Jackson0018 commited on
Commit
1ea155f
·
verified ·
1 Parent(s): ad324e3

Initial private upload

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 +6 -0
  2. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/DPO_configs.json +181 -0
  3. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/README.md +70 -0
  4. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/README.md +210 -0
  5. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/adapter_config.json +42 -0
  6. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/adapter_model.safetensors +3 -0
  7. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/chat_template.jinja +93 -0
  8. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/optimizer.pt +3 -0
  9. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/rng_state.pth +3 -0
  10. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/scheduler.pt +3 -0
  11. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/special_tokens_map.json +17 -0
  12. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/tokenizer.json +3 -0
  13. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/tokenizer_config.json +2066 -0
  14. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/trainer_state.json +1054 -0
  15. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/training_args.bin +3 -0
  16. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/chat_template.jinja +93 -0
  17. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/config.json +39 -0
  18. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/generation_config.json +12 -0
  19. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/model-00001-of-00003.safetensors +3 -0
  20. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/model-00002-of-00003.safetensors +3 -0
  21. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/model-00003-of-00003.safetensors +3 -0
  22. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/model.safetensors.index.json +262 -0
  23. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/special_tokens_map.json +16 -0
  24. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/tokenizer.json +3 -0
  25. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/tokenizer_config.json +2062 -0
  26. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/model_args.json +4 -0
  27. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/train_args.json +3 -0
  28. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/DPO_configs.json +181 -0
  29. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/README.md +70 -0
  30. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/README.md +210 -0
  31. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/adapter_config.json +42 -0
  32. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/adapter_model.safetensors +3 -0
  33. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/chat_template.jinja +93 -0
  34. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/optimizer.pt +3 -0
  35. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/rng_state.pth +3 -0
  36. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/scheduler.pt +3 -0
  37. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/special_tokens_map.json +17 -0
  38. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/tokenizer.json +3 -0
  39. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/tokenizer_config.json +2066 -0
  40. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/trainer_state.json +1054 -0
  41. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/training_args.bin +3 -0
  42. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/chat_template.jinja +93 -0
  43. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/config.json +39 -0
  44. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/generation_config.json +12 -0
  45. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/model-00001-of-00003.safetensors +3 -0
  46. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/model-00002-of-00003.safetensors +3 -0
  47. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/model-00003-of-00003.safetensors +3 -0
  48. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/model.safetensors.index.json +262 -0
  49. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/special_tokens_map.json +16 -0
  50. Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/tokenizer.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,9 @@ 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
+ Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/research_question_agent/checkpoint-681/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/research_question_agent/merged_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/DPO_configs.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "Trained_Models/Jackson0018/Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent",
3
+ "overwrite_output_dir": null,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "no",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 1,
10
+ "per_device_eval_batch_size": 4,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 32,
14
+ "eval_accumulation_steps": 2,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": 250,
17
+ "learning_rate": 1e-05,
18
+ "weight_decay": 0.01,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.999,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 0.6,
23
+ "num_train_epochs": 3.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "linear",
26
+ "lr_scheduler_kwargs": {},
27
+ "warmup_ratio": 0.1,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "Trained_Models/Jackson0018/Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/runs/Sep18_20-43-54_ai16",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": false,
35
+ "logging_steps": 10,
36
+ "logging_nan_inf_filter": false,
37
+ "save_strategy": "steps",
38
+ "save_steps": 10000,
39
+ "save_total_limit": null,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 3407,
48
+ "data_seed": 3407,
49
+ "jit_mode_eval": false,
50
+ "use_ipex": false,
51
+ "bf16": true,
52
+ "fp16": false,
53
+ "fp16_opt_level": "O1",
54
+ "half_precision_backend": "auto",
55
+ "bf16_full_eval": false,
56
+ "fp16_full_eval": false,
57
+ "tf32": null,
58
+ "local_rank": 0,
59
+ "ddp_backend": null,
60
+ "tpu_num_cores": null,
61
+ "tpu_metrics_debug": false,
62
+ "debug": [],
63
+ "dataloader_drop_last": false,
64
+ "eval_steps": null,
65
+ "dataloader_num_workers": 0,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": null,
69
+ "disable_tqdm": false,
70
+ "remove_unused_columns": true,
71
+ "label_names": null,
72
+ "load_best_model_at_end": false,
73
+ "metric_for_best_model": null,
74
+ "greater_is_better": null,
75
+ "ignore_data_skip": false,
76
+ "fsdp": [],
77
+ "fsdp_min_num_params": 0,
78
+ "fsdp_config": {
79
+ "min_num_params": 0,
80
+ "xla": false,
81
+ "xla_fsdp_v2": false,
82
+ "xla_fsdp_grad_ckpt": false
83
+ },
84
+ "fsdp_transformer_layer_cls_to_wrap": null,
85
+ "accelerator_config": {
86
+ "split_batches": false,
87
+ "dispatch_batches": null,
88
+ "even_batches": true,
89
+ "use_seedable_sampler": true,
90
+ "non_blocking": false,
91
+ "gradient_accumulation_kwargs": null
92
+ },
93
+ "deepspeed": null,
94
+ "label_smoothing_factor": 0.0,
95
+ "optim": "adamw_8bit",
96
+ "optim_args": null,
97
+ "adafactor": false,
98
+ "group_by_length": false,
99
+ "length_column_name": "length",
100
+ "report_to": [],
101
+ "ddp_find_unused_parameters": null,
102
+ "ddp_bucket_cap_mb": null,
103
+ "ddp_broadcast_buffers": null,
104
+ "dataloader_pin_memory": true,
105
+ "dataloader_persistent_workers": false,
106
+ "skip_memory_metrics": true,
107
+ "use_legacy_prediction_loop": false,
108
+ "push_to_hub": false,
109
+ "resume_from_checkpoint": null,
110
+ "hub_model_id": null,
111
+ "hub_strategy": "every_save",
112
+ "hub_token": "<HUB_TOKEN>",
113
+ "hub_private_repo": null,
114
+ "hub_always_push": false,
115
+ "hub_revision": null,
116
+ "gradient_checkpointing": false,
117
+ "gradient_checkpointing_kwargs": null,
118
+ "include_inputs_for_metrics": false,
119
+ "include_for_metrics": [],
120
+ "eval_do_concat_batches": true,
121
+ "fp16_backend": "auto",
122
+ "push_to_hub_model_id": null,
123
+ "push_to_hub_organization": null,
124
+ "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
125
+ "mp_parameters": "",
126
+ "auto_find_batch_size": true,
127
+ "full_determinism": false,
128
+ "torchdynamo": null,
129
+ "ray_scope": "last",
130
+ "ddp_timeout": 1800,
131
+ "torch_compile": false,
132
+ "torch_compile_backend": null,
133
+ "torch_compile_mode": null,
134
+ "include_tokens_per_second": false,
135
+ "include_num_input_tokens_seen": false,
136
+ "neftune_noise_alpha": null,
137
+ "optim_target_modules": null,
138
+ "batch_eval_metrics": false,
139
+ "eval_on_start": false,
140
+ "use_liger_kernel": false,
141
+ "liger_kernel_config": null,
142
+ "eval_use_gather_object": false,
143
+ "average_tokens_across_devices": false,
144
+ "model_init_kwargs": null,
145
+ "ref_model_init_kwargs": null,
146
+ "model_adapter_name": null,
147
+ "ref_adapter_name": null,
148
+ "force_use_ref_model": false,
149
+ "disable_dropout": true,
150
+ "use_logits_to_keep": false,
151
+ "dataset_num_proc": 2,
152
+ "padding_value": null,
153
+ "label_pad_token_id": -100,
154
+ "max_prompt_length": 2000,
155
+ "max_completion_length": 2000,
156
+ "max_length": 4000,
157
+ "truncation_mode": "keep_end",
158
+ "padding_free": false,
159
+ "precompute_ref_log_probs": false,
160
+ "precompute_ref_batch_size": null,
161
+ "tools": null,
162
+ "loss_type": "sigmoid",
163
+ "use_liger_loss": false,
164
+ "base_model_attribute_name": "model",
165
+ "beta": 0.1,
166
+ "f_divergence_type": "reverse_kl",
167
+ "f_alpha_divergence_coef": 1.0,
168
+ "reference_free": false,
169
+ "label_smoothing": 0.0,
170
+ "use_weighting": false,
171
+ "rpo_alpha": null,
172
+ "ld_alpha": null,
173
+ "discopop_tau": 0.05,
174
+ "loss_weights": null,
175
+ "sync_ref_model": false,
176
+ "ref_model_mixup_alpha": 0.6,
177
+ "ref_model_sync_steps": 512,
178
+ "generate_during_eval": false,
179
+ "vllm_sampling_params": null,
180
+ "unsloth_num_chunks": -1
181
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
3
+ library_name: transformers
4
+ model_name: experiment_agent
5
+ tags:
6
+ - generated_from_trainer
7
+ - unsloth
8
+ - trl
9
+ - dpo
10
+ licence: license
11
+ ---
12
+
13
+ # Model Card for experiment_agent
14
+
15
+ This model is a fine-tuned version of [unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit).
16
+ It has been trained using [TRL](https://github.com/huggingface/trl).
17
+
18
+ ## Quick start
19
+
20
+ ```python
21
+ from transformers import pipeline
22
+
23
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
24
+ generator = pipeline("text-generation", model="None", device="cuda")
25
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
26
+ print(output["generated_text"])
27
+ ```
28
+
29
+ ## Training procedure
30
+
31
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jackson0530/ScientificPaperRetrieval_Train-Train_DPO_unsloth/runs/4ppdrs38)
32
+
33
+
34
+ This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
35
+
36
+ ### Framework versions
37
+
38
+ - TRL: 0.21.0
39
+ - Transformers: 4.55.0
40
+ - Pytorch: 2.7.1
41
+ - Datasets: 3.6.0
42
+ - Tokenizers: 0.21.4
43
+
44
+ ## Citations
45
+
46
+ Cite DPO as:
47
+
48
+ ```bibtex
49
+ @inproceedings{rafailov2023direct,
50
+ title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
51
+ author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
52
+ year = 2023,
53
+ booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
54
+ url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
55
+ editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
56
+ }
57
+ ```
58
+
59
+ Cite TRL as:
60
+
61
+ ```bibtex
62
+ @misc{vonwerra2022trl,
63
+ title = {{TRL: Transformer Reinforcement Learning}},
64
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
65
+ year = 2020,
66
+ journal = {GitHub repository},
67
+ publisher = {GitHub},
68
+ howpublished = {\url{https://github.com/huggingface/trl}}
69
+ }
70
+ ```
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/README.md ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
7
+ - dpo
8
+ - lora
9
+ - transformers
10
+ - trl
11
+ - unsloth
12
+ ---
13
+
14
+ # Model Card for Model ID
15
+
16
+ <!-- Provide a quick summary of what the model is/does. -->
17
+
18
+
19
+
20
+ ## Model Details
21
+
22
+ ### Model Description
23
+
24
+ <!-- Provide a longer summary of what this model is. -->
25
+
26
+
27
+
28
+ - **Developed by:** [More Information Needed]
29
+ - **Funded by [optional]:** [More Information Needed]
30
+ - **Shared by [optional]:** [More Information Needed]
31
+ - **Model type:** [More Information Needed]
32
+ - **Language(s) (NLP):** [More Information Needed]
33
+ - **License:** [More Information Needed]
34
+ - **Finetuned from model [optional]:** [More Information Needed]
35
+
36
+ ### Model Sources [optional]
37
+
38
+ <!-- Provide the basic links for the model. -->
39
+
40
+ - **Repository:** [More Information Needed]
41
+ - **Paper [optional]:** [More Information Needed]
42
+ - **Demo [optional]:** [More Information Needed]
43
+
44
+ ## Uses
45
+
46
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
+
48
+ ### Direct Use
49
+
50
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Downstream Use [optional]
55
+
56
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
+
58
+ [More Information Needed]
59
+
60
+ ### Out-of-Scope Use
61
+
62
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ## Bias, Risks, and Limitations
67
+
68
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
+
70
+ [More Information Needed]
71
+
72
+ ### Recommendations
73
+
74
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
+
76
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
+
78
+ ## How to Get Started with the Model
79
+
80
+ Use the code below to get started with the model.
81
+
82
+ [More Information Needed]
83
+
84
+ ## Training Details
85
+
86
+ ### Training Data
87
+
88
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
89
+
90
+ [More Information Needed]
91
+
92
+ ### Training Procedure
93
+
94
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
+
96
+ #### Preprocessing [optional]
97
+
98
+ [More Information Needed]
99
+
100
+
101
+ #### Training Hyperparameters
102
+
103
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
+
105
+ #### Speeds, Sizes, Times [optional]
106
+
107
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
+
109
+ [More Information Needed]
110
+
111
+ ## Evaluation
112
+
113
+ <!-- This section describes the evaluation protocols and provides the results. -->
114
+
115
+ ### Testing Data, Factors & Metrics
116
+
117
+ #### Testing Data
118
+
119
+ <!-- This should link to a Dataset Card if possible. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Factors
124
+
125
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
+
127
+ [More Information Needed]
128
+
129
+ #### Metrics
130
+
131
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
+
133
+ [More Information Needed]
134
+
135
+ ### Results
136
+
137
+ [More Information Needed]
138
+
139
+ #### Summary
140
+
141
+
142
+
143
+ ## Model Examination [optional]
144
+
145
+ <!-- Relevant interpretability work for the model goes here -->
146
+
147
+ [More Information Needed]
148
+
149
+ ## Environmental Impact
150
+
151
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
+
153
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
154
+
155
+ - **Hardware Type:** [More Information Needed]
156
+ - **Hours used:** [More Information Needed]
157
+ - **Cloud Provider:** [More Information Needed]
158
+ - **Compute Region:** [More Information Needed]
159
+ - **Carbon Emitted:** [More Information Needed]
160
+
161
+ ## Technical Specifications [optional]
162
+
163
+ ### Model Architecture and Objective
164
+
165
+ [More Information Needed]
166
+
167
+ ### Compute Infrastructure
168
+
169
+ [More Information Needed]
170
+
171
+ #### Hardware
172
+
173
+ [More Information Needed]
174
+
175
+ #### Software
176
+
177
+ [More Information Needed]
178
+
179
+ ## Citation [optional]
180
+
181
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
+
183
+ **BibTeX:**
184
+
185
+ [More Information Needed]
186
+
187
+ **APA:**
188
+
189
+ [More Information Needed]
190
+
191
+ ## Glossary [optional]
192
+
193
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
+
195
+ [More Information Needed]
196
+
197
+ ## More Information [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Authors [optional]
202
+
203
+ [More Information Needed]
204
+
205
+ ## Model Card Contact
206
+
207
+ [More Information Needed]
208
+ ### Framework versions
209
+
210
+ - PEFT 0.17.0
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 64,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 64,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "v_proj",
29
+ "gate_proj",
30
+ "o_proj",
31
+ "down_proj",
32
+ "k_proj",
33
+ "up_proj",
34
+ "q_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36b6d80ccb221c36041b4154c8e6afbc26daf0d45d4ba0efb9de4f5aa2d2859c
3
+ size 389074464
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/chat_template.jinja ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- if strftime_now is defined %}
10
+ {%- set date_string = strftime_now("%d %b %Y") %}
11
+ {%- else %}
12
+ {%- set date_string = "26 Jul 2024" %}
13
+ {%- endif %}
14
+ {%- endif %}
15
+ {%- if not tools is defined %}
16
+ {%- set tools = none %}
17
+ {%- endif %}
18
+
19
+ {#- This block extracts the system message, so we can slot it into the right place. #}
20
+ {%- if messages[0]['role'] == 'system' %}
21
+ {%- set system_message = messages[0]['content']|trim %}
22
+ {%- set messages = messages[1:] %}
23
+ {%- else %}
24
+ {%- set system_message = "" %}
25
+ {%- endif %}
26
+
27
+ {#- System message #}
28
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
29
+ {%- if tools is not none %}
30
+ {{- "Environment: ipython\n" }}
31
+ {%- endif %}
32
+ {{- "Cutting Knowledge Date: December 2023\n" }}
33
+ {{- "Today Date: " + date_string + "\n\n" }}
34
+ {%- if tools is not none and not tools_in_user_message %}
35
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
36
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
37
+ {{- "Do not use variables.\n\n" }}
38
+ {%- for t in tools %}
39
+ {{- t | tojson(indent=4) }}
40
+ {{- "\n\n" }}
41
+ {%- endfor %}
42
+ {%- endif %}
43
+ {{- system_message }}
44
+ {{- "<|eot_id|>" }}
45
+
46
+ {#- Custom tools are passed in a user message with some extra guidance #}
47
+ {%- if tools_in_user_message and not tools is none %}
48
+ {#- Extract the first user message so we can plug it in here #}
49
+ {%- if messages | length != 0 %}
50
+ {%- set first_user_message = messages[0]['content']|trim %}
51
+ {%- set messages = messages[1:] %}
52
+ {%- else %}
53
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
54
+ {%- endif %}
55
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
56
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
57
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
58
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
59
+ {{- "Do not use variables.\n\n" }}
60
+ {%- for t in tools %}
61
+ {{- t | tojson(indent=4) }}
62
+ {{- "\n\n" }}
63
+ {%- endfor %}
64
+ {{- first_user_message + "<|eot_id|>"}}
65
+ {%- endif %}
66
+
67
+ {%- for message in messages %}
68
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
69
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
70
+ {%- elif 'tool_calls' in message %}
71
+ {%- if not message.tool_calls|length == 1 %}
72
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
73
+ {%- endif %}
74
+ {%- set tool_call = message.tool_calls[0].function %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- '{"name": "' + tool_call.name + '", ' }}
77
+ {{- '"parameters": ' }}
78
+ {{- tool_call.arguments | tojson }}
79
+ {{- "}" }}
80
+ {{- "<|eot_id|>" }}
81
+ {%- elif message.role == "tool" or message.role == "ipython" %}
82
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
83
+ {%- if message.content is mapping or message.content is iterable %}
84
+ {{- message.content | tojson }}
85
+ {%- else %}
86
+ {{- message.content }}
87
+ {%- endif %}
88
+ {{- "<|eot_id|>" }}
89
+ {%- endif %}
90
+ {%- endfor %}
91
+ {%- if add_generation_prompt %}
92
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
93
+ {%- endif %}
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bcfe2b6c0aa158b51087c4e4dc63f4735e5c15b4efabf354f91280704f433bd
3
+ size 198012101
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:181c5f0270cf39930062ddfa3767a2481d0c360f120b11f8e25dbf533a1cdaba
3
+ size 14645
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:148e7306497dc207073c9b6fe0ab52f28c76df842441b72a817edc0055612b40
3
+ size 1465
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/tokenizer_config.json ADDED
@@ -0,0 +1,2066 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "added_tokens_decoder": {
4
+ "128000": {
5
+ "content": "<|begin_of_text|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128001": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "128002": {
21
+ "content": "<|reserved_special_token_0|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "128003": {
29
+ "content": "<|reserved_special_token_1|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128004": {
37
+ "content": "<|finetune_right_pad_id|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128005": {
45
+ "content": "<|reserved_special_token_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128006": {
53
+ "content": "<|start_header_id|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128007": {
61
+ "content": "<|end_header_id|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128008": {
69
+ "content": "<|eom_id|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128009": {
77
+ "content": "<|eot_id|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128010": {
85
+ "content": "<|python_tag|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128011": {
93
+ "content": "<|reserved_special_token_3|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128012": {
101
+ "content": "<|reserved_special_token_4|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128013": {
109
+ "content": "<|reserved_special_token_5|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128014": {
117
+ "content": "<|reserved_special_token_6|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128015": {
125
+ "content": "<|reserved_special_token_7|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128016": {
133
+ "content": "<|reserved_special_token_8|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128017": {
141
+ "content": "<|reserved_special_token_9|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128018": {
149
+ "content": "<|reserved_special_token_10|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128019": {
157
+ "content": "<|reserved_special_token_11|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128020": {
165
+ "content": "<|reserved_special_token_12|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128021": {
173
+ "content": "<|reserved_special_token_13|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128022": {
181
+ "content": "<|reserved_special_token_14|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128023": {
189
+ "content": "<|reserved_special_token_15|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128024": {
197
+ "content": "<|reserved_special_token_16|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128025": {
205
+ "content": "<|reserved_special_token_17|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128026": {
213
+ "content": "<|reserved_special_token_18|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128027": {
221
+ "content": "<|reserved_special_token_19|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128028": {
229
+ "content": "<|reserved_special_token_20|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128029": {
237
+ "content": "<|reserved_special_token_21|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128030": {
245
+ "content": "<|reserved_special_token_22|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128031": {
253
+ "content": "<|reserved_special_token_23|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128032": {
261
+ "content": "<|reserved_special_token_24|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128033": {
269
+ "content": "<|reserved_special_token_25|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128034": {
277
+ "content": "<|reserved_special_token_26|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128035": {
285
+ "content": "<|reserved_special_token_27|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128036": {
293
+ "content": "<|reserved_special_token_28|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128037": {
301
+ "content": "<|reserved_special_token_29|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128038": {
309
+ "content": "<|reserved_special_token_30|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128039": {
317
+ "content": "<|reserved_special_token_31|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128040": {
325
+ "content": "<|reserved_special_token_32|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128041": {
333
+ "content": "<|reserved_special_token_33|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128042": {
341
+ "content": "<|reserved_special_token_34|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128043": {
349
+ "content": "<|reserved_special_token_35|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128044": {
357
+ "content": "<|reserved_special_token_36|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128045": {
365
+ "content": "<|reserved_special_token_37|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128046": {
373
+ "content": "<|reserved_special_token_38|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128047": {
381
+ "content": "<|reserved_special_token_39|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128048": {
389
+ "content": "<|reserved_special_token_40|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128049": {
397
+ "content": "<|reserved_special_token_41|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128050": {
405
+ "content": "<|reserved_special_token_42|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128051": {
413
+ "content": "<|reserved_special_token_43|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128052": {
421
+ "content": "<|reserved_special_token_44|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128053": {
429
+ "content": "<|reserved_special_token_45|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128054": {
437
+ "content": "<|reserved_special_token_46|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128055": {
445
+ "content": "<|reserved_special_token_47|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128056": {
453
+ "content": "<|reserved_special_token_48|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128057": {
461
+ "content": "<|reserved_special_token_49|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128058": {
469
+ "content": "<|reserved_special_token_50|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128059": {
477
+ "content": "<|reserved_special_token_51|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128060": {
485
+ "content": "<|reserved_special_token_52|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128061": {
493
+ "content": "<|reserved_special_token_53|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128062": {
501
+ "content": "<|reserved_special_token_54|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128063": {
509
+ "content": "<|reserved_special_token_55|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128064": {
517
+ "content": "<|reserved_special_token_56|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128065": {
525
+ "content": "<|reserved_special_token_57|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128066": {
533
+ "content": "<|reserved_special_token_58|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128067": {
541
+ "content": "<|reserved_special_token_59|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128068": {
549
+ "content": "<|reserved_special_token_60|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128069": {
557
+ "content": "<|reserved_special_token_61|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128070": {
565
+ "content": "<|reserved_special_token_62|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128071": {
573
+ "content": "<|reserved_special_token_63|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128072": {
581
+ "content": "<|reserved_special_token_64|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128073": {
589
+ "content": "<|reserved_special_token_65|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128074": {
597
+ "content": "<|reserved_special_token_66|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128075": {
605
+ "content": "<|reserved_special_token_67|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128076": {
613
+ "content": "<|reserved_special_token_68|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128077": {
621
+ "content": "<|reserved_special_token_69|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128078": {
629
+ "content": "<|reserved_special_token_70|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128079": {
637
+ "content": "<|reserved_special_token_71|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128080": {
645
+ "content": "<|reserved_special_token_72|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128081": {
653
+ "content": "<|reserved_special_token_73|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128082": {
661
+ "content": "<|reserved_special_token_74|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128083": {
669
+ "content": "<|reserved_special_token_75|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128084": {
677
+ "content": "<|reserved_special_token_76|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128085": {
685
+ "content": "<|reserved_special_token_77|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128086": {
693
+ "content": "<|reserved_special_token_78|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128087": {
701
+ "content": "<|reserved_special_token_79|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128088": {
709
+ "content": "<|reserved_special_token_80|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128089": {
717
+ "content": "<|reserved_special_token_81|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128090": {
725
+ "content": "<|reserved_special_token_82|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128091": {
733
+ "content": "<|reserved_special_token_83|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128092": {
741
+ "content": "<|reserved_special_token_84|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128093": {
749
+ "content": "<|reserved_special_token_85|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128094": {
757
+ "content": "<|reserved_special_token_86|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128095": {
765
+ "content": "<|reserved_special_token_87|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128096": {
773
+ "content": "<|reserved_special_token_88|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128097": {
781
+ "content": "<|reserved_special_token_89|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128098": {
789
+ "content": "<|reserved_special_token_90|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128099": {
797
+ "content": "<|reserved_special_token_91|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128100": {
805
+ "content": "<|reserved_special_token_92|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128101": {
813
+ "content": "<|reserved_special_token_93|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128102": {
821
+ "content": "<|reserved_special_token_94|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128103": {
829
+ "content": "<|reserved_special_token_95|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128104": {
837
+ "content": "<|reserved_special_token_96|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128105": {
845
+ "content": "<|reserved_special_token_97|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "128106": {
853
+ "content": "<|reserved_special_token_98|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "128107": {
861
+ "content": "<|reserved_special_token_99|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "128108": {
869
+ "content": "<|reserved_special_token_100|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "128109": {
877
+ "content": "<|reserved_special_token_101|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "128110": {
885
+ "content": "<|reserved_special_token_102|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "128111": {
893
+ "content": "<|reserved_special_token_103|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "128112": {
901
+ "content": "<|reserved_special_token_104|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "128113": {
909
+ "content": "<|reserved_special_token_105|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "128114": {
917
+ "content": "<|reserved_special_token_106|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "128115": {
925
+ "content": "<|reserved_special_token_107|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "128116": {
933
+ "content": "<|reserved_special_token_108|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "128117": {
941
+ "content": "<|reserved_special_token_109|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "128118": {
949
+ "content": "<|reserved_special_token_110|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "128119": {
957
+ "content": "<|reserved_special_token_111|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "128120": {
965
+ "content": "<|reserved_special_token_112|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "128121": {
973
+ "content": "<|reserved_special_token_113|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "128122": {
981
+ "content": "<|reserved_special_token_114|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "128123": {
989
+ "content": "<|reserved_special_token_115|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "128124": {
997
+ "content": "<|reserved_special_token_116|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "128125": {
1005
+ "content": "<|reserved_special_token_117|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "128126": {
1013
+ "content": "<|reserved_special_token_118|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "128127": {
1021
+ "content": "<|reserved_special_token_119|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "128128": {
1029
+ "content": "<|reserved_special_token_120|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "128129": {
1037
+ "content": "<|reserved_special_token_121|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "128130": {
1045
+ "content": "<|reserved_special_token_122|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "128131": {
1053
+ "content": "<|reserved_special_token_123|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "128132": {
1061
+ "content": "<|reserved_special_token_124|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "128133": {
1069
+ "content": "<|reserved_special_token_125|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "128134": {
1077
+ "content": "<|reserved_special_token_126|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "128135": {
1085
+ "content": "<|reserved_special_token_127|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "128136": {
1093
+ "content": "<|reserved_special_token_128|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "128137": {
1101
+ "content": "<|reserved_special_token_129|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "128138": {
1109
+ "content": "<|reserved_special_token_130|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "128139": {
1117
+ "content": "<|reserved_special_token_131|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "128140": {
1125
+ "content": "<|reserved_special_token_132|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "128141": {
1133
+ "content": "<|reserved_special_token_133|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "128142": {
1141
+ "content": "<|reserved_special_token_134|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "128143": {
1149
+ "content": "<|reserved_special_token_135|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "128144": {
1157
+ "content": "<|reserved_special_token_136|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "128145": {
1165
+ "content": "<|reserved_special_token_137|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "128146": {
1173
+ "content": "<|reserved_special_token_138|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "128147": {
1181
+ "content": "<|reserved_special_token_139|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "128148": {
1189
+ "content": "<|reserved_special_token_140|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "128149": {
1197
+ "content": "<|reserved_special_token_141|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "128150": {
1205
+ "content": "<|reserved_special_token_142|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "128151": {
1213
+ "content": "<|reserved_special_token_143|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "128152": {
1221
+ "content": "<|reserved_special_token_144|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "128153": {
1229
+ "content": "<|reserved_special_token_145|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "128154": {
1237
+ "content": "<|reserved_special_token_146|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "128155": {
1245
+ "content": "<|reserved_special_token_147|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "128156": {
1253
+ "content": "<|reserved_special_token_148|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "128157": {
1261
+ "content": "<|reserved_special_token_149|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "128158": {
1269
+ "content": "<|reserved_special_token_150|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "128159": {
1277
+ "content": "<|reserved_special_token_151|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "128160": {
1285
+ "content": "<|reserved_special_token_152|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "128161": {
1293
+ "content": "<|reserved_special_token_153|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "128162": {
1301
+ "content": "<|reserved_special_token_154|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "128163": {
1309
+ "content": "<|reserved_special_token_155|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "128164": {
1317
+ "content": "<|reserved_special_token_156|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "128165": {
1325
+ "content": "<|reserved_special_token_157|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "128166": {
1333
+ "content": "<|reserved_special_token_158|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "128167": {
1341
+ "content": "<|reserved_special_token_159|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "128168": {
1349
+ "content": "<|reserved_special_token_160|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "128169": {
1357
+ "content": "<|reserved_special_token_161|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "128170": {
1365
+ "content": "<|reserved_special_token_162|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "128171": {
1373
+ "content": "<|reserved_special_token_163|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "128172": {
1381
+ "content": "<|reserved_special_token_164|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "128173": {
1389
+ "content": "<|reserved_special_token_165|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "128174": {
1397
+ "content": "<|reserved_special_token_166|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "128175": {
1405
+ "content": "<|reserved_special_token_167|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "128176": {
1413
+ "content": "<|reserved_special_token_168|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "128177": {
1421
+ "content": "<|reserved_special_token_169|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "128178": {
1429
+ "content": "<|reserved_special_token_170|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "128179": {
1437
+ "content": "<|reserved_special_token_171|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "128180": {
1445
+ "content": "<|reserved_special_token_172|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "128181": {
1453
+ "content": "<|reserved_special_token_173|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "128182": {
1461
+ "content": "<|reserved_special_token_174|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "128183": {
1469
+ "content": "<|reserved_special_token_175|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "128184": {
1477
+ "content": "<|reserved_special_token_176|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "128185": {
1485
+ "content": "<|reserved_special_token_177|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "128186": {
1493
+ "content": "<|reserved_special_token_178|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "128187": {
1501
+ "content": "<|reserved_special_token_179|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "128188": {
1509
+ "content": "<|reserved_special_token_180|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "128189": {
1517
+ "content": "<|reserved_special_token_181|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "128190": {
1525
+ "content": "<|reserved_special_token_182|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "128191": {
1533
+ "content": "<|reserved_special_token_183|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "128192": {
1541
+ "content": "<|reserved_special_token_184|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "128193": {
1549
+ "content": "<|reserved_special_token_185|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "128194": {
1557
+ "content": "<|reserved_special_token_186|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "128195": {
1565
+ "content": "<|reserved_special_token_187|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "128196": {
1573
+ "content": "<|reserved_special_token_188|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "128197": {
1581
+ "content": "<|reserved_special_token_189|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "128198": {
1589
+ "content": "<|reserved_special_token_190|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "128199": {
1597
+ "content": "<|reserved_special_token_191|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "128200": {
1605
+ "content": "<|reserved_special_token_192|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "128201": {
1613
+ "content": "<|reserved_special_token_193|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "128202": {
1621
+ "content": "<|reserved_special_token_194|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "128203": {
1629
+ "content": "<|reserved_special_token_195|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "128204": {
1637
+ "content": "<|reserved_special_token_196|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "128205": {
1645
+ "content": "<|reserved_special_token_197|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "128206": {
1653
+ "content": "<|reserved_special_token_198|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "128207": {
1661
+ "content": "<|reserved_special_token_199|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ },
1668
+ "128208": {
1669
+ "content": "<|reserved_special_token_200|>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": true
1675
+ },
1676
+ "128209": {
1677
+ "content": "<|reserved_special_token_201|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": true
1683
+ },
1684
+ "128210": {
1685
+ "content": "<|reserved_special_token_202|>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": true
1691
+ },
1692
+ "128211": {
1693
+ "content": "<|reserved_special_token_203|>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": true
1699
+ },
1700
+ "128212": {
1701
+ "content": "<|reserved_special_token_204|>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": true
1707
+ },
1708
+ "128213": {
1709
+ "content": "<|reserved_special_token_205|>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": true
1715
+ },
1716
+ "128214": {
1717
+ "content": "<|reserved_special_token_206|>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": true
1723
+ },
1724
+ "128215": {
1725
+ "content": "<|reserved_special_token_207|>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": true
1731
+ },
1732
+ "128216": {
1733
+ "content": "<|reserved_special_token_208|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": true
1739
+ },
1740
+ "128217": {
1741
+ "content": "<|reserved_special_token_209|>",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": true
1747
+ },
1748
+ "128218": {
1749
+ "content": "<|reserved_special_token_210|>",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": true
1755
+ },
1756
+ "128219": {
1757
+ "content": "<|reserved_special_token_211|>",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": true
1763
+ },
1764
+ "128220": {
1765
+ "content": "<|reserved_special_token_212|>",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": true
1771
+ },
1772
+ "128221": {
1773
+ "content": "<|reserved_special_token_213|>",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": true
1779
+ },
1780
+ "128222": {
1781
+ "content": "<|reserved_special_token_214|>",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": true
1787
+ },
1788
+ "128223": {
1789
+ "content": "<|reserved_special_token_215|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": true
1795
+ },
1796
+ "128224": {
1797
+ "content": "<|reserved_special_token_216|>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": true
1803
+ },
1804
+ "128225": {
1805
+ "content": "<|reserved_special_token_217|>",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": true
1811
+ },
1812
+ "128226": {
1813
+ "content": "<|reserved_special_token_218|>",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": true
1819
+ },
1820
+ "128227": {
1821
+ "content": "<|reserved_special_token_219|>",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": true
1827
+ },
1828
+ "128228": {
1829
+ "content": "<|reserved_special_token_220|>",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": true
1835
+ },
1836
+ "128229": {
1837
+ "content": "<|reserved_special_token_221|>",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": true
1843
+ },
1844
+ "128230": {
1845
+ "content": "<|reserved_special_token_222|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": true
1851
+ },
1852
+ "128231": {
1853
+ "content": "<|reserved_special_token_223|>",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": true
1859
+ },
1860
+ "128232": {
1861
+ "content": "<|reserved_special_token_224|>",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": true
1867
+ },
1868
+ "128233": {
1869
+ "content": "<|reserved_special_token_225|>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": true
1875
+ },
1876
+ "128234": {
1877
+ "content": "<|reserved_special_token_226|>",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": true
1883
+ },
1884
+ "128235": {
1885
+ "content": "<|reserved_special_token_227|>",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": true
1891
+ },
1892
+ "128236": {
1893
+ "content": "<|reserved_special_token_228|>",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": true
1899
+ },
1900
+ "128237": {
1901
+ "content": "<|reserved_special_token_229|>",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": true
1907
+ },
1908
+ "128238": {
1909
+ "content": "<|reserved_special_token_230|>",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": true
1915
+ },
1916
+ "128239": {
1917
+ "content": "<|reserved_special_token_231|>",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": true
1923
+ },
1924
+ "128240": {
1925
+ "content": "<|reserved_special_token_232|>",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": true
1931
+ },
1932
+ "128241": {
1933
+ "content": "<|reserved_special_token_233|>",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": true
1939
+ },
1940
+ "128242": {
1941
+ "content": "<|reserved_special_token_234|>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": true
1947
+ },
1948
+ "128243": {
1949
+ "content": "<|reserved_special_token_235|>",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": true
1955
+ },
1956
+ "128244": {
1957
+ "content": "<|reserved_special_token_236|>",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": true
1963
+ },
1964
+ "128245": {
1965
+ "content": "<|reserved_special_token_237|>",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": true
1971
+ },
1972
+ "128246": {
1973
+ "content": "<|reserved_special_token_238|>",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": true
1979
+ },
1980
+ "128247": {
1981
+ "content": "<|reserved_special_token_239|>",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": true
1987
+ },
1988
+ "128248": {
1989
+ "content": "<|reserved_special_token_240|>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": true
1995
+ },
1996
+ "128249": {
1997
+ "content": "<|reserved_special_token_241|>",
1998
+ "lstrip": false,
1999
+ "normalized": false,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": true
2003
+ },
2004
+ "128250": {
2005
+ "content": "<|reserved_special_token_242|>",
2006
+ "lstrip": false,
2007
+ "normalized": false,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": true
2011
+ },
2012
+ "128251": {
2013
+ "content": "<|reserved_special_token_243|>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": true
2019
+ },
2020
+ "128252": {
2021
+ "content": "<|reserved_special_token_244|>",
2022
+ "lstrip": false,
2023
+ "normalized": false,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": true
2027
+ },
2028
+ "128253": {
2029
+ "content": "<|reserved_special_token_245|>",
2030
+ "lstrip": false,
2031
+ "normalized": false,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": true
2035
+ },
2036
+ "128254": {
2037
+ "content": "<|reserved_special_token_246|>",
2038
+ "lstrip": false,
2039
+ "normalized": false,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": true
2043
+ },
2044
+ "128255": {
2045
+ "content": "<|reserved_special_token_247|>",
2046
+ "lstrip": false,
2047
+ "normalized": false,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": true
2051
+ }
2052
+ },
2053
+ "bos_token": "<|begin_of_text|>",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|eot_id|>",
2063
+ "padding_side": "right",
2064
+ "tokenizer_class": "PreTrainedTokenizerFast",
2065
+ "unk_token": null
2066
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/trainer_state.json ADDED
@@ -0,0 +1,1054 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 681,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.04422332780541736,
14
+ "grad_norm": 4.622276782989502,
15
+ "learning_rate": 1.3043478260869566e-06,
16
+ "logits/chosen": 0.04871366173028946,
17
+ "logits/rejected": 0.04094501584768295,
18
+ "logps/chosen": -587.9451293945312,
19
+ "logps/rejected": -599.2677001953125,
20
+ "loss": 0.6991,
21
+ "rewards/accuracies": 0.39375001192092896,
22
+ "rewards/chosen": -0.003624162869527936,
23
+ "rewards/margins": -0.009800964035093784,
24
+ "rewards/rejected": 0.00617680000141263,
25
+ "step": 10
26
+ },
27
+ {
28
+ "epoch": 0.08844665561083472,
29
+ "grad_norm": 4.827854633331299,
30
+ "learning_rate": 2.7536231884057974e-06,
31
+ "logits/chosen": 0.039086777716875076,
32
+ "logits/rejected": 0.05382512882351875,
33
+ "logps/chosen": -590.7330322265625,
34
+ "logps/rejected": -596.154052734375,
35
+ "loss": 0.6949,
36
+ "rewards/accuracies": 0.484375,
37
+ "rewards/chosen": -0.001210870686918497,
38
+ "rewards/margins": -0.00042330287396907806,
39
+ "rewards/rejected": -0.0007875681039877236,
40
+ "step": 20
41
+ },
42
+ {
43
+ "epoch": 0.13266998341625208,
44
+ "grad_norm": 4.843283176422119,
45
+ "learning_rate": 4.202898550724638e-06,
46
+ "logits/chosen": 0.07005294412374496,
47
+ "logits/rejected": 0.07629252225160599,
48
+ "logps/chosen": -579.3927001953125,
49
+ "logps/rejected": -594.1946411132812,
50
+ "loss": 0.6949,
51
+ "rewards/accuracies": 0.5,
52
+ "rewards/chosen": -0.008031840436160564,
53
+ "rewards/margins": -0.00044345398782752454,
54
+ "rewards/rejected": -0.007588387466967106,
55
+ "step": 30
56
+ },
57
+ {
58
+ "epoch": 0.17689331122166943,
59
+ "grad_norm": 4.849563121795654,
60
+ "learning_rate": 5.652173913043479e-06,
61
+ "logits/chosen": 0.050349436700344086,
62
+ "logits/rejected": 0.04310324788093567,
63
+ "logps/chosen": -584.6341552734375,
64
+ "logps/rejected": -602.8211669921875,
65
+ "loss": 0.6951,
66
+ "rewards/accuracies": 0.5375000238418579,
67
+ "rewards/chosen": -0.02712143398821354,
68
+ "rewards/margins": -0.0007178877713158727,
69
+ "rewards/rejected": -0.02640354633331299,
70
+ "step": 40
71
+ },
72
+ {
73
+ "epoch": 0.22111663902708678,
74
+ "grad_norm": 4.782793045043945,
75
+ "learning_rate": 7.10144927536232e-06,
76
+ "logits/chosen": 0.06073029711842537,
77
+ "logits/rejected": 0.06483195722103119,
78
+ "logps/chosen": -588.3558349609375,
79
+ "logps/rejected": -575.1630859375,
80
+ "loss": 0.6957,
81
+ "rewards/accuracies": 0.484375,
82
+ "rewards/chosen": -0.04467263072729111,
83
+ "rewards/margins": -0.0019026808440685272,
84
+ "rewards/rejected": -0.04276995733380318,
85
+ "step": 50
86
+ },
87
+ {
88
+ "epoch": 0.26533996683250416,
89
+ "grad_norm": 4.875718593597412,
90
+ "learning_rate": 8.55072463768116e-06,
91
+ "logits/chosen": 0.07834223657846451,
92
+ "logits/rejected": 0.05809725448489189,
93
+ "logps/chosen": -591.7510986328125,
94
+ "logps/rejected": -589.9751586914062,
95
+ "loss": 0.6852,
96
+ "rewards/accuracies": 0.543749988079071,
97
+ "rewards/chosen": -0.05711676552891731,
98
+ "rewards/margins": 0.020368361845612526,
99
+ "rewards/rejected": -0.07748512923717499,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.3095632946379215,
104
+ "grad_norm": 5.004810333251953,
105
+ "learning_rate": 1e-05,
106
+ "logits/chosen": 0.06968727707862854,
107
+ "logits/rejected": 0.06882122159004211,
108
+ "logps/chosen": -580.2086181640625,
109
+ "logps/rejected": -589.474853515625,
110
+ "loss": 0.6871,
111
+ "rewards/accuracies": 0.5406249761581421,
112
+ "rewards/chosen": -0.08063866943120956,
113
+ "rewards/margins": 0.018481673672795296,
114
+ "rewards/rejected": -0.09912034124135971,
115
+ "step": 70
116
+ },
117
+ {
118
+ "epoch": 0.35378662244333886,
119
+ "grad_norm": 4.6248579025268555,
120
+ "learning_rate": 9.836601307189542e-06,
121
+ "logits/chosen": 0.05297359824180603,
122
+ "logits/rejected": 0.048554446548223495,
123
+ "logps/chosen": -603.814697265625,
124
+ "logps/rejected": -583.4642944335938,
125
+ "loss": 0.692,
126
+ "rewards/accuracies": 0.515625,
127
+ "rewards/chosen": -0.1368546038866043,
128
+ "rewards/margins": 0.015463963150978088,
129
+ "rewards/rejected": -0.1523185670375824,
130
+ "step": 80
131
+ },
132
+ {
133
+ "epoch": 0.39800995024875624,
134
+ "grad_norm": 4.781217098236084,
135
+ "learning_rate": 9.673202614379087e-06,
136
+ "logits/chosen": 0.0657927393913269,
137
+ "logits/rejected": 0.05678596347570419,
138
+ "logps/chosen": -573.3232421875,
139
+ "logps/rejected": -583.8043212890625,
140
+ "loss": 0.675,
141
+ "rewards/accuracies": 0.578125,
142
+ "rewards/chosen": -0.16061438620090485,
143
+ "rewards/margins": 0.05512550473213196,
144
+ "rewards/rejected": -0.2157398909330368,
145
+ "step": 90
146
+ },
147
+ {
148
+ "epoch": 0.44223327805417356,
149
+ "grad_norm": 5.497505187988281,
150
+ "learning_rate": 9.509803921568628e-06,
151
+ "logits/chosen": 0.06200551241636276,
152
+ "logits/rejected": 0.08481563627719879,
153
+ "logps/chosen": -587.5068359375,
154
+ "logps/rejected": -590.5346069335938,
155
+ "loss": 0.6827,
156
+ "rewards/accuracies": 0.59375,
157
+ "rewards/chosen": -0.2770426273345947,
158
+ "rewards/margins": 0.05209667608141899,
159
+ "rewards/rejected": -0.3291392922401428,
160
+ "step": 100
161
+ },
162
+ {
163
+ "epoch": 0.48645660585959094,
164
+ "grad_norm": 4.9616498947143555,
165
+ "learning_rate": 9.34640522875817e-06,
166
+ "logits/chosen": 0.07670322060585022,
167
+ "logits/rejected": 0.08130083978176117,
168
+ "logps/chosen": -580.2796020507812,
169
+ "logps/rejected": -573.5567626953125,
170
+ "loss": 0.686,
171
+ "rewards/accuracies": 0.578125,
172
+ "rewards/chosen": -0.30284205079078674,
173
+ "rewards/margins": 0.049282558262348175,
174
+ "rewards/rejected": -0.3521246016025543,
175
+ "step": 110
176
+ },
177
+ {
178
+ "epoch": 0.5306799336650083,
179
+ "grad_norm": 5.749575614929199,
180
+ "learning_rate": 9.183006535947713e-06,
181
+ "logits/chosen": 0.06149401143193245,
182
+ "logits/rejected": 0.06619513779878616,
183
+ "logps/chosen": -585.7532958984375,
184
+ "logps/rejected": -606.7704467773438,
185
+ "loss": 0.6651,
186
+ "rewards/accuracies": 0.609375,
187
+ "rewards/chosen": -0.26562389731407166,
188
+ "rewards/margins": 0.0957210436463356,
189
+ "rewards/rejected": -0.36134496331214905,
190
+ "step": 120
191
+ },
192
+ {
193
+ "epoch": 0.5749032614704257,
194
+ "grad_norm": 4.905361175537109,
195
+ "learning_rate": 9.019607843137256e-06,
196
+ "logits/chosen": 0.08098295331001282,
197
+ "logits/rejected": 0.06964148581027985,
198
+ "logps/chosen": -608.7659912109375,
199
+ "logps/rejected": -589.2445068359375,
200
+ "loss": 0.6795,
201
+ "rewards/accuracies": 0.5687500238418579,
202
+ "rewards/chosen": -0.3361450731754303,
203
+ "rewards/margins": 0.07554575800895691,
204
+ "rewards/rejected": -0.4116908013820648,
205
+ "step": 130
206
+ },
207
+ {
208
+ "epoch": 0.619126589275843,
209
+ "grad_norm": 5.035276889801025,
210
+ "learning_rate": 8.856209150326798e-06,
211
+ "logits/chosen": 0.0721609890460968,
212
+ "logits/rejected": 0.06741432845592499,
213
+ "logps/chosen": -614.2322387695312,
214
+ "logps/rejected": -603.1552734375,
215
+ "loss": 0.656,
216
+ "rewards/accuracies": 0.612500011920929,
217
+ "rewards/chosen": -0.23804862797260284,
218
+ "rewards/margins": 0.12134584039449692,
219
+ "rewards/rejected": -0.35939446091651917,
220
+ "step": 140
221
+ },
222
+ {
223
+ "epoch": 0.6633499170812603,
224
+ "grad_norm": 5.222947120666504,
225
+ "learning_rate": 8.69281045751634e-06,
226
+ "logits/chosen": 0.07082496583461761,
227
+ "logits/rejected": 0.08096617460250854,
228
+ "logps/chosen": -600.041259765625,
229
+ "logps/rejected": -605.6270141601562,
230
+ "loss": 0.6885,
231
+ "rewards/accuracies": 0.534375011920929,
232
+ "rewards/chosen": -0.3162144422531128,
233
+ "rewards/margins": 0.05429792404174805,
234
+ "rewards/rejected": -0.37051236629486084,
235
+ "step": 150
236
+ },
237
+ {
238
+ "epoch": 0.7075732448866777,
239
+ "grad_norm": 5.086350917816162,
240
+ "learning_rate": 8.529411764705883e-06,
241
+ "logits/chosen": 0.07016018778085709,
242
+ "logits/rejected": 0.05729135125875473,
243
+ "logps/chosen": -591.2280883789062,
244
+ "logps/rejected": -591.44677734375,
245
+ "loss": 0.67,
246
+ "rewards/accuracies": 0.596875011920929,
247
+ "rewards/chosen": -0.30853015184402466,
248
+ "rewards/margins": 0.0888347178697586,
249
+ "rewards/rejected": -0.39736485481262207,
250
+ "step": 160
251
+ },
252
+ {
253
+ "epoch": 0.7517965726920951,
254
+ "grad_norm": 5.048996448516846,
255
+ "learning_rate": 8.366013071895426e-06,
256
+ "logits/chosen": 0.04029928892850876,
257
+ "logits/rejected": 0.05272378399968147,
258
+ "logps/chosen": -592.8924560546875,
259
+ "logps/rejected": -594.070556640625,
260
+ "loss": 0.6694,
261
+ "rewards/accuracies": 0.565625011920929,
262
+ "rewards/chosen": -0.2784493863582611,
263
+ "rewards/margins": 0.09918699413537979,
264
+ "rewards/rejected": -0.3776364028453827,
265
+ "step": 170
266
+ },
267
+ {
268
+ "epoch": 0.7960199004975125,
269
+ "grad_norm": 5.479474067687988,
270
+ "learning_rate": 8.202614379084967e-06,
271
+ "logits/chosen": 0.09338949620723724,
272
+ "logits/rejected": 0.08512254804372787,
273
+ "logps/chosen": -612.8118896484375,
274
+ "logps/rejected": -590.0531005859375,
275
+ "loss": 0.685,
276
+ "rewards/accuracies": 0.534375011920929,
277
+ "rewards/chosen": -0.24138124287128448,
278
+ "rewards/margins": 0.05369025468826294,
279
+ "rewards/rejected": -0.29507148265838623,
280
+ "step": 180
281
+ },
282
+ {
283
+ "epoch": 0.8402432283029297,
284
+ "grad_norm": 4.761824131011963,
285
+ "learning_rate": 8.03921568627451e-06,
286
+ "logits/chosen": 0.08315663039684296,
287
+ "logits/rejected": 0.054749805480241776,
288
+ "logps/chosen": -581.3541259765625,
289
+ "logps/rejected": -585.2570190429688,
290
+ "loss": 0.676,
291
+ "rewards/accuracies": 0.5562499761581421,
292
+ "rewards/chosen": -0.20680022239685059,
293
+ "rewards/margins": 0.08268674463033676,
294
+ "rewards/rejected": -0.28948697447776794,
295
+ "step": 190
296
+ },
297
+ {
298
+ "epoch": 0.8844665561083471,
299
+ "grad_norm": 4.723191738128662,
300
+ "learning_rate": 7.875816993464053e-06,
301
+ "logits/chosen": 0.07468996942043304,
302
+ "logits/rejected": 0.07738003879785538,
303
+ "logps/chosen": -609.02783203125,
304
+ "logps/rejected": -593.884765625,
305
+ "loss": 0.6858,
306
+ "rewards/accuracies": 0.5625,
307
+ "rewards/chosen": -0.17657871544361115,
308
+ "rewards/margins": 0.060498666018247604,
309
+ "rewards/rejected": -0.23707738518714905,
310
+ "step": 200
311
+ },
312
+ {
313
+ "epoch": 0.9286898839137645,
314
+ "grad_norm": 5.222857475280762,
315
+ "learning_rate": 7.712418300653596e-06,
316
+ "logits/chosen": 0.08235542476177216,
317
+ "logits/rejected": 0.06947238743305206,
318
+ "logps/chosen": -589.630126953125,
319
+ "logps/rejected": -600.760009765625,
320
+ "loss": 0.6847,
321
+ "rewards/accuracies": 0.5625,
322
+ "rewards/chosen": -0.17190614342689514,
323
+ "rewards/margins": 0.06592313945293427,
324
+ "rewards/rejected": -0.2378292977809906,
325
+ "step": 210
326
+ },
327
+ {
328
+ "epoch": 0.9729132117191819,
329
+ "grad_norm": 4.568787097930908,
330
+ "learning_rate": 7.549019607843138e-06,
331
+ "logits/chosen": 0.0659804567694664,
332
+ "logits/rejected": 0.08157521486282349,
333
+ "logps/chosen": -570.6529541015625,
334
+ "logps/rejected": -579.2662963867188,
335
+ "loss": 0.6856,
336
+ "rewards/accuracies": 0.5874999761581421,
337
+ "rewards/chosen": -0.12612760066986084,
338
+ "rewards/margins": 0.05677683278918266,
339
+ "rewards/rejected": -0.1829044222831726,
340
+ "step": 220
341
+ },
342
+ {
343
+ "epoch": 1.0132669983416251,
344
+ "grad_norm": 4.5106611251831055,
345
+ "learning_rate": 7.385620915032681e-06,
346
+ "logits/chosen": 0.07642340660095215,
347
+ "logits/rejected": 0.06369760632514954,
348
+ "logps/chosen": -614.3958740234375,
349
+ "logps/rejected": -608.2275390625,
350
+ "loss": 0.6304,
351
+ "rewards/accuracies": 0.6506849527359009,
352
+ "rewards/chosen": -0.10391667485237122,
353
+ "rewards/margins": 0.17069660127162933,
354
+ "rewards/rejected": -0.27461323142051697,
355
+ "step": 230
356
+ },
357
+ {
358
+ "epoch": 1.0574903261470425,
359
+ "grad_norm": 4.022596836090088,
360
+ "learning_rate": 7.222222222222223e-06,
361
+ "logits/chosen": 0.08061325550079346,
362
+ "logits/rejected": 0.07459220290184021,
363
+ "logps/chosen": -571.9611206054688,
364
+ "logps/rejected": -595.8447875976562,
365
+ "loss": 0.5614,
366
+ "rewards/accuracies": 0.800000011920929,
367
+ "rewards/chosen": -0.0800560861825943,
368
+ "rewards/margins": 0.33351126313209534,
369
+ "rewards/rejected": -0.4135673940181732,
370
+ "step": 240
371
+ },
372
+ {
373
+ "epoch": 1.10171365395246,
374
+ "grad_norm": 4.588108539581299,
375
+ "learning_rate": 7.058823529411766e-06,
376
+ "logits/chosen": 0.06551264226436615,
377
+ "logits/rejected": 0.06965593248605728,
378
+ "logps/chosen": -607.150390625,
379
+ "logps/rejected": -592.1593017578125,
380
+ "loss": 0.5725,
381
+ "rewards/accuracies": 0.7562500238418579,
382
+ "rewards/chosen": -0.13619938492774963,
383
+ "rewards/margins": 0.3180665075778961,
384
+ "rewards/rejected": -0.45426592230796814,
385
+ "step": 250
386
+ },
387
+ {
388
+ "epoch": 1.1459369817578773,
389
+ "grad_norm": 4.052699089050293,
390
+ "learning_rate": 6.895424836601308e-06,
391
+ "logits/chosen": 0.053865671157836914,
392
+ "logits/rejected": 0.07656464725732803,
393
+ "logps/chosen": -591.7940063476562,
394
+ "logps/rejected": -588.6275634765625,
395
+ "loss": 0.5558,
396
+ "rewards/accuracies": 0.762499988079071,
397
+ "rewards/chosen": -0.15596291422843933,
398
+ "rewards/margins": 0.35838812589645386,
399
+ "rewards/rejected": -0.5143510103225708,
400
+ "step": 260
401
+ },
402
+ {
403
+ "epoch": 1.1901603095632947,
404
+ "grad_norm": 4.410710334777832,
405
+ "learning_rate": 6.732026143790851e-06,
406
+ "logits/chosen": 0.07962622493505478,
407
+ "logits/rejected": 0.0747472494840622,
408
+ "logps/chosen": -605.1287841796875,
409
+ "logps/rejected": -585.3924560546875,
410
+ "loss": 0.5332,
411
+ "rewards/accuracies": 0.793749988079071,
412
+ "rewards/chosen": -0.15009275078773499,
413
+ "rewards/margins": 0.433537095785141,
414
+ "rewards/rejected": -0.5836297869682312,
415
+ "step": 270
416
+ },
417
+ {
418
+ "epoch": 1.234383637368712,
419
+ "grad_norm": 4.496598720550537,
420
+ "learning_rate": 6.568627450980393e-06,
421
+ "logits/chosen": 0.08427608758211136,
422
+ "logits/rejected": 0.08272510021924973,
423
+ "logps/chosen": -588.9246826171875,
424
+ "logps/rejected": -590.2930908203125,
425
+ "loss": 0.5405,
426
+ "rewards/accuracies": 0.7906249761581421,
427
+ "rewards/chosen": -0.10737033188343048,
428
+ "rewards/margins": 0.41487225890159607,
429
+ "rewards/rejected": -0.5222426056861877,
430
+ "step": 280
431
+ },
432
+ {
433
+ "epoch": 1.2786069651741294,
434
+ "grad_norm": 4.3100457191467285,
435
+ "learning_rate": 6.405228758169935e-06,
436
+ "logits/chosen": 0.10898424685001373,
437
+ "logits/rejected": 0.09974032640457153,
438
+ "logps/chosen": -567.9619140625,
439
+ "logps/rejected": -578.3641357421875,
440
+ "loss": 0.5387,
441
+ "rewards/accuracies": 0.793749988079071,
442
+ "rewards/chosen": -0.11027959734201431,
443
+ "rewards/margins": 0.4299299120903015,
444
+ "rewards/rejected": -0.5402094721794128,
445
+ "step": 290
446
+ },
447
+ {
448
+ "epoch": 1.3228302929795466,
449
+ "grad_norm": 5.263061046600342,
450
+ "learning_rate": 6.241830065359478e-06,
451
+ "logits/chosen": 0.08369974046945572,
452
+ "logits/rejected": 0.07651132345199585,
453
+ "logps/chosen": -592.3204345703125,
454
+ "logps/rejected": -584.3158569335938,
455
+ "loss": 0.5284,
456
+ "rewards/accuracies": 0.7906249761581421,
457
+ "rewards/chosen": -0.06656303256750107,
458
+ "rewards/margins": 0.45896658301353455,
459
+ "rewards/rejected": -0.5255296230316162,
460
+ "step": 300
461
+ },
462
+ {
463
+ "epoch": 1.3670536207849642,
464
+ "grad_norm": 4.775884628295898,
465
+ "learning_rate": 6.07843137254902e-06,
466
+ "logits/chosen": 0.07591135799884796,
467
+ "logits/rejected": 0.08917959034442902,
468
+ "logps/chosen": -579.1502685546875,
469
+ "logps/rejected": -586.9732666015625,
470
+ "loss": 0.5223,
471
+ "rewards/accuracies": 0.7875000238418579,
472
+ "rewards/chosen": -0.004171231295913458,
473
+ "rewards/margins": 0.482229083776474,
474
+ "rewards/rejected": -0.4864003658294678,
475
+ "step": 310
476
+ },
477
+ {
478
+ "epoch": 1.4112769485903813,
479
+ "grad_norm": 5.165349006652832,
480
+ "learning_rate": 5.9150326797385625e-06,
481
+ "logits/chosen": 0.05393245071172714,
482
+ "logits/rejected": 0.06285496056079865,
483
+ "logps/chosen": -594.8931274414062,
484
+ "logps/rejected": -599.5316162109375,
485
+ "loss": 0.5254,
486
+ "rewards/accuracies": 0.796875,
487
+ "rewards/chosen": -0.019928421825170517,
488
+ "rewards/margins": 0.46136680245399475,
489
+ "rewards/rejected": -0.4812951982021332,
490
+ "step": 320
491
+ },
492
+ {
493
+ "epoch": 1.4555002763957987,
494
+ "grad_norm": 5.701517581939697,
495
+ "learning_rate": 5.7516339869281045e-06,
496
+ "logits/chosen": 0.050967223942279816,
497
+ "logits/rejected": 0.049500782042741776,
498
+ "logps/chosen": -596.6493530273438,
499
+ "logps/rejected": -608.5526123046875,
500
+ "loss": 0.5448,
501
+ "rewards/accuracies": 0.7437499761581421,
502
+ "rewards/chosen": -0.10576356947422028,
503
+ "rewards/margins": 0.44363728165626526,
504
+ "rewards/rejected": -0.5494009256362915,
505
+ "step": 330
506
+ },
507
+ {
508
+ "epoch": 1.499723604201216,
509
+ "grad_norm": 5.582211971282959,
510
+ "learning_rate": 5.588235294117647e-06,
511
+ "logits/chosen": 0.07688289880752563,
512
+ "logits/rejected": 0.05430004745721817,
513
+ "logps/chosen": -592.6009521484375,
514
+ "logps/rejected": -599.5895385742188,
515
+ "loss": 0.5368,
516
+ "rewards/accuracies": 0.7749999761581421,
517
+ "rewards/chosen": -0.11324721574783325,
518
+ "rewards/margins": 0.43297114968299866,
519
+ "rewards/rejected": -0.5462183952331543,
520
+ "step": 340
521
+ },
522
+ {
523
+ "epoch": 1.5439469320066335,
524
+ "grad_norm": 5.305120468139648,
525
+ "learning_rate": 5.4248366013071894e-06,
526
+ "logits/chosen": 0.08117028325796127,
527
+ "logits/rejected": 0.05573394149541855,
528
+ "logps/chosen": -577.6001586914062,
529
+ "logps/rejected": -616.7808227539062,
530
+ "loss": 0.534,
531
+ "rewards/accuracies": 0.7749999761581421,
532
+ "rewards/chosen": -0.10302220284938812,
533
+ "rewards/margins": 0.45644623041152954,
534
+ "rewards/rejected": -0.5594683885574341,
535
+ "step": 350
536
+ },
537
+ {
538
+ "epoch": 1.5881702598120508,
539
+ "grad_norm": 4.980655193328857,
540
+ "learning_rate": 5.261437908496732e-06,
541
+ "logits/chosen": 0.09816692769527435,
542
+ "logits/rejected": 0.0806182473897934,
543
+ "logps/chosen": -576.7900390625,
544
+ "logps/rejected": -576.9078369140625,
545
+ "loss": 0.5183,
546
+ "rewards/accuracies": 0.7875000238418579,
547
+ "rewards/chosen": -0.04400457814335823,
548
+ "rewards/margins": 0.4879058301448822,
549
+ "rewards/rejected": -0.5319104194641113,
550
+ "step": 360
551
+ },
552
+ {
553
+ "epoch": 1.6323935876174682,
554
+ "grad_norm": 5.539422988891602,
555
+ "learning_rate": 5.098039215686274e-06,
556
+ "logits/chosen": 0.06238880008459091,
557
+ "logits/rejected": 0.08907127380371094,
558
+ "logps/chosen": -605.7498779296875,
559
+ "logps/rejected": -592.5785522460938,
560
+ "loss": 0.5382,
561
+ "rewards/accuracies": 0.7875000238418579,
562
+ "rewards/chosen": -0.0004440300108399242,
563
+ "rewards/margins": 0.4214852452278137,
564
+ "rewards/rejected": -0.421929270029068,
565
+ "step": 370
566
+ },
567
+ {
568
+ "epoch": 1.6766169154228856,
569
+ "grad_norm": 4.907400608062744,
570
+ "learning_rate": 4.934640522875817e-06,
571
+ "logits/chosen": 0.09402688592672348,
572
+ "logits/rejected": 0.10355579853057861,
573
+ "logps/chosen": -582.4727783203125,
574
+ "logps/rejected": -575.2383422851562,
575
+ "loss": 0.5102,
576
+ "rewards/accuracies": 0.800000011920929,
577
+ "rewards/chosen": 0.053891755640506744,
578
+ "rewards/margins": 0.4978780746459961,
579
+ "rewards/rejected": -0.44398632645606995,
580
+ "step": 380
581
+ },
582
+ {
583
+ "epoch": 1.720840243228303,
584
+ "grad_norm": 5.559103488922119,
585
+ "learning_rate": 4.77124183006536e-06,
586
+ "logits/chosen": 0.06364494562149048,
587
+ "logits/rejected": 0.07669045776128769,
588
+ "logps/chosen": -608.1865844726562,
589
+ "logps/rejected": -610.16455078125,
590
+ "loss": 0.5402,
591
+ "rewards/accuracies": 0.7406250238418579,
592
+ "rewards/chosen": -0.017969857901334763,
593
+ "rewards/margins": 0.43957605957984924,
594
+ "rewards/rejected": -0.45754584670066833,
595
+ "step": 390
596
+ },
597
+ {
598
+ "epoch": 1.7650635710337204,
599
+ "grad_norm": 5.398365020751953,
600
+ "learning_rate": 4.607843137254902e-06,
601
+ "logits/chosen": 0.0586751289665699,
602
+ "logits/rejected": 0.04953053593635559,
603
+ "logps/chosen": -575.0404052734375,
604
+ "logps/rejected": -600.0374145507812,
605
+ "loss": 0.5211,
606
+ "rewards/accuracies": 0.793749988079071,
607
+ "rewards/chosen": -0.07709486782550812,
608
+ "rewards/margins": 0.484605610370636,
609
+ "rewards/rejected": -0.5617004632949829,
610
+ "step": 400
611
+ },
612
+ {
613
+ "epoch": 1.8092868988391375,
614
+ "grad_norm": 5.3915629386901855,
615
+ "learning_rate": 4.444444444444444e-06,
616
+ "logits/chosen": 0.04845741018652916,
617
+ "logits/rejected": 0.06371285766363144,
618
+ "logps/chosen": -589.5303955078125,
619
+ "logps/rejected": -589.7510375976562,
620
+ "loss": 0.5323,
621
+ "rewards/accuracies": 0.7749999761581421,
622
+ "rewards/chosen": -0.08309822529554367,
623
+ "rewards/margins": 0.4489211142063141,
624
+ "rewards/rejected": -0.532019317150116,
625
+ "step": 410
626
+ },
627
+ {
628
+ "epoch": 1.8535102266445551,
629
+ "grad_norm": 5.704387664794922,
630
+ "learning_rate": 4.281045751633987e-06,
631
+ "logits/chosen": 0.03185851126909256,
632
+ "logits/rejected": 0.04209734871983528,
633
+ "logps/chosen": -586.9105224609375,
634
+ "logps/rejected": -597.8375244140625,
635
+ "loss": 0.5048,
636
+ "rewards/accuracies": 0.815625011920929,
637
+ "rewards/chosen": -0.13690757751464844,
638
+ "rewards/margins": 0.5262494683265686,
639
+ "rewards/rejected": -0.6631569862365723,
640
+ "step": 420
641
+ },
642
+ {
643
+ "epoch": 1.8977335544499723,
644
+ "grad_norm": 5.61472225189209,
645
+ "learning_rate": 4.11764705882353e-06,
646
+ "logits/chosen": 0.06846825778484344,
647
+ "logits/rejected": 0.045934658497571945,
648
+ "logps/chosen": -584.31201171875,
649
+ "logps/rejected": -611.8671875,
650
+ "loss": 0.5353,
651
+ "rewards/accuracies": 0.7562500238418579,
652
+ "rewards/chosen": -0.20534837245941162,
653
+ "rewards/margins": 0.4642485976219177,
654
+ "rewards/rejected": -0.6695970296859741,
655
+ "step": 430
656
+ },
657
+ {
658
+ "epoch": 1.9419568822553899,
659
+ "grad_norm": 5.488383769989014,
660
+ "learning_rate": 3.954248366013072e-06,
661
+ "logits/chosen": 0.01902499794960022,
662
+ "logits/rejected": 0.019859401509165764,
663
+ "logps/chosen": -596.5375366210938,
664
+ "logps/rejected": -600.3779296875,
665
+ "loss": 0.4973,
666
+ "rewards/accuracies": 0.831250011920929,
667
+ "rewards/chosen": -0.14263077080249786,
668
+ "rewards/margins": 0.5519839525222778,
669
+ "rewards/rejected": -0.6946146488189697,
670
+ "step": 440
671
+ },
672
+ {
673
+ "epoch": 1.986180210060807,
674
+ "grad_norm": 5.584505558013916,
675
+ "learning_rate": 3.7908496732026144e-06,
676
+ "logits/chosen": 0.028192508965730667,
677
+ "logits/rejected": 0.031691137701272964,
678
+ "logps/chosen": -611.2737426757812,
679
+ "logps/rejected": -621.2968139648438,
680
+ "loss": 0.5124,
681
+ "rewards/accuracies": 0.7875000238418579,
682
+ "rewards/chosen": -0.16103509068489075,
683
+ "rewards/margins": 0.5284713506698608,
684
+ "rewards/rejected": -0.6895063519477844,
685
+ "step": 450
686
+ },
687
+ {
688
+ "epoch": 2.0265339966832503,
689
+ "grad_norm": 4.323789119720459,
690
+ "learning_rate": 3.6274509803921573e-06,
691
+ "logits/chosen": 0.03420591354370117,
692
+ "logits/rejected": 0.01977560855448246,
693
+ "logps/chosen": -586.8990478515625,
694
+ "logps/rejected": -596.7354736328125,
695
+ "loss": 0.4669,
696
+ "rewards/accuracies": 0.8904109597206116,
697
+ "rewards/chosen": -0.036540526896715164,
698
+ "rewards/margins": 0.7149255871772766,
699
+ "rewards/rejected": -0.7514661550521851,
700
+ "step": 460
701
+ },
702
+ {
703
+ "epoch": 2.070757324488668,
704
+ "grad_norm": 4.4482340812683105,
705
+ "learning_rate": 3.4640522875816997e-06,
706
+ "logits/chosen": -0.007327643223106861,
707
+ "logits/rejected": -0.0031558361370116472,
708
+ "logps/chosen": -601.0980224609375,
709
+ "logps/rejected": -598.2813720703125,
710
+ "loss": 0.3959,
711
+ "rewards/accuracies": 0.940625011920929,
712
+ "rewards/chosen": 0.021305236965417862,
713
+ "rewards/margins": 0.820387065410614,
714
+ "rewards/rejected": -0.7990819215774536,
715
+ "step": 470
716
+ },
717
+ {
718
+ "epoch": 2.114980652294085,
719
+ "grad_norm": 5.130751132965088,
720
+ "learning_rate": 3.300653594771242e-06,
721
+ "logits/chosen": 0.030287161469459534,
722
+ "logits/rejected": 0.019675543531775475,
723
+ "logps/chosen": -578.3929443359375,
724
+ "logps/rejected": -604.7178344726562,
725
+ "loss": 0.3989,
726
+ "rewards/accuracies": 0.918749988079071,
727
+ "rewards/chosen": -0.022884676232933998,
728
+ "rewards/margins": 0.8230856657028198,
729
+ "rewards/rejected": -0.8459703326225281,
730
+ "step": 480
731
+ },
732
+ {
733
+ "epoch": 2.1592039800995027,
734
+ "grad_norm": 4.648355960845947,
735
+ "learning_rate": 3.1372549019607846e-06,
736
+ "logits/chosen": 0.017573697492480278,
737
+ "logits/rejected": 0.018800828605890274,
738
+ "logps/chosen": -606.2241821289062,
739
+ "logps/rejected": -615.8743896484375,
740
+ "loss": 0.4038,
741
+ "rewards/accuracies": 0.9156249761581421,
742
+ "rewards/chosen": -0.07522483170032501,
743
+ "rewards/margins": 0.8257174491882324,
744
+ "rewards/rejected": -0.9009422063827515,
745
+ "step": 490
746
+ },
747
+ {
748
+ "epoch": 2.20342730790492,
749
+ "grad_norm": 5.236668109893799,
750
+ "learning_rate": 2.973856209150327e-06,
751
+ "logits/chosen": 0.007241242565214634,
752
+ "logits/rejected": 0.03648309037089348,
753
+ "logps/chosen": -604.1732177734375,
754
+ "logps/rejected": -596.2252197265625,
755
+ "loss": 0.4097,
756
+ "rewards/accuracies": 0.9125000238418579,
757
+ "rewards/chosen": -0.13245585560798645,
758
+ "rewards/margins": 0.8045696020126343,
759
+ "rewards/rejected": -0.9370256662368774,
760
+ "step": 500
761
+ },
762
+ {
763
+ "epoch": 2.2476506357103374,
764
+ "grad_norm": 4.557862758636475,
765
+ "learning_rate": 2.8104575163398695e-06,
766
+ "logits/chosen": -0.001453867880627513,
767
+ "logits/rejected": -0.028539365157485008,
768
+ "logps/chosen": -588.1824951171875,
769
+ "logps/rejected": -578.2048950195312,
770
+ "loss": 0.4147,
771
+ "rewards/accuracies": 0.909375011920929,
772
+ "rewards/chosen": -0.16303281486034393,
773
+ "rewards/margins": 0.7795251607894897,
774
+ "rewards/rejected": -0.9425579905509949,
775
+ "step": 510
776
+ },
777
+ {
778
+ "epoch": 2.2918739635157546,
779
+ "grad_norm": 4.835983753204346,
780
+ "learning_rate": 2.647058823529412e-06,
781
+ "logits/chosen": -0.016575729474425316,
782
+ "logits/rejected": -0.02309141680598259,
783
+ "logps/chosen": -587.0806884765625,
784
+ "logps/rejected": -598.1487426757812,
785
+ "loss": 0.3908,
786
+ "rewards/accuracies": 0.921875,
787
+ "rewards/chosen": -0.09063522517681122,
788
+ "rewards/margins": 0.8614276647567749,
789
+ "rewards/rejected": -0.9520629048347473,
790
+ "step": 520
791
+ },
792
+ {
793
+ "epoch": 2.336097291321172,
794
+ "grad_norm": 4.019218921661377,
795
+ "learning_rate": 2.4836601307189544e-06,
796
+ "logits/chosen": -0.0013664938742294908,
797
+ "logits/rejected": 0.0055546266958117485,
798
+ "logps/chosen": -580.6363525390625,
799
+ "logps/rejected": -602.9906005859375,
800
+ "loss": 0.3808,
801
+ "rewards/accuracies": 0.921875,
802
+ "rewards/chosen": -0.056635819375514984,
803
+ "rewards/margins": 0.9210506677627563,
804
+ "rewards/rejected": -0.9776862859725952,
805
+ "step": 530
806
+ },
807
+ {
808
+ "epoch": 2.3803206191265893,
809
+ "grad_norm": 5.916384696960449,
810
+ "learning_rate": 2.320261437908497e-06,
811
+ "logits/chosen": 0.0044000945053994656,
812
+ "logits/rejected": 0.015144201926887035,
813
+ "logps/chosen": -582.1693115234375,
814
+ "logps/rejected": -605.7127685546875,
815
+ "loss": 0.391,
816
+ "rewards/accuracies": 0.909375011920929,
817
+ "rewards/chosen": -0.07502246648073196,
818
+ "rewards/margins": 0.8852497339248657,
819
+ "rewards/rejected": -0.9602723121643066,
820
+ "step": 540
821
+ },
822
+ {
823
+ "epoch": 2.4245439469320065,
824
+ "grad_norm": 4.3538498878479,
825
+ "learning_rate": 2.1568627450980393e-06,
826
+ "logits/chosen": -0.010578664019703865,
827
+ "logits/rejected": -0.023884272202849388,
828
+ "logps/chosen": -595.3650512695312,
829
+ "logps/rejected": -598.5260009765625,
830
+ "loss": 0.3969,
831
+ "rewards/accuracies": 0.903124988079071,
832
+ "rewards/chosen": -0.1108994334936142,
833
+ "rewards/margins": 0.8538322448730469,
834
+ "rewards/rejected": -0.9647315740585327,
835
+ "step": 550
836
+ },
837
+ {
838
+ "epoch": 2.468767274737424,
839
+ "grad_norm": 5.35381555557251,
840
+ "learning_rate": 1.993464052287582e-06,
841
+ "logits/chosen": -0.009531346149742603,
842
+ "logits/rejected": 0.011208529584109783,
843
+ "logps/chosen": -573.8714599609375,
844
+ "logps/rejected": -594.52880859375,
845
+ "loss": 0.3856,
846
+ "rewards/accuracies": 0.9125000238418579,
847
+ "rewards/chosen": -0.10468001663684845,
848
+ "rewards/margins": 0.9035927057266235,
849
+ "rewards/rejected": -1.0082727670669556,
850
+ "step": 560
851
+ },
852
+ {
853
+ "epoch": 2.5129906025428412,
854
+ "grad_norm": 4.9416184425354,
855
+ "learning_rate": 1.8300653594771242e-06,
856
+ "logits/chosen": -0.023597296327352524,
857
+ "logits/rejected": -0.008983732201159,
858
+ "logps/chosen": -597.69140625,
859
+ "logps/rejected": -601.5765380859375,
860
+ "loss": 0.3884,
861
+ "rewards/accuracies": 0.9312499761581421,
862
+ "rewards/chosen": -0.11435458809137344,
863
+ "rewards/margins": 0.8766048550605774,
864
+ "rewards/rejected": -0.9909593462944031,
865
+ "step": 570
866
+ },
867
+ {
868
+ "epoch": 2.557213930348259,
869
+ "grad_norm": 4.8288397789001465,
870
+ "learning_rate": 1.6666666666666667e-06,
871
+ "logits/chosen": -0.03557625040411949,
872
+ "logits/rejected": -0.025343498215079308,
873
+ "logps/chosen": -590.052978515625,
874
+ "logps/rejected": -594.0569458007812,
875
+ "loss": 0.4105,
876
+ "rewards/accuracies": 0.903124988079071,
877
+ "rewards/chosen": -0.15470431745052338,
878
+ "rewards/margins": 0.817722499370575,
879
+ "rewards/rejected": -0.9724267721176147,
880
+ "step": 580
881
+ },
882
+ {
883
+ "epoch": 2.601437258153676,
884
+ "grad_norm": 4.905878067016602,
885
+ "learning_rate": 1.5032679738562091e-06,
886
+ "logits/chosen": -0.045511119067668915,
887
+ "logits/rejected": -0.0338752418756485,
888
+ "logps/chosen": -598.2936401367188,
889
+ "logps/rejected": -605.7059936523438,
890
+ "loss": 0.3568,
891
+ "rewards/accuracies": 0.918749988079071,
892
+ "rewards/chosen": -0.0584266297519207,
893
+ "rewards/margins": 1.0054492950439453,
894
+ "rewards/rejected": -1.0638759136199951,
895
+ "step": 590
896
+ },
897
+ {
898
+ "epoch": 2.645660585959093,
899
+ "grad_norm": 4.741994857788086,
900
+ "learning_rate": 1.3398692810457518e-06,
901
+ "logits/chosen": -0.02620157226920128,
902
+ "logits/rejected": -0.018892209976911545,
903
+ "logps/chosen": -581.8662719726562,
904
+ "logps/rejected": -600.461669921875,
905
+ "loss": 0.3948,
906
+ "rewards/accuracies": 0.9125000238418579,
907
+ "rewards/chosen": -0.17441710829734802,
908
+ "rewards/margins": 0.8677401542663574,
909
+ "rewards/rejected": -1.0421574115753174,
910
+ "step": 600
911
+ },
912
+ {
913
+ "epoch": 2.6898839137645107,
914
+ "grad_norm": 5.826453685760498,
915
+ "learning_rate": 1.1764705882352942e-06,
916
+ "logits/chosen": -0.008898942731320858,
917
+ "logits/rejected": -0.03388778120279312,
918
+ "logps/chosen": -571.172607421875,
919
+ "logps/rejected": -593.5325927734375,
920
+ "loss": 0.3948,
921
+ "rewards/accuracies": 0.90625,
922
+ "rewards/chosen": -0.19272010028362274,
923
+ "rewards/margins": 0.8866632580757141,
924
+ "rewards/rejected": -1.079383373260498,
925
+ "step": 610
926
+ },
927
+ {
928
+ "epoch": 2.7341072415699283,
929
+ "grad_norm": 4.771381855010986,
930
+ "learning_rate": 1.0130718954248367e-06,
931
+ "logits/chosen": -0.0574166476726532,
932
+ "logits/rejected": -0.028346698731184006,
933
+ "logps/chosen": -598.5902099609375,
934
+ "logps/rejected": -592.706787109375,
935
+ "loss": 0.377,
936
+ "rewards/accuracies": 0.909375011920929,
937
+ "rewards/chosen": -0.16375410556793213,
938
+ "rewards/margins": 0.9357239603996277,
939
+ "rewards/rejected": -1.0994781255722046,
940
+ "step": 620
941
+ },
942
+ {
943
+ "epoch": 2.7783305693753455,
944
+ "grad_norm": 5.956160068511963,
945
+ "learning_rate": 8.496732026143792e-07,
946
+ "logits/chosen": -0.06000574305653572,
947
+ "logits/rejected": -0.05480455234646797,
948
+ "logps/chosen": -593.5914916992188,
949
+ "logps/rejected": -600.48193359375,
950
+ "loss": 0.3902,
951
+ "rewards/accuracies": 0.8968750238418579,
952
+ "rewards/chosen": -0.248348206281662,
953
+ "rewards/margins": 0.9147202372550964,
954
+ "rewards/rejected": -1.1630685329437256,
955
+ "step": 630
956
+ },
957
+ {
958
+ "epoch": 2.8225538971807627,
959
+ "grad_norm": 5.042098045349121,
960
+ "learning_rate": 6.862745098039217e-07,
961
+ "logits/chosen": -0.04940969869494438,
962
+ "logits/rejected": -0.0693870261311531,
963
+ "logps/chosen": -600.4397583007812,
964
+ "logps/rejected": -604.2900390625,
965
+ "loss": 0.3645,
966
+ "rewards/accuracies": 0.918749988079071,
967
+ "rewards/chosen": -0.10940253734588623,
968
+ "rewards/margins": 0.9673919677734375,
969
+ "rewards/rejected": -1.0767946243286133,
970
+ "step": 640
971
+ },
972
+ {
973
+ "epoch": 2.8667772249861803,
974
+ "grad_norm": 5.1368303298950195,
975
+ "learning_rate": 5.228758169934641e-07,
976
+ "logits/chosen": -0.04057068005204201,
977
+ "logits/rejected": -0.05581367015838623,
978
+ "logps/chosen": -589.011474609375,
979
+ "logps/rejected": -603.7899169921875,
980
+ "loss": 0.3756,
981
+ "rewards/accuracies": 0.940625011920929,
982
+ "rewards/chosen": -0.09446386247873306,
983
+ "rewards/margins": 0.9616195559501648,
984
+ "rewards/rejected": -1.0560834407806396,
985
+ "step": 650
986
+ },
987
+ {
988
+ "epoch": 2.9110005527915974,
989
+ "grad_norm": 4.918249130249023,
990
+ "learning_rate": 3.5947712418300653e-07,
991
+ "logits/chosen": -0.031595371663570404,
992
+ "logits/rejected": -0.01696063205599785,
993
+ "logps/chosen": -598.3043212890625,
994
+ "logps/rejected": -597.2545166015625,
995
+ "loss": 0.3842,
996
+ "rewards/accuracies": 0.921875,
997
+ "rewards/chosen": -0.1629355251789093,
998
+ "rewards/margins": 0.9083429574966431,
999
+ "rewards/rejected": -1.07127845287323,
1000
+ "step": 660
1001
+ },
1002
+ {
1003
+ "epoch": 2.955223880597015,
1004
+ "grad_norm": 5.079927444458008,
1005
+ "learning_rate": 1.9607843137254904e-07,
1006
+ "logits/chosen": -0.04399857670068741,
1007
+ "logits/rejected": -0.030833452939987183,
1008
+ "logps/chosen": -592.1138916015625,
1009
+ "logps/rejected": -602.4498291015625,
1010
+ "loss": 0.373,
1011
+ "rewards/accuracies": 0.921875,
1012
+ "rewards/chosen": -0.15153846144676208,
1013
+ "rewards/margins": 0.9492796659469604,
1014
+ "rewards/rejected": -1.1008182764053345,
1015
+ "step": 670
1016
+ },
1017
+ {
1018
+ "epoch": 2.999447208402432,
1019
+ "grad_norm": 5.419740200042725,
1020
+ "learning_rate": 3.267973856209151e-08,
1021
+ "logits/chosen": -0.04406694695353508,
1022
+ "logits/rejected": -0.020651107653975487,
1023
+ "logps/chosen": -593.6739501953125,
1024
+ "logps/rejected": -597.9281616210938,
1025
+ "loss": 0.4197,
1026
+ "rewards/accuracies": 0.862500011920929,
1027
+ "rewards/chosen": -0.21595032513141632,
1028
+ "rewards/margins": 0.8144658803939819,
1029
+ "rewards/rejected": -1.0304162502288818,
1030
+ "step": 680
1031
+ }
1032
+ ],
1033
+ "logging_steps": 10,
1034
+ "max_steps": 681,
1035
+ "num_input_tokens_seen": 0,
1036
+ "num_train_epochs": 3,
1037
+ "save_steps": 10000,
1038
+ "stateful_callbacks": {
1039
+ "TrainerControl": {
1040
+ "args": {
1041
+ "should_epoch_stop": false,
1042
+ "should_evaluate": false,
1043
+ "should_log": false,
1044
+ "should_save": true,
1045
+ "should_training_stop": true
1046
+ },
1047
+ "attributes": {}
1048
+ }
1049
+ },
1050
+ "total_flos": 0.0,
1051
+ "train_batch_size": 1,
1052
+ "trial_name": null,
1053
+ "trial_params": null
1054
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/checkpoint-681/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b179f7ad315d0759c50712f8893152a93c3d9d8048ad612dba0018db90479b
3
+ size 7057
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/chat_template.jinja ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- if strftime_now is defined %}
10
+ {%- set date_string = strftime_now("%d %b %Y") %}
11
+ {%- else %}
12
+ {%- set date_string = "26 Jul 2024" %}
13
+ {%- endif %}
14
+ {%- endif %}
15
+ {%- if not tools is defined %}
16
+ {%- set tools = none %}
17
+ {%- endif %}
18
+
19
+ {#- This block extracts the system message, so we can slot it into the right place. #}
20
+ {%- if messages[0]['role'] == 'system' %}
21
+ {%- set system_message = messages[0]['content']|trim %}
22
+ {%- set messages = messages[1:] %}
23
+ {%- else %}
24
+ {%- set system_message = "" %}
25
+ {%- endif %}
26
+
27
+ {#- System message #}
28
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
29
+ {%- if tools is not none %}
30
+ {{- "Environment: ipython\n" }}
31
+ {%- endif %}
32
+ {{- "Cutting Knowledge Date: December 2023\n" }}
33
+ {{- "Today Date: " + date_string + "\n\n" }}
34
+ {%- if tools is not none and not tools_in_user_message %}
35
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
36
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
37
+ {{- "Do not use variables.\n\n" }}
38
+ {%- for t in tools %}
39
+ {{- t | tojson(indent=4) }}
40
+ {{- "\n\n" }}
41
+ {%- endfor %}
42
+ {%- endif %}
43
+ {{- system_message }}
44
+ {{- "<|eot_id|>" }}
45
+
46
+ {#- Custom tools are passed in a user message with some extra guidance #}
47
+ {%- if tools_in_user_message and not tools is none %}
48
+ {#- Extract the first user message so we can plug it in here #}
49
+ {%- if messages | length != 0 %}
50
+ {%- set first_user_message = messages[0]['content']|trim %}
51
+ {%- set messages = messages[1:] %}
52
+ {%- else %}
53
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
54
+ {%- endif %}
55
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
56
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
57
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
58
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
59
+ {{- "Do not use variables.\n\n" }}
60
+ {%- for t in tools %}
61
+ {{- t | tojson(indent=4) }}
62
+ {{- "\n\n" }}
63
+ {%- endfor %}
64
+ {{- first_user_message + "<|eot_id|>"}}
65
+ {%- endif %}
66
+
67
+ {%- for message in messages %}
68
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
69
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
70
+ {%- elif 'tool_calls' in message %}
71
+ {%- if not message.tool_calls|length == 1 %}
72
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
73
+ {%- endif %}
74
+ {%- set tool_call = message.tool_calls[0].function %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- '{"name": "' + tool_call.name + '", ' }}
77
+ {{- '"parameters": ' }}
78
+ {{- tool_call.arguments | tojson }}
79
+ {{- "}" }}
80
+ {{- "<|eot_id|>" }}
81
+ {%- elif message.role == "tool" or message.role == "ipython" %}
82
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
83
+ {%- if message.content is mapping or message.content is iterable %}
84
+ {{- message.content | tojson }}
85
+ {%- else %}
86
+ {{- message.content }}
87
+ {%- endif %}
88
+ {{- "<|eot_id|>" }}
89
+ {%- endif %}
90
+ {%- endfor %}
91
+ {%- if add_generation_prompt %}
92
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
93
+ {%- endif %}
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 3072,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 8192,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 24,
22
+ "num_hidden_layers": 28,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": {
27
+ "factor": 32.0,
28
+ "high_freq_factor": 4.0,
29
+ "low_freq_factor": 1.0,
30
+ "original_max_position_embeddings": 8192,
31
+ "rope_type": "llama3"
32
+ },
33
+ "rope_theta": 500000.0,
34
+ "tie_word_embeddings": true,
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.55.0",
37
+ "use_cache": true,
38
+ "vocab_size": 128256
39
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.55.0"
12
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbd908ba4d750eede442739aae7b502dbb2245232bca2bea115ba2dbb7c26b9e
3
+ size 4998767360
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88c96bb743a02ebb8a9c080df1c9707e08bf5afc6d725647578c64457ca38a86
3
+ size 4932808968
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5a1ba7ae30f56dc2e593794caaffbd8fa932448e6121272a3f1aad7d568e0c
3
+ size 2919452168
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 3212749824,
4
+ "total_size": 12850999296
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
198
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
199
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
200
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
201
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
202
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
203
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
204
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
205
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
206
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
207
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
208
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
209
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
210
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
211
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
212
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
213
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
214
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
215
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
225
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
226
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
227
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
228
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
229
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
230
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
231
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
232
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
233
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
234
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
235
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
236
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
237
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
238
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
239
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
240
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
241
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
242
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
244
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
247
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
258
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
259
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
260
+ "model.norm.weight": "model-00003-of-00003.safetensors"
261
+ }
262
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/merged_model/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/model_args.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "model_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
3
+ "agent_name": "experiment_agent"
4
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/experiment_agent/train_args.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "load_in_4bit": true
3
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/DPO_configs.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "Trained_Models/Jackson0018/Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent",
3
+ "overwrite_output_dir": null,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "no",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 1,
10
+ "per_device_eval_batch_size": 4,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 32,
14
+ "eval_accumulation_steps": 2,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": 250,
17
+ "learning_rate": 1e-05,
18
+ "weight_decay": 0.01,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.999,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 0.6,
23
+ "num_train_epochs": 3.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "linear",
26
+ "lr_scheduler_kwargs": {},
27
+ "warmup_ratio": 0.1,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "Trained_Models/Jackson0018/Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/runs/Sep18_17-09-20_ai21",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": false,
35
+ "logging_steps": 10,
36
+ "logging_nan_inf_filter": false,
37
+ "save_strategy": "steps",
38
+ "save_steps": 10000,
39
+ "save_total_limit": null,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 3407,
48
+ "data_seed": 3407,
49
+ "jit_mode_eval": false,
50
+ "use_ipex": false,
51
+ "bf16": true,
52
+ "fp16": false,
53
+ "fp16_opt_level": "O1",
54
+ "half_precision_backend": "auto",
55
+ "bf16_full_eval": false,
56
+ "fp16_full_eval": false,
57
+ "tf32": null,
58
+ "local_rank": 0,
59
+ "ddp_backend": null,
60
+ "tpu_num_cores": null,
61
+ "tpu_metrics_debug": false,
62
+ "debug": [],
63
+ "dataloader_drop_last": false,
64
+ "eval_steps": null,
65
+ "dataloader_num_workers": 0,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": null,
69
+ "disable_tqdm": false,
70
+ "remove_unused_columns": true,
71
+ "label_names": null,
72
+ "load_best_model_at_end": false,
73
+ "metric_for_best_model": null,
74
+ "greater_is_better": null,
75
+ "ignore_data_skip": false,
76
+ "fsdp": [],
77
+ "fsdp_min_num_params": 0,
78
+ "fsdp_config": {
79
+ "min_num_params": 0,
80
+ "xla": false,
81
+ "xla_fsdp_v2": false,
82
+ "xla_fsdp_grad_ckpt": false
83
+ },
84
+ "fsdp_transformer_layer_cls_to_wrap": null,
85
+ "accelerator_config": {
86
+ "split_batches": false,
87
+ "dispatch_batches": null,
88
+ "even_batches": true,
89
+ "use_seedable_sampler": true,
90
+ "non_blocking": false,
91
+ "gradient_accumulation_kwargs": null
92
+ },
93
+ "deepspeed": null,
94
+ "label_smoothing_factor": 0.0,
95
+ "optim": "adamw_8bit",
96
+ "optim_args": null,
97
+ "adafactor": false,
98
+ "group_by_length": false,
99
+ "length_column_name": "length",
100
+ "report_to": [],
101
+ "ddp_find_unused_parameters": null,
102
+ "ddp_bucket_cap_mb": null,
103
+ "ddp_broadcast_buffers": null,
104
+ "dataloader_pin_memory": true,
105
+ "dataloader_persistent_workers": false,
106
+ "skip_memory_metrics": true,
107
+ "use_legacy_prediction_loop": false,
108
+ "push_to_hub": false,
109
+ "resume_from_checkpoint": null,
110
+ "hub_model_id": null,
111
+ "hub_strategy": "every_save",
112
+ "hub_token": "<HUB_TOKEN>",
113
+ "hub_private_repo": null,
114
+ "hub_always_push": false,
115
+ "hub_revision": null,
116
+ "gradient_checkpointing": false,
117
+ "gradient_checkpointing_kwargs": null,
118
+ "include_inputs_for_metrics": false,
119
+ "include_for_metrics": [],
120
+ "eval_do_concat_batches": true,
121
+ "fp16_backend": "auto",
122
+ "push_to_hub_model_id": null,
123
+ "push_to_hub_organization": null,
124
+ "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
125
+ "mp_parameters": "",
126
+ "auto_find_batch_size": true,
127
+ "full_determinism": false,
128
+ "torchdynamo": null,
129
+ "ray_scope": "last",
130
+ "ddp_timeout": 1800,
131
+ "torch_compile": false,
132
+ "torch_compile_backend": null,
133
+ "torch_compile_mode": null,
134
+ "include_tokens_per_second": false,
135
+ "include_num_input_tokens_seen": false,
136
+ "neftune_noise_alpha": null,
137
+ "optim_target_modules": null,
138
+ "batch_eval_metrics": false,
139
+ "eval_on_start": false,
140
+ "use_liger_kernel": false,
141
+ "liger_kernel_config": null,
142
+ "eval_use_gather_object": false,
143
+ "average_tokens_across_devices": false,
144
+ "model_init_kwargs": null,
145
+ "ref_model_init_kwargs": null,
146
+ "model_adapter_name": null,
147
+ "ref_adapter_name": null,
148
+ "force_use_ref_model": false,
149
+ "disable_dropout": true,
150
+ "use_logits_to_keep": false,
151
+ "dataset_num_proc": 2,
152
+ "padding_value": null,
153
+ "label_pad_token_id": -100,
154
+ "max_prompt_length": 2000,
155
+ "max_completion_length": 2000,
156
+ "max_length": 4000,
157
+ "truncation_mode": "keep_end",
158
+ "padding_free": false,
159
+ "precompute_ref_log_probs": false,
160
+ "precompute_ref_batch_size": null,
161
+ "tools": null,
162
+ "loss_type": "sigmoid",
163
+ "use_liger_loss": false,
164
+ "base_model_attribute_name": "model",
165
+ "beta": 0.1,
166
+ "f_divergence_type": "reverse_kl",
167
+ "f_alpha_divergence_coef": 1.0,
168
+ "reference_free": false,
169
+ "label_smoothing": 0.0,
170
+ "use_weighting": false,
171
+ "rpo_alpha": null,
172
+ "ld_alpha": null,
173
+ "discopop_tau": 0.05,
174
+ "loss_weights": null,
175
+ "sync_ref_model": false,
176
+ "ref_model_mixup_alpha": 0.6,
177
+ "ref_model_sync_steps": 512,
178
+ "generate_during_eval": false,
179
+ "vllm_sampling_params": null,
180
+ "unsloth_num_chunks": -1
181
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
3
+ library_name: transformers
4
+ model_name: method_agent
5
+ tags:
6
+ - generated_from_trainer
7
+ - trl
8
+ - unsloth
9
+ - dpo
10
+ licence: license
11
+ ---
12
+
13
+ # Model Card for method_agent
14
+
15
+ This model is a fine-tuned version of [unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit).
16
+ It has been trained using [TRL](https://github.com/huggingface/trl).
17
+
18
+ ## Quick start
19
+
20
+ ```python
21
+ from transformers import pipeline
22
+
23
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
24
+ generator = pipeline("text-generation", model="None", device="cuda")
25
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
26
+ print(output["generated_text"])
27
+ ```
28
+
29
+ ## Training procedure
30
+
31
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jackson0530/ScientificPaperRetrieval_Train-Train_DPO_unsloth/runs/vfymu37e)
32
+
33
+
34
+ This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
35
+
36
+ ### Framework versions
37
+
38
+ - TRL: 0.21.0
39
+ - Transformers: 4.55.0
40
+ - Pytorch: 2.7.1
41
+ - Datasets: 3.6.0
42
+ - Tokenizers: 0.21.4
43
+
44
+ ## Citations
45
+
46
+ Cite DPO as:
47
+
48
+ ```bibtex
49
+ @inproceedings{rafailov2023direct,
50
+ title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
51
+ author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
52
+ year = 2023,
53
+ booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
54
+ url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
55
+ editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
56
+ }
57
+ ```
58
+
59
+ Cite TRL as:
60
+
61
+ ```bibtex
62
+ @misc{vonwerra2022trl,
63
+ title = {{TRL: Transformer Reinforcement Learning}},
64
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
65
+ year = 2020,
66
+ journal = {GitHub repository},
67
+ publisher = {GitHub},
68
+ howpublished = {\url{https://github.com/huggingface/trl}}
69
+ }
70
+ ```
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/README.md ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
7
+ - dpo
8
+ - lora
9
+ - transformers
10
+ - trl
11
+ - unsloth
12
+ ---
13
+
14
+ # Model Card for Model ID
15
+
16
+ <!-- Provide a quick summary of what the model is/does. -->
17
+
18
+
19
+
20
+ ## Model Details
21
+
22
+ ### Model Description
23
+
24
+ <!-- Provide a longer summary of what this model is. -->
25
+
26
+
27
+
28
+ - **Developed by:** [More Information Needed]
29
+ - **Funded by [optional]:** [More Information Needed]
30
+ - **Shared by [optional]:** [More Information Needed]
31
+ - **Model type:** [More Information Needed]
32
+ - **Language(s) (NLP):** [More Information Needed]
33
+ - **License:** [More Information Needed]
34
+ - **Finetuned from model [optional]:** [More Information Needed]
35
+
36
+ ### Model Sources [optional]
37
+
38
+ <!-- Provide the basic links for the model. -->
39
+
40
+ - **Repository:** [More Information Needed]
41
+ - **Paper [optional]:** [More Information Needed]
42
+ - **Demo [optional]:** [More Information Needed]
43
+
44
+ ## Uses
45
+
46
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
47
+
48
+ ### Direct Use
49
+
50
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Downstream Use [optional]
55
+
56
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
57
+
58
+ [More Information Needed]
59
+
60
+ ### Out-of-Scope Use
61
+
62
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
63
+
64
+ [More Information Needed]
65
+
66
+ ## Bias, Risks, and Limitations
67
+
68
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
69
+
70
+ [More Information Needed]
71
+
72
+ ### Recommendations
73
+
74
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
75
+
76
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
77
+
78
+ ## How to Get Started with the Model
79
+
80
+ Use the code below to get started with the model.
81
+
82
+ [More Information Needed]
83
+
84
+ ## Training Details
85
+
86
+ ### Training Data
87
+
88
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
89
+
90
+ [More Information Needed]
91
+
92
+ ### Training Procedure
93
+
94
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
95
+
96
+ #### Preprocessing [optional]
97
+
98
+ [More Information Needed]
99
+
100
+
101
+ #### Training Hyperparameters
102
+
103
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
104
+
105
+ #### Speeds, Sizes, Times [optional]
106
+
107
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
108
+
109
+ [More Information Needed]
110
+
111
+ ## Evaluation
112
+
113
+ <!-- This section describes the evaluation protocols and provides the results. -->
114
+
115
+ ### Testing Data, Factors & Metrics
116
+
117
+ #### Testing Data
118
+
119
+ <!-- This should link to a Dataset Card if possible. -->
120
+
121
+ [More Information Needed]
122
+
123
+ #### Factors
124
+
125
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
126
+
127
+ [More Information Needed]
128
+
129
+ #### Metrics
130
+
131
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
132
+
133
+ [More Information Needed]
134
+
135
+ ### Results
136
+
137
+ [More Information Needed]
138
+
139
+ #### Summary
140
+
141
+
142
+
143
+ ## Model Examination [optional]
144
+
145
+ <!-- Relevant interpretability work for the model goes here -->
146
+
147
+ [More Information Needed]
148
+
149
+ ## Environmental Impact
150
+
151
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
152
+
153
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
154
+
155
+ - **Hardware Type:** [More Information Needed]
156
+ - **Hours used:** [More Information Needed]
157
+ - **Cloud Provider:** [More Information Needed]
158
+ - **Compute Region:** [More Information Needed]
159
+ - **Carbon Emitted:** [More Information Needed]
160
+
161
+ ## Technical Specifications [optional]
162
+
163
+ ### Model Architecture and Objective
164
+
165
+ [More Information Needed]
166
+
167
+ ### Compute Infrastructure
168
+
169
+ [More Information Needed]
170
+
171
+ #### Hardware
172
+
173
+ [More Information Needed]
174
+
175
+ #### Software
176
+
177
+ [More Information Needed]
178
+
179
+ ## Citation [optional]
180
+
181
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
182
+
183
+ **BibTeX:**
184
+
185
+ [More Information Needed]
186
+
187
+ **APA:**
188
+
189
+ [More Information Needed]
190
+
191
+ ## Glossary [optional]
192
+
193
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
194
+
195
+ [More Information Needed]
196
+
197
+ ## More Information [optional]
198
+
199
+ [More Information Needed]
200
+
201
+ ## Model Card Authors [optional]
202
+
203
+ [More Information Needed]
204
+
205
+ ## Model Card Contact
206
+
207
+ [More Information Needed]
208
+ ### Framework versions
209
+
210
+ - PEFT 0.17.0
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 64,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 64,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "up_proj",
29
+ "o_proj",
30
+ "gate_proj",
31
+ "v_proj",
32
+ "q_proj",
33
+ "k_proj",
34
+ "down_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7cd7bdb3fb61c6a2a2693ee5a3ef1f3a6c3239651df74f1cc73fd1f656a2420
3
+ size 389074464
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/chat_template.jinja ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- if strftime_now is defined %}
10
+ {%- set date_string = strftime_now("%d %b %Y") %}
11
+ {%- else %}
12
+ {%- set date_string = "26 Jul 2024" %}
13
+ {%- endif %}
14
+ {%- endif %}
15
+ {%- if not tools is defined %}
16
+ {%- set tools = none %}
17
+ {%- endif %}
18
+
19
+ {#- This block extracts the system message, so we can slot it into the right place. #}
20
+ {%- if messages[0]['role'] == 'system' %}
21
+ {%- set system_message = messages[0]['content']|trim %}
22
+ {%- set messages = messages[1:] %}
23
+ {%- else %}
24
+ {%- set system_message = "" %}
25
+ {%- endif %}
26
+
27
+ {#- System message #}
28
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
29
+ {%- if tools is not none %}
30
+ {{- "Environment: ipython\n" }}
31
+ {%- endif %}
32
+ {{- "Cutting Knowledge Date: December 2023\n" }}
33
+ {{- "Today Date: " + date_string + "\n\n" }}
34
+ {%- if tools is not none and not tools_in_user_message %}
35
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
36
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
37
+ {{- "Do not use variables.\n\n" }}
38
+ {%- for t in tools %}
39
+ {{- t | tojson(indent=4) }}
40
+ {{- "\n\n" }}
41
+ {%- endfor %}
42
+ {%- endif %}
43
+ {{- system_message }}
44
+ {{- "<|eot_id|>" }}
45
+
46
+ {#- Custom tools are passed in a user message with some extra guidance #}
47
+ {%- if tools_in_user_message and not tools is none %}
48
+ {#- Extract the first user message so we can plug it in here #}
49
+ {%- if messages | length != 0 %}
50
+ {%- set first_user_message = messages[0]['content']|trim %}
51
+ {%- set messages = messages[1:] %}
52
+ {%- else %}
53
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
54
+ {%- endif %}
55
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
56
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
57
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
58
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
59
+ {{- "Do not use variables.\n\n" }}
60
+ {%- for t in tools %}
61
+ {{- t | tojson(indent=4) }}
62
+ {{- "\n\n" }}
63
+ {%- endfor %}
64
+ {{- first_user_message + "<|eot_id|>"}}
65
+ {%- endif %}
66
+
67
+ {%- for message in messages %}
68
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
69
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
70
+ {%- elif 'tool_calls' in message %}
71
+ {%- if not message.tool_calls|length == 1 %}
72
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
73
+ {%- endif %}
74
+ {%- set tool_call = message.tool_calls[0].function %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- '{"name": "' + tool_call.name + '", ' }}
77
+ {{- '"parameters": ' }}
78
+ {{- tool_call.arguments | tojson }}
79
+ {{- "}" }}
80
+ {{- "<|eot_id|>" }}
81
+ {%- elif message.role == "tool" or message.role == "ipython" %}
82
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
83
+ {%- if message.content is mapping or message.content is iterable %}
84
+ {{- message.content | tojson }}
85
+ {%- else %}
86
+ {{- message.content }}
87
+ {%- endif %}
88
+ {{- "<|eot_id|>" }}
89
+ {%- endif %}
90
+ {%- endfor %}
91
+ {%- if add_generation_prompt %}
92
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
93
+ {%- endif %}
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad114157b2e24b8a93785b9fd33956d838215b31cf5878c5f59a7fc039b64b0c
3
+ size 198012101
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:181c5f0270cf39930062ddfa3767a2481d0c360f120b11f8e25dbf533a1cdaba
3
+ size 14645
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:148e7306497dc207073c9b6fe0ab52f28c76df842441b72a817edc0055612b40
3
+ size 1465
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/tokenizer_config.json ADDED
@@ -0,0 +1,2066 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "added_tokens_decoder": {
4
+ "128000": {
5
+ "content": "<|begin_of_text|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128001": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "128002": {
21
+ "content": "<|reserved_special_token_0|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "128003": {
29
+ "content": "<|reserved_special_token_1|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128004": {
37
+ "content": "<|finetune_right_pad_id|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128005": {
45
+ "content": "<|reserved_special_token_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128006": {
53
+ "content": "<|start_header_id|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128007": {
61
+ "content": "<|end_header_id|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128008": {
69
+ "content": "<|eom_id|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128009": {
77
+ "content": "<|eot_id|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128010": {
85
+ "content": "<|python_tag|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128011": {
93
+ "content": "<|reserved_special_token_3|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128012": {
101
+ "content": "<|reserved_special_token_4|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128013": {
109
+ "content": "<|reserved_special_token_5|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128014": {
117
+ "content": "<|reserved_special_token_6|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128015": {
125
+ "content": "<|reserved_special_token_7|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128016": {
133
+ "content": "<|reserved_special_token_8|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128017": {
141
+ "content": "<|reserved_special_token_9|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128018": {
149
+ "content": "<|reserved_special_token_10|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128019": {
157
+ "content": "<|reserved_special_token_11|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128020": {
165
+ "content": "<|reserved_special_token_12|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128021": {
173
+ "content": "<|reserved_special_token_13|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128022": {
181
+ "content": "<|reserved_special_token_14|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128023": {
189
+ "content": "<|reserved_special_token_15|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128024": {
197
+ "content": "<|reserved_special_token_16|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128025": {
205
+ "content": "<|reserved_special_token_17|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128026": {
213
+ "content": "<|reserved_special_token_18|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128027": {
221
+ "content": "<|reserved_special_token_19|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128028": {
229
+ "content": "<|reserved_special_token_20|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128029": {
237
+ "content": "<|reserved_special_token_21|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128030": {
245
+ "content": "<|reserved_special_token_22|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128031": {
253
+ "content": "<|reserved_special_token_23|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128032": {
261
+ "content": "<|reserved_special_token_24|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128033": {
269
+ "content": "<|reserved_special_token_25|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128034": {
277
+ "content": "<|reserved_special_token_26|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128035": {
285
+ "content": "<|reserved_special_token_27|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128036": {
293
+ "content": "<|reserved_special_token_28|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128037": {
301
+ "content": "<|reserved_special_token_29|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128038": {
309
+ "content": "<|reserved_special_token_30|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128039": {
317
+ "content": "<|reserved_special_token_31|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128040": {
325
+ "content": "<|reserved_special_token_32|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128041": {
333
+ "content": "<|reserved_special_token_33|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128042": {
341
+ "content": "<|reserved_special_token_34|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128043": {
349
+ "content": "<|reserved_special_token_35|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128044": {
357
+ "content": "<|reserved_special_token_36|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128045": {
365
+ "content": "<|reserved_special_token_37|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128046": {
373
+ "content": "<|reserved_special_token_38|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128047": {
381
+ "content": "<|reserved_special_token_39|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128048": {
389
+ "content": "<|reserved_special_token_40|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128049": {
397
+ "content": "<|reserved_special_token_41|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128050": {
405
+ "content": "<|reserved_special_token_42|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128051": {
413
+ "content": "<|reserved_special_token_43|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128052": {
421
+ "content": "<|reserved_special_token_44|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128053": {
429
+ "content": "<|reserved_special_token_45|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128054": {
437
+ "content": "<|reserved_special_token_46|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128055": {
445
+ "content": "<|reserved_special_token_47|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128056": {
453
+ "content": "<|reserved_special_token_48|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128057": {
461
+ "content": "<|reserved_special_token_49|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128058": {
469
+ "content": "<|reserved_special_token_50|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128059": {
477
+ "content": "<|reserved_special_token_51|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128060": {
485
+ "content": "<|reserved_special_token_52|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128061": {
493
+ "content": "<|reserved_special_token_53|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128062": {
501
+ "content": "<|reserved_special_token_54|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128063": {
509
+ "content": "<|reserved_special_token_55|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128064": {
517
+ "content": "<|reserved_special_token_56|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128065": {
525
+ "content": "<|reserved_special_token_57|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128066": {
533
+ "content": "<|reserved_special_token_58|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128067": {
541
+ "content": "<|reserved_special_token_59|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128068": {
549
+ "content": "<|reserved_special_token_60|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128069": {
557
+ "content": "<|reserved_special_token_61|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128070": {
565
+ "content": "<|reserved_special_token_62|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128071": {
573
+ "content": "<|reserved_special_token_63|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128072": {
581
+ "content": "<|reserved_special_token_64|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128073": {
589
+ "content": "<|reserved_special_token_65|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128074": {
597
+ "content": "<|reserved_special_token_66|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128075": {
605
+ "content": "<|reserved_special_token_67|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128076": {
613
+ "content": "<|reserved_special_token_68|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128077": {
621
+ "content": "<|reserved_special_token_69|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128078": {
629
+ "content": "<|reserved_special_token_70|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128079": {
637
+ "content": "<|reserved_special_token_71|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128080": {
645
+ "content": "<|reserved_special_token_72|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128081": {
653
+ "content": "<|reserved_special_token_73|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128082": {
661
+ "content": "<|reserved_special_token_74|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128083": {
669
+ "content": "<|reserved_special_token_75|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128084": {
677
+ "content": "<|reserved_special_token_76|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128085": {
685
+ "content": "<|reserved_special_token_77|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128086": {
693
+ "content": "<|reserved_special_token_78|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128087": {
701
+ "content": "<|reserved_special_token_79|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128088": {
709
+ "content": "<|reserved_special_token_80|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128089": {
717
+ "content": "<|reserved_special_token_81|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128090": {
725
+ "content": "<|reserved_special_token_82|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128091": {
733
+ "content": "<|reserved_special_token_83|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128092": {
741
+ "content": "<|reserved_special_token_84|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128093": {
749
+ "content": "<|reserved_special_token_85|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128094": {
757
+ "content": "<|reserved_special_token_86|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128095": {
765
+ "content": "<|reserved_special_token_87|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128096": {
773
+ "content": "<|reserved_special_token_88|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128097": {
781
+ "content": "<|reserved_special_token_89|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128098": {
789
+ "content": "<|reserved_special_token_90|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128099": {
797
+ "content": "<|reserved_special_token_91|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128100": {
805
+ "content": "<|reserved_special_token_92|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128101": {
813
+ "content": "<|reserved_special_token_93|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128102": {
821
+ "content": "<|reserved_special_token_94|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128103": {
829
+ "content": "<|reserved_special_token_95|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128104": {
837
+ "content": "<|reserved_special_token_96|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128105": {
845
+ "content": "<|reserved_special_token_97|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "128106": {
853
+ "content": "<|reserved_special_token_98|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "128107": {
861
+ "content": "<|reserved_special_token_99|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "128108": {
869
+ "content": "<|reserved_special_token_100|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "128109": {
877
+ "content": "<|reserved_special_token_101|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "128110": {
885
+ "content": "<|reserved_special_token_102|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "128111": {
893
+ "content": "<|reserved_special_token_103|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "128112": {
901
+ "content": "<|reserved_special_token_104|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "128113": {
909
+ "content": "<|reserved_special_token_105|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "128114": {
917
+ "content": "<|reserved_special_token_106|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "128115": {
925
+ "content": "<|reserved_special_token_107|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "128116": {
933
+ "content": "<|reserved_special_token_108|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "128117": {
941
+ "content": "<|reserved_special_token_109|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "128118": {
949
+ "content": "<|reserved_special_token_110|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "128119": {
957
+ "content": "<|reserved_special_token_111|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "128120": {
965
+ "content": "<|reserved_special_token_112|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "128121": {
973
+ "content": "<|reserved_special_token_113|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "128122": {
981
+ "content": "<|reserved_special_token_114|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "128123": {
989
+ "content": "<|reserved_special_token_115|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "128124": {
997
+ "content": "<|reserved_special_token_116|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "128125": {
1005
+ "content": "<|reserved_special_token_117|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "128126": {
1013
+ "content": "<|reserved_special_token_118|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "128127": {
1021
+ "content": "<|reserved_special_token_119|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "128128": {
1029
+ "content": "<|reserved_special_token_120|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "128129": {
1037
+ "content": "<|reserved_special_token_121|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "128130": {
1045
+ "content": "<|reserved_special_token_122|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "128131": {
1053
+ "content": "<|reserved_special_token_123|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "128132": {
1061
+ "content": "<|reserved_special_token_124|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "128133": {
1069
+ "content": "<|reserved_special_token_125|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "128134": {
1077
+ "content": "<|reserved_special_token_126|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "128135": {
1085
+ "content": "<|reserved_special_token_127|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "128136": {
1093
+ "content": "<|reserved_special_token_128|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "128137": {
1101
+ "content": "<|reserved_special_token_129|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "128138": {
1109
+ "content": "<|reserved_special_token_130|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "128139": {
1117
+ "content": "<|reserved_special_token_131|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "128140": {
1125
+ "content": "<|reserved_special_token_132|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "128141": {
1133
+ "content": "<|reserved_special_token_133|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "128142": {
1141
+ "content": "<|reserved_special_token_134|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "128143": {
1149
+ "content": "<|reserved_special_token_135|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "128144": {
1157
+ "content": "<|reserved_special_token_136|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "128145": {
1165
+ "content": "<|reserved_special_token_137|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "128146": {
1173
+ "content": "<|reserved_special_token_138|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "128147": {
1181
+ "content": "<|reserved_special_token_139|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "128148": {
1189
+ "content": "<|reserved_special_token_140|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "128149": {
1197
+ "content": "<|reserved_special_token_141|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "128150": {
1205
+ "content": "<|reserved_special_token_142|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "128151": {
1213
+ "content": "<|reserved_special_token_143|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "128152": {
1221
+ "content": "<|reserved_special_token_144|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "128153": {
1229
+ "content": "<|reserved_special_token_145|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "128154": {
1237
+ "content": "<|reserved_special_token_146|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "128155": {
1245
+ "content": "<|reserved_special_token_147|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "128156": {
1253
+ "content": "<|reserved_special_token_148|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "128157": {
1261
+ "content": "<|reserved_special_token_149|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "128158": {
1269
+ "content": "<|reserved_special_token_150|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "128159": {
1277
+ "content": "<|reserved_special_token_151|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "128160": {
1285
+ "content": "<|reserved_special_token_152|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "128161": {
1293
+ "content": "<|reserved_special_token_153|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "128162": {
1301
+ "content": "<|reserved_special_token_154|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "128163": {
1309
+ "content": "<|reserved_special_token_155|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "128164": {
1317
+ "content": "<|reserved_special_token_156|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "128165": {
1325
+ "content": "<|reserved_special_token_157|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "128166": {
1333
+ "content": "<|reserved_special_token_158|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "128167": {
1341
+ "content": "<|reserved_special_token_159|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "128168": {
1349
+ "content": "<|reserved_special_token_160|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "128169": {
1357
+ "content": "<|reserved_special_token_161|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "128170": {
1365
+ "content": "<|reserved_special_token_162|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "128171": {
1373
+ "content": "<|reserved_special_token_163|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "128172": {
1381
+ "content": "<|reserved_special_token_164|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "128173": {
1389
+ "content": "<|reserved_special_token_165|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "128174": {
1397
+ "content": "<|reserved_special_token_166|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "128175": {
1405
+ "content": "<|reserved_special_token_167|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "128176": {
1413
+ "content": "<|reserved_special_token_168|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "128177": {
1421
+ "content": "<|reserved_special_token_169|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "128178": {
1429
+ "content": "<|reserved_special_token_170|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "128179": {
1437
+ "content": "<|reserved_special_token_171|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "128180": {
1445
+ "content": "<|reserved_special_token_172|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "128181": {
1453
+ "content": "<|reserved_special_token_173|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "128182": {
1461
+ "content": "<|reserved_special_token_174|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "128183": {
1469
+ "content": "<|reserved_special_token_175|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "128184": {
1477
+ "content": "<|reserved_special_token_176|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "128185": {
1485
+ "content": "<|reserved_special_token_177|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "128186": {
1493
+ "content": "<|reserved_special_token_178|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "128187": {
1501
+ "content": "<|reserved_special_token_179|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "128188": {
1509
+ "content": "<|reserved_special_token_180|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "128189": {
1517
+ "content": "<|reserved_special_token_181|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "128190": {
1525
+ "content": "<|reserved_special_token_182|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "128191": {
1533
+ "content": "<|reserved_special_token_183|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "128192": {
1541
+ "content": "<|reserved_special_token_184|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "128193": {
1549
+ "content": "<|reserved_special_token_185|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "128194": {
1557
+ "content": "<|reserved_special_token_186|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "128195": {
1565
+ "content": "<|reserved_special_token_187|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "128196": {
1573
+ "content": "<|reserved_special_token_188|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "128197": {
1581
+ "content": "<|reserved_special_token_189|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "128198": {
1589
+ "content": "<|reserved_special_token_190|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "128199": {
1597
+ "content": "<|reserved_special_token_191|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "128200": {
1605
+ "content": "<|reserved_special_token_192|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "128201": {
1613
+ "content": "<|reserved_special_token_193|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "128202": {
1621
+ "content": "<|reserved_special_token_194|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "128203": {
1629
+ "content": "<|reserved_special_token_195|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "128204": {
1637
+ "content": "<|reserved_special_token_196|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "128205": {
1645
+ "content": "<|reserved_special_token_197|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "128206": {
1653
+ "content": "<|reserved_special_token_198|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "128207": {
1661
+ "content": "<|reserved_special_token_199|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ },
1668
+ "128208": {
1669
+ "content": "<|reserved_special_token_200|>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": true
1675
+ },
1676
+ "128209": {
1677
+ "content": "<|reserved_special_token_201|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": true
1683
+ },
1684
+ "128210": {
1685
+ "content": "<|reserved_special_token_202|>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": true
1691
+ },
1692
+ "128211": {
1693
+ "content": "<|reserved_special_token_203|>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": true
1699
+ },
1700
+ "128212": {
1701
+ "content": "<|reserved_special_token_204|>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": true
1707
+ },
1708
+ "128213": {
1709
+ "content": "<|reserved_special_token_205|>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": true
1715
+ },
1716
+ "128214": {
1717
+ "content": "<|reserved_special_token_206|>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": true
1723
+ },
1724
+ "128215": {
1725
+ "content": "<|reserved_special_token_207|>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": true
1731
+ },
1732
+ "128216": {
1733
+ "content": "<|reserved_special_token_208|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": true
1739
+ },
1740
+ "128217": {
1741
+ "content": "<|reserved_special_token_209|>",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": true
1747
+ },
1748
+ "128218": {
1749
+ "content": "<|reserved_special_token_210|>",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": true
1755
+ },
1756
+ "128219": {
1757
+ "content": "<|reserved_special_token_211|>",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": true
1763
+ },
1764
+ "128220": {
1765
+ "content": "<|reserved_special_token_212|>",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": true
1771
+ },
1772
+ "128221": {
1773
+ "content": "<|reserved_special_token_213|>",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": true
1779
+ },
1780
+ "128222": {
1781
+ "content": "<|reserved_special_token_214|>",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": true
1787
+ },
1788
+ "128223": {
1789
+ "content": "<|reserved_special_token_215|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": true
1795
+ },
1796
+ "128224": {
1797
+ "content": "<|reserved_special_token_216|>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": true
1803
+ },
1804
+ "128225": {
1805
+ "content": "<|reserved_special_token_217|>",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": true
1811
+ },
1812
+ "128226": {
1813
+ "content": "<|reserved_special_token_218|>",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": true
1819
+ },
1820
+ "128227": {
1821
+ "content": "<|reserved_special_token_219|>",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": true
1827
+ },
1828
+ "128228": {
1829
+ "content": "<|reserved_special_token_220|>",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": true
1835
+ },
1836
+ "128229": {
1837
+ "content": "<|reserved_special_token_221|>",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": true
1843
+ },
1844
+ "128230": {
1845
+ "content": "<|reserved_special_token_222|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": true
1851
+ },
1852
+ "128231": {
1853
+ "content": "<|reserved_special_token_223|>",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": true
1859
+ },
1860
+ "128232": {
1861
+ "content": "<|reserved_special_token_224|>",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": true
1867
+ },
1868
+ "128233": {
1869
+ "content": "<|reserved_special_token_225|>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": true
1875
+ },
1876
+ "128234": {
1877
+ "content": "<|reserved_special_token_226|>",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": true
1883
+ },
1884
+ "128235": {
1885
+ "content": "<|reserved_special_token_227|>",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": true
1891
+ },
1892
+ "128236": {
1893
+ "content": "<|reserved_special_token_228|>",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": true
1899
+ },
1900
+ "128237": {
1901
+ "content": "<|reserved_special_token_229|>",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": true
1907
+ },
1908
+ "128238": {
1909
+ "content": "<|reserved_special_token_230|>",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": true
1915
+ },
1916
+ "128239": {
1917
+ "content": "<|reserved_special_token_231|>",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": true
1923
+ },
1924
+ "128240": {
1925
+ "content": "<|reserved_special_token_232|>",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": true
1931
+ },
1932
+ "128241": {
1933
+ "content": "<|reserved_special_token_233|>",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": true
1939
+ },
1940
+ "128242": {
1941
+ "content": "<|reserved_special_token_234|>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": true
1947
+ },
1948
+ "128243": {
1949
+ "content": "<|reserved_special_token_235|>",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": true
1955
+ },
1956
+ "128244": {
1957
+ "content": "<|reserved_special_token_236|>",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": true
1963
+ },
1964
+ "128245": {
1965
+ "content": "<|reserved_special_token_237|>",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": true
1971
+ },
1972
+ "128246": {
1973
+ "content": "<|reserved_special_token_238|>",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": true
1979
+ },
1980
+ "128247": {
1981
+ "content": "<|reserved_special_token_239|>",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": true
1987
+ },
1988
+ "128248": {
1989
+ "content": "<|reserved_special_token_240|>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": true
1995
+ },
1996
+ "128249": {
1997
+ "content": "<|reserved_special_token_241|>",
1998
+ "lstrip": false,
1999
+ "normalized": false,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": true
2003
+ },
2004
+ "128250": {
2005
+ "content": "<|reserved_special_token_242|>",
2006
+ "lstrip": false,
2007
+ "normalized": false,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": true
2011
+ },
2012
+ "128251": {
2013
+ "content": "<|reserved_special_token_243|>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": true
2019
+ },
2020
+ "128252": {
2021
+ "content": "<|reserved_special_token_244|>",
2022
+ "lstrip": false,
2023
+ "normalized": false,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": true
2027
+ },
2028
+ "128253": {
2029
+ "content": "<|reserved_special_token_245|>",
2030
+ "lstrip": false,
2031
+ "normalized": false,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": true
2035
+ },
2036
+ "128254": {
2037
+ "content": "<|reserved_special_token_246|>",
2038
+ "lstrip": false,
2039
+ "normalized": false,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": true
2043
+ },
2044
+ "128255": {
2045
+ "content": "<|reserved_special_token_247|>",
2046
+ "lstrip": false,
2047
+ "normalized": false,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": true
2051
+ }
2052
+ },
2053
+ "bos_token": "<|begin_of_text|>",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|eot_id|>",
2063
+ "padding_side": "right",
2064
+ "tokenizer_class": "PreTrainedTokenizerFast",
2065
+ "unk_token": null
2066
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/trainer_state.json ADDED
@@ -0,0 +1,1054 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 681,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.04422332780541736,
14
+ "grad_norm": 4.790396690368652,
15
+ "learning_rate": 1.3043478260869566e-06,
16
+ "logits/chosen": 0.04381329566240311,
17
+ "logits/rejected": 0.04483645409345627,
18
+ "logps/chosen": -728.4164428710938,
19
+ "logps/rejected": -731.026611328125,
20
+ "loss": 0.6948,
21
+ "rewards/accuracies": 0.3843750059604645,
22
+ "rewards/chosen": -0.003515386488288641,
23
+ "rewards/margins": -0.0008750634151510894,
24
+ "rewards/rejected": -0.0026403237134218216,
25
+ "step": 10
26
+ },
27
+ {
28
+ "epoch": 0.08844665561083472,
29
+ "grad_norm": 4.758171081542969,
30
+ "learning_rate": 2.7536231884057974e-06,
31
+ "logits/chosen": 0.030101006850600243,
32
+ "logits/rejected": 0.04583113640546799,
33
+ "logps/chosen": -742.5394287109375,
34
+ "logps/rejected": -748.9163818359375,
35
+ "loss": 0.6916,
36
+ "rewards/accuracies": 0.5249999761581421,
37
+ "rewards/chosen": 0.002908935071900487,
38
+ "rewards/margins": 0.006221208721399307,
39
+ "rewards/rejected": -0.0033122722525149584,
40
+ "step": 20
41
+ },
42
+ {
43
+ "epoch": 0.13266998341625208,
44
+ "grad_norm": 4.813444137573242,
45
+ "learning_rate": 4.202898550724638e-06,
46
+ "logits/chosen": 0.02294868603348732,
47
+ "logits/rejected": 0.029255345463752747,
48
+ "logps/chosen": -731.0952758789062,
49
+ "logps/rejected": -732.937744140625,
50
+ "loss": 0.692,
51
+ "rewards/accuracies": 0.5093749761581421,
52
+ "rewards/chosen": 0.0037192150484770536,
53
+ "rewards/margins": 0.0055237761698663235,
54
+ "rewards/rejected": -0.0018045619362965226,
55
+ "step": 30
56
+ },
57
+ {
58
+ "epoch": 0.17689331122166943,
59
+ "grad_norm": 4.748613357543945,
60
+ "learning_rate": 5.652173913043479e-06,
61
+ "logits/chosen": 0.044733427464962006,
62
+ "logits/rejected": 0.05274449661374092,
63
+ "logps/chosen": -719.3658447265625,
64
+ "logps/rejected": -719.8641357421875,
65
+ "loss": 0.6927,
66
+ "rewards/accuracies": 0.515625,
67
+ "rewards/chosen": -0.0022461418993771076,
68
+ "rewards/margins": 0.004312057979404926,
69
+ "rewards/rejected": -0.006558198481798172,
70
+ "step": 40
71
+ },
72
+ {
73
+ "epoch": 0.22111663902708678,
74
+ "grad_norm": 4.6473870277404785,
75
+ "learning_rate": 7.10144927536232e-06,
76
+ "logits/chosen": 0.03331096097826958,
77
+ "logits/rejected": 0.0421629473567009,
78
+ "logps/chosen": -737.8939819335938,
79
+ "logps/rejected": -734.4947509765625,
80
+ "loss": 0.692,
81
+ "rewards/accuracies": 0.53125,
82
+ "rewards/chosen": -0.01443431805819273,
83
+ "rewards/margins": 0.006192862056195736,
84
+ "rewards/rejected": -0.020627180114388466,
85
+ "step": 50
86
+ },
87
+ {
88
+ "epoch": 0.26533996683250416,
89
+ "grad_norm": 4.642758846282959,
90
+ "learning_rate": 8.55072463768116e-06,
91
+ "logits/chosen": 0.04314127191901207,
92
+ "logits/rejected": 0.05254172161221504,
93
+ "logps/chosen": -729.43896484375,
94
+ "logps/rejected": -730.7892456054688,
95
+ "loss": 0.6976,
96
+ "rewards/accuracies": 0.4593749940395355,
97
+ "rewards/chosen": -0.045683566480875015,
98
+ "rewards/margins": -0.004720248747617006,
99
+ "rewards/rejected": -0.040963314473629,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.3095632946379215,
104
+ "grad_norm": 5.186121463775635,
105
+ "learning_rate": 1e-05,
106
+ "logits/chosen": 0.05982046201825142,
107
+ "logits/rejected": 0.03808462619781494,
108
+ "logps/chosen": -723.9749755859375,
109
+ "logps/rejected": -744.6295166015625,
110
+ "loss": 0.6856,
111
+ "rewards/accuracies": 0.5625,
112
+ "rewards/chosen": -0.08461500704288483,
113
+ "rewards/margins": 0.02133195847272873,
114
+ "rewards/rejected": -0.10594695806503296,
115
+ "step": 70
116
+ },
117
+ {
118
+ "epoch": 0.35378662244333886,
119
+ "grad_norm": 5.109858989715576,
120
+ "learning_rate": 9.836601307189542e-06,
121
+ "logits/chosen": 0.0626436322927475,
122
+ "logits/rejected": 0.05610467866063118,
123
+ "logps/chosen": -727.2723388671875,
124
+ "logps/rejected": -745.8995971679688,
125
+ "loss": 0.6754,
126
+ "rewards/accuracies": 0.6031249761581421,
127
+ "rewards/chosen": -0.18606416881084442,
128
+ "rewards/margins": 0.04679690673947334,
129
+ "rewards/rejected": -0.23286108672618866,
130
+ "step": 80
131
+ },
132
+ {
133
+ "epoch": 0.39800995024875624,
134
+ "grad_norm": 5.292272090911865,
135
+ "learning_rate": 9.673202614379087e-06,
136
+ "logits/chosen": 0.06960556656122208,
137
+ "logits/rejected": 0.039967454969882965,
138
+ "logps/chosen": -733.6961669921875,
139
+ "logps/rejected": -761.5883178710938,
140
+ "loss": 0.6854,
141
+ "rewards/accuracies": 0.6000000238418579,
142
+ "rewards/chosen": -0.387228786945343,
143
+ "rewards/margins": 0.054472416639328,
144
+ "rewards/rejected": -0.4417012333869934,
145
+ "step": 90
146
+ },
147
+ {
148
+ "epoch": 0.44223327805417356,
149
+ "grad_norm": 4.919251441955566,
150
+ "learning_rate": 9.509803921568628e-06,
151
+ "logits/chosen": 0.05361657589673996,
152
+ "logits/rejected": 0.06048021838068962,
153
+ "logps/chosen": -734.3363647460938,
154
+ "logps/rejected": -745.5941162109375,
155
+ "loss": 0.6713,
156
+ "rewards/accuracies": 0.6000000238418579,
157
+ "rewards/chosen": -0.3496004641056061,
158
+ "rewards/margins": 0.09100104868412018,
159
+ "rewards/rejected": -0.44060152769088745,
160
+ "step": 100
161
+ },
162
+ {
163
+ "epoch": 0.48645660585959094,
164
+ "grad_norm": 5.160704612731934,
165
+ "learning_rate": 9.34640522875817e-06,
166
+ "logits/chosen": 0.0832233652472496,
167
+ "logits/rejected": 0.0829404965043068,
168
+ "logps/chosen": -712.3724975585938,
169
+ "logps/rejected": -731.3763427734375,
170
+ "loss": 0.6641,
171
+ "rewards/accuracies": 0.606249988079071,
172
+ "rewards/chosen": -0.3445834219455719,
173
+ "rewards/margins": 0.1040186733007431,
174
+ "rewards/rejected": -0.4486021101474762,
175
+ "step": 110
176
+ },
177
+ {
178
+ "epoch": 0.5306799336650083,
179
+ "grad_norm": 5.216368675231934,
180
+ "learning_rate": 9.183006535947713e-06,
181
+ "logits/chosen": 0.09449528157711029,
182
+ "logits/rejected": 0.09642904251813889,
183
+ "logps/chosen": -722.156494140625,
184
+ "logps/rejected": -743.7281494140625,
185
+ "loss": 0.6834,
186
+ "rewards/accuracies": 0.5625,
187
+ "rewards/chosen": -0.36909720301628113,
188
+ "rewards/margins": 0.07888008654117584,
189
+ "rewards/rejected": -0.44797730445861816,
190
+ "step": 120
191
+ },
192
+ {
193
+ "epoch": 0.5749032614704257,
194
+ "grad_norm": 4.724834442138672,
195
+ "learning_rate": 9.019607843137256e-06,
196
+ "logits/chosen": 0.0621442086994648,
197
+ "logits/rejected": 0.07144450396299362,
198
+ "logps/chosen": -742.7794799804688,
199
+ "logps/rejected": -736.7177124023438,
200
+ "loss": 0.681,
201
+ "rewards/accuracies": 0.5531250238418579,
202
+ "rewards/chosen": -0.3034251630306244,
203
+ "rewards/margins": 0.08017623424530029,
204
+ "rewards/rejected": -0.38360142707824707,
205
+ "step": 130
206
+ },
207
+ {
208
+ "epoch": 0.619126589275843,
209
+ "grad_norm": 4.898759841918945,
210
+ "learning_rate": 8.856209150326798e-06,
211
+ "logits/chosen": 0.04492335766553879,
212
+ "logits/rejected": 0.03912752866744995,
213
+ "logps/chosen": -740.8240356445312,
214
+ "logps/rejected": -743.07421875,
215
+ "loss": 0.6846,
216
+ "rewards/accuracies": 0.5531250238418579,
217
+ "rewards/chosen": -0.23928704857826233,
218
+ "rewards/margins": 0.05961174517869949,
219
+ "rewards/rejected": -0.29889875650405884,
220
+ "step": 140
221
+ },
222
+ {
223
+ "epoch": 0.6633499170812603,
224
+ "grad_norm": 5.013856410980225,
225
+ "learning_rate": 8.69281045751634e-06,
226
+ "logits/chosen": 0.08045239746570587,
227
+ "logits/rejected": 0.05332386493682861,
228
+ "logps/chosen": -716.9520263671875,
229
+ "logps/rejected": -734.15087890625,
230
+ "loss": 0.6883,
231
+ "rewards/accuracies": 0.512499988079071,
232
+ "rewards/chosen": -0.20123827457427979,
233
+ "rewards/margins": 0.04300180822610855,
234
+ "rewards/rejected": -0.24424007534980774,
235
+ "step": 150
236
+ },
237
+ {
238
+ "epoch": 0.7075732448866777,
239
+ "grad_norm": 5.19525146484375,
240
+ "learning_rate": 8.529411764705883e-06,
241
+ "logits/chosen": 0.08354561775922775,
242
+ "logits/rejected": 0.08688858151435852,
243
+ "logps/chosen": -735.034423828125,
244
+ "logps/rejected": -728.8670654296875,
245
+ "loss": 0.6845,
246
+ "rewards/accuracies": 0.543749988079071,
247
+ "rewards/chosen": -0.2239237278699875,
248
+ "rewards/margins": 0.05551205202937126,
249
+ "rewards/rejected": -0.27943581342697144,
250
+ "step": 160
251
+ },
252
+ {
253
+ "epoch": 0.7517965726920951,
254
+ "grad_norm": 4.709688186645508,
255
+ "learning_rate": 8.366013071895426e-06,
256
+ "logits/chosen": 0.06281667202711105,
257
+ "logits/rejected": 0.0647297203540802,
258
+ "logps/chosen": -730.1607055664062,
259
+ "logps/rejected": -746.8670654296875,
260
+ "loss": 0.6592,
261
+ "rewards/accuracies": 0.606249988079071,
262
+ "rewards/chosen": -0.20454207062721252,
263
+ "rewards/margins": 0.11324167251586914,
264
+ "rewards/rejected": -0.31778374314308167,
265
+ "step": 170
266
+ },
267
+ {
268
+ "epoch": 0.7960199004975125,
269
+ "grad_norm": 5.488134860992432,
270
+ "learning_rate": 8.202614379084967e-06,
271
+ "logits/chosen": 0.0930996835231781,
272
+ "logits/rejected": 0.08414415270090103,
273
+ "logps/chosen": -725.2960205078125,
274
+ "logps/rejected": -775.2146606445312,
275
+ "loss": 0.6795,
276
+ "rewards/accuracies": 0.5249999761581421,
277
+ "rewards/chosen": -0.25839635729789734,
278
+ "rewards/margins": 0.07942540943622589,
279
+ "rewards/rejected": -0.33782175183296204,
280
+ "step": 180
281
+ },
282
+ {
283
+ "epoch": 0.8402432283029297,
284
+ "grad_norm": 4.902462005615234,
285
+ "learning_rate": 8.03921568627451e-06,
286
+ "logits/chosen": 0.09041520208120346,
287
+ "logits/rejected": 0.06629060208797455,
288
+ "logps/chosen": -731.51708984375,
289
+ "logps/rejected": -739.4097900390625,
290
+ "loss": 0.672,
291
+ "rewards/accuracies": 0.5718749761581421,
292
+ "rewards/chosen": -0.23305967450141907,
293
+ "rewards/margins": 0.10220291465520859,
294
+ "rewards/rejected": -0.33526256680488586,
295
+ "step": 190
296
+ },
297
+ {
298
+ "epoch": 0.8844665561083471,
299
+ "grad_norm": 5.58554744720459,
300
+ "learning_rate": 7.875816993464053e-06,
301
+ "logits/chosen": 0.051689356565475464,
302
+ "logits/rejected": 0.06769050657749176,
303
+ "logps/chosen": -739.4915771484375,
304
+ "logps/rejected": -725.6425170898438,
305
+ "loss": 0.7064,
306
+ "rewards/accuracies": 0.5093749761581421,
307
+ "rewards/chosen": -0.21364755928516388,
308
+ "rewards/margins": 0.02411894127726555,
309
+ "rewards/rejected": -0.23776647448539734,
310
+ "step": 200
311
+ },
312
+ {
313
+ "epoch": 0.9286898839137645,
314
+ "grad_norm": 4.862222194671631,
315
+ "learning_rate": 7.712418300653596e-06,
316
+ "logits/chosen": 0.055795442312955856,
317
+ "logits/rejected": 0.03738347440958023,
318
+ "logps/chosen": -726.047607421875,
319
+ "logps/rejected": -739.7125854492188,
320
+ "loss": 0.6762,
321
+ "rewards/accuracies": 0.5874999761581421,
322
+ "rewards/chosen": -0.10979459434747696,
323
+ "rewards/margins": 0.06270661950111389,
324
+ "rewards/rejected": -0.17250122129917145,
325
+ "step": 210
326
+ },
327
+ {
328
+ "epoch": 0.9729132117191819,
329
+ "grad_norm": 4.868091106414795,
330
+ "learning_rate": 7.549019607843138e-06,
331
+ "logits/chosen": 0.04195914790034294,
332
+ "logits/rejected": 0.032586462795734406,
333
+ "logps/chosen": -731.987060546875,
334
+ "logps/rejected": -732.9818115234375,
335
+ "loss": 0.6575,
336
+ "rewards/accuracies": 0.609375,
337
+ "rewards/chosen": -0.07238633930683136,
338
+ "rewards/margins": 0.10007746517658234,
339
+ "rewards/rejected": -0.1724638044834137,
340
+ "step": 220
341
+ },
342
+ {
343
+ "epoch": 1.0132669983416251,
344
+ "grad_norm": 4.432958126068115,
345
+ "learning_rate": 7.385620915032681e-06,
346
+ "logits/chosen": 0.06051809340715408,
347
+ "logits/rejected": 0.06229462847113609,
348
+ "logps/chosen": -744.738037109375,
349
+ "logps/rejected": -732.5635375976562,
350
+ "loss": 0.655,
351
+ "rewards/accuracies": 0.6061643958091736,
352
+ "rewards/chosen": -0.05340927094221115,
353
+ "rewards/margins": 0.1157979667186737,
354
+ "rewards/rejected": -0.16920721530914307,
355
+ "step": 230
356
+ },
357
+ {
358
+ "epoch": 1.0574903261470425,
359
+ "grad_norm": 4.822523593902588,
360
+ "learning_rate": 7.222222222222223e-06,
361
+ "logits/chosen": 0.058093439787626266,
362
+ "logits/rejected": 0.045171890407800674,
363
+ "logps/chosen": -719.8130493164062,
364
+ "logps/rejected": -723.9993286132812,
365
+ "loss": 0.5916,
366
+ "rewards/accuracies": 0.784375011920929,
367
+ "rewards/chosen": 0.05049055814743042,
368
+ "rewards/margins": 0.2431502342224121,
369
+ "rewards/rejected": -0.1926596611738205,
370
+ "step": 240
371
+ },
372
+ {
373
+ "epoch": 1.10171365395246,
374
+ "grad_norm": 4.782036781311035,
375
+ "learning_rate": 7.058823529411766e-06,
376
+ "logits/chosen": 0.04392114281654358,
377
+ "logits/rejected": 0.059817828238010406,
378
+ "logps/chosen": -731.9445190429688,
379
+ "logps/rejected": -726.6593627929688,
380
+ "loss": 0.5797,
381
+ "rewards/accuracies": 0.7749999761581421,
382
+ "rewards/chosen": 0.094142384827137,
383
+ "rewards/margins": 0.28396254777908325,
384
+ "rewards/rejected": -0.18982017040252686,
385
+ "step": 250
386
+ },
387
+ {
388
+ "epoch": 1.1459369817578773,
389
+ "grad_norm": 4.681788444519043,
390
+ "learning_rate": 6.895424836601308e-06,
391
+ "logits/chosen": 0.043982647359371185,
392
+ "logits/rejected": 0.02721981704235077,
393
+ "logps/chosen": -716.9434814453125,
394
+ "logps/rejected": -714.9886474609375,
395
+ "loss": 0.5638,
396
+ "rewards/accuracies": 0.8125,
397
+ "rewards/chosen": 0.16104814410209656,
398
+ "rewards/margins": 0.31297585368156433,
399
+ "rewards/rejected": -0.15192770957946777,
400
+ "step": 260
401
+ },
402
+ {
403
+ "epoch": 1.1901603095632947,
404
+ "grad_norm": 4.722538471221924,
405
+ "learning_rate": 6.732026143790851e-06,
406
+ "logits/chosen": 0.045235857367515564,
407
+ "logits/rejected": 0.03866427391767502,
408
+ "logps/chosen": -720.7646484375,
409
+ "logps/rejected": -754.4002075195312,
410
+ "loss": 0.5669,
411
+ "rewards/accuracies": 0.778124988079071,
412
+ "rewards/chosen": 0.15809854865074158,
413
+ "rewards/margins": 0.3200320601463318,
414
+ "rewards/rejected": -0.16193348169326782,
415
+ "step": 270
416
+ },
417
+ {
418
+ "epoch": 1.234383637368712,
419
+ "grad_norm": 4.4413676261901855,
420
+ "learning_rate": 6.568627450980393e-06,
421
+ "logits/chosen": 0.04960431158542633,
422
+ "logits/rejected": 0.061859630048274994,
423
+ "logps/chosen": -715.8693237304688,
424
+ "logps/rejected": -731.6129150390625,
425
+ "loss": 0.5595,
426
+ "rewards/accuracies": 0.8031250238418579,
427
+ "rewards/chosen": 0.09889017045497894,
428
+ "rewards/margins": 0.34460878372192383,
429
+ "rewards/rejected": -0.24571862816810608,
430
+ "step": 280
431
+ },
432
+ {
433
+ "epoch": 1.2786069651741294,
434
+ "grad_norm": 4.595752716064453,
435
+ "learning_rate": 6.405228758169935e-06,
436
+ "logits/chosen": 0.06502333283424377,
437
+ "logits/rejected": 0.08728229999542236,
438
+ "logps/chosen": -745.6444702148438,
439
+ "logps/rejected": -743.4767456054688,
440
+ "loss": 0.5627,
441
+ "rewards/accuracies": 0.78125,
442
+ "rewards/chosen": 0.01279296912252903,
443
+ "rewards/margins": 0.3560728132724762,
444
+ "rewards/rejected": -0.3432798385620117,
445
+ "step": 290
446
+ },
447
+ {
448
+ "epoch": 1.3228302929795466,
449
+ "grad_norm": 4.692018985748291,
450
+ "learning_rate": 6.241830065359478e-06,
451
+ "logits/chosen": 0.06166895106434822,
452
+ "logits/rejected": 0.06510673463344574,
453
+ "logps/chosen": -717.4259033203125,
454
+ "logps/rejected": -737.3069458007812,
455
+ "loss": 0.5591,
456
+ "rewards/accuracies": 0.7749999761581421,
457
+ "rewards/chosen": 0.07057665288448334,
458
+ "rewards/margins": 0.3498940169811249,
459
+ "rewards/rejected": -0.27931737899780273,
460
+ "step": 300
461
+ },
462
+ {
463
+ "epoch": 1.3670536207849642,
464
+ "grad_norm": 4.717708587646484,
465
+ "learning_rate": 6.07843137254902e-06,
466
+ "logits/chosen": 0.049081962555646896,
467
+ "logits/rejected": 0.0610041543841362,
468
+ "logps/chosen": -731.8494873046875,
469
+ "logps/rejected": -729.4095458984375,
470
+ "loss": 0.5301,
471
+ "rewards/accuracies": 0.8343750238418579,
472
+ "rewards/chosen": 0.05301738902926445,
473
+ "rewards/margins": 0.4233063757419586,
474
+ "rewards/rejected": -0.3702889680862427,
475
+ "step": 310
476
+ },
477
+ {
478
+ "epoch": 1.4112769485903813,
479
+ "grad_norm": 4.894641876220703,
480
+ "learning_rate": 5.9150326797385625e-06,
481
+ "logits/chosen": 0.05939660593867302,
482
+ "logits/rejected": 0.06258915364742279,
483
+ "logps/chosen": -725.5255126953125,
484
+ "logps/rejected": -738.7193603515625,
485
+ "loss": 0.565,
486
+ "rewards/accuracies": 0.778124988079071,
487
+ "rewards/chosen": -0.0629616528749466,
488
+ "rewards/margins": 0.34772786498069763,
489
+ "rewards/rejected": -0.4106895327568054,
490
+ "step": 320
491
+ },
492
+ {
493
+ "epoch": 1.4555002763957987,
494
+ "grad_norm": 5.753345489501953,
495
+ "learning_rate": 5.7516339869281045e-06,
496
+ "logits/chosen": 0.0666918009519577,
497
+ "logits/rejected": 0.05174440145492554,
498
+ "logps/chosen": -729.0175170898438,
499
+ "logps/rejected": -743.8700561523438,
500
+ "loss": 0.5362,
501
+ "rewards/accuracies": 0.815625011920929,
502
+ "rewards/chosen": 0.019142625853419304,
503
+ "rewards/margins": 0.4241827428340912,
504
+ "rewards/rejected": -0.40504011511802673,
505
+ "step": 330
506
+ },
507
+ {
508
+ "epoch": 1.499723604201216,
509
+ "grad_norm": 4.6361846923828125,
510
+ "learning_rate": 5.588235294117647e-06,
511
+ "logits/chosen": 0.041943300515413284,
512
+ "logits/rejected": 0.05258619785308838,
513
+ "logps/chosen": -741.4943237304688,
514
+ "logps/rejected": -739.9080810546875,
515
+ "loss": 0.5257,
516
+ "rewards/accuracies": 0.824999988079071,
517
+ "rewards/chosen": -0.000494301610160619,
518
+ "rewards/margins": 0.44224825501441956,
519
+ "rewards/rejected": -0.4427425265312195,
520
+ "step": 340
521
+ },
522
+ {
523
+ "epoch": 1.5439469320066335,
524
+ "grad_norm": 4.803311347961426,
525
+ "learning_rate": 5.4248366013071894e-06,
526
+ "logits/chosen": 0.05372584983706474,
527
+ "logits/rejected": 0.02776780165731907,
528
+ "logps/chosen": -737.3201904296875,
529
+ "logps/rejected": -766.5046997070312,
530
+ "loss": 0.5404,
531
+ "rewards/accuracies": 0.809374988079071,
532
+ "rewards/chosen": -0.024867769330739975,
533
+ "rewards/margins": 0.4128110408782959,
534
+ "rewards/rejected": -0.43767881393432617,
535
+ "step": 350
536
+ },
537
+ {
538
+ "epoch": 1.5881702598120508,
539
+ "grad_norm": 5.092834949493408,
540
+ "learning_rate": 5.261437908496732e-06,
541
+ "logits/chosen": 0.03891930729150772,
542
+ "logits/rejected": 0.03924475237727165,
543
+ "logps/chosen": -734.5875244140625,
544
+ "logps/rejected": -749.2198486328125,
545
+ "loss": 0.5214,
546
+ "rewards/accuracies": 0.8125,
547
+ "rewards/chosen": 0.015210029669106007,
548
+ "rewards/margins": 0.4552536606788635,
549
+ "rewards/rejected": -0.4400436282157898,
550
+ "step": 360
551
+ },
552
+ {
553
+ "epoch": 1.6323935876174682,
554
+ "grad_norm": 4.926650524139404,
555
+ "learning_rate": 5.098039215686274e-06,
556
+ "logits/chosen": 0.02469441294670105,
557
+ "logits/rejected": 0.02297321707010269,
558
+ "logps/chosen": -716.6813354492188,
559
+ "logps/rejected": -748.6106567382812,
560
+ "loss": 0.5339,
561
+ "rewards/accuracies": 0.793749988079071,
562
+ "rewards/chosen": -0.022239599376916885,
563
+ "rewards/margins": 0.43930119276046753,
564
+ "rewards/rejected": -0.4615407884120941,
565
+ "step": 370
566
+ },
567
+ {
568
+ "epoch": 1.6766169154228856,
569
+ "grad_norm": 4.795474529266357,
570
+ "learning_rate": 4.934640522875817e-06,
571
+ "logits/chosen": 0.035248156636953354,
572
+ "logits/rejected": 0.03529531508684158,
573
+ "logps/chosen": -740.4767456054688,
574
+ "logps/rejected": -748.4019775390625,
575
+ "loss": 0.5256,
576
+ "rewards/accuracies": 0.78125,
577
+ "rewards/chosen": -0.060587454587221146,
578
+ "rewards/margins": 0.4593600630760193,
579
+ "rewards/rejected": -0.5199474692344666,
580
+ "step": 380
581
+ },
582
+ {
583
+ "epoch": 1.720840243228303,
584
+ "grad_norm": 5.012288570404053,
585
+ "learning_rate": 4.77124183006536e-06,
586
+ "logits/chosen": 0.02772427722811699,
587
+ "logits/rejected": 0.03079628385603428,
588
+ "logps/chosen": -726.2144775390625,
589
+ "logps/rejected": -732.8980712890625,
590
+ "loss": 0.5242,
591
+ "rewards/accuracies": 0.78125,
592
+ "rewards/chosen": -0.035477008670568466,
593
+ "rewards/margins": 0.4730597138404846,
594
+ "rewards/rejected": -0.508536696434021,
595
+ "step": 390
596
+ },
597
+ {
598
+ "epoch": 1.7650635710337204,
599
+ "grad_norm": 4.907037734985352,
600
+ "learning_rate": 4.607843137254902e-06,
601
+ "logits/chosen": 0.012238780967891216,
602
+ "logits/rejected": 0.028159579262137413,
603
+ "logps/chosen": -738.3775634765625,
604
+ "logps/rejected": -763.4334106445312,
605
+ "loss": 0.5253,
606
+ "rewards/accuracies": 0.800000011920929,
607
+ "rewards/chosen": -0.08436703681945801,
608
+ "rewards/margins": 0.46338599920272827,
609
+ "rewards/rejected": -0.547753095626831,
610
+ "step": 400
611
+ },
612
+ {
613
+ "epoch": 1.8092868988391375,
614
+ "grad_norm": 5.278862953186035,
615
+ "learning_rate": 4.444444444444444e-06,
616
+ "logits/chosen": 0.06223682686686516,
617
+ "logits/rejected": 0.038531407713890076,
618
+ "logps/chosen": -718.9315185546875,
619
+ "logps/rejected": -733.304443359375,
620
+ "loss": 0.5326,
621
+ "rewards/accuracies": 0.7875000238418579,
622
+ "rewards/chosen": -0.016453227028250694,
623
+ "rewards/margins": 0.4501055181026459,
624
+ "rewards/rejected": -0.46655869483947754,
625
+ "step": 410
626
+ },
627
+ {
628
+ "epoch": 1.8535102266445551,
629
+ "grad_norm": 5.821231365203857,
630
+ "learning_rate": 4.281045751633987e-06,
631
+ "logits/chosen": 0.026631712913513184,
632
+ "logits/rejected": 0.003854078007861972,
633
+ "logps/chosen": -736.3001708984375,
634
+ "logps/rejected": -749.7689208984375,
635
+ "loss": 0.5177,
636
+ "rewards/accuracies": 0.7875000238418579,
637
+ "rewards/chosen": -0.0025982498191297054,
638
+ "rewards/margins": 0.4969322681427002,
639
+ "rewards/rejected": -0.49953049421310425,
640
+ "step": 420
641
+ },
642
+ {
643
+ "epoch": 1.8977335544499723,
644
+ "grad_norm": 6.272520542144775,
645
+ "learning_rate": 4.11764705882353e-06,
646
+ "logits/chosen": 0.029291704297065735,
647
+ "logits/rejected": 0.03380614146590233,
648
+ "logps/chosen": -719.34521484375,
649
+ "logps/rejected": -729.5531005859375,
650
+ "loss": 0.5273,
651
+ "rewards/accuracies": 0.784375011920929,
652
+ "rewards/chosen": -0.10191933810710907,
653
+ "rewards/margins": 0.47232216596603394,
654
+ "rewards/rejected": -0.5742415189743042,
655
+ "step": 430
656
+ },
657
+ {
658
+ "epoch": 1.9419568822553899,
659
+ "grad_norm": 5.418857097625732,
660
+ "learning_rate": 3.954248366013072e-06,
661
+ "logits/chosen": 0.03151711821556091,
662
+ "logits/rejected": 0.024101505056023598,
663
+ "logps/chosen": -717.4995727539062,
664
+ "logps/rejected": -744.1138916015625,
665
+ "loss": 0.5265,
666
+ "rewards/accuracies": 0.800000011920929,
667
+ "rewards/chosen": -0.020029040053486824,
668
+ "rewards/margins": 0.4863404631614685,
669
+ "rewards/rejected": -0.5063695311546326,
670
+ "step": 440
671
+ },
672
+ {
673
+ "epoch": 1.986180210060807,
674
+ "grad_norm": 5.959162712097168,
675
+ "learning_rate": 3.7908496732026144e-06,
676
+ "logits/chosen": 0.014398257248103619,
677
+ "logits/rejected": 0.0016744869062677026,
678
+ "logps/chosen": -729.6848754882812,
679
+ "logps/rejected": -741.1746826171875,
680
+ "loss": 0.5458,
681
+ "rewards/accuracies": 0.7718750238418579,
682
+ "rewards/chosen": -0.0837007686495781,
683
+ "rewards/margins": 0.4181123673915863,
684
+ "rewards/rejected": -0.5018131136894226,
685
+ "step": 450
686
+ },
687
+ {
688
+ "epoch": 2.0265339966832503,
689
+ "grad_norm": 4.350944519042969,
690
+ "learning_rate": 3.6274509803921573e-06,
691
+ "logits/chosen": -0.012623141519725323,
692
+ "logits/rejected": 0.005572776310145855,
693
+ "logps/chosen": -720.2206420898438,
694
+ "logps/rejected": -728.574462890625,
695
+ "loss": 0.4513,
696
+ "rewards/accuracies": 0.8698630332946777,
697
+ "rewards/chosen": 0.10156527161598206,
698
+ "rewards/margins": 0.6784384250640869,
699
+ "rewards/rejected": -0.5768731236457825,
700
+ "step": 460
701
+ },
702
+ {
703
+ "epoch": 2.070757324488668,
704
+ "grad_norm": 4.335951805114746,
705
+ "learning_rate": 3.4640522875816997e-06,
706
+ "logits/chosen": 0.0014554306399077177,
707
+ "logits/rejected": 0.004570366349071264,
708
+ "logps/chosen": -729.8797607421875,
709
+ "logps/rejected": -730.48876953125,
710
+ "loss": 0.4085,
711
+ "rewards/accuracies": 0.934374988079071,
712
+ "rewards/chosen": 0.1204359158873558,
713
+ "rewards/margins": 0.7754749059677124,
714
+ "rewards/rejected": -0.6550389528274536,
715
+ "step": 470
716
+ },
717
+ {
718
+ "epoch": 2.114980652294085,
719
+ "grad_norm": 4.060268878936768,
720
+ "learning_rate": 3.300653594771242e-06,
721
+ "logits/chosen": 0.007412907667458057,
722
+ "logits/rejected": 0.0010502435034140944,
723
+ "logps/chosen": -720.0541381835938,
724
+ "logps/rejected": -757.34033203125,
725
+ "loss": 0.4128,
726
+ "rewards/accuracies": 0.925000011920929,
727
+ "rewards/chosen": 0.09448285400867462,
728
+ "rewards/margins": 0.7659561038017273,
729
+ "rewards/rejected": -0.6714732050895691,
730
+ "step": 480
731
+ },
732
+ {
733
+ "epoch": 2.1592039800995027,
734
+ "grad_norm": 4.638291358947754,
735
+ "learning_rate": 3.1372549019607846e-06,
736
+ "logits/chosen": -0.006247128359973431,
737
+ "logits/rejected": -0.0032988134771585464,
738
+ "logps/chosen": -733.0958251953125,
739
+ "logps/rejected": -737.65234375,
740
+ "loss": 0.4004,
741
+ "rewards/accuracies": 0.9375,
742
+ "rewards/chosen": 0.11138612031936646,
743
+ "rewards/margins": 0.7981661558151245,
744
+ "rewards/rejected": -0.6867799758911133,
745
+ "step": 490
746
+ },
747
+ {
748
+ "epoch": 2.20342730790492,
749
+ "grad_norm": 4.45103645324707,
750
+ "learning_rate": 2.973856209150327e-06,
751
+ "logits/chosen": -0.025618869811296463,
752
+ "logits/rejected": -0.003555983304977417,
753
+ "logps/chosen": -738.6025390625,
754
+ "logps/rejected": -738.1941528320312,
755
+ "loss": 0.4162,
756
+ "rewards/accuracies": 0.934374988079071,
757
+ "rewards/chosen": 0.03812215477228165,
758
+ "rewards/margins": 0.7537471055984497,
759
+ "rewards/rejected": -0.7156248688697815,
760
+ "step": 500
761
+ },
762
+ {
763
+ "epoch": 2.2476506357103374,
764
+ "grad_norm": 5.358262538909912,
765
+ "learning_rate": 2.8104575163398695e-06,
766
+ "logits/chosen": -0.01752624474465847,
767
+ "logits/rejected": -0.02874870039522648,
768
+ "logps/chosen": -719.39404296875,
769
+ "logps/rejected": -750.3357543945312,
770
+ "loss": 0.3967,
771
+ "rewards/accuracies": 0.9312499761581421,
772
+ "rewards/chosen": 0.11151006072759628,
773
+ "rewards/margins": 0.8284163475036621,
774
+ "rewards/rejected": -0.7169061899185181,
775
+ "step": 510
776
+ },
777
+ {
778
+ "epoch": 2.2918739635157546,
779
+ "grad_norm": 4.445791721343994,
780
+ "learning_rate": 2.647058823529412e-06,
781
+ "logits/chosen": -0.024961207062005997,
782
+ "logits/rejected": -0.024318331852555275,
783
+ "logps/chosen": -718.005859375,
784
+ "logps/rejected": -739.5359497070312,
785
+ "loss": 0.3875,
786
+ "rewards/accuracies": 0.9375,
787
+ "rewards/chosen": 0.15413782000541687,
788
+ "rewards/margins": 0.8626806139945984,
789
+ "rewards/rejected": -0.7085427045822144,
790
+ "step": 520
791
+ },
792
+ {
793
+ "epoch": 2.336097291321172,
794
+ "grad_norm": 4.365763187408447,
795
+ "learning_rate": 2.4836601307189544e-06,
796
+ "logits/chosen": -0.034866154193878174,
797
+ "logits/rejected": -0.03424055501818657,
798
+ "logps/chosen": -719.3134765625,
799
+ "logps/rejected": -745.9971923828125,
800
+ "loss": 0.4116,
801
+ "rewards/accuracies": 0.90625,
802
+ "rewards/chosen": 0.05673253536224365,
803
+ "rewards/margins": 0.7981484532356262,
804
+ "rewards/rejected": -0.7414158582687378,
805
+ "step": 530
806
+ },
807
+ {
808
+ "epoch": 2.3803206191265893,
809
+ "grad_norm": 4.658866882324219,
810
+ "learning_rate": 2.320261437908497e-06,
811
+ "logits/chosen": -0.0428851917386055,
812
+ "logits/rejected": -0.030463075265288353,
813
+ "logps/chosen": -724.3384399414062,
814
+ "logps/rejected": -739.2413940429688,
815
+ "loss": 0.4009,
816
+ "rewards/accuracies": 0.918749988079071,
817
+ "rewards/chosen": 0.13520367443561554,
818
+ "rewards/margins": 0.8265008926391602,
819
+ "rewards/rejected": -0.691297173500061,
820
+ "step": 540
821
+ },
822
+ {
823
+ "epoch": 2.4245439469320065,
824
+ "grad_norm": 5.0705413818359375,
825
+ "learning_rate": 2.1568627450980393e-06,
826
+ "logits/chosen": -0.048854976892471313,
827
+ "logits/rejected": -0.02665240690112114,
828
+ "logps/chosen": -734.3904418945312,
829
+ "logps/rejected": -752.8912963867188,
830
+ "loss": 0.3929,
831
+ "rewards/accuracies": 0.9375,
832
+ "rewards/chosen": 0.10146461427211761,
833
+ "rewards/margins": 0.8288280367851257,
834
+ "rewards/rejected": -0.7273633480072021,
835
+ "step": 550
836
+ },
837
+ {
838
+ "epoch": 2.468767274737424,
839
+ "grad_norm": 4.395069599151611,
840
+ "learning_rate": 1.993464052287582e-06,
841
+ "logits/chosen": -0.04929124191403389,
842
+ "logits/rejected": -0.032390229403972626,
843
+ "logps/chosen": -723.6656494140625,
844
+ "logps/rejected": -749.4322509765625,
845
+ "loss": 0.3903,
846
+ "rewards/accuracies": 0.925000011920929,
847
+ "rewards/chosen": 0.08241494745016098,
848
+ "rewards/margins": 0.858893871307373,
849
+ "rewards/rejected": -0.7764789462089539,
850
+ "step": 560
851
+ },
852
+ {
853
+ "epoch": 2.5129906025428412,
854
+ "grad_norm": 5.670328617095947,
855
+ "learning_rate": 1.8300653594771242e-06,
856
+ "logits/chosen": -0.030128519982099533,
857
+ "logits/rejected": -0.03409530594944954,
858
+ "logps/chosen": -733.5093383789062,
859
+ "logps/rejected": -746.30322265625,
860
+ "loss": 0.3994,
861
+ "rewards/accuracies": 0.9156249761581421,
862
+ "rewards/chosen": 0.03978142887353897,
863
+ "rewards/margins": 0.8246067762374878,
864
+ "rewards/rejected": -0.784825325012207,
865
+ "step": 570
866
+ },
867
+ {
868
+ "epoch": 2.557213930348259,
869
+ "grad_norm": 4.946484565734863,
870
+ "learning_rate": 1.6666666666666667e-06,
871
+ "logits/chosen": -0.04696577042341232,
872
+ "logits/rejected": -0.03670218959450722,
873
+ "logps/chosen": -736.0384521484375,
874
+ "logps/rejected": -737.9381103515625,
875
+ "loss": 0.4027,
876
+ "rewards/accuracies": 0.9312499761581421,
877
+ "rewards/chosen": -0.06862092018127441,
878
+ "rewards/margins": 0.8046183586120605,
879
+ "rewards/rejected": -0.8732392191886902,
880
+ "step": 580
881
+ },
882
+ {
883
+ "epoch": 2.601437258153676,
884
+ "grad_norm": 5.617839336395264,
885
+ "learning_rate": 1.5032679738562091e-06,
886
+ "logits/chosen": -0.028207072988152504,
887
+ "logits/rejected": -0.030728602781891823,
888
+ "logps/chosen": -708.9717407226562,
889
+ "logps/rejected": -739.5012817382812,
890
+ "loss": 0.4165,
891
+ "rewards/accuracies": 0.90625,
892
+ "rewards/chosen": -0.06656770408153534,
893
+ "rewards/margins": 0.7756827473640442,
894
+ "rewards/rejected": -0.8422503471374512,
895
+ "step": 590
896
+ },
897
+ {
898
+ "epoch": 2.645660585959093,
899
+ "grad_norm": 4.4014434814453125,
900
+ "learning_rate": 1.3398692810457518e-06,
901
+ "logits/chosen": -0.04994772747159004,
902
+ "logits/rejected": -0.04960205405950546,
903
+ "logps/chosen": -730.4518432617188,
904
+ "logps/rejected": -776.23681640625,
905
+ "loss": 0.3912,
906
+ "rewards/accuracies": 0.934374988079071,
907
+ "rewards/chosen": -0.030826589092612267,
908
+ "rewards/margins": 0.8611711263656616,
909
+ "rewards/rejected": -0.8919976949691772,
910
+ "step": 600
911
+ },
912
+ {
913
+ "epoch": 2.6898839137645107,
914
+ "grad_norm": 5.267344951629639,
915
+ "learning_rate": 1.1764705882352942e-06,
916
+ "logits/chosen": -0.06058899685740471,
917
+ "logits/rejected": -0.061273373663425446,
918
+ "logps/chosen": -750.5161743164062,
919
+ "logps/rejected": -740.4485473632812,
920
+ "loss": 0.3912,
921
+ "rewards/accuracies": 0.925000011920929,
922
+ "rewards/chosen": -0.021410521119832993,
923
+ "rewards/margins": 0.8524140119552612,
924
+ "rewards/rejected": -0.8738245964050293,
925
+ "step": 610
926
+ },
927
+ {
928
+ "epoch": 2.7341072415699283,
929
+ "grad_norm": 4.529972076416016,
930
+ "learning_rate": 1.0130718954248367e-06,
931
+ "logits/chosen": -0.03833835572004318,
932
+ "logits/rejected": -0.06139983981847763,
933
+ "logps/chosen": -716.7005615234375,
934
+ "logps/rejected": -752.87646484375,
935
+ "loss": 0.3971,
936
+ "rewards/accuracies": 0.90625,
937
+ "rewards/chosen": -0.04045793414115906,
938
+ "rewards/margins": 0.863679051399231,
939
+ "rewards/rejected": -0.9041368365287781,
940
+ "step": 620
941
+ },
942
+ {
943
+ "epoch": 2.7783305693753455,
944
+ "grad_norm": 4.896629333496094,
945
+ "learning_rate": 8.496732026143792e-07,
946
+ "logits/chosen": -0.07116003334522247,
947
+ "logits/rejected": -0.06485187262296677,
948
+ "logps/chosen": -747.3123779296875,
949
+ "logps/rejected": -753.5182495117188,
950
+ "loss": 0.4332,
951
+ "rewards/accuracies": 0.8843749761581421,
952
+ "rewards/chosen": -0.10428781807422638,
953
+ "rewards/margins": 0.757138729095459,
954
+ "rewards/rejected": -0.8614265322685242,
955
+ "step": 630
956
+ },
957
+ {
958
+ "epoch": 2.8225538971807627,
959
+ "grad_norm": 5.05888557434082,
960
+ "learning_rate": 6.862745098039217e-07,
961
+ "logits/chosen": -0.05649835988879204,
962
+ "logits/rejected": -0.06368318200111389,
963
+ "logps/chosen": -722.1294555664062,
964
+ "logps/rejected": -749.5657958984375,
965
+ "loss": 0.3959,
966
+ "rewards/accuracies": 0.8999999761581421,
967
+ "rewards/chosen": -0.054598577320575714,
968
+ "rewards/margins": 0.8572176694869995,
969
+ "rewards/rejected": -0.9118162393569946,
970
+ "step": 640
971
+ },
972
+ {
973
+ "epoch": 2.8667772249861803,
974
+ "grad_norm": 4.937535285949707,
975
+ "learning_rate": 5.228758169934641e-07,
976
+ "logits/chosen": -0.0641440600156784,
977
+ "logits/rejected": -0.0582139678299427,
978
+ "logps/chosen": -726.2035522460938,
979
+ "logps/rejected": -738.3570556640625,
980
+ "loss": 0.4025,
981
+ "rewards/accuracies": 0.9125000238418579,
982
+ "rewards/chosen": -0.13398374617099762,
983
+ "rewards/margins": 0.8152621984481812,
984
+ "rewards/rejected": -0.9492460489273071,
985
+ "step": 650
986
+ },
987
+ {
988
+ "epoch": 2.9110005527915974,
989
+ "grad_norm": 5.47641134262085,
990
+ "learning_rate": 3.5947712418300653e-07,
991
+ "logits/chosen": -0.04556625708937645,
992
+ "logits/rejected": -0.05585021898150444,
993
+ "logps/chosen": -722.315185546875,
994
+ "logps/rejected": -730.5087280273438,
995
+ "loss": 0.396,
996
+ "rewards/accuracies": 0.918749988079071,
997
+ "rewards/chosen": -0.017090801149606705,
998
+ "rewards/margins": 0.8597989082336426,
999
+ "rewards/rejected": -0.876889705657959,
1000
+ "step": 660
1001
+ },
1002
+ {
1003
+ "epoch": 2.955223880597015,
1004
+ "grad_norm": 5.2933759689331055,
1005
+ "learning_rate": 1.9607843137254904e-07,
1006
+ "logits/chosen": -0.09119975566864014,
1007
+ "logits/rejected": -0.10483505576848984,
1008
+ "logps/chosen": -735.6546630859375,
1009
+ "logps/rejected": -744.5277709960938,
1010
+ "loss": 0.3861,
1011
+ "rewards/accuracies": 0.9281250238418579,
1012
+ "rewards/chosen": -0.043585747480392456,
1013
+ "rewards/margins": 0.8988669514656067,
1014
+ "rewards/rejected": -0.942452609539032,
1015
+ "step": 670
1016
+ },
1017
+ {
1018
+ "epoch": 2.999447208402432,
1019
+ "grad_norm": 4.8971757888793945,
1020
+ "learning_rate": 3.267973856209151e-08,
1021
+ "logits/chosen": -0.060855887830257416,
1022
+ "logits/rejected": -0.08228183537721634,
1023
+ "logps/chosen": -735.1665649414062,
1024
+ "logps/rejected": -755.8302001953125,
1025
+ "loss": 0.3898,
1026
+ "rewards/accuracies": 0.90625,
1027
+ "rewards/chosen": -0.05536114051938057,
1028
+ "rewards/margins": 0.8813594579696655,
1029
+ "rewards/rejected": -0.9367205500602722,
1030
+ "step": 680
1031
+ }
1032
+ ],
1033
+ "logging_steps": 10,
1034
+ "max_steps": 681,
1035
+ "num_input_tokens_seen": 0,
1036
+ "num_train_epochs": 3,
1037
+ "save_steps": 10000,
1038
+ "stateful_callbacks": {
1039
+ "TrainerControl": {
1040
+ "args": {
1041
+ "should_epoch_stop": false,
1042
+ "should_evaluate": false,
1043
+ "should_log": false,
1044
+ "should_save": true,
1045
+ "should_training_stop": true
1046
+ },
1047
+ "attributes": {}
1048
+ }
1049
+ },
1050
+ "total_flos": 0.0,
1051
+ "train_batch_size": 1,
1052
+ "trial_name": null,
1053
+ "trial_params": null
1054
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/checkpoint-681/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4139dcbd132a5e85936ba530465c836e6c8c260e39f6779a59d245461d9abe5c
3
+ size 7057
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/chat_template.jinja ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- if strftime_now is defined %}
10
+ {%- set date_string = strftime_now("%d %b %Y") %}
11
+ {%- else %}
12
+ {%- set date_string = "26 Jul 2024" %}
13
+ {%- endif %}
14
+ {%- endif %}
15
+ {%- if not tools is defined %}
16
+ {%- set tools = none %}
17
+ {%- endif %}
18
+
19
+ {#- This block extracts the system message, so we can slot it into the right place. #}
20
+ {%- if messages[0]['role'] == 'system' %}
21
+ {%- set system_message = messages[0]['content']|trim %}
22
+ {%- set messages = messages[1:] %}
23
+ {%- else %}
24
+ {%- set system_message = "" %}
25
+ {%- endif %}
26
+
27
+ {#- System message #}
28
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
29
+ {%- if tools is not none %}
30
+ {{- "Environment: ipython\n" }}
31
+ {%- endif %}
32
+ {{- "Cutting Knowledge Date: December 2023\n" }}
33
+ {{- "Today Date: " + date_string + "\n\n" }}
34
+ {%- if tools is not none and not tools_in_user_message %}
35
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
36
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
37
+ {{- "Do not use variables.\n\n" }}
38
+ {%- for t in tools %}
39
+ {{- t | tojson(indent=4) }}
40
+ {{- "\n\n" }}
41
+ {%- endfor %}
42
+ {%- endif %}
43
+ {{- system_message }}
44
+ {{- "<|eot_id|>" }}
45
+
46
+ {#- Custom tools are passed in a user message with some extra guidance #}
47
+ {%- if tools_in_user_message and not tools is none %}
48
+ {#- Extract the first user message so we can plug it in here #}
49
+ {%- if messages | length != 0 %}
50
+ {%- set first_user_message = messages[0]['content']|trim %}
51
+ {%- set messages = messages[1:] %}
52
+ {%- else %}
53
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
54
+ {%- endif %}
55
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
56
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
57
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
58
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
59
+ {{- "Do not use variables.\n\n" }}
60
+ {%- for t in tools %}
61
+ {{- t | tojson(indent=4) }}
62
+ {{- "\n\n" }}
63
+ {%- endfor %}
64
+ {{- first_user_message + "<|eot_id|>"}}
65
+ {%- endif %}
66
+
67
+ {%- for message in messages %}
68
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
69
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
70
+ {%- elif 'tool_calls' in message %}
71
+ {%- if not message.tool_calls|length == 1 %}
72
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
73
+ {%- endif %}
74
+ {%- set tool_call = message.tool_calls[0].function %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- '{"name": "' + tool_call.name + '", ' }}
77
+ {{- '"parameters": ' }}
78
+ {{- tool_call.arguments | tojson }}
79
+ {{- "}" }}
80
+ {{- "<|eot_id|>" }}
81
+ {%- elif message.role == "tool" or message.role == "ipython" %}
82
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
83
+ {%- if message.content is mapping or message.content is iterable %}
84
+ {{- message.content | tojson }}
85
+ {%- else %}
86
+ {{- message.content }}
87
+ {%- endif %}
88
+ {{- "<|eot_id|>" }}
89
+ {%- endif %}
90
+ {%- endfor %}
91
+ {%- if add_generation_prompt %}
92
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
93
+ {%- endif %}
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 3072,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 8192,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 24,
22
+ "num_hidden_layers": 28,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": {
27
+ "factor": 32.0,
28
+ "high_freq_factor": 4.0,
29
+ "low_freq_factor": 1.0,
30
+ "original_max_position_embeddings": 8192,
31
+ "rope_type": "llama3"
32
+ },
33
+ "rope_theta": 500000.0,
34
+ "tie_word_embeddings": true,
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.55.0",
37
+ "use_cache": true,
38
+ "vocab_size": 128256
39
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.55.0"
12
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ae5e391ed87e177fcb0a702a6615b5c92f5573c64d34070e0faa98119ee73c
3
+ size 4998767360
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e12e3a57291a9cd5873a493089c2c793c11efb60ea175c2de90d8a6632ee5f00
3
+ size 4932808968
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca723bb2b75cfa5647b74360ffe187ef5998466adb9dc8099b543d78e70b2fed
3
+ size 2919452168
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 3212749824,
4
+ "total_size": 12850999296
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
198
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
199
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
200
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
201
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
202
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
203
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
204
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
205
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
206
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
207
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
208
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
209
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
210
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
211
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
212
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
213
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
214
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
215
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
225
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
226
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
227
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
228
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
229
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
230
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
231
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
232
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
233
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
234
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
235
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
236
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
237
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
238
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
239
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
240
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
241
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
242
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
244
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
247
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
258
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
259
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
260
+ "model.norm.weight": "model-00003-of-00003.safetensors"
261
+ }
262
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
Preference_Set_Llama-3.2-3B-Instruct_INFV_ref_as_gt_True_IterRet_individual_recall_True_top_k_30/meta-llama/Llama-3.2-3B-Instruct/method_agent/merged_model/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920