-Distill-Qwen-7B#BSZ:2#ACC:4_no_error_data_871/checkpoint-68/tokenizer_config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<|end▁of▁sentence|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<|User|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": false
21
+ },
22
+ "151645": {
23
+ "content": "<|Assistant|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "151646": {
31
+ "content": "<|begin▁of▁sentence|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|EOT|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "151648": {
47
+ "content": "<think>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "151649": {
55
+ "content": "</think>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ }
182
+ },
183
+ "bos_token": "<|begin▁of▁sentence|>",
184
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin��>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\\n'}}{% endif %}",
185
+ "clean_up_tokenization_spaces": false,
186
+ "eos_token": "<|end▁of▁sentence|>",
187
+ "legacy": true,
188
+ "model_max_length": 30000,
189
+ "pad_token": "<|end▁of▁sentence|>",
190
+ "sp_model_kwargs": {},
191
+ "tokenizer_class": "LlamaTokenizer",
192
+ "unk_token": null,
193
+ "use_default_system_prompt": false
194
+ }
sft_search/JOB:29477#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_ques_keywords_filtered_data_727_ablation/checkpoint-46/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c48f08eda140833118fd90e98fab40d14edc614b988fe872d1bb55e5b644831
3
+ size 4877660776
sft_search/JOB:29477#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_ques_keywords_filtered_data_727_ablation/checkpoint-46/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e471c40a89f98c9b814068d39abaff53211d85a44e3a7fdcc12a4358f10609ad
3
+ size 4932751008
sft_search/JOB:29477#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_ques_keywords_filtered_data_727_ablation/checkpoint-46/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7282131044a02553501cc98ee23e98522c9b773533061ad84344f52e0e526b80
3
+ size 4330865200
sft_search/JOB:29477#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_ques_keywords_filtered_data_727_ablation/checkpoint-46/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:376c3edc00b2635734f7751bfcf100d66d3956095138466b4ba52270162a8c07
3
+ size 1089994880
sft_search/JOB:29477#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_ques_keywords_filtered_data_727_ablation/checkpoint-46/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
sft_search/JOB:29477#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_ablation_ques_keywords_filtered_data_727_ablation/checkpoint-46/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3b7798198a4c2944d6a6de189cfa15e1839a07aba7769bff2558f81cc8a9965
3
+ size 7544
sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-55/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-55/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/capacity/userdata/models/Qwen2.5-7B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.0",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
sft_search/JOB:30936#LR:1e-5#BASE:Qwen2.5-7B-Instruct#TOKEN:Qwen2.5-7B-Instruct#BSZ:2#ACC:4_math_qwq_4524_selected_add_prompt_871/checkpoint-55/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.46.0"
14
+ }