codecodebear commited on
Commit
b0afa2a
·
verified ·
1 Parent(s): 8d5d39f

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +60 -0
  2. csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/README.md +61 -0
  3. csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/adapter_config.json +39 -0
  4. csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/all_results.json +8 -0
  5. csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/chat_template.jinja +5 -0
  6. csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/README.md +202 -0
  7. csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/adapter_config.json +39 -0
  8. csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/chat_template.jinja +5 -0
  9. csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/special_tokens_map.json +26 -0
  10. csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/tokenizer_config.json +2076 -0
  11. csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/trainer_state.json +685 -0
  12. csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/special_tokens_map.json +26 -0
  13. csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/tokenizer_config.json +2076 -0
  14. csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/train_results.json +8 -0
  15. csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/trainer_log.jsonl +94 -0
  16. csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/trainer_state.json +694 -0
  17. csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/training_loss.png +0 -0
  18. csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/README.md +61 -0
  19. csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/adapter_config.json +39 -0
  20. csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/all_results.json +8 -0
  21. csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/chat_template.jinja +5 -0
  22. csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/adapter_config.json +39 -0
  23. csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/chat_template.jinja +5 -0
  24. csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/special_tokens_map.json +26 -0
  25. csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/tokenizer_config.json +2076 -0
  26. csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/trainer_state.json +685 -0
  27. csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/special_tokens_map.json +26 -0
  28. csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/tokenizer_config.json +2076 -0
  29. csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/train_results.json +8 -0
  30. csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/trainer_log.jsonl +94 -0
  31. csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/trainer_state.json +694 -0
  32. csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/training_loss.png +0 -0
  33. csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/README.md +61 -0
  34. csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/added_tokens.json +28 -0
  35. csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/train_results.json +8 -0
  36. csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/vocab.json +0 -0
  37. gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/all_results.json +8 -0
  38. gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/README.md +202 -0
  39. gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/chat_template.jinja +5 -0
  40. gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/special_tokens_map.json +26 -0
  41. gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/tokenizer_config.json +2076 -0
  42. gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/trainer_state.json +685 -0
  43. gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/train_results.json +8 -0
  44. gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/trainer_log.jsonl +94 -0
  45. gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/trainer_state.json +694 -0
  46. gsm8k__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/README.md +61 -0
  47. gsm8k__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/adapter_config.json +39 -0
  48. gsm8k__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/all_results.json +8 -0
  49. gsm8k__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/chat_template.jinja +5 -0
  50. gsm8k__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/README.md +202 -0
.gitattributes CHANGED
@@ -8,6 +8,8 @@
8
  *.h5 filter=lfs diff=lfs merge=lfs -text
9
  *.joblib filter=lfs diff=lfs merge=lfs -text
10
  *.lfs.* filter=lfs diff=lfs merge=lfs -text
 
 
11
  *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
  *.model filter=lfs diff=lfs merge=lfs -text
13
  *.msgpack filter=lfs diff=lfs merge=lfs -text
@@ -33,3 +35,61 @@ 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
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  *.h5 filter=lfs diff=lfs merge=lfs -text
9
  *.joblib filter=lfs diff=lfs merge=lfs -text
10
  *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.lz4 filter=lfs diff=lfs merge=lfs -text
12
+ *.mds filter=lfs diff=lfs merge=lfs -text
13
  *.mlmodel filter=lfs diff=lfs merge=lfs -text
14
  *.model filter=lfs diff=lfs merge=lfs -text
15
  *.msgpack filter=lfs diff=lfs merge=lfs -text
 
35
  *.zip filter=lfs diff=lfs merge=lfs -text
36
  *.zst filter=lfs diff=lfs merge=lfs -text
37
  *tfevents* filter=lfs diff=lfs merge=lfs -text
38
+ # Audio files - uncompressed
39
+ *.pcm filter=lfs diff=lfs merge=lfs -text
40
+ *.sam filter=lfs diff=lfs merge=lfs -text
41
+ *.raw filter=lfs diff=lfs merge=lfs -text
42
+ # Audio files - compressed
43
+ *.aac filter=lfs diff=lfs merge=lfs -text
44
+ *.flac filter=lfs diff=lfs merge=lfs -text
45
+ *.mp3 filter=lfs diff=lfs merge=lfs -text
46
+ *.ogg filter=lfs diff=lfs merge=lfs -text
47
+ *.wav filter=lfs diff=lfs merge=lfs -text
48
+ # Image files - uncompressed
49
+ *.bmp filter=lfs diff=lfs merge=lfs -text
50
+ *.gif filter=lfs diff=lfs merge=lfs -text
51
+ *.png filter=lfs diff=lfs merge=lfs -text
52
+ *.tiff filter=lfs diff=lfs merge=lfs -text
53
+ # Image files - compressed
54
+ *.jpg filter=lfs diff=lfs merge=lfs -text
55
+ *.jpeg filter=lfs diff=lfs merge=lfs -text
56
+ *.webp filter=lfs diff=lfs merge=lfs -text
57
+ # Video files - compressed
58
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
59
+ *.webm filter=lfs diff=lfs merge=lfs -text
60
+ gsm8k__qwen3_8b__n2000_t1t2_s0_all_variants_r16_bs4_lr5e6_e3/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
61
+ gsm8k__llama3_8b_instruct__n2000_t1t2_s0_all_variants_r8_bs4_lr5e6_e3/lora/sft/checkpoint-1251/tokenizer.json filter=lfs diff=lfs merge=lfs -text
62
+ gsm8k__llama3_8b_instruct__n2000_t1t2_s0_all_variants_r16_bs4_lr5e6_e3/lora/sft/checkpoint-1251/tokenizer.json filter=lfs diff=lfs merge=lfs -text
63
+ gsm8k__llama3_8b_instruct__n2000_t1t2_s0_all_variants_r16_bs4_lr5e6_e3/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
64
+ gsm8k__qwen3_8b__n2000_t1t2_s0_all_variants_r16_bs4_lr5e6_e3/lora/sft/checkpoint-1251/tokenizer.json filter=lfs diff=lfs merge=lfs -text
65
+ gsm8k__llama3_8b_instruct__n2000_t1t2_s0_all_variants_r8_bs4_lr5e6_e3/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
66
+ csqa__llama3_8b_instruct__n2000_t1t2_s0_all_variants_r8_bs4_lr5e6_e3/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
67
+ csqa__qwen3_8b__n2000_t1t2_s0_all_variants_r8_bs4_lr5e6_e3/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
68
+ csqa__llama3_8b_instruct__n2000_t1t2_s0_all_variants_r8_bs4_lr5e6_e3/lora/sft/checkpoint-1251/tokenizer.json filter=lfs diff=lfs merge=lfs -text
69
+ csqa__qwen3_8b__n2000_t1t2_s0_all_variants_r8_bs4_lr5e6_e3/lora/sft/checkpoint-1251/tokenizer.json filter=lfs diff=lfs merge=lfs -text
70
+ csqa__qwen3_8b__n5000_t1t2_s0_no_bare_ss_r8_bs4_lr1e5_e3_f/lora/sft/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
71
+ csqa__qwen3_8b__n5000_t1t2_s0_no_bare_ss_r8_bs4_lr1e5_e3_f/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
72
+ csqa__qwen3_8b__n5000_t1t2_s0_half_bare_ss_r8_bs4_lr1e5_e3_f/lora/sft/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
73
+ csqa__qwen3_8b__n5000_t1t2_s0_bare_100_r8_bs4_lr1e5_e3_f/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
74
+ csqa__llama3_8b_instruct__n5000_t1t2_s0_all_variants_r8_bs4_lr1e5_e3_f/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
75
+ gsm8k__qwen3_8b__n5000_t1t2_s0_all_variants_r8_bs4_lr1e5_e3_f/lora/sft/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
+ gsm8k__qwen3_8b__n5000_t1t2_s0_all_variants_r8_bs4_lr1e5_e3_f/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
77
+ gsm8k__llama3_8b_instruct__n5000_t1t2_s0_all_variants_r8_bs4_lr1e5_e3_f/lora/sft/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
78
+ csqa__qwen3_8b__n5000_t1t2_s0_all_variants_r8_bs4_lr1e5_e3_f/lora/sft/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
79
+ csqa__qwen3_8b__n5000_t1t2_s0_all_variants_r8_bs4_lr1e5_e3_f/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
80
+ csqa__llama3_8b_instruct__n5000_t1t2_s0_all_variants_r8_bs4_lr1e5_e3_f/lora/sft/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
81
+ csqa__qwen3_8b__n5000_t1t2_s0_bare_100_r8_bs4_lr1e5_e3_f/lora/sft/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
82
+ csqa__qwen3_8b__n2000_t1t2_s0_all_variants_r8_bs4_lr5e6_e3_f/lora/sft/checkpoint-375/tokenizer.json filter=lfs diff=lfs merge=lfs -text
83
+ csqa__qwen3_8b__n4000_t1t2_s0_all_variants_r8_bs4_lr5e6_e3_f/lora/sft/checkpoint-750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
84
+ gsm8k__llama3_8b_instruct__n5000_t1t2_s0_all_variants_r8_bs4_lr5e6_e3_f/lora/sft/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
85
+ gsm8k__llama3_8b_instruct__n5000_t1t2_s0_all_variants_r8_bs4_lr5e6_e3_f/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
86
+ gsm8k__llama3_8b_instruct__n5000_t1t2_s0_all_variants_r8_bs4_lr1e5_e3_f/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
87
+ csqa__qwen3_8b__n5000_t1t2_s0_half_bare_ss_r8_bs4_lr1e5_e3_f/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
88
+ csqa__qwen3_8b__n2000_t1t2_s0_all_variants_r8_bs4_lr5e6_e3_f/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
89
+ csqa__qwen3_8b__n4000_t1t2_s0_all_variants_r8_bs4_lr5e6_e3_f/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
90
+ csqa__llama3_8b_instruct__n5000_t1t2_s0_bare_100_r8_bs4_lr1e5_e3_f/lora/sft/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
91
+ gsm8k__llama3_8b_instruct__n5000_t1t2_s0_bare_100_r8_bs4_lr1e5_e3_f/lora/sft/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
92
+ gsm8k__llama3_8b_instruct__n5000_t1t2_s0_bare_100_r8_bs4_lr1e5_e3_f/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
93
+ csqa__llama3_8b_instruct__n5000_t1t2_s0_bare_100_r8_bs4_lr1e5_e3_f/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
94
+ gsm8k__qwen3_8b__n5000_t1t2_s0_bare_100_r8_bs4_lr1e5_e3_f/lora/sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
95
+ gsm8k__qwen3_8b__n5000_t1t2_s0_bare_100_r8_bs4_lr1e5_e3_f/lora/sft/checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: sft
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # sft
18
+
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the csqa__llama3_8b_instruct__n5000_t1t2_s0_all_variants_r8_bs4_lr1e5_e3_f_lora_sft dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 8
44
+ - total_train_batch_size: 32
45
+ - total_eval_batch_size: 64
46
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 3
50
+
51
+ ### Training results
52
+
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - PEFT 0.15.2
58
+ - Transformers 4.52.4
59
+ - Pytorch 2.7.0+cu126
60
+ - Datasets 3.6.0
61
+ - Tokenizers 0.21.1
csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "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": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "o_proj",
28
+ "up_proj",
29
+ "down_proj",
30
+ "v_proj",
31
+ "gate_proj",
32
+ "k_proj",
33
+ "q_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.743012015112192e+17,
4
+ "train_loss": 0.24353379998217248,
5
+ "train_runtime": 417.0434,
6
+ "train_samples_per_second": 71.935,
7
+ "train_steps_per_second": 2.252
8
+ }
csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "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": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "o_proj",
28
+ "up_proj",
29
+ "down_proj",
30
+ "v_proj",
31
+ "gate_proj",
32
+ "k_proj",
33
+ "q_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eom_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|eot_id|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": "<|eot_id|>"
26
+ }
csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/tokenizer_config.json ADDED
@@ -0,0 +1,2076 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<|eom_id|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ }
2059
+ },
2060
+ "additional_special_tokens": [
2061
+ "<|eom_id|>"
2062
+ ],
2063
+ "bos_token": "<|begin_of_text|>",
2064
+ "clean_up_tokenization_spaces": true,
2065
+ "eos_token": "<|eot_id|>",
2066
+ "extra_special_tokens": {},
2067
+ "model_input_names": [
2068
+ "input_ids",
2069
+ "attention_mask"
2070
+ ],
2071
+ "model_max_length": 1000000000000000019884624838656,
2072
+ "pad_token": "<|eot_id|>",
2073
+ "padding_side": "right",
2074
+ "split_special_tokens": false,
2075
+ "tokenizer_class": "PreTrainedTokenizer"
2076
+ }
csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/trainer_state.json ADDED
@@ -0,0 +1,685 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 939,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.03194888178913738,
14
+ "grad_norm": 7.985681533813477,
15
+ "learning_rate": 9.574468085106384e-07,
16
+ "loss": 0.9821,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.06389776357827476,
21
+ "grad_norm": 6.881392002105713,
22
+ "learning_rate": 2.021276595744681e-06,
23
+ "loss": 0.8509,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.09584664536741214,
28
+ "grad_norm": 10.480123519897461,
29
+ "learning_rate": 3.0851063829787237e-06,
30
+ "loss": 0.75,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.12779552715654952,
35
+ "grad_norm": 7.8626580238342285,
36
+ "learning_rate": 4.148936170212766e-06,
37
+ "loss": 0.9936,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.1597444089456869,
42
+ "grad_norm": 8.295928001403809,
43
+ "learning_rate": 5.212765957446809e-06,
44
+ "loss": 1.0561,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.19169329073482427,
49
+ "grad_norm": 7.584471225738525,
50
+ "learning_rate": 6.276595744680851e-06,
51
+ "loss": 0.5626,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.22364217252396165,
56
+ "grad_norm": 2.6033592224121094,
57
+ "learning_rate": 7.340425531914894e-06,
58
+ "loss": 0.3743,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.25559105431309903,
63
+ "grad_norm": 1.9967396259307861,
64
+ "learning_rate": 8.404255319148937e-06,
65
+ "loss": 0.369,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.28753993610223644,
70
+ "grad_norm": 2.95963454246521,
71
+ "learning_rate": 9.46808510638298e-06,
72
+ "loss": 0.3685,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.3194888178913738,
77
+ "grad_norm": 2.9198951721191406,
78
+ "learning_rate": 9.999136119166803e-06,
79
+ "loss": 0.3087,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.3514376996805112,
84
+ "grad_norm": 4.476741790771484,
85
+ "learning_rate": 9.9922268634943e-06,
86
+ "loss": 0.3387,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.38338658146964855,
91
+ "grad_norm": 3.1304333209991455,
92
+ "learning_rate": 9.978417901361958e-06,
93
+ "loss": 0.3385,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.41533546325878595,
98
+ "grad_norm": 2.121204376220703,
99
+ "learning_rate": 9.95772831799724e-06,
100
+ "loss": 0.3599,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.4472843450479233,
105
+ "grad_norm": 3.431854009628296,
106
+ "learning_rate": 9.930186708264902e-06,
107
+ "loss": 0.3075,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.4792332268370607,
112
+ "grad_norm": 2.422917604446411,
113
+ "learning_rate": 9.895831137146319e-06,
114
+ "loss": 0.2748,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.5111821086261981,
119
+ "grad_norm": 2.377556800842285,
120
+ "learning_rate": 9.854709087130261e-06,
121
+ "loss": 0.3323,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.5431309904153354,
126
+ "grad_norm": 2.3795032501220703,
127
+ "learning_rate": 9.80687739258782e-06,
128
+ "loss": 0.3026,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.5750798722044729,
133
+ "grad_norm": 2.1829874515533447,
134
+ "learning_rate": 9.7524021612222e-06,
135
+ "loss": 0.3791,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.6070287539936102,
140
+ "grad_norm": 2.441211223602295,
141
+ "learning_rate": 9.691358682701927e-06,
142
+ "loss": 0.2602,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.6389776357827476,
147
+ "grad_norm": 3.1940858364105225,
148
+ "learning_rate": 9.623831324603755e-06,
149
+ "loss": 0.3211,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.670926517571885,
154
+ "grad_norm": 3.239070177078247,
155
+ "learning_rate": 9.549913415809084e-06,
156
+ "loss": 0.3072,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.7028753993610224,
161
+ "grad_norm": 2.6575536727905273,
162
+ "learning_rate": 9.469707117515068e-06,
163
+ "loss": 0.2705,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.7348242811501597,
168
+ "grad_norm": 2.2929205894470215,
169
+ "learning_rate": 9.383323282038632e-06,
170
+ "loss": 0.3077,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.7667731629392971,
175
+ "grad_norm": 2.578460931777954,
176
+ "learning_rate": 9.29088129960862e-06,
177
+ "loss": 0.2396,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.7987220447284346,
182
+ "grad_norm": 2.8940231800079346,
183
+ "learning_rate": 9.192508933357753e-06,
184
+ "loss": 0.232,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.8306709265175719,
189
+ "grad_norm": 3.649961233139038,
190
+ "learning_rate": 9.088342142742493e-06,
191
+ "loss": 0.2611,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.8626198083067093,
196
+ "grad_norm": 2.731320858001709,
197
+ "learning_rate": 8.978524895634842e-06,
198
+ "loss": 0.2602,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.8945686900958466,
203
+ "grad_norm": 2.602999210357666,
204
+ "learning_rate": 8.86320896934581e-06,
205
+ "loss": 0.2813,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.9265175718849841,
210
+ "grad_norm": 2.6834731101989746,
211
+ "learning_rate": 8.742553740855507e-06,
212
+ "loss": 0.2768,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.9584664536741214,
217
+ "grad_norm": 5.155102252960205,
218
+ "learning_rate": 8.616725966539831e-06,
219
+ "loss": 0.2767,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.9904153354632588,
224
+ "grad_norm": 2.8492870330810547,
225
+ "learning_rate": 8.485899551698166e-06,
226
+ "loss": 0.242,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 1.0223642172523961,
231
+ "grad_norm": 3.060006856918335,
232
+ "learning_rate": 8.350255310200611e-06,
233
+ "loss": 0.2333,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 1.0543130990415335,
238
+ "grad_norm": 2.774890661239624,
239
+ "learning_rate": 8.209980714586955e-06,
240
+ "loss": 0.1976,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 1.0862619808306708,
245
+ "grad_norm": 3.210256576538086,
246
+ "learning_rate": 8.065269636962765e-06,
247
+ "loss": 0.1871,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 1.1182108626198084,
252
+ "grad_norm": 3.5963973999023438,
253
+ "learning_rate": 7.916322081050708e-06,
254
+ "loss": 0.2517,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 1.1501597444089458,
259
+ "grad_norm": 3.179945230484009,
260
+ "learning_rate": 7.76334390576742e-06,
261
+ "loss": 0.2281,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 1.182108626198083,
266
+ "grad_norm": 3.3402700424194336,
267
+ "learning_rate": 7.60654654070796e-06,
268
+ "loss": 0.2391,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 1.2140575079872205,
273
+ "grad_norm": 4.659540176391602,
274
+ "learning_rate": 7.446146693931111e-06,
275
+ "loss": 0.2158,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 1.2460063897763578,
280
+ "grad_norm": 3.430946111679077,
281
+ "learning_rate": 7.282366052449351e-06,
282
+ "loss": 0.1977,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 1.2779552715654952,
287
+ "grad_norm": 5.393412113189697,
288
+ "learning_rate": 7.115430975837457e-06,
289
+ "loss": 0.244,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 1.3099041533546325,
294
+ "grad_norm": 4.035030841827393,
295
+ "learning_rate": 6.945572183383229e-06,
296
+ "loss": 0.1882,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 1.34185303514377,
301
+ "grad_norm": 4.140837669372559,
302
+ "learning_rate": 6.773024435212678e-06,
303
+ "loss": 0.1843,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 1.3738019169329074,
308
+ "grad_norm": 4.740901470184326,
309
+ "learning_rate": 6.598026207830428e-06,
310
+ "loss": 0.1746,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 1.4057507987220448,
315
+ "grad_norm": 4.8010478019714355,
316
+ "learning_rate": 6.4208193645237314e-06,
317
+ "loss": 0.2283,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 1.4376996805111821,
322
+ "grad_norm": 4.866089344024658,
323
+ "learning_rate": 6.241648821085666e-06,
324
+ "loss": 0.2261,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 1.4696485623003195,
329
+ "grad_norm": 2.8326566219329834,
330
+ "learning_rate": 6.060762207319479e-06,
331
+ "loss": 0.2209,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 1.5015974440894568,
336
+ "grad_norm": 3.0169363021850586,
337
+ "learning_rate": 5.878409524791931e-06,
338
+ "loss": 0.1455,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 1.5335463258785942,
343
+ "grad_norm": 3.077761650085449,
344
+ "learning_rate": 5.694842801308651e-06,
345
+ "loss": 0.1713,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 1.5654952076677318,
350
+ "grad_norm": 3.5070152282714844,
351
+ "learning_rate": 5.510315742589042e-06,
352
+ "loss": 0.178,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.5974440894568689,
357
+ "grad_norm": 6.417858123779297,
358
+ "learning_rate": 5.325083381622165e-06,
359
+ "loss": 0.193,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.6293929712460065,
364
+ "grad_norm": 3.914149284362793,
365
+ "learning_rate": 5.139401726188208e-06,
366
+ "loss": 0.1762,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 1.6613418530351438,
371
+ "grad_norm": 5.518365383148193,
372
+ "learning_rate": 4.953527405032723e-06,
373
+ "loss": 0.1902,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 1.6932907348242812,
378
+ "grad_norm": 4.855342864990234,
379
+ "learning_rate": 4.767717313182611e-06,
380
+ "loss": 0.2097,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 1.7252396166134185,
385
+ "grad_norm": 4.270645618438721,
386
+ "learning_rate": 4.582228256894093e-06,
387
+ "loss": 0.1425,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.7571884984025559,
392
+ "grad_norm": 3.6671032905578613,
393
+ "learning_rate": 4.397316598723385e-06,
394
+ "loss": 0.1833,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 1.7891373801916934,
399
+ "grad_norm": 4.310007572174072,
400
+ "learning_rate": 4.2132379032105695e-06,
401
+ "loss": 0.1828,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 1.8210862619808306,
406
+ "grad_norm": 4.031312942504883,
407
+ "learning_rate": 4.030246583666437e-06,
408
+ "loss": 0.1813,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 1.8530351437699681,
413
+ "grad_norm": 4.36567497253418,
414
+ "learning_rate": 3.848595550550401e-06,
415
+ "loss": 0.1479,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 1.8849840255591053,
420
+ "grad_norm": 5.056768417358398,
421
+ "learning_rate": 3.668535861925509e-06,
422
+ "loss": 0.1875,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 1.9169329073482428,
427
+ "grad_norm": 4.989704132080078,
428
+ "learning_rate": 3.4903163764736104e-06,
429
+ "loss": 0.1493,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 1.9488817891373802,
434
+ "grad_norm": 3.9728195667266846,
435
+ "learning_rate": 3.314183409550293e-06,
436
+ "loss": 0.1982,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 1.9808306709265175,
441
+ "grad_norm": 6.375687599182129,
442
+ "learning_rate": 3.140380392754901e-06,
443
+ "loss": 0.1614,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 2.012779552715655,
448
+ "grad_norm": 3.3576982021331787,
449
+ "learning_rate": 2.969147537486175e-06,
450
+ "loss": 0.1327,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 2.0447284345047922,
455
+ "grad_norm": 6.22568941116333,
456
+ "learning_rate": 2.800721502948506e-06,
457
+ "loss": 0.1498,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 2.07667731629393,
462
+ "grad_norm": 4.179130554199219,
463
+ "learning_rate": 2.635335069067617e-06,
464
+ "loss": 0.1661,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 2.108626198083067,
469
+ "grad_norm": 2.9003777503967285,
470
+ "learning_rate": 2.4732168147677927e-06,
471
+ "loss": 0.1328,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 2.1405750798722045,
476
+ "grad_norm": 4.278232574462891,
477
+ "learning_rate": 2.314590802055232e-06,
478
+ "loss": 0.1325,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 2.1725239616613417,
483
+ "grad_norm": 3.038297653198242,
484
+ "learning_rate": 2.159676266344222e-06,
485
+ "loss": 0.1219,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 2.2044728434504792,
490
+ "grad_norm": 4.630241394042969,
491
+ "learning_rate": 2.0086873134540626e-06,
492
+ "loss": 0.1318,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 2.236421725239617,
497
+ "grad_norm": 5.753234386444092,
498
+ "learning_rate": 1.8618326236955908e-06,
499
+ "loss": 0.1336,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 2.268370607028754,
504
+ "grad_norm": 5.695158958435059,
505
+ "learning_rate": 1.7193151634562071e-06,
506
+ "loss": 0.1301,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 2.3003194888178915,
511
+ "grad_norm": 5.081648349761963,
512
+ "learning_rate": 1.581331904682089e-06,
513
+ "loss": 0.1834,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 2.3322683706070286,
518
+ "grad_norm": 5.1463303565979,
519
+ "learning_rate": 1.4480735526452427e-06,
520
+ "loss": 0.134,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 2.364217252396166,
525
+ "grad_norm": 2.7472803592681885,
526
+ "learning_rate": 1.319724282371664e-06,
527
+ "loss": 0.1412,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 2.3961661341853033,
532
+ "grad_norm": 4.516757965087891,
533
+ "learning_rate": 1.1964614840949002e-06,
534
+ "loss": 0.1468,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 2.428115015974441,
539
+ "grad_norm": 2.91664457321167,
540
+ "learning_rate": 1.078455518086784e-06,
541
+ "loss": 0.1184,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 2.460063897763578,
546
+ "grad_norm": 5.58245325088501,
547
+ "learning_rate": 9.658694792042284e-07,
548
+ "loss": 0.1172,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 2.4920127795527156,
553
+ "grad_norm": 4.261997699737549,
554
+ "learning_rate": 8.58858971477457e-07,
555
+ "loss": 0.128,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 2.523961661341853,
560
+ "grad_norm": 1.8599541187286377,
561
+ "learning_rate": 7.575718930512516e-07,
562
+ "loss": 0.1045,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 2.5559105431309903,
567
+ "grad_norm": 4.205503463745117,
568
+ "learning_rate": 6.621482317764105e-07,
569
+ "loss": 0.1008,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 2.587859424920128,
574
+ "grad_norm": 4.916066646575928,
575
+ "learning_rate": 5.727198717339511e-07,
576
+ "loss": 0.1411,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 2.619808306709265,
581
+ "grad_norm": 3.8452095985412598,
582
+ "learning_rate": 4.894104109594466e-07,
583
+ "loss": 0.1301,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 2.6517571884984026,
588
+ "grad_norm": 3.041799306869507,
589
+ "learning_rate": 4.123349906194357e-07,
590
+ "loss": 0.1361,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 2.68370607028754,
595
+ "grad_norm": 4.102115631103516,
596
+ "learning_rate": 3.416001358759635e-07,
597
+ "loss": 0.1204,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 2.7156549520766773,
602
+ "grad_norm": 5.494898796081543,
603
+ "learning_rate": 2.7730360865923954e-07,
604
+ "loss": 0.1107,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 2.747603833865815,
609
+ "grad_norm": 3.739745616912842,
610
+ "learning_rate": 2.1953427255185122e-07,
611
+ "loss": 0.1139,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 2.779552715654952,
616
+ "grad_norm": 7.225273132324219,
617
+ "learning_rate": 1.6837196997130434e-07,
618
+ "loss": 0.1447,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 2.8115015974440896,
623
+ "grad_norm": 2.620412826538086,
624
+ "learning_rate": 1.2388741182062348e-07,
625
+ "loss": 0.0981,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 2.8434504792332267,
630
+ "grad_norm": 5.001463413238525,
631
+ "learning_rate": 8.614207975952083e-08,
632
+ "loss": 0.1251,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 2.8753993610223643,
637
+ "grad_norm": 5.668241500854492,
638
+ "learning_rate": 5.518814123121885e-08,
639
+ "loss": 0.1274,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 2.9073482428115014,
644
+ "grad_norm": 2.917762517929077,
645
+ "learning_rate": 3.10683773623488e-08,
646
+ "loss": 0.1004,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 2.939297124600639,
651
+ "grad_norm": 4.0876665115356445,
652
+ "learning_rate": 1.3816123835588835e-08,
653
+ "loss": 0.1038,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 2.9712460063897765,
658
+ "grad_norm": 5.677676677703857,
659
+ "learning_rate": 3.4552248167507576e-09,
660
+ "loss": 0.1681,
661
+ "step": 930
662
+ }
663
+ ],
664
+ "logging_steps": 10,
665
+ "max_steps": 939,
666
+ "num_input_tokens_seen": 0,
667
+ "num_train_epochs": 3,
668
+ "save_steps": 2000,
669
+ "stateful_callbacks": {
670
+ "TrainerControl": {
671
+ "args": {
672
+ "should_epoch_stop": false,
673
+ "should_evaluate": false,
674
+ "should_log": false,
675
+ "should_save": true,
676
+ "should_training_stop": true
677
+ },
678
+ "attributes": {}
679
+ }
680
+ },
681
+ "total_flos": 1.743012015112192e+17,
682
+ "train_batch_size": 4,
683
+ "trial_name": null,
684
+ "trial_params": null
685
+ }
csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eom_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|eot_id|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": "<|eot_id|>"
26
+ }
csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/tokenizer_config.json ADDED
@@ -0,0 +1,2076 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<|eom_id|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ }
2059
+ },
2060
+ "additional_special_tokens": [
2061
+ "<|eom_id|>"
2062
+ ],
2063
+ "bos_token": "<|begin_of_text|>",
2064
+ "clean_up_tokenization_spaces": true,
2065
+ "eos_token": "<|eot_id|>",
2066
+ "extra_special_tokens": {},
2067
+ "model_input_names": [
2068
+ "input_ids",
2069
+ "attention_mask"
2070
+ ],
2071
+ "model_max_length": 1000000000000000019884624838656,
2072
+ "pad_token": "<|eot_id|>",
2073
+ "padding_side": "right",
2074
+ "split_special_tokens": false,
2075
+ "tokenizer_class": "PreTrainedTokenizer"
2076
+ }
csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.743012015112192e+17,
4
+ "train_loss": 0.24353379998217248,
5
+ "train_runtime": 417.0434,
6
+ "train_samples_per_second": 71.935,
7
+ "train_steps_per_second": 2.252
8
+ }
csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/trainer_log.jsonl ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 939, "loss": 0.9821, "lr": 9.574468085106384e-07, "epoch": 0.03194888178913738, "percentage": 1.06, "elapsed_time": "0:00:05", "remaining_time": "0:08:14"}
2
+ {"current_steps": 20, "total_steps": 939, "loss": 0.8509, "lr": 2.021276595744681e-06, "epoch": 0.06389776357827476, "percentage": 2.13, "elapsed_time": "0:00:09", "remaining_time": "0:07:19"}
3
+ {"current_steps": 30, "total_steps": 939, "loss": 0.75, "lr": 3.0851063829787237e-06, "epoch": 0.09584664536741214, "percentage": 3.19, "elapsed_time": "0:00:13", "remaining_time": "0:06:59"}
4
+ {"current_steps": 40, "total_steps": 939, "loss": 0.9936, "lr": 4.148936170212766e-06, "epoch": 0.12779552715654952, "percentage": 4.26, "elapsed_time": "0:00:18", "remaining_time": "0:06:46"}
5
+ {"current_steps": 50, "total_steps": 939, "loss": 1.0561, "lr": 5.212765957446809e-06, "epoch": 0.1597444089456869, "percentage": 5.32, "elapsed_time": "0:00:22", "remaining_time": "0:06:37"}
6
+ {"current_steps": 60, "total_steps": 939, "loss": 0.5626, "lr": 6.276595744680851e-06, "epoch": 0.19169329073482427, "percentage": 6.39, "elapsed_time": "0:00:26", "remaining_time": "0:06:31"}
7
+ {"current_steps": 70, "total_steps": 939, "loss": 0.3743, "lr": 7.340425531914894e-06, "epoch": 0.22364217252396165, "percentage": 7.45, "elapsed_time": "0:00:30", "remaining_time": "0:06:24"}
8
+ {"current_steps": 80, "total_steps": 939, "loss": 0.369, "lr": 8.404255319148937e-06, "epoch": 0.25559105431309903, "percentage": 8.52, "elapsed_time": "0:00:35", "remaining_time": "0:06:19"}
9
+ {"current_steps": 90, "total_steps": 939, "loss": 0.3685, "lr": 9.46808510638298e-06, "epoch": 0.28753993610223644, "percentage": 9.58, "elapsed_time": "0:00:39", "remaining_time": "0:06:13"}
10
+ {"current_steps": 100, "total_steps": 939, "loss": 0.3087, "lr": 9.999136119166803e-06, "epoch": 0.3194888178913738, "percentage": 10.65, "elapsed_time": "0:00:43", "remaining_time": "0:06:07"}
11
+ {"current_steps": 110, "total_steps": 939, "loss": 0.3387, "lr": 9.9922268634943e-06, "epoch": 0.3514376996805112, "percentage": 11.71, "elapsed_time": "0:00:48", "remaining_time": "0:06:02"}
12
+ {"current_steps": 120, "total_steps": 939, "loss": 0.3385, "lr": 9.978417901361958e-06, "epoch": 0.38338658146964855, "percentage": 12.78, "elapsed_time": "0:00:52", "remaining_time": "0:05:56"}
13
+ {"current_steps": 130, "total_steps": 939, "loss": 0.3599, "lr": 9.95772831799724e-06, "epoch": 0.41533546325878595, "percentage": 13.84, "elapsed_time": "0:00:56", "remaining_time": "0:05:52"}
14
+ {"current_steps": 140, "total_steps": 939, "loss": 0.3075, "lr": 9.930186708264902e-06, "epoch": 0.4472843450479233, "percentage": 14.91, "elapsed_time": "0:01:00", "remaining_time": "0:05:47"}
15
+ {"current_steps": 150, "total_steps": 939, "loss": 0.2748, "lr": 9.895831137146319e-06, "epoch": 0.4792332268370607, "percentage": 15.97, "elapsed_time": "0:01:05", "remaining_time": "0:05:43"}
16
+ {"current_steps": 160, "total_steps": 939, "loss": 0.3323, "lr": 9.854709087130261e-06, "epoch": 0.5111821086261981, "percentage": 17.04, "elapsed_time": "0:01:09", "remaining_time": "0:05:38"}
17
+ {"current_steps": 170, "total_steps": 939, "loss": 0.3026, "lr": 9.80687739258782e-06, "epoch": 0.5431309904153354, "percentage": 18.1, "elapsed_time": "0:01:13", "remaining_time": "0:05:33"}
18
+ {"current_steps": 180, "total_steps": 939, "loss": 0.3791, "lr": 9.7524021612222e-06, "epoch": 0.5750798722044729, "percentage": 19.17, "elapsed_time": "0:01:18", "remaining_time": "0:05:29"}
19
+ {"current_steps": 190, "total_steps": 939, "loss": 0.2602, "lr": 9.691358682701927e-06, "epoch": 0.6070287539936102, "percentage": 20.23, "elapsed_time": "0:01:22", "remaining_time": "0:05:24"}
20
+ {"current_steps": 200, "total_steps": 939, "loss": 0.3211, "lr": 9.623831324603755e-06, "epoch": 0.6389776357827476, "percentage": 21.3, "elapsed_time": "0:01:26", "remaining_time": "0:05:19"}
21
+ {"current_steps": 210, "total_steps": 939, "loss": 0.3072, "lr": 9.549913415809084e-06, "epoch": 0.670926517571885, "percentage": 22.36, "elapsed_time": "0:01:30", "remaining_time": "0:05:15"}
22
+ {"current_steps": 220, "total_steps": 939, "loss": 0.2705, "lr": 9.469707117515068e-06, "epoch": 0.7028753993610224, "percentage": 23.43, "elapsed_time": "0:01:35", "remaining_time": "0:05:10"}
23
+ {"current_steps": 230, "total_steps": 939, "loss": 0.3077, "lr": 9.383323282038632e-06, "epoch": 0.7348242811501597, "percentage": 24.49, "elapsed_time": "0:01:39", "remaining_time": "0:05:06"}
24
+ {"current_steps": 240, "total_steps": 939, "loss": 0.2396, "lr": 9.29088129960862e-06, "epoch": 0.7667731629392971, "percentage": 25.56, "elapsed_time": "0:01:43", "remaining_time": "0:05:01"}
25
+ {"current_steps": 250, "total_steps": 939, "loss": 0.232, "lr": 9.192508933357753e-06, "epoch": 0.7987220447284346, "percentage": 26.62, "elapsed_time": "0:01:47", "remaining_time": "0:04:56"}
26
+ {"current_steps": 260, "total_steps": 939, "loss": 0.2611, "lr": 9.088342142742493e-06, "epoch": 0.8306709265175719, "percentage": 27.69, "elapsed_time": "0:01:51", "remaining_time": "0:04:52"}
27
+ {"current_steps": 270, "total_steps": 939, "loss": 0.2602, "lr": 8.978524895634842e-06, "epoch": 0.8626198083067093, "percentage": 28.75, "elapsed_time": "0:01:56", "remaining_time": "0:04:48"}
28
+ {"current_steps": 280, "total_steps": 939, "loss": 0.2813, "lr": 8.86320896934581e-06, "epoch": 0.8945686900958466, "percentage": 29.82, "elapsed_time": "0:02:00", "remaining_time": "0:04:43"}
29
+ {"current_steps": 290, "total_steps": 939, "loss": 0.2768, "lr": 8.742553740855507e-06, "epoch": 0.9265175718849841, "percentage": 30.88, "elapsed_time": "0:02:04", "remaining_time": "0:04:39"}
30
+ {"current_steps": 300, "total_steps": 939, "loss": 0.2767, "lr": 8.616725966539831e-06, "epoch": 0.9584664536741214, "percentage": 31.95, "elapsed_time": "0:02:09", "remaining_time": "0:04:34"}
31
+ {"current_steps": 310, "total_steps": 939, "loss": 0.242, "lr": 8.485899551698166e-06, "epoch": 0.9904153354632588, "percentage": 33.01, "elapsed_time": "0:02:13", "remaining_time": "0:04:30"}
32
+ {"current_steps": 320, "total_steps": 939, "loss": 0.2333, "lr": 8.350255310200611e-06, "epoch": 1.0223642172523961, "percentage": 34.08, "elapsed_time": "0:02:17", "remaining_time": "0:04:26"}
33
+ {"current_steps": 330, "total_steps": 939, "loss": 0.1976, "lr": 8.209980714586955e-06, "epoch": 1.0543130990415335, "percentage": 35.14, "elapsed_time": "0:02:21", "remaining_time": "0:04:21"}
34
+ {"current_steps": 340, "total_steps": 939, "loss": 0.1871, "lr": 8.065269636962765e-06, "epoch": 1.0862619808306708, "percentage": 36.21, "elapsed_time": "0:02:26", "remaining_time": "0:04:17"}
35
+ {"current_steps": 350, "total_steps": 939, "loss": 0.2517, "lr": 7.916322081050708e-06, "epoch": 1.1182108626198084, "percentage": 37.27, "elapsed_time": "0:02:30", "remaining_time": "0:04:13"}
36
+ {"current_steps": 360, "total_steps": 939, "loss": 0.2281, "lr": 7.76334390576742e-06, "epoch": 1.1501597444089458, "percentage": 38.34, "elapsed_time": "0:02:34", "remaining_time": "0:04:08"}
37
+ {"current_steps": 370, "total_steps": 939, "loss": 0.2391, "lr": 7.60654654070796e-06, "epoch": 1.182108626198083, "percentage": 39.4, "elapsed_time": "0:02:38", "remaining_time": "0:04:04"}
38
+ {"current_steps": 380, "total_steps": 939, "loss": 0.2158, "lr": 7.446146693931111e-06, "epoch": 1.2140575079872205, "percentage": 40.47, "elapsed_time": "0:02:43", "remaining_time": "0:03:59"}
39
+ {"current_steps": 390, "total_steps": 939, "loss": 0.1977, "lr": 7.282366052449351e-06, "epoch": 1.2460063897763578, "percentage": 41.53, "elapsed_time": "0:02:47", "remaining_time": "0:03:55"}
40
+ {"current_steps": 400, "total_steps": 939, "loss": 0.244, "lr": 7.115430975837457e-06, "epoch": 1.2779552715654952, "percentage": 42.6, "elapsed_time": "0:02:51", "remaining_time": "0:03:51"}
41
+ {"current_steps": 410, "total_steps": 939, "loss": 0.1882, "lr": 6.945572183383229e-06, "epoch": 1.3099041533546325, "percentage": 43.66, "elapsed_time": "0:02:55", "remaining_time": "0:03:46"}
42
+ {"current_steps": 420, "total_steps": 939, "loss": 0.1843, "lr": 6.773024435212678e-06, "epoch": 1.34185303514377, "percentage": 44.73, "elapsed_time": "0:03:00", "remaining_time": "0:03:42"}
43
+ {"current_steps": 430, "total_steps": 939, "loss": 0.1746, "lr": 6.598026207830428e-06, "epoch": 1.3738019169329074, "percentage": 45.79, "elapsed_time": "0:03:04", "remaining_time": "0:03:38"}
44
+ {"current_steps": 440, "total_steps": 939, "loss": 0.2283, "lr": 6.4208193645237314e-06, "epoch": 1.4057507987220448, "percentage": 46.86, "elapsed_time": "0:03:08", "remaining_time": "0:03:33"}
45
+ {"current_steps": 450, "total_steps": 939, "loss": 0.2261, "lr": 6.241648821085666e-06, "epoch": 1.4376996805111821, "percentage": 47.92, "elapsed_time": "0:03:12", "remaining_time": "0:03:29"}
46
+ {"current_steps": 460, "total_steps": 939, "loss": 0.2209, "lr": 6.060762207319479e-06, "epoch": 1.4696485623003195, "percentage": 48.99, "elapsed_time": "0:03:17", "remaining_time": "0:03:25"}
47
+ {"current_steps": 470, "total_steps": 939, "loss": 0.1455, "lr": 5.878409524791931e-06, "epoch": 1.5015974440894568, "percentage": 50.05, "elapsed_time": "0:03:21", "remaining_time": "0:03:20"}
48
+ {"current_steps": 480, "total_steps": 939, "loss": 0.1713, "lr": 5.694842801308651e-06, "epoch": 1.5335463258785942, "percentage": 51.12, "elapsed_time": "0:03:25", "remaining_time": "0:03:16"}
49
+ {"current_steps": 490, "total_steps": 939, "loss": 0.178, "lr": 5.510315742589042e-06, "epoch": 1.5654952076677318, "percentage": 52.18, "elapsed_time": "0:03:29", "remaining_time": "0:03:12"}
50
+ {"current_steps": 500, "total_steps": 939, "loss": 0.193, "lr": 5.325083381622165e-06, "epoch": 1.5974440894568689, "percentage": 53.25, "elapsed_time": "0:03:34", "remaining_time": "0:03:08"}
51
+ {"current_steps": 510, "total_steps": 939, "loss": 0.1762, "lr": 5.139401726188208e-06, "epoch": 1.6293929712460065, "percentage": 54.31, "elapsed_time": "0:03:38", "remaining_time": "0:03:03"}
52
+ {"current_steps": 520, "total_steps": 939, "loss": 0.1902, "lr": 4.953527405032723e-06, "epoch": 1.6613418530351438, "percentage": 55.38, "elapsed_time": "0:03:42", "remaining_time": "0:02:59"}
53
+ {"current_steps": 530, "total_steps": 939, "loss": 0.2097, "lr": 4.767717313182611e-06, "epoch": 1.6932907348242812, "percentage": 56.44, "elapsed_time": "0:03:47", "remaining_time": "0:02:55"}
54
+ {"current_steps": 540, "total_steps": 939, "loss": 0.1425, "lr": 4.582228256894093e-06, "epoch": 1.7252396166134185, "percentage": 57.51, "elapsed_time": "0:03:51", "remaining_time": "0:02:50"}
55
+ {"current_steps": 550, "total_steps": 939, "loss": 0.1833, "lr": 4.397316598723385e-06, "epoch": 1.7571884984025559, "percentage": 58.57, "elapsed_time": "0:03:55", "remaining_time": "0:02:46"}
56
+ {"current_steps": 560, "total_steps": 939, "loss": 0.1828, "lr": 4.2132379032105695e-06, "epoch": 1.7891373801916934, "percentage": 59.64, "elapsed_time": "0:03:59", "remaining_time": "0:02:42"}
57
+ {"current_steps": 570, "total_steps": 939, "loss": 0.1813, "lr": 4.030246583666437e-06, "epoch": 1.8210862619808306, "percentage": 60.7, "elapsed_time": "0:04:04", "remaining_time": "0:02:38"}
58
+ {"current_steps": 580, "total_steps": 939, "loss": 0.1479, "lr": 3.848595550550401e-06, "epoch": 1.8530351437699681, "percentage": 61.77, "elapsed_time": "0:04:08", "remaining_time": "0:02:33"}
59
+ {"current_steps": 590, "total_steps": 939, "loss": 0.1875, "lr": 3.668535861925509e-06, "epoch": 1.8849840255591053, "percentage": 62.83, "elapsed_time": "0:04:12", "remaining_time": "0:02:29"}
60
+ {"current_steps": 600, "total_steps": 939, "loss": 0.1493, "lr": 3.4903163764736104e-06, "epoch": 1.9169329073482428, "percentage": 63.9, "elapsed_time": "0:04:17", "remaining_time": "0:02:25"}
61
+ {"current_steps": 610, "total_steps": 939, "loss": 0.1982, "lr": 3.314183409550293e-06, "epoch": 1.9488817891373802, "percentage": 64.96, "elapsed_time": "0:04:21", "remaining_time": "0:02:20"}
62
+ {"current_steps": 620, "total_steps": 939, "loss": 0.1614, "lr": 3.140380392754901e-06, "epoch": 1.9808306709265175, "percentage": 66.03, "elapsed_time": "0:04:25", "remaining_time": "0:02:16"}
63
+ {"current_steps": 630, "total_steps": 939, "loss": 0.1327, "lr": 2.969147537486175e-06, "epoch": 2.012779552715655, "percentage": 67.09, "elapsed_time": "0:04:30", "remaining_time": "0:02:12"}
64
+ {"current_steps": 640, "total_steps": 939, "loss": 0.1498, "lr": 2.800721502948506e-06, "epoch": 2.0447284345047922, "percentage": 68.16, "elapsed_time": "0:04:34", "remaining_time": "0:02:08"}
65
+ {"current_steps": 650, "total_steps": 939, "loss": 0.1661, "lr": 2.635335069067617e-06, "epoch": 2.07667731629393, "percentage": 69.22, "elapsed_time": "0:04:38", "remaining_time": "0:02:03"}
66
+ {"current_steps": 660, "total_steps": 939, "loss": 0.1328, "lr": 2.4732168147677927e-06, "epoch": 2.108626198083067, "percentage": 70.29, "elapsed_time": "0:04:42", "remaining_time": "0:01:59"}
67
+ {"current_steps": 670, "total_steps": 939, "loss": 0.1325, "lr": 2.314590802055232e-06, "epoch": 2.1405750798722045, "percentage": 71.35, "elapsed_time": "0:04:46", "remaining_time": "0:01:55"}
68
+ {"current_steps": 680, "total_steps": 939, "loss": 0.1219, "lr": 2.159676266344222e-06, "epoch": 2.1725239616613417, "percentage": 72.42, "elapsed_time": "0:04:51", "remaining_time": "0:01:50"}
69
+ {"current_steps": 690, "total_steps": 939, "loss": 0.1318, "lr": 2.0086873134540626e-06, "epoch": 2.2044728434504792, "percentage": 73.48, "elapsed_time": "0:04:55", "remaining_time": "0:01:46"}
70
+ {"current_steps": 700, "total_steps": 939, "loss": 0.1336, "lr": 1.8618326236955908e-06, "epoch": 2.236421725239617, "percentage": 74.55, "elapsed_time": "0:04:59", "remaining_time": "0:01:42"}
71
+ {"current_steps": 710, "total_steps": 939, "loss": 0.1301, "lr": 1.7193151634562071e-06, "epoch": 2.268370607028754, "percentage": 75.61, "elapsed_time": "0:05:04", "remaining_time": "0:01:38"}
72
+ {"current_steps": 720, "total_steps": 939, "loss": 0.1834, "lr": 1.581331904682089e-06, "epoch": 2.3003194888178915, "percentage": 76.68, "elapsed_time": "0:05:08", "remaining_time": "0:01:33"}
73
+ {"current_steps": 730, "total_steps": 939, "loss": 0.134, "lr": 1.4480735526452427e-06, "epoch": 2.3322683706070286, "percentage": 77.74, "elapsed_time": "0:05:12", "remaining_time": "0:01:29"}
74
+ {"current_steps": 740, "total_steps": 939, "loss": 0.1412, "lr": 1.319724282371664e-06, "epoch": 2.364217252396166, "percentage": 78.81, "elapsed_time": "0:05:16", "remaining_time": "0:01:25"}
75
+ {"current_steps": 750, "total_steps": 939, "loss": 0.1468, "lr": 1.1964614840949002e-06, "epoch": 2.3961661341853033, "percentage": 79.87, "elapsed_time": "0:05:21", "remaining_time": "0:01:20"}
76
+ {"current_steps": 760, "total_steps": 939, "loss": 0.1184, "lr": 1.078455518086784e-06, "epoch": 2.428115015974441, "percentage": 80.94, "elapsed_time": "0:05:25", "remaining_time": "0:01:16"}
77
+ {"current_steps": 770, "total_steps": 939, "loss": 0.1172, "lr": 9.658694792042284e-07, "epoch": 2.460063897763578, "percentage": 82.0, "elapsed_time": "0:05:29", "remaining_time": "0:01:12"}
78
+ {"current_steps": 780, "total_steps": 939, "loss": 0.128, "lr": 8.58858971477457e-07, "epoch": 2.4920127795527156, "percentage": 83.07, "elapsed_time": "0:05:33", "remaining_time": "0:01:08"}
79
+ {"current_steps": 790, "total_steps": 939, "loss": 0.1045, "lr": 7.575718930512516e-07, "epoch": 2.523961661341853, "percentage": 84.13, "elapsed_time": "0:05:38", "remaining_time": "0:01:03"}
80
+ {"current_steps": 800, "total_steps": 939, "loss": 0.1008, "lr": 6.621482317764105e-07, "epoch": 2.5559105431309903, "percentage": 85.2, "elapsed_time": "0:05:42", "remaining_time": "0:00:59"}
81
+ {"current_steps": 810, "total_steps": 939, "loss": 0.1411, "lr": 5.727198717339511e-07, "epoch": 2.587859424920128, "percentage": 86.26, "elapsed_time": "0:05:46", "remaining_time": "0:00:55"}
82
+ {"current_steps": 820, "total_steps": 939, "loss": 0.1301, "lr": 4.894104109594466e-07, "epoch": 2.619808306709265, "percentage": 87.33, "elapsed_time": "0:05:50", "remaining_time": "0:00:50"}
83
+ {"current_steps": 830, "total_steps": 939, "loss": 0.1361, "lr": 4.123349906194357e-07, "epoch": 2.6517571884984026, "percentage": 88.39, "elapsed_time": "0:05:55", "remaining_time": "0:00:46"}
84
+ {"current_steps": 840, "total_steps": 939, "loss": 0.1204, "lr": 3.416001358759635e-07, "epoch": 2.68370607028754, "percentage": 89.46, "elapsed_time": "0:05:59", "remaining_time": "0:00:42"}
85
+ {"current_steps": 850, "total_steps": 939, "loss": 0.1107, "lr": 2.7730360865923954e-07, "epoch": 2.7156549520766773, "percentage": 90.52, "elapsed_time": "0:06:03", "remaining_time": "0:00:38"}
86
+ {"current_steps": 860, "total_steps": 939, "loss": 0.1139, "lr": 2.1953427255185122e-07, "epoch": 2.747603833865815, "percentage": 91.59, "elapsed_time": "0:06:07", "remaining_time": "0:00:33"}
87
+ {"current_steps": 870, "total_steps": 939, "loss": 0.1447, "lr": 1.6837196997130434e-07, "epoch": 2.779552715654952, "percentage": 92.65, "elapsed_time": "0:06:11", "remaining_time": "0:00:29"}
88
+ {"current_steps": 880, "total_steps": 939, "loss": 0.0981, "lr": 1.2388741182062348e-07, "epoch": 2.8115015974440896, "percentage": 93.72, "elapsed_time": "0:06:16", "remaining_time": "0:00:25"}
89
+ {"current_steps": 890, "total_steps": 939, "loss": 0.1251, "lr": 8.614207975952083e-08, "epoch": 2.8434504792332267, "percentage": 94.78, "elapsed_time": "0:06:20", "remaining_time": "0:00:20"}
90
+ {"current_steps": 900, "total_steps": 939, "loss": 0.1274, "lr": 5.518814123121885e-08, "epoch": 2.8753993610223643, "percentage": 95.85, "elapsed_time": "0:06:24", "remaining_time": "0:00:16"}
91
+ {"current_steps": 910, "total_steps": 939, "loss": 0.1004, "lr": 3.10683773623488e-08, "epoch": 2.9073482428115014, "percentage": 96.91, "elapsed_time": "0:06:28", "remaining_time": "0:00:12"}
92
+ {"current_steps": 920, "total_steps": 939, "loss": 0.1038, "lr": 1.3816123835588835e-08, "epoch": 2.939297124600639, "percentage": 97.98, "elapsed_time": "0:06:33", "remaining_time": "0:00:08"}
93
+ {"current_steps": 930, "total_steps": 939, "loss": 0.1681, "lr": 3.4552248167507576e-09, "epoch": 2.9712460063897765, "percentage": 99.04, "elapsed_time": "0:06:37", "remaining_time": "0:00:03"}
94
+ {"current_steps": 939, "total_steps": 939, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:06:42", "remaining_time": "0:00:00"}
csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/trainer_state.json ADDED
@@ -0,0 +1,694 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 939,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.03194888178913738,
14
+ "grad_norm": 7.985681533813477,
15
+ "learning_rate": 9.574468085106384e-07,
16
+ "loss": 0.9821,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.06389776357827476,
21
+ "grad_norm": 6.881392002105713,
22
+ "learning_rate": 2.021276595744681e-06,
23
+ "loss": 0.8509,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.09584664536741214,
28
+ "grad_norm": 10.480123519897461,
29
+ "learning_rate": 3.0851063829787237e-06,
30
+ "loss": 0.75,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.12779552715654952,
35
+ "grad_norm": 7.8626580238342285,
36
+ "learning_rate": 4.148936170212766e-06,
37
+ "loss": 0.9936,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.1597444089456869,
42
+ "grad_norm": 8.295928001403809,
43
+ "learning_rate": 5.212765957446809e-06,
44
+ "loss": 1.0561,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.19169329073482427,
49
+ "grad_norm": 7.584471225738525,
50
+ "learning_rate": 6.276595744680851e-06,
51
+ "loss": 0.5626,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.22364217252396165,
56
+ "grad_norm": 2.6033592224121094,
57
+ "learning_rate": 7.340425531914894e-06,
58
+ "loss": 0.3743,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.25559105431309903,
63
+ "grad_norm": 1.9967396259307861,
64
+ "learning_rate": 8.404255319148937e-06,
65
+ "loss": 0.369,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.28753993610223644,
70
+ "grad_norm": 2.95963454246521,
71
+ "learning_rate": 9.46808510638298e-06,
72
+ "loss": 0.3685,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.3194888178913738,
77
+ "grad_norm": 2.9198951721191406,
78
+ "learning_rate": 9.999136119166803e-06,
79
+ "loss": 0.3087,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.3514376996805112,
84
+ "grad_norm": 4.476741790771484,
85
+ "learning_rate": 9.9922268634943e-06,
86
+ "loss": 0.3387,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.38338658146964855,
91
+ "grad_norm": 3.1304333209991455,
92
+ "learning_rate": 9.978417901361958e-06,
93
+ "loss": 0.3385,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.41533546325878595,
98
+ "grad_norm": 2.121204376220703,
99
+ "learning_rate": 9.95772831799724e-06,
100
+ "loss": 0.3599,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.4472843450479233,
105
+ "grad_norm": 3.431854009628296,
106
+ "learning_rate": 9.930186708264902e-06,
107
+ "loss": 0.3075,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.4792332268370607,
112
+ "grad_norm": 2.422917604446411,
113
+ "learning_rate": 9.895831137146319e-06,
114
+ "loss": 0.2748,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.5111821086261981,
119
+ "grad_norm": 2.377556800842285,
120
+ "learning_rate": 9.854709087130261e-06,
121
+ "loss": 0.3323,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.5431309904153354,
126
+ "grad_norm": 2.3795032501220703,
127
+ "learning_rate": 9.80687739258782e-06,
128
+ "loss": 0.3026,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.5750798722044729,
133
+ "grad_norm": 2.1829874515533447,
134
+ "learning_rate": 9.7524021612222e-06,
135
+ "loss": 0.3791,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.6070287539936102,
140
+ "grad_norm": 2.441211223602295,
141
+ "learning_rate": 9.691358682701927e-06,
142
+ "loss": 0.2602,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.6389776357827476,
147
+ "grad_norm": 3.1940858364105225,
148
+ "learning_rate": 9.623831324603755e-06,
149
+ "loss": 0.3211,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.670926517571885,
154
+ "grad_norm": 3.239070177078247,
155
+ "learning_rate": 9.549913415809084e-06,
156
+ "loss": 0.3072,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.7028753993610224,
161
+ "grad_norm": 2.6575536727905273,
162
+ "learning_rate": 9.469707117515068e-06,
163
+ "loss": 0.2705,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.7348242811501597,
168
+ "grad_norm": 2.2929205894470215,
169
+ "learning_rate": 9.383323282038632e-06,
170
+ "loss": 0.3077,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.7667731629392971,
175
+ "grad_norm": 2.578460931777954,
176
+ "learning_rate": 9.29088129960862e-06,
177
+ "loss": 0.2396,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.7987220447284346,
182
+ "grad_norm": 2.8940231800079346,
183
+ "learning_rate": 9.192508933357753e-06,
184
+ "loss": 0.232,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.8306709265175719,
189
+ "grad_norm": 3.649961233139038,
190
+ "learning_rate": 9.088342142742493e-06,
191
+ "loss": 0.2611,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.8626198083067093,
196
+ "grad_norm": 2.731320858001709,
197
+ "learning_rate": 8.978524895634842e-06,
198
+ "loss": 0.2602,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.8945686900958466,
203
+ "grad_norm": 2.602999210357666,
204
+ "learning_rate": 8.86320896934581e-06,
205
+ "loss": 0.2813,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.9265175718849841,
210
+ "grad_norm": 2.6834731101989746,
211
+ "learning_rate": 8.742553740855507e-06,
212
+ "loss": 0.2768,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.9584664536741214,
217
+ "grad_norm": 5.155102252960205,
218
+ "learning_rate": 8.616725966539831e-06,
219
+ "loss": 0.2767,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.9904153354632588,
224
+ "grad_norm": 2.8492870330810547,
225
+ "learning_rate": 8.485899551698166e-06,
226
+ "loss": 0.242,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 1.0223642172523961,
231
+ "grad_norm": 3.060006856918335,
232
+ "learning_rate": 8.350255310200611e-06,
233
+ "loss": 0.2333,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 1.0543130990415335,
238
+ "grad_norm": 2.774890661239624,
239
+ "learning_rate": 8.209980714586955e-06,
240
+ "loss": 0.1976,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 1.0862619808306708,
245
+ "grad_norm": 3.210256576538086,
246
+ "learning_rate": 8.065269636962765e-06,
247
+ "loss": 0.1871,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 1.1182108626198084,
252
+ "grad_norm": 3.5963973999023438,
253
+ "learning_rate": 7.916322081050708e-06,
254
+ "loss": 0.2517,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 1.1501597444089458,
259
+ "grad_norm": 3.179945230484009,
260
+ "learning_rate": 7.76334390576742e-06,
261
+ "loss": 0.2281,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 1.182108626198083,
266
+ "grad_norm": 3.3402700424194336,
267
+ "learning_rate": 7.60654654070796e-06,
268
+ "loss": 0.2391,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 1.2140575079872205,
273
+ "grad_norm": 4.659540176391602,
274
+ "learning_rate": 7.446146693931111e-06,
275
+ "loss": 0.2158,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 1.2460063897763578,
280
+ "grad_norm": 3.430946111679077,
281
+ "learning_rate": 7.282366052449351e-06,
282
+ "loss": 0.1977,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 1.2779552715654952,
287
+ "grad_norm": 5.393412113189697,
288
+ "learning_rate": 7.115430975837457e-06,
289
+ "loss": 0.244,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 1.3099041533546325,
294
+ "grad_norm": 4.035030841827393,
295
+ "learning_rate": 6.945572183383229e-06,
296
+ "loss": 0.1882,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 1.34185303514377,
301
+ "grad_norm": 4.140837669372559,
302
+ "learning_rate": 6.773024435212678e-06,
303
+ "loss": 0.1843,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 1.3738019169329074,
308
+ "grad_norm": 4.740901470184326,
309
+ "learning_rate": 6.598026207830428e-06,
310
+ "loss": 0.1746,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 1.4057507987220448,
315
+ "grad_norm": 4.8010478019714355,
316
+ "learning_rate": 6.4208193645237314e-06,
317
+ "loss": 0.2283,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 1.4376996805111821,
322
+ "grad_norm": 4.866089344024658,
323
+ "learning_rate": 6.241648821085666e-06,
324
+ "loss": 0.2261,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 1.4696485623003195,
329
+ "grad_norm": 2.8326566219329834,
330
+ "learning_rate": 6.060762207319479e-06,
331
+ "loss": 0.2209,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 1.5015974440894568,
336
+ "grad_norm": 3.0169363021850586,
337
+ "learning_rate": 5.878409524791931e-06,
338
+ "loss": 0.1455,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 1.5335463258785942,
343
+ "grad_norm": 3.077761650085449,
344
+ "learning_rate": 5.694842801308651e-06,
345
+ "loss": 0.1713,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 1.5654952076677318,
350
+ "grad_norm": 3.5070152282714844,
351
+ "learning_rate": 5.510315742589042e-06,
352
+ "loss": 0.178,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.5974440894568689,
357
+ "grad_norm": 6.417858123779297,
358
+ "learning_rate": 5.325083381622165e-06,
359
+ "loss": 0.193,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.6293929712460065,
364
+ "grad_norm": 3.914149284362793,
365
+ "learning_rate": 5.139401726188208e-06,
366
+ "loss": 0.1762,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 1.6613418530351438,
371
+ "grad_norm": 5.518365383148193,
372
+ "learning_rate": 4.953527405032723e-06,
373
+ "loss": 0.1902,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 1.6932907348242812,
378
+ "grad_norm": 4.855342864990234,
379
+ "learning_rate": 4.767717313182611e-06,
380
+ "loss": 0.2097,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 1.7252396166134185,
385
+ "grad_norm": 4.270645618438721,
386
+ "learning_rate": 4.582228256894093e-06,
387
+ "loss": 0.1425,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.7571884984025559,
392
+ "grad_norm": 3.6671032905578613,
393
+ "learning_rate": 4.397316598723385e-06,
394
+ "loss": 0.1833,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 1.7891373801916934,
399
+ "grad_norm": 4.310007572174072,
400
+ "learning_rate": 4.2132379032105695e-06,
401
+ "loss": 0.1828,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 1.8210862619808306,
406
+ "grad_norm": 4.031312942504883,
407
+ "learning_rate": 4.030246583666437e-06,
408
+ "loss": 0.1813,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 1.8530351437699681,
413
+ "grad_norm": 4.36567497253418,
414
+ "learning_rate": 3.848595550550401e-06,
415
+ "loss": 0.1479,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 1.8849840255591053,
420
+ "grad_norm": 5.056768417358398,
421
+ "learning_rate": 3.668535861925509e-06,
422
+ "loss": 0.1875,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 1.9169329073482428,
427
+ "grad_norm": 4.989704132080078,
428
+ "learning_rate": 3.4903163764736104e-06,
429
+ "loss": 0.1493,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 1.9488817891373802,
434
+ "grad_norm": 3.9728195667266846,
435
+ "learning_rate": 3.314183409550293e-06,
436
+ "loss": 0.1982,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 1.9808306709265175,
441
+ "grad_norm": 6.375687599182129,
442
+ "learning_rate": 3.140380392754901e-06,
443
+ "loss": 0.1614,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 2.012779552715655,
448
+ "grad_norm": 3.3576982021331787,
449
+ "learning_rate": 2.969147537486175e-06,
450
+ "loss": 0.1327,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 2.0447284345047922,
455
+ "grad_norm": 6.22568941116333,
456
+ "learning_rate": 2.800721502948506e-06,
457
+ "loss": 0.1498,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 2.07667731629393,
462
+ "grad_norm": 4.179130554199219,
463
+ "learning_rate": 2.635335069067617e-06,
464
+ "loss": 0.1661,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 2.108626198083067,
469
+ "grad_norm": 2.9003777503967285,
470
+ "learning_rate": 2.4732168147677927e-06,
471
+ "loss": 0.1328,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 2.1405750798722045,
476
+ "grad_norm": 4.278232574462891,
477
+ "learning_rate": 2.314590802055232e-06,
478
+ "loss": 0.1325,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 2.1725239616613417,
483
+ "grad_norm": 3.038297653198242,
484
+ "learning_rate": 2.159676266344222e-06,
485
+ "loss": 0.1219,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 2.2044728434504792,
490
+ "grad_norm": 4.630241394042969,
491
+ "learning_rate": 2.0086873134540626e-06,
492
+ "loss": 0.1318,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 2.236421725239617,
497
+ "grad_norm": 5.753234386444092,
498
+ "learning_rate": 1.8618326236955908e-06,
499
+ "loss": 0.1336,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 2.268370607028754,
504
+ "grad_norm": 5.695158958435059,
505
+ "learning_rate": 1.7193151634562071e-06,
506
+ "loss": 0.1301,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 2.3003194888178915,
511
+ "grad_norm": 5.081648349761963,
512
+ "learning_rate": 1.581331904682089e-06,
513
+ "loss": 0.1834,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 2.3322683706070286,
518
+ "grad_norm": 5.1463303565979,
519
+ "learning_rate": 1.4480735526452427e-06,
520
+ "loss": 0.134,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 2.364217252396166,
525
+ "grad_norm": 2.7472803592681885,
526
+ "learning_rate": 1.319724282371664e-06,
527
+ "loss": 0.1412,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 2.3961661341853033,
532
+ "grad_norm": 4.516757965087891,
533
+ "learning_rate": 1.1964614840949002e-06,
534
+ "loss": 0.1468,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 2.428115015974441,
539
+ "grad_norm": 2.91664457321167,
540
+ "learning_rate": 1.078455518086784e-06,
541
+ "loss": 0.1184,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 2.460063897763578,
546
+ "grad_norm": 5.58245325088501,
547
+ "learning_rate": 9.658694792042284e-07,
548
+ "loss": 0.1172,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 2.4920127795527156,
553
+ "grad_norm": 4.261997699737549,
554
+ "learning_rate": 8.58858971477457e-07,
555
+ "loss": 0.128,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 2.523961661341853,
560
+ "grad_norm": 1.8599541187286377,
561
+ "learning_rate": 7.575718930512516e-07,
562
+ "loss": 0.1045,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 2.5559105431309903,
567
+ "grad_norm": 4.205503463745117,
568
+ "learning_rate": 6.621482317764105e-07,
569
+ "loss": 0.1008,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 2.587859424920128,
574
+ "grad_norm": 4.916066646575928,
575
+ "learning_rate": 5.727198717339511e-07,
576
+ "loss": 0.1411,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 2.619808306709265,
581
+ "grad_norm": 3.8452095985412598,
582
+ "learning_rate": 4.894104109594466e-07,
583
+ "loss": 0.1301,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 2.6517571884984026,
588
+ "grad_norm": 3.041799306869507,
589
+ "learning_rate": 4.123349906194357e-07,
590
+ "loss": 0.1361,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 2.68370607028754,
595
+ "grad_norm": 4.102115631103516,
596
+ "learning_rate": 3.416001358759635e-07,
597
+ "loss": 0.1204,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 2.7156549520766773,
602
+ "grad_norm": 5.494898796081543,
603
+ "learning_rate": 2.7730360865923954e-07,
604
+ "loss": 0.1107,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 2.747603833865815,
609
+ "grad_norm": 3.739745616912842,
610
+ "learning_rate": 2.1953427255185122e-07,
611
+ "loss": 0.1139,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 2.779552715654952,
616
+ "grad_norm": 7.225273132324219,
617
+ "learning_rate": 1.6837196997130434e-07,
618
+ "loss": 0.1447,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 2.8115015974440896,
623
+ "grad_norm": 2.620412826538086,
624
+ "learning_rate": 1.2388741182062348e-07,
625
+ "loss": 0.0981,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 2.8434504792332267,
630
+ "grad_norm": 5.001463413238525,
631
+ "learning_rate": 8.614207975952083e-08,
632
+ "loss": 0.1251,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 2.8753993610223643,
637
+ "grad_norm": 5.668241500854492,
638
+ "learning_rate": 5.518814123121885e-08,
639
+ "loss": 0.1274,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 2.9073482428115014,
644
+ "grad_norm": 2.917762517929077,
645
+ "learning_rate": 3.10683773623488e-08,
646
+ "loss": 0.1004,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 2.939297124600639,
651
+ "grad_norm": 4.0876665115356445,
652
+ "learning_rate": 1.3816123835588835e-08,
653
+ "loss": 0.1038,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 2.9712460063897765,
658
+ "grad_norm": 5.677676677703857,
659
+ "learning_rate": 3.4552248167507576e-09,
660
+ "loss": 0.1681,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 3.0,
665
+ "step": 939,
666
+ "total_flos": 1.743012015112192e+17,
667
+ "train_loss": 0.24353379998217248,
668
+ "train_runtime": 417.0434,
669
+ "train_samples_per_second": 71.935,
670
+ "train_steps_per_second": 2.252
671
+ }
672
+ ],
673
+ "logging_steps": 10,
674
+ "max_steps": 939,
675
+ "num_input_tokens_seen": 0,
676
+ "num_train_epochs": 3,
677
+ "save_steps": 2000,
678
+ "stateful_callbacks": {
679
+ "TrainerControl": {
680
+ "args": {
681
+ "should_epoch_stop": false,
682
+ "should_evaluate": false,
683
+ "should_log": false,
684
+ "should_save": true,
685
+ "should_training_stop": true
686
+ },
687
+ "attributes": {}
688
+ }
689
+ },
690
+ "total_flos": 1.743012015112192e+17,
691
+ "train_batch_size": 4,
692
+ "trial_name": null,
693
+ "trial_params": null
694
+ }
csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/training_loss.png ADDED
csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: sft
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # sft
18
+
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the csqa__llama3_8b_instruct__n5000_t1t2_s0_bare_100_r8_bs4_lr1e5_e3_f_lora_sft dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 8
44
+ - total_train_batch_size: 32
45
+ - total_eval_batch_size: 64
46
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 3
50
+
51
+ ### Training results
52
+
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - PEFT 0.15.2
58
+ - Transformers 4.52.4
59
+ - Pytorch 2.7.0+cu126
60
+ - Datasets 3.6.0
61
+ - Tokenizers 0.21.1
csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "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": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "k_proj",
29
+ "up_proj",
30
+ "o_proj",
31
+ "down_proj",
32
+ "v_proj",
33
+ "q_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.4199451468745933e+17,
4
+ "train_loss": 0.24831230267168233,
5
+ "train_runtime": 397.5389,
6
+ "train_samples_per_second": 75.464,
7
+ "train_steps_per_second": 2.362
8
+ }
csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "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": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "k_proj",
29
+ "up_proj",
30
+ "o_proj",
31
+ "down_proj",
32
+ "v_proj",
33
+ "q_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eom_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|eot_id|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": "<|eot_id|>"
26
+ }
csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/tokenizer_config.json ADDED
@@ -0,0 +1,2076 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<|eom_id|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ }
2059
+ },
2060
+ "additional_special_tokens": [
2061
+ "<|eom_id|>"
2062
+ ],
2063
+ "bos_token": "<|begin_of_text|>",
2064
+ "clean_up_tokenization_spaces": true,
2065
+ "eos_token": "<|eot_id|>",
2066
+ "extra_special_tokens": {},
2067
+ "model_input_names": [
2068
+ "input_ids",
2069
+ "attention_mask"
2070
+ ],
2071
+ "model_max_length": 1000000000000000019884624838656,
2072
+ "pad_token": "<|eot_id|>",
2073
+ "padding_side": "right",
2074
+ "split_special_tokens": false,
2075
+ "tokenizer_class": "PreTrainedTokenizer"
2076
+ }
csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/trainer_state.json ADDED
@@ -0,0 +1,685 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 939,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.03194888178913738,
14
+ "grad_norm": 3.3638806343078613,
15
+ "learning_rate": 9.574468085106384e-07,
16
+ "loss": 0.584,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.06389776357827476,
21
+ "grad_norm": 5.313608646392822,
22
+ "learning_rate": 2.021276595744681e-06,
23
+ "loss": 0.6545,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.09584664536741214,
28
+ "grad_norm": 5.749417781829834,
29
+ "learning_rate": 3.0851063829787237e-06,
30
+ "loss": 0.6041,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.12779552715654952,
35
+ "grad_norm": 6.4460344314575195,
36
+ "learning_rate": 4.148936170212766e-06,
37
+ "loss": 0.6218,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.1597444089456869,
42
+ "grad_norm": 3.865777015686035,
43
+ "learning_rate": 5.212765957446809e-06,
44
+ "loss": 0.5896,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.19169329073482427,
49
+ "grad_norm": 3.308546543121338,
50
+ "learning_rate": 6.276595744680851e-06,
51
+ "loss": 0.4319,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.22364217252396165,
56
+ "grad_norm": 2.443190097808838,
57
+ "learning_rate": 7.340425531914894e-06,
58
+ "loss": 0.3147,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.25559105431309903,
63
+ "grad_norm": 2.9960899353027344,
64
+ "learning_rate": 8.404255319148937e-06,
65
+ "loss": 0.3473,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.28753993610223644,
70
+ "grad_norm": 1.943822979927063,
71
+ "learning_rate": 9.46808510638298e-06,
72
+ "loss": 0.3431,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.3194888178913738,
77
+ "grad_norm": 2.0522427558898926,
78
+ "learning_rate": 9.999136119166803e-06,
79
+ "loss": 0.3306,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.3514376996805112,
84
+ "grad_norm": 2.008436441421509,
85
+ "learning_rate": 9.9922268634943e-06,
86
+ "loss": 0.37,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.38338658146964855,
91
+ "grad_norm": 2.1567893028259277,
92
+ "learning_rate": 9.978417901361958e-06,
93
+ "loss": 0.3488,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.41533546325878595,
98
+ "grad_norm": 2.1556904315948486,
99
+ "learning_rate": 9.95772831799724e-06,
100
+ "loss": 0.3809,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.4472843450479233,
105
+ "grad_norm": 2.0375113487243652,
106
+ "learning_rate": 9.930186708264902e-06,
107
+ "loss": 0.3194,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.4792332268370607,
112
+ "grad_norm": 2.677859306335449,
113
+ "learning_rate": 9.895831137146319e-06,
114
+ "loss": 0.3024,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.5111821086261981,
119
+ "grad_norm": 3.1313719749450684,
120
+ "learning_rate": 9.854709087130261e-06,
121
+ "loss": 0.3068,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.5431309904153354,
126
+ "grad_norm": 1.9139297008514404,
127
+ "learning_rate": 9.80687739258782e-06,
128
+ "loss": 0.2974,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.5750798722044729,
133
+ "grad_norm": 2.1181929111480713,
134
+ "learning_rate": 9.7524021612222e-06,
135
+ "loss": 0.3032,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.6070287539936102,
140
+ "grad_norm": 3.785930633544922,
141
+ "learning_rate": 9.691358682701927e-06,
142
+ "loss": 0.2976,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.6389776357827476,
147
+ "grad_norm": 3.5499579906463623,
148
+ "learning_rate": 9.623831324603755e-06,
149
+ "loss": 0.2954,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.670926517571885,
154
+ "grad_norm": 2.3221206665039062,
155
+ "learning_rate": 9.549913415809084e-06,
156
+ "loss": 0.2869,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.7028753993610224,
161
+ "grad_norm": 1.9535017013549805,
162
+ "learning_rate": 9.469707117515068e-06,
163
+ "loss": 0.3024,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.7348242811501597,
168
+ "grad_norm": 2.6838748455047607,
169
+ "learning_rate": 9.383323282038632e-06,
170
+ "loss": 0.2958,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.7667731629392971,
175
+ "grad_norm": 1.966650366783142,
176
+ "learning_rate": 9.29088129960862e-06,
177
+ "loss": 0.2811,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.7987220447284346,
182
+ "grad_norm": 4.060133934020996,
183
+ "learning_rate": 9.192508933357753e-06,
184
+ "loss": 0.2515,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.8306709265175719,
189
+ "grad_norm": 2.4708683490753174,
190
+ "learning_rate": 9.088342142742493e-06,
191
+ "loss": 0.2964,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.8626198083067093,
196
+ "grad_norm": 3.6799099445343018,
197
+ "learning_rate": 8.978524895634842e-06,
198
+ "loss": 0.3039,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.8945686900958466,
203
+ "grad_norm": 3.000821828842163,
204
+ "learning_rate": 8.86320896934581e-06,
205
+ "loss": 0.3146,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.9265175718849841,
210
+ "grad_norm": 2.4160258769989014,
211
+ "learning_rate": 8.742553740855507e-06,
212
+ "loss": 0.3276,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.9584664536741214,
217
+ "grad_norm": 2.8584442138671875,
218
+ "learning_rate": 8.616725966539831e-06,
219
+ "loss": 0.3105,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.9904153354632588,
224
+ "grad_norm": 2.9464054107666016,
225
+ "learning_rate": 8.485899551698166e-06,
226
+ "loss": 0.2819,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 1.0223642172523961,
231
+ "grad_norm": 3.89704966545105,
232
+ "learning_rate": 8.350255310200611e-06,
233
+ "loss": 0.242,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 1.0543130990415335,
238
+ "grad_norm": 3.0110085010528564,
239
+ "learning_rate": 8.209980714586955e-06,
240
+ "loss": 0.2555,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 1.0862619808306708,
245
+ "grad_norm": 3.9178524017333984,
246
+ "learning_rate": 8.065269636962765e-06,
247
+ "loss": 0.2421,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 1.1182108626198084,
252
+ "grad_norm": 3.428340196609497,
253
+ "learning_rate": 7.916322081050708e-06,
254
+ "loss": 0.2937,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 1.1501597444089458,
259
+ "grad_norm": 2.2544026374816895,
260
+ "learning_rate": 7.76334390576742e-06,
261
+ "loss": 0.2694,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 1.182108626198083,
266
+ "grad_norm": 2.596172332763672,
267
+ "learning_rate": 7.60654654070796e-06,
268
+ "loss": 0.2464,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 1.2140575079872205,
273
+ "grad_norm": 3.9734742641448975,
274
+ "learning_rate": 7.446146693931111e-06,
275
+ "loss": 0.2318,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 1.2460063897763578,
280
+ "grad_norm": 3.436984062194824,
281
+ "learning_rate": 7.282366052449351e-06,
282
+ "loss": 0.2052,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 1.2779552715654952,
287
+ "grad_norm": 4.291993618011475,
288
+ "learning_rate": 7.115430975837457e-06,
289
+ "loss": 0.2335,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 1.3099041533546325,
294
+ "grad_norm": 3.5695717334747314,
295
+ "learning_rate": 6.945572183383229e-06,
296
+ "loss": 0.2119,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 1.34185303514377,
301
+ "grad_norm": 5.036863803863525,
302
+ "learning_rate": 6.773024435212678e-06,
303
+ "loss": 0.2489,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 1.3738019169329074,
308
+ "grad_norm": 4.83351993560791,
309
+ "learning_rate": 6.598026207830428e-06,
310
+ "loss": 0.2323,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 1.4057507987220448,
315
+ "grad_norm": 3.500155210494995,
316
+ "learning_rate": 6.4208193645237314e-06,
317
+ "loss": 0.2528,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 1.4376996805111821,
322
+ "grad_norm": 4.529000282287598,
323
+ "learning_rate": 6.241648821085666e-06,
324
+ "loss": 0.2303,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 1.4696485623003195,
329
+ "grad_norm": 1.649246096611023,
330
+ "learning_rate": 6.060762207319479e-06,
331
+ "loss": 0.2117,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 1.5015974440894568,
336
+ "grad_norm": 5.397870063781738,
337
+ "learning_rate": 5.878409524791931e-06,
338
+ "loss": 0.212,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 1.5335463258785942,
343
+ "grad_norm": 4.360300064086914,
344
+ "learning_rate": 5.694842801308651e-06,
345
+ "loss": 0.2395,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 1.5654952076677318,
350
+ "grad_norm": 5.323873043060303,
351
+ "learning_rate": 5.510315742589042e-06,
352
+ "loss": 0.2089,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.5974440894568689,
357
+ "grad_norm": 2.8005800247192383,
358
+ "learning_rate": 5.325083381622165e-06,
359
+ "loss": 0.1908,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.6293929712460065,
364
+ "grad_norm": 4.072391510009766,
365
+ "learning_rate": 5.139401726188208e-06,
366
+ "loss": 0.1869,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 1.6613418530351438,
371
+ "grad_norm": 4.611303329467773,
372
+ "learning_rate": 4.953527405032723e-06,
373
+ "loss": 0.1866,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 1.6932907348242812,
378
+ "grad_norm": 4.1683430671691895,
379
+ "learning_rate": 4.767717313182611e-06,
380
+ "loss": 0.2438,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 1.7252396166134185,
385
+ "grad_norm": 5.027125358581543,
386
+ "learning_rate": 4.582228256894093e-06,
387
+ "loss": 0.2268,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.7571884984025559,
392
+ "grad_norm": 3.748115062713623,
393
+ "learning_rate": 4.397316598723385e-06,
394
+ "loss": 0.2523,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 1.7891373801916934,
399
+ "grad_norm": 3.894868850708008,
400
+ "learning_rate": 4.2132379032105695e-06,
401
+ "loss": 0.1895,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 1.8210862619808306,
406
+ "grad_norm": 4.707362174987793,
407
+ "learning_rate": 4.030246583666437e-06,
408
+ "loss": 0.1883,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 1.8530351437699681,
413
+ "grad_norm": 4.535495281219482,
414
+ "learning_rate": 3.848595550550401e-06,
415
+ "loss": 0.2061,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 1.8849840255591053,
420
+ "grad_norm": 5.2252044677734375,
421
+ "learning_rate": 3.668535861925509e-06,
422
+ "loss": 0.1867,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 1.9169329073482428,
427
+ "grad_norm": 4.363283634185791,
428
+ "learning_rate": 3.4903163764736104e-06,
429
+ "loss": 0.1621,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 1.9488817891373802,
434
+ "grad_norm": 4.024950981140137,
435
+ "learning_rate": 3.314183409550293e-06,
436
+ "loss": 0.1941,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 1.9808306709265175,
441
+ "grad_norm": 3.9747886657714844,
442
+ "learning_rate": 3.140380392754901e-06,
443
+ "loss": 0.2098,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 2.012779552715655,
448
+ "grad_norm": 2.5899300575256348,
449
+ "learning_rate": 2.969147537486175e-06,
450
+ "loss": 0.1673,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 2.0447284345047922,
455
+ "grad_norm": 5.285285472869873,
456
+ "learning_rate": 2.800721502948506e-06,
457
+ "loss": 0.1983,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 2.07667731629393,
462
+ "grad_norm": 4.855522632598877,
463
+ "learning_rate": 2.635335069067617e-06,
464
+ "loss": 0.174,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 2.108626198083067,
469
+ "grad_norm": 2.8326239585876465,
470
+ "learning_rate": 2.4732168147677927e-06,
471
+ "loss": 0.1396,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 2.1405750798722045,
476
+ "grad_norm": 4.1815409660339355,
477
+ "learning_rate": 2.314590802055232e-06,
478
+ "loss": 0.1603,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 2.1725239616613417,
483
+ "grad_norm": 4.818963050842285,
484
+ "learning_rate": 2.159676266344222e-06,
485
+ "loss": 0.162,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 2.2044728434504792,
490
+ "grad_norm": 3.489180088043213,
491
+ "learning_rate": 2.0086873134540626e-06,
492
+ "loss": 0.14,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 2.236421725239617,
497
+ "grad_norm": 5.792989253997803,
498
+ "learning_rate": 1.8618326236955908e-06,
499
+ "loss": 0.1582,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 2.268370607028754,
504
+ "grad_norm": 7.210322856903076,
505
+ "learning_rate": 1.7193151634562071e-06,
506
+ "loss": 0.1674,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 2.3003194888178915,
511
+ "grad_norm": 3.8412885665893555,
512
+ "learning_rate": 1.581331904682089e-06,
513
+ "loss": 0.1357,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 2.3322683706070286,
518
+ "grad_norm": 7.757709503173828,
519
+ "learning_rate": 1.4480735526452427e-06,
520
+ "loss": 0.2142,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 2.364217252396166,
525
+ "grad_norm": 3.101224184036255,
526
+ "learning_rate": 1.319724282371664e-06,
527
+ "loss": 0.1787,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 2.3961661341853033,
532
+ "grad_norm": 6.599401950836182,
533
+ "learning_rate": 1.1964614840949002e-06,
534
+ "loss": 0.18,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 2.428115015974441,
539
+ "grad_norm": 4.533216953277588,
540
+ "learning_rate": 1.078455518086784e-06,
541
+ "loss": 0.1343,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 2.460063897763578,
546
+ "grad_norm": 4.923655986785889,
547
+ "learning_rate": 9.658694792042284e-07,
548
+ "loss": 0.1753,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 2.4920127795527156,
553
+ "grad_norm": 7.162405967712402,
554
+ "learning_rate": 8.58858971477457e-07,
555
+ "loss": 0.1883,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 2.523961661341853,
560
+ "grad_norm": 4.407649040222168,
561
+ "learning_rate": 7.575718930512516e-07,
562
+ "loss": 0.1424,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 2.5559105431309903,
567
+ "grad_norm": 3.630793333053589,
568
+ "learning_rate": 6.621482317764105e-07,
569
+ "loss": 0.1599,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 2.587859424920128,
574
+ "grad_norm": 4.121254920959473,
575
+ "learning_rate": 5.727198717339511e-07,
576
+ "loss": 0.1815,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 2.619808306709265,
581
+ "grad_norm": 5.419968605041504,
582
+ "learning_rate": 4.894104109594466e-07,
583
+ "loss": 0.1513,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 2.6517571884984026,
588
+ "grad_norm": 5.140281677246094,
589
+ "learning_rate": 4.123349906194357e-07,
590
+ "loss": 0.1183,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 2.68370607028754,
595
+ "grad_norm": 4.626114368438721,
596
+ "learning_rate": 3.416001358759635e-07,
597
+ "loss": 0.1448,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 2.7156549520766773,
602
+ "grad_norm": 6.971862316131592,
603
+ "learning_rate": 2.7730360865923954e-07,
604
+ "loss": 0.1515,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 2.747603833865815,
609
+ "grad_norm": 6.2547712326049805,
610
+ "learning_rate": 2.1953427255185122e-07,
611
+ "loss": 0.1712,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 2.779552715654952,
616
+ "grad_norm": 3.562861442565918,
617
+ "learning_rate": 1.6837196997130434e-07,
618
+ "loss": 0.1712,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 2.8115015974440896,
623
+ "grad_norm": 4.5032124519348145,
624
+ "learning_rate": 1.2388741182062348e-07,
625
+ "loss": 0.1648,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 2.8434504792332267,
630
+ "grad_norm": 5.417168140411377,
631
+ "learning_rate": 8.614207975952083e-08,
632
+ "loss": 0.1899,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 2.8753993610223643,
637
+ "grad_norm": 6.31259298324585,
638
+ "learning_rate": 5.518814123121885e-08,
639
+ "loss": 0.1264,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 2.9073482428115014,
644
+ "grad_norm": 2.681699514389038,
645
+ "learning_rate": 3.10683773623488e-08,
646
+ "loss": 0.135,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 2.939297124600639,
651
+ "grad_norm": 4.384430885314941,
652
+ "learning_rate": 1.3816123835588835e-08,
653
+ "loss": 0.1274,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 2.9712460063897765,
658
+ "grad_norm": 3.9094367027282715,
659
+ "learning_rate": 3.4552248167507576e-09,
660
+ "loss": 0.1743,
661
+ "step": 930
662
+ }
663
+ ],
664
+ "logging_steps": 10,
665
+ "max_steps": 939,
666
+ "num_input_tokens_seen": 0,
667
+ "num_train_epochs": 3,
668
+ "save_steps": 2000,
669
+ "stateful_callbacks": {
670
+ "TrainerControl": {
671
+ "args": {
672
+ "should_epoch_stop": false,
673
+ "should_evaluate": false,
674
+ "should_log": false,
675
+ "should_save": true,
676
+ "should_training_stop": true
677
+ },
678
+ "attributes": {}
679
+ }
680
+ },
681
+ "total_flos": 1.4199451468745933e+17,
682
+ "train_batch_size": 4,
683
+ "trial_name": null,
684
+ "trial_params": null
685
+ }
csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eom_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|eot_id|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": "<|eot_id|>"
26
+ }
csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/tokenizer_config.json ADDED
@@ -0,0 +1,2076 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<|eom_id|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ }
2059
+ },
2060
+ "additional_special_tokens": [
2061
+ "<|eom_id|>"
2062
+ ],
2063
+ "bos_token": "<|begin_of_text|>",
2064
+ "clean_up_tokenization_spaces": true,
2065
+ "eos_token": "<|eot_id|>",
2066
+ "extra_special_tokens": {},
2067
+ "model_input_names": [
2068
+ "input_ids",
2069
+ "attention_mask"
2070
+ ],
2071
+ "model_max_length": 1000000000000000019884624838656,
2072
+ "pad_token": "<|eot_id|>",
2073
+ "padding_side": "right",
2074
+ "split_special_tokens": false,
2075
+ "tokenizer_class": "PreTrainedTokenizer"
2076
+ }
csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.4199451468745933e+17,
4
+ "train_loss": 0.24831230267168233,
5
+ "train_runtime": 397.5389,
6
+ "train_samples_per_second": 75.464,
7
+ "train_steps_per_second": 2.362
8
+ }
csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/trainer_log.jsonl ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 939, "loss": 0.584, "lr": 9.574468085106384e-07, "epoch": 0.03194888178913738, "percentage": 1.06, "elapsed_time": "0:00:05", "remaining_time": "0:07:53"}
2
+ {"current_steps": 20, "total_steps": 939, "loss": 0.6545, "lr": 2.021276595744681e-06, "epoch": 0.06389776357827476, "percentage": 2.13, "elapsed_time": "0:00:09", "remaining_time": "0:07:03"}
3
+ {"current_steps": 30, "total_steps": 939, "loss": 0.6041, "lr": 3.0851063829787237e-06, "epoch": 0.09584664536741214, "percentage": 3.19, "elapsed_time": "0:00:13", "remaining_time": "0:06:43"}
4
+ {"current_steps": 40, "total_steps": 939, "loss": 0.6218, "lr": 4.148936170212766e-06, "epoch": 0.12779552715654952, "percentage": 4.26, "elapsed_time": "0:00:17", "remaining_time": "0:06:31"}
5
+ {"current_steps": 50, "total_steps": 939, "loss": 0.5896, "lr": 5.212765957446809e-06, "epoch": 0.1597444089456869, "percentage": 5.32, "elapsed_time": "0:00:21", "remaining_time": "0:06:23"}
6
+ {"current_steps": 60, "total_steps": 939, "loss": 0.4319, "lr": 6.276595744680851e-06, "epoch": 0.19169329073482427, "percentage": 6.39, "elapsed_time": "0:00:25", "remaining_time": "0:06:16"}
7
+ {"current_steps": 70, "total_steps": 939, "loss": 0.3147, "lr": 7.340425531914894e-06, "epoch": 0.22364217252396165, "percentage": 7.45, "elapsed_time": "0:00:29", "remaining_time": "0:06:09"}
8
+ {"current_steps": 80, "total_steps": 939, "loss": 0.3473, "lr": 8.404255319148937e-06, "epoch": 0.25559105431309903, "percentage": 8.52, "elapsed_time": "0:00:33", "remaining_time": "0:06:03"}
9
+ {"current_steps": 90, "total_steps": 939, "loss": 0.3431, "lr": 9.46808510638298e-06, "epoch": 0.28753993610223644, "percentage": 9.58, "elapsed_time": "0:00:37", "remaining_time": "0:05:57"}
10
+ {"current_steps": 100, "total_steps": 939, "loss": 0.3306, "lr": 9.999136119166803e-06, "epoch": 0.3194888178913738, "percentage": 10.65, "elapsed_time": "0:00:41", "remaining_time": "0:05:52"}
11
+ {"current_steps": 110, "total_steps": 939, "loss": 0.37, "lr": 9.9922268634943e-06, "epoch": 0.3514376996805112, "percentage": 11.71, "elapsed_time": "0:00:46", "remaining_time": "0:05:47"}
12
+ {"current_steps": 120, "total_steps": 939, "loss": 0.3488, "lr": 9.978417901361958e-06, "epoch": 0.38338658146964855, "percentage": 12.78, "elapsed_time": "0:00:50", "remaining_time": "0:05:42"}
13
+ {"current_steps": 130, "total_steps": 939, "loss": 0.3809, "lr": 9.95772831799724e-06, "epoch": 0.41533546325878595, "percentage": 13.84, "elapsed_time": "0:00:54", "remaining_time": "0:05:37"}
14
+ {"current_steps": 140, "total_steps": 939, "loss": 0.3194, "lr": 9.930186708264902e-06, "epoch": 0.4472843450479233, "percentage": 14.91, "elapsed_time": "0:00:58", "remaining_time": "0:05:32"}
15
+ {"current_steps": 150, "total_steps": 939, "loss": 0.3024, "lr": 9.895831137146319e-06, "epoch": 0.4792332268370607, "percentage": 15.97, "elapsed_time": "0:01:02", "remaining_time": "0:05:28"}
16
+ {"current_steps": 160, "total_steps": 939, "loss": 0.3068, "lr": 9.854709087130261e-06, "epoch": 0.5111821086261981, "percentage": 17.04, "elapsed_time": "0:01:06", "remaining_time": "0:05:23"}
17
+ {"current_steps": 170, "total_steps": 939, "loss": 0.2974, "lr": 9.80687739258782e-06, "epoch": 0.5431309904153354, "percentage": 18.1, "elapsed_time": "0:01:10", "remaining_time": "0:05:19"}
18
+ {"current_steps": 180, "total_steps": 939, "loss": 0.3032, "lr": 9.7524021612222e-06, "epoch": 0.5750798722044729, "percentage": 19.17, "elapsed_time": "0:01:14", "remaining_time": "0:05:14"}
19
+ {"current_steps": 190, "total_steps": 939, "loss": 0.2976, "lr": 9.691358682701927e-06, "epoch": 0.6070287539936102, "percentage": 20.23, "elapsed_time": "0:01:18", "remaining_time": "0:05:10"}
20
+ {"current_steps": 200, "total_steps": 939, "loss": 0.2954, "lr": 9.623831324603755e-06, "epoch": 0.6389776357827476, "percentage": 21.3, "elapsed_time": "0:01:22", "remaining_time": "0:05:06"}
21
+ {"current_steps": 210, "total_steps": 939, "loss": 0.2869, "lr": 9.549913415809084e-06, "epoch": 0.670926517571885, "percentage": 22.36, "elapsed_time": "0:01:26", "remaining_time": "0:05:01"}
22
+ {"current_steps": 220, "total_steps": 939, "loss": 0.3024, "lr": 9.469707117515068e-06, "epoch": 0.7028753993610224, "percentage": 23.43, "elapsed_time": "0:01:31", "remaining_time": "0:04:57"}
23
+ {"current_steps": 230, "total_steps": 939, "loss": 0.2958, "lr": 9.383323282038632e-06, "epoch": 0.7348242811501597, "percentage": 24.49, "elapsed_time": "0:01:35", "remaining_time": "0:04:53"}
24
+ {"current_steps": 240, "total_steps": 939, "loss": 0.2811, "lr": 9.29088129960862e-06, "epoch": 0.7667731629392971, "percentage": 25.56, "elapsed_time": "0:01:39", "remaining_time": "0:04:49"}
25
+ {"current_steps": 250, "total_steps": 939, "loss": 0.2515, "lr": 9.192508933357753e-06, "epoch": 0.7987220447284346, "percentage": 26.62, "elapsed_time": "0:01:43", "remaining_time": "0:04:44"}
26
+ {"current_steps": 260, "total_steps": 939, "loss": 0.2964, "lr": 9.088342142742493e-06, "epoch": 0.8306709265175719, "percentage": 27.69, "elapsed_time": "0:01:47", "remaining_time": "0:04:40"}
27
+ {"current_steps": 270, "total_steps": 939, "loss": 0.3039, "lr": 8.978524895634842e-06, "epoch": 0.8626198083067093, "percentage": 28.75, "elapsed_time": "0:01:51", "remaining_time": "0:04:36"}
28
+ {"current_steps": 280, "total_steps": 939, "loss": 0.3146, "lr": 8.86320896934581e-06, "epoch": 0.8945686900958466, "percentage": 29.82, "elapsed_time": "0:01:55", "remaining_time": "0:04:32"}
29
+ {"current_steps": 290, "total_steps": 939, "loss": 0.3276, "lr": 8.742553740855507e-06, "epoch": 0.9265175718849841, "percentage": 30.88, "elapsed_time": "0:01:59", "remaining_time": "0:04:28"}
30
+ {"current_steps": 300, "total_steps": 939, "loss": 0.3105, "lr": 8.616725966539831e-06, "epoch": 0.9584664536741214, "percentage": 31.95, "elapsed_time": "0:02:03", "remaining_time": "0:04:24"}
31
+ {"current_steps": 310, "total_steps": 939, "loss": 0.2819, "lr": 8.485899551698166e-06, "epoch": 0.9904153354632588, "percentage": 33.01, "elapsed_time": "0:02:08", "remaining_time": "0:04:19"}
32
+ {"current_steps": 320, "total_steps": 939, "loss": 0.242, "lr": 8.350255310200611e-06, "epoch": 1.0223642172523961, "percentage": 34.08, "elapsed_time": "0:02:12", "remaining_time": "0:04:16"}
33
+ {"current_steps": 330, "total_steps": 939, "loss": 0.2555, "lr": 8.209980714586955e-06, "epoch": 1.0543130990415335, "percentage": 35.14, "elapsed_time": "0:02:16", "remaining_time": "0:04:12"}
34
+ {"current_steps": 340, "total_steps": 939, "loss": 0.2421, "lr": 8.065269636962765e-06, "epoch": 1.0862619808306708, "percentage": 36.21, "elapsed_time": "0:02:20", "remaining_time": "0:04:07"}
35
+ {"current_steps": 350, "total_steps": 939, "loss": 0.2937, "lr": 7.916322081050708e-06, "epoch": 1.1182108626198084, "percentage": 37.27, "elapsed_time": "0:02:24", "remaining_time": "0:04:03"}
36
+ {"current_steps": 360, "total_steps": 939, "loss": 0.2694, "lr": 7.76334390576742e-06, "epoch": 1.1501597444089458, "percentage": 38.34, "elapsed_time": "0:02:28", "remaining_time": "0:03:59"}
37
+ {"current_steps": 370, "total_steps": 939, "loss": 0.2464, "lr": 7.60654654070796e-06, "epoch": 1.182108626198083, "percentage": 39.4, "elapsed_time": "0:02:32", "remaining_time": "0:03:55"}
38
+ {"current_steps": 380, "total_steps": 939, "loss": 0.2318, "lr": 7.446146693931111e-06, "epoch": 1.2140575079872205, "percentage": 40.47, "elapsed_time": "0:02:37", "remaining_time": "0:03:51"}
39
+ {"current_steps": 390, "total_steps": 939, "loss": 0.2052, "lr": 7.282366052449351e-06, "epoch": 1.2460063897763578, "percentage": 41.53, "elapsed_time": "0:02:41", "remaining_time": "0:03:46"}
40
+ {"current_steps": 400, "total_steps": 939, "loss": 0.2335, "lr": 7.115430975837457e-06, "epoch": 1.2779552715654952, "percentage": 42.6, "elapsed_time": "0:02:45", "remaining_time": "0:03:42"}
41
+ {"current_steps": 410, "total_steps": 939, "loss": 0.2119, "lr": 6.945572183383229e-06, "epoch": 1.3099041533546325, "percentage": 43.66, "elapsed_time": "0:02:49", "remaining_time": "0:03:38"}
42
+ {"current_steps": 420, "total_steps": 939, "loss": 0.2489, "lr": 6.773024435212678e-06, "epoch": 1.34185303514377, "percentage": 44.73, "elapsed_time": "0:02:53", "remaining_time": "0:03:34"}
43
+ {"current_steps": 430, "total_steps": 939, "loss": 0.2323, "lr": 6.598026207830428e-06, "epoch": 1.3738019169329074, "percentage": 45.79, "elapsed_time": "0:02:57", "remaining_time": "0:03:30"}
44
+ {"current_steps": 440, "total_steps": 939, "loss": 0.2528, "lr": 6.4208193645237314e-06, "epoch": 1.4057507987220448, "percentage": 46.86, "elapsed_time": "0:03:01", "remaining_time": "0:03:26"}
45
+ {"current_steps": 450, "total_steps": 939, "loss": 0.2303, "lr": 6.241648821085666e-06, "epoch": 1.4376996805111821, "percentage": 47.92, "elapsed_time": "0:03:05", "remaining_time": "0:03:21"}
46
+ {"current_steps": 460, "total_steps": 939, "loss": 0.2117, "lr": 6.060762207319479e-06, "epoch": 1.4696485623003195, "percentage": 48.99, "elapsed_time": "0:03:09", "remaining_time": "0:03:17"}
47
+ {"current_steps": 470, "total_steps": 939, "loss": 0.212, "lr": 5.878409524791931e-06, "epoch": 1.5015974440894568, "percentage": 50.05, "elapsed_time": "0:03:14", "remaining_time": "0:03:13"}
48
+ {"current_steps": 480, "total_steps": 939, "loss": 0.2395, "lr": 5.694842801308651e-06, "epoch": 1.5335463258785942, "percentage": 51.12, "elapsed_time": "0:03:18", "remaining_time": "0:03:09"}
49
+ {"current_steps": 490, "total_steps": 939, "loss": 0.2089, "lr": 5.510315742589042e-06, "epoch": 1.5654952076677318, "percentage": 52.18, "elapsed_time": "0:03:22", "remaining_time": "0:03:05"}
50
+ {"current_steps": 500, "total_steps": 939, "loss": 0.1908, "lr": 5.325083381622165e-06, "epoch": 1.5974440894568689, "percentage": 53.25, "elapsed_time": "0:03:26", "remaining_time": "0:03:01"}
51
+ {"current_steps": 510, "total_steps": 939, "loss": 0.1869, "lr": 5.139401726188208e-06, "epoch": 1.6293929712460065, "percentage": 54.31, "elapsed_time": "0:03:30", "remaining_time": "0:02:56"}
52
+ {"current_steps": 520, "total_steps": 939, "loss": 0.1866, "lr": 4.953527405032723e-06, "epoch": 1.6613418530351438, "percentage": 55.38, "elapsed_time": "0:03:34", "remaining_time": "0:02:52"}
53
+ {"current_steps": 530, "total_steps": 939, "loss": 0.2438, "lr": 4.767717313182611e-06, "epoch": 1.6932907348242812, "percentage": 56.44, "elapsed_time": "0:03:38", "remaining_time": "0:02:48"}
54
+ {"current_steps": 540, "total_steps": 939, "loss": 0.2268, "lr": 4.582228256894093e-06, "epoch": 1.7252396166134185, "percentage": 57.51, "elapsed_time": "0:03:42", "remaining_time": "0:02:44"}
55
+ {"current_steps": 550, "total_steps": 939, "loss": 0.2523, "lr": 4.397316598723385e-06, "epoch": 1.7571884984025559, "percentage": 58.57, "elapsed_time": "0:03:46", "remaining_time": "0:02:40"}
56
+ {"current_steps": 560, "total_steps": 939, "loss": 0.1895, "lr": 4.2132379032105695e-06, "epoch": 1.7891373801916934, "percentage": 59.64, "elapsed_time": "0:03:50", "remaining_time": "0:02:36"}
57
+ {"current_steps": 570, "total_steps": 939, "loss": 0.1883, "lr": 4.030246583666437e-06, "epoch": 1.8210862619808306, "percentage": 60.7, "elapsed_time": "0:03:54", "remaining_time": "0:02:32"}
58
+ {"current_steps": 580, "total_steps": 939, "loss": 0.2061, "lr": 3.848595550550401e-06, "epoch": 1.8530351437699681, "percentage": 61.77, "elapsed_time": "0:03:58", "remaining_time": "0:02:27"}
59
+ {"current_steps": 590, "total_steps": 939, "loss": 0.1867, "lr": 3.668535861925509e-06, "epoch": 1.8849840255591053, "percentage": 62.83, "elapsed_time": "0:04:03", "remaining_time": "0:02:23"}
60
+ {"current_steps": 600, "total_steps": 939, "loss": 0.1621, "lr": 3.4903163764736104e-06, "epoch": 1.9169329073482428, "percentage": 63.9, "elapsed_time": "0:04:07", "remaining_time": "0:02:19"}
61
+ {"current_steps": 610, "total_steps": 939, "loss": 0.1941, "lr": 3.314183409550293e-06, "epoch": 1.9488817891373802, "percentage": 64.96, "elapsed_time": "0:04:11", "remaining_time": "0:02:15"}
62
+ {"current_steps": 620, "total_steps": 939, "loss": 0.2098, "lr": 3.140380392754901e-06, "epoch": 1.9808306709265175, "percentage": 66.03, "elapsed_time": "0:04:15", "remaining_time": "0:02:11"}
63
+ {"current_steps": 630, "total_steps": 939, "loss": 0.1673, "lr": 2.969147537486175e-06, "epoch": 2.012779552715655, "percentage": 67.09, "elapsed_time": "0:04:19", "remaining_time": "0:02:07"}
64
+ {"current_steps": 640, "total_steps": 939, "loss": 0.1983, "lr": 2.800721502948506e-06, "epoch": 2.0447284345047922, "percentage": 68.16, "elapsed_time": "0:04:23", "remaining_time": "0:02:03"}
65
+ {"current_steps": 650, "total_steps": 939, "loss": 0.174, "lr": 2.635335069067617e-06, "epoch": 2.07667731629393, "percentage": 69.22, "elapsed_time": "0:04:27", "remaining_time": "0:01:59"}
66
+ {"current_steps": 660, "total_steps": 939, "loss": 0.1396, "lr": 2.4732168147677927e-06, "epoch": 2.108626198083067, "percentage": 70.29, "elapsed_time": "0:04:32", "remaining_time": "0:01:55"}
67
+ {"current_steps": 670, "total_steps": 939, "loss": 0.1603, "lr": 2.314590802055232e-06, "epoch": 2.1405750798722045, "percentage": 71.35, "elapsed_time": "0:04:36", "remaining_time": "0:01:50"}
68
+ {"current_steps": 680, "total_steps": 939, "loss": 0.162, "lr": 2.159676266344222e-06, "epoch": 2.1725239616613417, "percentage": 72.42, "elapsed_time": "0:04:40", "remaining_time": "0:01:46"}
69
+ {"current_steps": 690, "total_steps": 939, "loss": 0.14, "lr": 2.0086873134540626e-06, "epoch": 2.2044728434504792, "percentage": 73.48, "elapsed_time": "0:04:44", "remaining_time": "0:01:42"}
70
+ {"current_steps": 700, "total_steps": 939, "loss": 0.1582, "lr": 1.8618326236955908e-06, "epoch": 2.236421725239617, "percentage": 74.55, "elapsed_time": "0:04:48", "remaining_time": "0:01:38"}
71
+ {"current_steps": 710, "total_steps": 939, "loss": 0.1674, "lr": 1.7193151634562071e-06, "epoch": 2.268370607028754, "percentage": 75.61, "elapsed_time": "0:04:52", "remaining_time": "0:01:34"}
72
+ {"current_steps": 720, "total_steps": 939, "loss": 0.1357, "lr": 1.581331904682089e-06, "epoch": 2.3003194888178915, "percentage": 76.68, "elapsed_time": "0:04:56", "remaining_time": "0:01:30"}
73
+ {"current_steps": 730, "total_steps": 939, "loss": 0.2142, "lr": 1.4480735526452427e-06, "epoch": 2.3322683706070286, "percentage": 77.74, "elapsed_time": "0:05:00", "remaining_time": "0:01:26"}
74
+ {"current_steps": 740, "total_steps": 939, "loss": 0.1787, "lr": 1.319724282371664e-06, "epoch": 2.364217252396166, "percentage": 78.81, "elapsed_time": "0:05:04", "remaining_time": "0:01:22"}
75
+ {"current_steps": 750, "total_steps": 939, "loss": 0.18, "lr": 1.1964614840949002e-06, "epoch": 2.3961661341853033, "percentage": 79.87, "elapsed_time": "0:05:09", "remaining_time": "0:01:17"}
76
+ {"current_steps": 760, "total_steps": 939, "loss": 0.1343, "lr": 1.078455518086784e-06, "epoch": 2.428115015974441, "percentage": 80.94, "elapsed_time": "0:05:13", "remaining_time": "0:01:13"}
77
+ {"current_steps": 770, "total_steps": 939, "loss": 0.1753, "lr": 9.658694792042284e-07, "epoch": 2.460063897763578, "percentage": 82.0, "elapsed_time": "0:05:17", "remaining_time": "0:01:09"}
78
+ {"current_steps": 780, "total_steps": 939, "loss": 0.1883, "lr": 8.58858971477457e-07, "epoch": 2.4920127795527156, "percentage": 83.07, "elapsed_time": "0:05:21", "remaining_time": "0:01:05"}
79
+ {"current_steps": 790, "total_steps": 939, "loss": 0.1424, "lr": 7.575718930512516e-07, "epoch": 2.523961661341853, "percentage": 84.13, "elapsed_time": "0:05:25", "remaining_time": "0:01:01"}
80
+ {"current_steps": 800, "total_steps": 939, "loss": 0.1599, "lr": 6.621482317764105e-07, "epoch": 2.5559105431309903, "percentage": 85.2, "elapsed_time": "0:05:29", "remaining_time": "0:00:57"}
81
+ {"current_steps": 810, "total_steps": 939, "loss": 0.1815, "lr": 5.727198717339511e-07, "epoch": 2.587859424920128, "percentage": 86.26, "elapsed_time": "0:05:34", "remaining_time": "0:00:53"}
82
+ {"current_steps": 820, "total_steps": 939, "loss": 0.1513, "lr": 4.894104109594466e-07, "epoch": 2.619808306709265, "percentage": 87.33, "elapsed_time": "0:05:38", "remaining_time": "0:00:49"}
83
+ {"current_steps": 830, "total_steps": 939, "loss": 0.1183, "lr": 4.123349906194357e-07, "epoch": 2.6517571884984026, "percentage": 88.39, "elapsed_time": "0:05:42", "remaining_time": "0:00:44"}
84
+ {"current_steps": 840, "total_steps": 939, "loss": 0.1448, "lr": 3.416001358759635e-07, "epoch": 2.68370607028754, "percentage": 89.46, "elapsed_time": "0:05:46", "remaining_time": "0:00:40"}
85
+ {"current_steps": 850, "total_steps": 939, "loss": 0.1515, "lr": 2.7730360865923954e-07, "epoch": 2.7156549520766773, "percentage": 90.52, "elapsed_time": "0:05:50", "remaining_time": "0:00:36"}
86
+ {"current_steps": 860, "total_steps": 939, "loss": 0.1712, "lr": 2.1953427255185122e-07, "epoch": 2.747603833865815, "percentage": 91.59, "elapsed_time": "0:05:54", "remaining_time": "0:00:32"}
87
+ {"current_steps": 870, "total_steps": 939, "loss": 0.1712, "lr": 1.6837196997130434e-07, "epoch": 2.779552715654952, "percentage": 92.65, "elapsed_time": "0:05:58", "remaining_time": "0:00:28"}
88
+ {"current_steps": 880, "total_steps": 939, "loss": 0.1648, "lr": 1.2388741182062348e-07, "epoch": 2.8115015974440896, "percentage": 93.72, "elapsed_time": "0:06:02", "remaining_time": "0:00:24"}
89
+ {"current_steps": 890, "total_steps": 939, "loss": 0.1899, "lr": 8.614207975952083e-08, "epoch": 2.8434504792332267, "percentage": 94.78, "elapsed_time": "0:06:07", "remaining_time": "0:00:20"}
90
+ {"current_steps": 900, "total_steps": 939, "loss": 0.1264, "lr": 5.518814123121885e-08, "epoch": 2.8753993610223643, "percentage": 95.85, "elapsed_time": "0:06:11", "remaining_time": "0:00:16"}
91
+ {"current_steps": 910, "total_steps": 939, "loss": 0.135, "lr": 3.10683773623488e-08, "epoch": 2.9073482428115014, "percentage": 96.91, "elapsed_time": "0:06:15", "remaining_time": "0:00:11"}
92
+ {"current_steps": 920, "total_steps": 939, "loss": 0.1274, "lr": 1.3816123835588835e-08, "epoch": 2.939297124600639, "percentage": 97.98, "elapsed_time": "0:06:19", "remaining_time": "0:00:07"}
93
+ {"current_steps": 930, "total_steps": 939, "loss": 0.1743, "lr": 3.4552248167507576e-09, "epoch": 2.9712460063897765, "percentage": 99.04, "elapsed_time": "0:06:23", "remaining_time": "0:00:03"}
94
+ {"current_steps": 939, "total_steps": 939, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:06:27", "remaining_time": "0:00:00"}
csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/trainer_state.json ADDED
@@ -0,0 +1,694 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 939,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.03194888178913738,
14
+ "grad_norm": 3.3638806343078613,
15
+ "learning_rate": 9.574468085106384e-07,
16
+ "loss": 0.584,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.06389776357827476,
21
+ "grad_norm": 5.313608646392822,
22
+ "learning_rate": 2.021276595744681e-06,
23
+ "loss": 0.6545,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.09584664536741214,
28
+ "grad_norm": 5.749417781829834,
29
+ "learning_rate": 3.0851063829787237e-06,
30
+ "loss": 0.6041,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.12779552715654952,
35
+ "grad_norm": 6.4460344314575195,
36
+ "learning_rate": 4.148936170212766e-06,
37
+ "loss": 0.6218,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.1597444089456869,
42
+ "grad_norm": 3.865777015686035,
43
+ "learning_rate": 5.212765957446809e-06,
44
+ "loss": 0.5896,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.19169329073482427,
49
+ "grad_norm": 3.308546543121338,
50
+ "learning_rate": 6.276595744680851e-06,
51
+ "loss": 0.4319,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.22364217252396165,
56
+ "grad_norm": 2.443190097808838,
57
+ "learning_rate": 7.340425531914894e-06,
58
+ "loss": 0.3147,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.25559105431309903,
63
+ "grad_norm": 2.9960899353027344,
64
+ "learning_rate": 8.404255319148937e-06,
65
+ "loss": 0.3473,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.28753993610223644,
70
+ "grad_norm": 1.943822979927063,
71
+ "learning_rate": 9.46808510638298e-06,
72
+ "loss": 0.3431,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.3194888178913738,
77
+ "grad_norm": 2.0522427558898926,
78
+ "learning_rate": 9.999136119166803e-06,
79
+ "loss": 0.3306,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.3514376996805112,
84
+ "grad_norm": 2.008436441421509,
85
+ "learning_rate": 9.9922268634943e-06,
86
+ "loss": 0.37,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.38338658146964855,
91
+ "grad_norm": 2.1567893028259277,
92
+ "learning_rate": 9.978417901361958e-06,
93
+ "loss": 0.3488,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.41533546325878595,
98
+ "grad_norm": 2.1556904315948486,
99
+ "learning_rate": 9.95772831799724e-06,
100
+ "loss": 0.3809,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.4472843450479233,
105
+ "grad_norm": 2.0375113487243652,
106
+ "learning_rate": 9.930186708264902e-06,
107
+ "loss": 0.3194,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.4792332268370607,
112
+ "grad_norm": 2.677859306335449,
113
+ "learning_rate": 9.895831137146319e-06,
114
+ "loss": 0.3024,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.5111821086261981,
119
+ "grad_norm": 3.1313719749450684,
120
+ "learning_rate": 9.854709087130261e-06,
121
+ "loss": 0.3068,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.5431309904153354,
126
+ "grad_norm": 1.9139297008514404,
127
+ "learning_rate": 9.80687739258782e-06,
128
+ "loss": 0.2974,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.5750798722044729,
133
+ "grad_norm": 2.1181929111480713,
134
+ "learning_rate": 9.7524021612222e-06,
135
+ "loss": 0.3032,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.6070287539936102,
140
+ "grad_norm": 3.785930633544922,
141
+ "learning_rate": 9.691358682701927e-06,
142
+ "loss": 0.2976,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.6389776357827476,
147
+ "grad_norm": 3.5499579906463623,
148
+ "learning_rate": 9.623831324603755e-06,
149
+ "loss": 0.2954,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.670926517571885,
154
+ "grad_norm": 2.3221206665039062,
155
+ "learning_rate": 9.549913415809084e-06,
156
+ "loss": 0.2869,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.7028753993610224,
161
+ "grad_norm": 1.9535017013549805,
162
+ "learning_rate": 9.469707117515068e-06,
163
+ "loss": 0.3024,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.7348242811501597,
168
+ "grad_norm": 2.6838748455047607,
169
+ "learning_rate": 9.383323282038632e-06,
170
+ "loss": 0.2958,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.7667731629392971,
175
+ "grad_norm": 1.966650366783142,
176
+ "learning_rate": 9.29088129960862e-06,
177
+ "loss": 0.2811,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.7987220447284346,
182
+ "grad_norm": 4.060133934020996,
183
+ "learning_rate": 9.192508933357753e-06,
184
+ "loss": 0.2515,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.8306709265175719,
189
+ "grad_norm": 2.4708683490753174,
190
+ "learning_rate": 9.088342142742493e-06,
191
+ "loss": 0.2964,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.8626198083067093,
196
+ "grad_norm": 3.6799099445343018,
197
+ "learning_rate": 8.978524895634842e-06,
198
+ "loss": 0.3039,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.8945686900958466,
203
+ "grad_norm": 3.000821828842163,
204
+ "learning_rate": 8.86320896934581e-06,
205
+ "loss": 0.3146,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.9265175718849841,
210
+ "grad_norm": 2.4160258769989014,
211
+ "learning_rate": 8.742553740855507e-06,
212
+ "loss": 0.3276,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.9584664536741214,
217
+ "grad_norm": 2.8584442138671875,
218
+ "learning_rate": 8.616725966539831e-06,
219
+ "loss": 0.3105,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.9904153354632588,
224
+ "grad_norm": 2.9464054107666016,
225
+ "learning_rate": 8.485899551698166e-06,
226
+ "loss": 0.2819,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 1.0223642172523961,
231
+ "grad_norm": 3.89704966545105,
232
+ "learning_rate": 8.350255310200611e-06,
233
+ "loss": 0.242,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 1.0543130990415335,
238
+ "grad_norm": 3.0110085010528564,
239
+ "learning_rate": 8.209980714586955e-06,
240
+ "loss": 0.2555,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 1.0862619808306708,
245
+ "grad_norm": 3.9178524017333984,
246
+ "learning_rate": 8.065269636962765e-06,
247
+ "loss": 0.2421,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 1.1182108626198084,
252
+ "grad_norm": 3.428340196609497,
253
+ "learning_rate": 7.916322081050708e-06,
254
+ "loss": 0.2937,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 1.1501597444089458,
259
+ "grad_norm": 2.2544026374816895,
260
+ "learning_rate": 7.76334390576742e-06,
261
+ "loss": 0.2694,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 1.182108626198083,
266
+ "grad_norm": 2.596172332763672,
267
+ "learning_rate": 7.60654654070796e-06,
268
+ "loss": 0.2464,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 1.2140575079872205,
273
+ "grad_norm": 3.9734742641448975,
274
+ "learning_rate": 7.446146693931111e-06,
275
+ "loss": 0.2318,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 1.2460063897763578,
280
+ "grad_norm": 3.436984062194824,
281
+ "learning_rate": 7.282366052449351e-06,
282
+ "loss": 0.2052,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 1.2779552715654952,
287
+ "grad_norm": 4.291993618011475,
288
+ "learning_rate": 7.115430975837457e-06,
289
+ "loss": 0.2335,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 1.3099041533546325,
294
+ "grad_norm": 3.5695717334747314,
295
+ "learning_rate": 6.945572183383229e-06,
296
+ "loss": 0.2119,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 1.34185303514377,
301
+ "grad_norm": 5.036863803863525,
302
+ "learning_rate": 6.773024435212678e-06,
303
+ "loss": 0.2489,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 1.3738019169329074,
308
+ "grad_norm": 4.83351993560791,
309
+ "learning_rate": 6.598026207830428e-06,
310
+ "loss": 0.2323,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 1.4057507987220448,
315
+ "grad_norm": 3.500155210494995,
316
+ "learning_rate": 6.4208193645237314e-06,
317
+ "loss": 0.2528,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 1.4376996805111821,
322
+ "grad_norm": 4.529000282287598,
323
+ "learning_rate": 6.241648821085666e-06,
324
+ "loss": 0.2303,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 1.4696485623003195,
329
+ "grad_norm": 1.649246096611023,
330
+ "learning_rate": 6.060762207319479e-06,
331
+ "loss": 0.2117,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 1.5015974440894568,
336
+ "grad_norm": 5.397870063781738,
337
+ "learning_rate": 5.878409524791931e-06,
338
+ "loss": 0.212,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 1.5335463258785942,
343
+ "grad_norm": 4.360300064086914,
344
+ "learning_rate": 5.694842801308651e-06,
345
+ "loss": 0.2395,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 1.5654952076677318,
350
+ "grad_norm": 5.323873043060303,
351
+ "learning_rate": 5.510315742589042e-06,
352
+ "loss": 0.2089,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.5974440894568689,
357
+ "grad_norm": 2.8005800247192383,
358
+ "learning_rate": 5.325083381622165e-06,
359
+ "loss": 0.1908,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.6293929712460065,
364
+ "grad_norm": 4.072391510009766,
365
+ "learning_rate": 5.139401726188208e-06,
366
+ "loss": 0.1869,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 1.6613418530351438,
371
+ "grad_norm": 4.611303329467773,
372
+ "learning_rate": 4.953527405032723e-06,
373
+ "loss": 0.1866,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 1.6932907348242812,
378
+ "grad_norm": 4.1683430671691895,
379
+ "learning_rate": 4.767717313182611e-06,
380
+ "loss": 0.2438,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 1.7252396166134185,
385
+ "grad_norm": 5.027125358581543,
386
+ "learning_rate": 4.582228256894093e-06,
387
+ "loss": 0.2268,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.7571884984025559,
392
+ "grad_norm": 3.748115062713623,
393
+ "learning_rate": 4.397316598723385e-06,
394
+ "loss": 0.2523,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 1.7891373801916934,
399
+ "grad_norm": 3.894868850708008,
400
+ "learning_rate": 4.2132379032105695e-06,
401
+ "loss": 0.1895,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 1.8210862619808306,
406
+ "grad_norm": 4.707362174987793,
407
+ "learning_rate": 4.030246583666437e-06,
408
+ "loss": 0.1883,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 1.8530351437699681,
413
+ "grad_norm": 4.535495281219482,
414
+ "learning_rate": 3.848595550550401e-06,
415
+ "loss": 0.2061,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 1.8849840255591053,
420
+ "grad_norm": 5.2252044677734375,
421
+ "learning_rate": 3.668535861925509e-06,
422
+ "loss": 0.1867,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 1.9169329073482428,
427
+ "grad_norm": 4.363283634185791,
428
+ "learning_rate": 3.4903163764736104e-06,
429
+ "loss": 0.1621,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 1.9488817891373802,
434
+ "grad_norm": 4.024950981140137,
435
+ "learning_rate": 3.314183409550293e-06,
436
+ "loss": 0.1941,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 1.9808306709265175,
441
+ "grad_norm": 3.9747886657714844,
442
+ "learning_rate": 3.140380392754901e-06,
443
+ "loss": 0.2098,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 2.012779552715655,
448
+ "grad_norm": 2.5899300575256348,
449
+ "learning_rate": 2.969147537486175e-06,
450
+ "loss": 0.1673,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 2.0447284345047922,
455
+ "grad_norm": 5.285285472869873,
456
+ "learning_rate": 2.800721502948506e-06,
457
+ "loss": 0.1983,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 2.07667731629393,
462
+ "grad_norm": 4.855522632598877,
463
+ "learning_rate": 2.635335069067617e-06,
464
+ "loss": 0.174,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 2.108626198083067,
469
+ "grad_norm": 2.8326239585876465,
470
+ "learning_rate": 2.4732168147677927e-06,
471
+ "loss": 0.1396,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 2.1405750798722045,
476
+ "grad_norm": 4.1815409660339355,
477
+ "learning_rate": 2.314590802055232e-06,
478
+ "loss": 0.1603,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 2.1725239616613417,
483
+ "grad_norm": 4.818963050842285,
484
+ "learning_rate": 2.159676266344222e-06,
485
+ "loss": 0.162,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 2.2044728434504792,
490
+ "grad_norm": 3.489180088043213,
491
+ "learning_rate": 2.0086873134540626e-06,
492
+ "loss": 0.14,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 2.236421725239617,
497
+ "grad_norm": 5.792989253997803,
498
+ "learning_rate": 1.8618326236955908e-06,
499
+ "loss": 0.1582,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 2.268370607028754,
504
+ "grad_norm": 7.210322856903076,
505
+ "learning_rate": 1.7193151634562071e-06,
506
+ "loss": 0.1674,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 2.3003194888178915,
511
+ "grad_norm": 3.8412885665893555,
512
+ "learning_rate": 1.581331904682089e-06,
513
+ "loss": 0.1357,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 2.3322683706070286,
518
+ "grad_norm": 7.757709503173828,
519
+ "learning_rate": 1.4480735526452427e-06,
520
+ "loss": 0.2142,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 2.364217252396166,
525
+ "grad_norm": 3.101224184036255,
526
+ "learning_rate": 1.319724282371664e-06,
527
+ "loss": 0.1787,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 2.3961661341853033,
532
+ "grad_norm": 6.599401950836182,
533
+ "learning_rate": 1.1964614840949002e-06,
534
+ "loss": 0.18,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 2.428115015974441,
539
+ "grad_norm": 4.533216953277588,
540
+ "learning_rate": 1.078455518086784e-06,
541
+ "loss": 0.1343,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 2.460063897763578,
546
+ "grad_norm": 4.923655986785889,
547
+ "learning_rate": 9.658694792042284e-07,
548
+ "loss": 0.1753,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 2.4920127795527156,
553
+ "grad_norm": 7.162405967712402,
554
+ "learning_rate": 8.58858971477457e-07,
555
+ "loss": 0.1883,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 2.523961661341853,
560
+ "grad_norm": 4.407649040222168,
561
+ "learning_rate": 7.575718930512516e-07,
562
+ "loss": 0.1424,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 2.5559105431309903,
567
+ "grad_norm": 3.630793333053589,
568
+ "learning_rate": 6.621482317764105e-07,
569
+ "loss": 0.1599,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 2.587859424920128,
574
+ "grad_norm": 4.121254920959473,
575
+ "learning_rate": 5.727198717339511e-07,
576
+ "loss": 0.1815,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 2.619808306709265,
581
+ "grad_norm": 5.419968605041504,
582
+ "learning_rate": 4.894104109594466e-07,
583
+ "loss": 0.1513,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 2.6517571884984026,
588
+ "grad_norm": 5.140281677246094,
589
+ "learning_rate": 4.123349906194357e-07,
590
+ "loss": 0.1183,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 2.68370607028754,
595
+ "grad_norm": 4.626114368438721,
596
+ "learning_rate": 3.416001358759635e-07,
597
+ "loss": 0.1448,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 2.7156549520766773,
602
+ "grad_norm": 6.971862316131592,
603
+ "learning_rate": 2.7730360865923954e-07,
604
+ "loss": 0.1515,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 2.747603833865815,
609
+ "grad_norm": 6.2547712326049805,
610
+ "learning_rate": 2.1953427255185122e-07,
611
+ "loss": 0.1712,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 2.779552715654952,
616
+ "grad_norm": 3.562861442565918,
617
+ "learning_rate": 1.6837196997130434e-07,
618
+ "loss": 0.1712,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 2.8115015974440896,
623
+ "grad_norm": 4.5032124519348145,
624
+ "learning_rate": 1.2388741182062348e-07,
625
+ "loss": 0.1648,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 2.8434504792332267,
630
+ "grad_norm": 5.417168140411377,
631
+ "learning_rate": 8.614207975952083e-08,
632
+ "loss": 0.1899,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 2.8753993610223643,
637
+ "grad_norm": 6.31259298324585,
638
+ "learning_rate": 5.518814123121885e-08,
639
+ "loss": 0.1264,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 2.9073482428115014,
644
+ "grad_norm": 2.681699514389038,
645
+ "learning_rate": 3.10683773623488e-08,
646
+ "loss": 0.135,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 2.939297124600639,
651
+ "grad_norm": 4.384430885314941,
652
+ "learning_rate": 1.3816123835588835e-08,
653
+ "loss": 0.1274,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 2.9712460063897765,
658
+ "grad_norm": 3.9094367027282715,
659
+ "learning_rate": 3.4552248167507576e-09,
660
+ "loss": 0.1743,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 3.0,
665
+ "step": 939,
666
+ "total_flos": 1.4199451468745933e+17,
667
+ "train_loss": 0.24831230267168233,
668
+ "train_runtime": 397.5389,
669
+ "train_samples_per_second": 75.464,
670
+ "train_steps_per_second": 2.362
671
+ }
672
+ ],
673
+ "logging_steps": 10,
674
+ "max_steps": 939,
675
+ "num_input_tokens_seen": 0,
676
+ "num_train_epochs": 3,
677
+ "save_steps": 2000,
678
+ "stateful_callbacks": {
679
+ "TrainerControl": {
680
+ "args": {
681
+ "should_epoch_stop": false,
682
+ "should_evaluate": false,
683
+ "should_log": false,
684
+ "should_save": true,
685
+ "should_training_stop": true
686
+ },
687
+ "attributes": {}
688
+ }
689
+ },
690
+ "total_flos": 1.4199451468745933e+17,
691
+ "train_batch_size": 4,
692
+ "trial_name": null,
693
+ "trial_params": null
694
+ }
csqa__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/training_loss.png ADDED
csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: Qwen/Qwen3-8B
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: sft
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # sft
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the csqa__qwen3_8b__n5000_t1t2_s0_all_variants_r8_bs4_lr1e5_e3_f_lora_sft dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 8
44
+ - total_train_batch_size: 32
45
+ - total_eval_batch_size: 64
46
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 3
50
+
51
+ ### Training results
52
+
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - PEFT 0.15.2
58
+ - Transformers 4.52.4
59
+ - Pytorch 2.7.0+cu126
60
+ - Datasets 3.6.0
61
+ - Tokenizers 0.21.1
csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.8033509624132403e+17,
4
+ "train_loss": 0.5275962893256999,
5
+ "train_runtime": 463.0949,
6
+ "train_samples_per_second": 64.782,
7
+ "train_steps_per_second": 2.028
8
+ }
csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 2.4342577580448154e+17,
4
+ "train_loss": 0.41667796907841337,
5
+ "train_runtime": 499.1967,
6
+ "train_samples_per_second": 60.097,
7
+ "train_steps_per_second": 1.881
8
+ }
gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eom_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|eot_id|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": "<|eot_id|>"
26
+ }
gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/tokenizer_config.json ADDED
@@ -0,0 +1,2076 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<|eom_id|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ }
2059
+ },
2060
+ "additional_special_tokens": [
2061
+ "<|eom_id|>"
2062
+ ],
2063
+ "bos_token": "<|begin_of_text|>",
2064
+ "clean_up_tokenization_spaces": true,
2065
+ "eos_token": "<|eot_id|>",
2066
+ "extra_special_tokens": {},
2067
+ "model_input_names": [
2068
+ "input_ids",
2069
+ "attention_mask"
2070
+ ],
2071
+ "model_max_length": 1000000000000000019884624838656,
2072
+ "pad_token": "<|eot_id|>",
2073
+ "padding_side": "right",
2074
+ "split_special_tokens": false,
2075
+ "tokenizer_class": "PreTrainedTokenizer"
2076
+ }
gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/trainer_state.json ADDED
@@ -0,0 +1,685 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 939,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.03194888178913738,
14
+ "grad_norm": 10.445302963256836,
15
+ "learning_rate": 9.574468085106384e-07,
16
+ "loss": 1.1215,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.06389776357827476,
21
+ "grad_norm": 6.524072170257568,
22
+ "learning_rate": 2.021276595744681e-06,
23
+ "loss": 1.0612,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.09584664536741214,
28
+ "grad_norm": 9.06125259399414,
29
+ "learning_rate": 3.0851063829787237e-06,
30
+ "loss": 1.1456,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.12779552715654952,
35
+ "grad_norm": 7.754812240600586,
36
+ "learning_rate": 4.148936170212766e-06,
37
+ "loss": 1.167,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.1597444089456869,
42
+ "grad_norm": 6.150674343109131,
43
+ "learning_rate": 5.212765957446809e-06,
44
+ "loss": 0.8876,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.19169329073482427,
49
+ "grad_norm": 3.6968953609466553,
50
+ "learning_rate": 6.276595744680851e-06,
51
+ "loss": 0.6745,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.22364217252396165,
56
+ "grad_norm": 2.0117056369781494,
57
+ "learning_rate": 7.340425531914894e-06,
58
+ "loss": 0.5948,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.25559105431309903,
63
+ "grad_norm": 2.015714406967163,
64
+ "learning_rate": 8.404255319148937e-06,
65
+ "loss": 0.5838,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.28753993610223644,
70
+ "grad_norm": 2.0278899669647217,
71
+ "learning_rate": 9.46808510638298e-06,
72
+ "loss": 0.5852,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.3194888178913738,
77
+ "grad_norm": 1.7055463790893555,
78
+ "learning_rate": 9.999136119166803e-06,
79
+ "loss": 0.5371,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.3514376996805112,
84
+ "grad_norm": 2.0075223445892334,
85
+ "learning_rate": 9.9922268634943e-06,
86
+ "loss": 0.5588,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.38338658146964855,
91
+ "grad_norm": 2.5569844245910645,
92
+ "learning_rate": 9.978417901361958e-06,
93
+ "loss": 0.5363,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.41533546325878595,
98
+ "grad_norm": 3.164818286895752,
99
+ "learning_rate": 9.95772831799724e-06,
100
+ "loss": 0.4908,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.4472843450479233,
105
+ "grad_norm": 2.094508171081543,
106
+ "learning_rate": 9.930186708264902e-06,
107
+ "loss": 0.4938,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.4792332268370607,
112
+ "grad_norm": 2.319535970687866,
113
+ "learning_rate": 9.895831137146319e-06,
114
+ "loss": 0.4804,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.5111821086261981,
119
+ "grad_norm": 2.136704683303833,
120
+ "learning_rate": 9.854709087130261e-06,
121
+ "loss": 0.5004,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.5431309904153354,
126
+ "grad_norm": 1.9635846614837646,
127
+ "learning_rate": 9.80687739258782e-06,
128
+ "loss": 0.4596,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.5750798722044729,
133
+ "grad_norm": 2.6207661628723145,
134
+ "learning_rate": 9.7524021612222e-06,
135
+ "loss": 0.4839,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.6070287539936102,
140
+ "grad_norm": 2.431267023086548,
141
+ "learning_rate": 9.691358682701927e-06,
142
+ "loss": 0.4526,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.6389776357827476,
147
+ "grad_norm": 2.977464199066162,
148
+ "learning_rate": 9.623831324603755e-06,
149
+ "loss": 0.4709,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.670926517571885,
154
+ "grad_norm": 2.57798171043396,
155
+ "learning_rate": 9.549913415809084e-06,
156
+ "loss": 0.4471,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.7028753993610224,
161
+ "grad_norm": 2.74763560295105,
162
+ "learning_rate": 9.469707117515068e-06,
163
+ "loss": 0.4229,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.7348242811501597,
168
+ "grad_norm": 3.0384881496429443,
169
+ "learning_rate": 9.383323282038632e-06,
170
+ "loss": 0.4018,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.7667731629392971,
175
+ "grad_norm": 2.6778738498687744,
176
+ "learning_rate": 9.29088129960862e-06,
177
+ "loss": 0.4784,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.7987220447284346,
182
+ "grad_norm": 3.22487735748291,
183
+ "learning_rate": 9.192508933357753e-06,
184
+ "loss": 0.4493,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.8306709265175719,
189
+ "grad_norm": 2.5190269947052,
190
+ "learning_rate": 9.088342142742493e-06,
191
+ "loss": 0.4492,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.8626198083067093,
196
+ "grad_norm": 2.3401877880096436,
197
+ "learning_rate": 8.978524895634842e-06,
198
+ "loss": 0.4557,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.8945686900958466,
203
+ "grad_norm": 2.725109100341797,
204
+ "learning_rate": 8.86320896934581e-06,
205
+ "loss": 0.4353,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.9265175718849841,
210
+ "grad_norm": 3.324842691421509,
211
+ "learning_rate": 8.742553740855507e-06,
212
+ "loss": 0.4475,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.9584664536741214,
217
+ "grad_norm": 2.9460716247558594,
218
+ "learning_rate": 8.616725966539831e-06,
219
+ "loss": 0.4585,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.9904153354632588,
224
+ "grad_norm": 3.3959391117095947,
225
+ "learning_rate": 8.485899551698166e-06,
226
+ "loss": 0.4099,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 1.0223642172523961,
231
+ "grad_norm": 3.2734692096710205,
232
+ "learning_rate": 8.350255310200611e-06,
233
+ "loss": 0.4175,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 1.0543130990415335,
238
+ "grad_norm": 4.019186496734619,
239
+ "learning_rate": 8.209980714586955e-06,
240
+ "loss": 0.3992,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 1.0862619808306708,
245
+ "grad_norm": 3.6706490516662598,
246
+ "learning_rate": 8.065269636962765e-06,
247
+ "loss": 0.3998,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 1.1182108626198084,
252
+ "grad_norm": 3.0696253776550293,
253
+ "learning_rate": 7.916322081050708e-06,
254
+ "loss": 0.3891,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 1.1501597444089458,
259
+ "grad_norm": 2.8689801692962646,
260
+ "learning_rate": 7.76334390576742e-06,
261
+ "loss": 0.3915,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 1.182108626198083,
266
+ "grad_norm": 2.8732635974884033,
267
+ "learning_rate": 7.60654654070796e-06,
268
+ "loss": 0.3798,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 1.2140575079872205,
273
+ "grad_norm": 4.922475814819336,
274
+ "learning_rate": 7.446146693931111e-06,
275
+ "loss": 0.3801,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 1.2460063897763578,
280
+ "grad_norm": 3.499190330505371,
281
+ "learning_rate": 7.282366052449351e-06,
282
+ "loss": 0.3691,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 1.2779552715654952,
287
+ "grad_norm": 3.9021763801574707,
288
+ "learning_rate": 7.115430975837457e-06,
289
+ "loss": 0.3794,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 1.3099041533546325,
294
+ "grad_norm": 4.84491491317749,
295
+ "learning_rate": 6.945572183383229e-06,
296
+ "loss": 0.3479,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 1.34185303514377,
301
+ "grad_norm": 4.468801021575928,
302
+ "learning_rate": 6.773024435212678e-06,
303
+ "loss": 0.3492,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 1.3738019169329074,
308
+ "grad_norm": 4.482706069946289,
309
+ "learning_rate": 6.598026207830428e-06,
310
+ "loss": 0.3569,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 1.4057507987220448,
315
+ "grad_norm": 3.455061197280884,
316
+ "learning_rate": 6.4208193645237314e-06,
317
+ "loss": 0.3987,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 1.4376996805111821,
322
+ "grad_norm": 3.639888286590576,
323
+ "learning_rate": 6.241648821085666e-06,
324
+ "loss": 0.3589,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 1.4696485623003195,
329
+ "grad_norm": 6.02905797958374,
330
+ "learning_rate": 6.060762207319479e-06,
331
+ "loss": 0.4122,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 1.5015974440894568,
336
+ "grad_norm": 4.491400241851807,
337
+ "learning_rate": 5.878409524791931e-06,
338
+ "loss": 0.3542,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 1.5335463258785942,
343
+ "grad_norm": 3.850947618484497,
344
+ "learning_rate": 5.694842801308651e-06,
345
+ "loss": 0.3719,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 1.5654952076677318,
350
+ "grad_norm": 3.6334033012390137,
351
+ "learning_rate": 5.510315742589042e-06,
352
+ "loss": 0.3259,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.5974440894568689,
357
+ "grad_norm": 5.071944236755371,
358
+ "learning_rate": 5.325083381622165e-06,
359
+ "loss": 0.3428,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.6293929712460065,
364
+ "grad_norm": 3.8090009689331055,
365
+ "learning_rate": 5.139401726188208e-06,
366
+ "loss": 0.3764,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 1.6613418530351438,
371
+ "grad_norm": 3.925981283187866,
372
+ "learning_rate": 4.953527405032723e-06,
373
+ "loss": 0.383,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 1.6932907348242812,
378
+ "grad_norm": 6.125942230224609,
379
+ "learning_rate": 4.767717313182611e-06,
380
+ "loss": 0.3533,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 1.7252396166134185,
385
+ "grad_norm": 3.9766414165496826,
386
+ "learning_rate": 4.582228256894093e-06,
387
+ "loss": 0.3652,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.7571884984025559,
392
+ "grad_norm": 7.139044284820557,
393
+ "learning_rate": 4.397316598723385e-06,
394
+ "loss": 0.3213,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 1.7891373801916934,
399
+ "grad_norm": 4.280309200286865,
400
+ "learning_rate": 4.2132379032105695e-06,
401
+ "loss": 0.3486,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 1.8210862619808306,
406
+ "grad_norm": 3.9839210510253906,
407
+ "learning_rate": 4.030246583666437e-06,
408
+ "loss": 0.3161,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 1.8530351437699681,
413
+ "grad_norm": 5.437602519989014,
414
+ "learning_rate": 3.848595550550401e-06,
415
+ "loss": 0.3472,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 1.8849840255591053,
420
+ "grad_norm": 5.817410469055176,
421
+ "learning_rate": 3.668535861925509e-06,
422
+ "loss": 0.3888,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 1.9169329073482428,
427
+ "grad_norm": 5.5709381103515625,
428
+ "learning_rate": 3.4903163764736104e-06,
429
+ "loss": 0.3225,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 1.9488817891373802,
434
+ "grad_norm": 4.854086399078369,
435
+ "learning_rate": 3.314183409550293e-06,
436
+ "loss": 0.3637,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 1.9808306709265175,
441
+ "grad_norm": 5.341320037841797,
442
+ "learning_rate": 3.140380392754901e-06,
443
+ "loss": 0.3309,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 2.012779552715655,
448
+ "grad_norm": 4.052433013916016,
449
+ "learning_rate": 2.969147537486175e-06,
450
+ "loss": 0.3188,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 2.0447284345047922,
455
+ "grad_norm": 6.213695049285889,
456
+ "learning_rate": 2.800721502948506e-06,
457
+ "loss": 0.3058,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 2.07667731629393,
462
+ "grad_norm": 5.307283878326416,
463
+ "learning_rate": 2.635335069067617e-06,
464
+ "loss": 0.3417,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 2.108626198083067,
469
+ "grad_norm": 5.063953876495361,
470
+ "learning_rate": 2.4732168147677927e-06,
471
+ "loss": 0.3195,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 2.1405750798722045,
476
+ "grad_norm": 7.373411655426025,
477
+ "learning_rate": 2.314590802055232e-06,
478
+ "loss": 0.2989,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 2.1725239616613417,
483
+ "grad_norm": 9.082876205444336,
484
+ "learning_rate": 2.159676266344222e-06,
485
+ "loss": 0.3187,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 2.2044728434504792,
490
+ "grad_norm": 7.071778297424316,
491
+ "learning_rate": 2.0086873134540626e-06,
492
+ "loss": 0.3064,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 2.236421725239617,
497
+ "grad_norm": 4.376129627227783,
498
+ "learning_rate": 1.8618326236955908e-06,
499
+ "loss": 0.3114,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 2.268370607028754,
504
+ "grad_norm": 6.112962245941162,
505
+ "learning_rate": 1.7193151634562071e-06,
506
+ "loss": 0.2955,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 2.3003194888178915,
511
+ "grad_norm": 5.760268688201904,
512
+ "learning_rate": 1.581331904682089e-06,
513
+ "loss": 0.2825,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 2.3322683706070286,
518
+ "grad_norm": 6.972622394561768,
519
+ "learning_rate": 1.4480735526452427e-06,
520
+ "loss": 0.2928,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 2.364217252396166,
525
+ "grad_norm": 8.442282676696777,
526
+ "learning_rate": 1.319724282371664e-06,
527
+ "loss": 0.3024,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 2.3961661341853033,
532
+ "grad_norm": 4.642228603363037,
533
+ "learning_rate": 1.1964614840949002e-06,
534
+ "loss": 0.3522,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 2.428115015974441,
539
+ "grad_norm": 4.407663822174072,
540
+ "learning_rate": 1.078455518086784e-06,
541
+ "loss": 0.2863,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 2.460063897763578,
546
+ "grad_norm": 5.7068986892700195,
547
+ "learning_rate": 9.658694792042284e-07,
548
+ "loss": 0.273,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 2.4920127795527156,
553
+ "grad_norm": 9.480902671813965,
554
+ "learning_rate": 8.58858971477457e-07,
555
+ "loss": 0.2948,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 2.523961661341853,
560
+ "grad_norm": 6.3506693840026855,
561
+ "learning_rate": 7.575718930512516e-07,
562
+ "loss": 0.2945,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 2.5559105431309903,
567
+ "grad_norm": 4.636996269226074,
568
+ "learning_rate": 6.621482317764105e-07,
569
+ "loss": 0.2694,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 2.587859424920128,
574
+ "grad_norm": 6.740283489227295,
575
+ "learning_rate": 5.727198717339511e-07,
576
+ "loss": 0.2632,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 2.619808306709265,
581
+ "grad_norm": 5.469799518585205,
582
+ "learning_rate": 4.894104109594466e-07,
583
+ "loss": 0.2781,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 2.6517571884984026,
588
+ "grad_norm": 8.596780776977539,
589
+ "learning_rate": 4.123349906194357e-07,
590
+ "loss": 0.3137,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 2.68370607028754,
595
+ "grad_norm": 6.271667957305908,
596
+ "learning_rate": 3.416001358759635e-07,
597
+ "loss": 0.2815,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 2.7156549520766773,
602
+ "grad_norm": 10.2745361328125,
603
+ "learning_rate": 2.7730360865923954e-07,
604
+ "loss": 0.3089,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 2.747603833865815,
609
+ "grad_norm": 5.311823844909668,
610
+ "learning_rate": 2.1953427255185122e-07,
611
+ "loss": 0.3243,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 2.779552715654952,
616
+ "grad_norm": 5.055395126342773,
617
+ "learning_rate": 1.6837196997130434e-07,
618
+ "loss": 0.2945,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 2.8115015974440896,
623
+ "grad_norm": 9.366786003112793,
624
+ "learning_rate": 1.2388741182062348e-07,
625
+ "loss": 0.3142,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 2.8434504792332267,
630
+ "grad_norm": 6.428186416625977,
631
+ "learning_rate": 8.614207975952083e-08,
632
+ "loss": 0.2833,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 2.8753993610223643,
637
+ "grad_norm": 6.8983612060546875,
638
+ "learning_rate": 5.518814123121885e-08,
639
+ "loss": 0.3235,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 2.9073482428115014,
644
+ "grad_norm": 6.682745933532715,
645
+ "learning_rate": 3.10683773623488e-08,
646
+ "loss": 0.3097,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 2.939297124600639,
651
+ "grad_norm": 7.35684871673584,
652
+ "learning_rate": 1.3816123835588835e-08,
653
+ "loss": 0.2829,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 2.9712460063897765,
658
+ "grad_norm": 5.339282035827637,
659
+ "learning_rate": 3.4552248167507576e-09,
660
+ "loss": 0.3004,
661
+ "step": 930
662
+ }
663
+ ],
664
+ "logging_steps": 10,
665
+ "max_steps": 939,
666
+ "num_input_tokens_seen": 0,
667
+ "num_train_epochs": 3,
668
+ "save_steps": 2000,
669
+ "stateful_callbacks": {
670
+ "TrainerControl": {
671
+ "args": {
672
+ "should_epoch_stop": false,
673
+ "should_evaluate": false,
674
+ "should_log": false,
675
+ "should_save": true,
676
+ "should_training_stop": true
677
+ },
678
+ "attributes": {}
679
+ }
680
+ },
681
+ "total_flos": 2.4342577580448154e+17,
682
+ "train_batch_size": 4,
683
+ "trial_name": null,
684
+ "trial_params": null
685
+ }
gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 2.4342577580448154e+17,
4
+ "train_loss": 0.41667796907841337,
5
+ "train_runtime": 499.1967,
6
+ "train_samples_per_second": 60.097,
7
+ "train_steps_per_second": 1.881
8
+ }
gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/trainer_log.jsonl ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 939, "loss": 1.1215, "lr": 9.574468085106384e-07, "epoch": 0.03194888178913738, "percentage": 1.06, "elapsed_time": "0:00:05", "remaining_time": "0:09:10"}
2
+ {"current_steps": 20, "total_steps": 939, "loss": 1.0612, "lr": 2.021276595744681e-06, "epoch": 0.06389776357827476, "percentage": 2.13, "elapsed_time": "0:00:10", "remaining_time": "0:08:19"}
3
+ {"current_steps": 30, "total_steps": 939, "loss": 1.1456, "lr": 3.0851063829787237e-06, "epoch": 0.09584664536741214, "percentage": 3.19, "elapsed_time": "0:00:16", "remaining_time": "0:08:09"}
4
+ {"current_steps": 40, "total_steps": 939, "loss": 1.167, "lr": 4.148936170212766e-06, "epoch": 0.12779552715654952, "percentage": 4.26, "elapsed_time": "0:00:21", "remaining_time": "0:07:56"}
5
+ {"current_steps": 50, "total_steps": 939, "loss": 0.8876, "lr": 5.212765957446809e-06, "epoch": 0.1597444089456869, "percentage": 5.32, "elapsed_time": "0:00:26", "remaining_time": "0:07:45"}
6
+ {"current_steps": 60, "total_steps": 939, "loss": 0.6745, "lr": 6.276595744680851e-06, "epoch": 0.19169329073482427, "percentage": 6.39, "elapsed_time": "0:00:31", "remaining_time": "0:07:39"}
7
+ {"current_steps": 70, "total_steps": 939, "loss": 0.5948, "lr": 7.340425531914894e-06, "epoch": 0.22364217252396165, "percentage": 7.45, "elapsed_time": "0:00:36", "remaining_time": "0:07:32"}
8
+ {"current_steps": 80, "total_steps": 939, "loss": 0.5838, "lr": 8.404255319148937e-06, "epoch": 0.25559105431309903, "percentage": 8.52, "elapsed_time": "0:00:41", "remaining_time": "0:07:27"}
9
+ {"current_steps": 90, "total_steps": 939, "loss": 0.5852, "lr": 9.46808510638298e-06, "epoch": 0.28753993610223644, "percentage": 9.58, "elapsed_time": "0:00:46", "remaining_time": "0:07:23"}
10
+ {"current_steps": 100, "total_steps": 939, "loss": 0.5371, "lr": 9.999136119166803e-06, "epoch": 0.3194888178913738, "percentage": 10.65, "elapsed_time": "0:00:51", "remaining_time": "0:07:15"}
11
+ {"current_steps": 110, "total_steps": 939, "loss": 0.5588, "lr": 9.9922268634943e-06, "epoch": 0.3514376996805112, "percentage": 11.71, "elapsed_time": "0:00:57", "remaining_time": "0:07:10"}
12
+ {"current_steps": 120, "total_steps": 939, "loss": 0.5363, "lr": 9.978417901361958e-06, "epoch": 0.38338658146964855, "percentage": 12.78, "elapsed_time": "0:01:02", "remaining_time": "0:07:07"}
13
+ {"current_steps": 130, "total_steps": 939, "loss": 0.4908, "lr": 9.95772831799724e-06, "epoch": 0.41533546325878595, "percentage": 13.84, "elapsed_time": "0:01:07", "remaining_time": "0:07:01"}
14
+ {"current_steps": 140, "total_steps": 939, "loss": 0.4938, "lr": 9.930186708264902e-06, "epoch": 0.4472843450479233, "percentage": 14.91, "elapsed_time": "0:01:12", "remaining_time": "0:06:56"}
15
+ {"current_steps": 150, "total_steps": 939, "loss": 0.4804, "lr": 9.895831137146319e-06, "epoch": 0.4792332268370607, "percentage": 15.97, "elapsed_time": "0:01:18", "remaining_time": "0:06:51"}
16
+ {"current_steps": 160, "total_steps": 939, "loss": 0.5004, "lr": 9.854709087130261e-06, "epoch": 0.5111821086261981, "percentage": 17.04, "elapsed_time": "0:01:23", "remaining_time": "0:06:46"}
17
+ {"current_steps": 170, "total_steps": 939, "loss": 0.4596, "lr": 9.80687739258782e-06, "epoch": 0.5431309904153354, "percentage": 18.1, "elapsed_time": "0:01:28", "remaining_time": "0:06:39"}
18
+ {"current_steps": 180, "total_steps": 939, "loss": 0.4839, "lr": 9.7524021612222e-06, "epoch": 0.5750798722044729, "percentage": 19.17, "elapsed_time": "0:01:33", "remaining_time": "0:06:35"}
19
+ {"current_steps": 190, "total_steps": 939, "loss": 0.4526, "lr": 9.691358682701927e-06, "epoch": 0.6070287539936102, "percentage": 20.23, "elapsed_time": "0:01:38", "remaining_time": "0:06:30"}
20
+ {"current_steps": 200, "total_steps": 939, "loss": 0.4709, "lr": 9.623831324603755e-06, "epoch": 0.6389776357827476, "percentage": 21.3, "elapsed_time": "0:01:44", "remaining_time": "0:06:25"}
21
+ {"current_steps": 210, "total_steps": 939, "loss": 0.4471, "lr": 9.549913415809084e-06, "epoch": 0.670926517571885, "percentage": 22.36, "elapsed_time": "0:01:49", "remaining_time": "0:06:19"}
22
+ {"current_steps": 220, "total_steps": 939, "loss": 0.4229, "lr": 9.469707117515068e-06, "epoch": 0.7028753993610224, "percentage": 23.43, "elapsed_time": "0:01:54", "remaining_time": "0:06:13"}
23
+ {"current_steps": 230, "total_steps": 939, "loss": 0.4018, "lr": 9.383323282038632e-06, "epoch": 0.7348242811501597, "percentage": 24.49, "elapsed_time": "0:01:59", "remaining_time": "0:06:08"}
24
+ {"current_steps": 240, "total_steps": 939, "loss": 0.4784, "lr": 9.29088129960862e-06, "epoch": 0.7667731629392971, "percentage": 25.56, "elapsed_time": "0:02:04", "remaining_time": "0:06:02"}
25
+ {"current_steps": 250, "total_steps": 939, "loss": 0.4493, "lr": 9.192508933357753e-06, "epoch": 0.7987220447284346, "percentage": 26.62, "elapsed_time": "0:02:09", "remaining_time": "0:05:57"}
26
+ {"current_steps": 260, "total_steps": 939, "loss": 0.4492, "lr": 9.088342142742493e-06, "epoch": 0.8306709265175719, "percentage": 27.69, "elapsed_time": "0:02:14", "remaining_time": "0:05:52"}
27
+ {"current_steps": 270, "total_steps": 939, "loss": 0.4557, "lr": 8.978524895634842e-06, "epoch": 0.8626198083067093, "percentage": 28.75, "elapsed_time": "0:02:19", "remaining_time": "0:05:46"}
28
+ {"current_steps": 280, "total_steps": 939, "loss": 0.4353, "lr": 8.86320896934581e-06, "epoch": 0.8945686900958466, "percentage": 29.82, "elapsed_time": "0:02:24", "remaining_time": "0:05:40"}
29
+ {"current_steps": 290, "total_steps": 939, "loss": 0.4475, "lr": 8.742553740855507e-06, "epoch": 0.9265175718849841, "percentage": 30.88, "elapsed_time": "0:02:29", "remaining_time": "0:05:35"}
30
+ {"current_steps": 300, "total_steps": 939, "loss": 0.4585, "lr": 8.616725966539831e-06, "epoch": 0.9584664536741214, "percentage": 31.95, "elapsed_time": "0:02:35", "remaining_time": "0:05:30"}
31
+ {"current_steps": 310, "total_steps": 939, "loss": 0.4099, "lr": 8.485899551698166e-06, "epoch": 0.9904153354632588, "percentage": 33.01, "elapsed_time": "0:02:40", "remaining_time": "0:05:25"}
32
+ {"current_steps": 320, "total_steps": 939, "loss": 0.4175, "lr": 8.350255310200611e-06, "epoch": 1.0223642172523961, "percentage": 34.08, "elapsed_time": "0:02:45", "remaining_time": "0:05:20"}
33
+ {"current_steps": 330, "total_steps": 939, "loss": 0.3992, "lr": 8.209980714586955e-06, "epoch": 1.0543130990415335, "percentage": 35.14, "elapsed_time": "0:02:50", "remaining_time": "0:05:15"}
34
+ {"current_steps": 340, "total_steps": 939, "loss": 0.3998, "lr": 8.065269636962765e-06, "epoch": 1.0862619808306708, "percentage": 36.21, "elapsed_time": "0:02:55", "remaining_time": "0:05:09"}
35
+ {"current_steps": 350, "total_steps": 939, "loss": 0.3891, "lr": 7.916322081050708e-06, "epoch": 1.1182108626198084, "percentage": 37.27, "elapsed_time": "0:03:00", "remaining_time": "0:05:04"}
36
+ {"current_steps": 360, "total_steps": 939, "loss": 0.3915, "lr": 7.76334390576742e-06, "epoch": 1.1501597444089458, "percentage": 38.34, "elapsed_time": "0:03:05", "remaining_time": "0:04:58"}
37
+ {"current_steps": 370, "total_steps": 939, "loss": 0.3798, "lr": 7.60654654070796e-06, "epoch": 1.182108626198083, "percentage": 39.4, "elapsed_time": "0:03:11", "remaining_time": "0:04:53"}
38
+ {"current_steps": 380, "total_steps": 939, "loss": 0.3801, "lr": 7.446146693931111e-06, "epoch": 1.2140575079872205, "percentage": 40.47, "elapsed_time": "0:03:16", "remaining_time": "0:04:48"}
39
+ {"current_steps": 390, "total_steps": 939, "loss": 0.3691, "lr": 7.282366052449351e-06, "epoch": 1.2460063897763578, "percentage": 41.53, "elapsed_time": "0:03:21", "remaining_time": "0:04:43"}
40
+ {"current_steps": 400, "total_steps": 939, "loss": 0.3794, "lr": 7.115430975837457e-06, "epoch": 1.2779552715654952, "percentage": 42.6, "elapsed_time": "0:03:26", "remaining_time": "0:04:38"}
41
+ {"current_steps": 410, "total_steps": 939, "loss": 0.3479, "lr": 6.945572183383229e-06, "epoch": 1.3099041533546325, "percentage": 43.66, "elapsed_time": "0:03:31", "remaining_time": "0:04:32"}
42
+ {"current_steps": 420, "total_steps": 939, "loss": 0.3492, "lr": 6.773024435212678e-06, "epoch": 1.34185303514377, "percentage": 44.73, "elapsed_time": "0:03:36", "remaining_time": "0:04:27"}
43
+ {"current_steps": 430, "total_steps": 939, "loss": 0.3569, "lr": 6.598026207830428e-06, "epoch": 1.3738019169329074, "percentage": 45.79, "elapsed_time": "0:03:41", "remaining_time": "0:04:22"}
44
+ {"current_steps": 440, "total_steps": 939, "loss": 0.3987, "lr": 6.4208193645237314e-06, "epoch": 1.4057507987220448, "percentage": 46.86, "elapsed_time": "0:03:46", "remaining_time": "0:04:16"}
45
+ {"current_steps": 450, "total_steps": 939, "loss": 0.3589, "lr": 6.241648821085666e-06, "epoch": 1.4376996805111821, "percentage": 47.92, "elapsed_time": "0:03:51", "remaining_time": "0:04:11"}
46
+ {"current_steps": 460, "total_steps": 939, "loss": 0.4122, "lr": 6.060762207319479e-06, "epoch": 1.4696485623003195, "percentage": 48.99, "elapsed_time": "0:03:56", "remaining_time": "0:04:06"}
47
+ {"current_steps": 470, "total_steps": 939, "loss": 0.3542, "lr": 5.878409524791931e-06, "epoch": 1.5015974440894568, "percentage": 50.05, "elapsed_time": "0:04:02", "remaining_time": "0:04:01"}
48
+ {"current_steps": 480, "total_steps": 939, "loss": 0.3719, "lr": 5.694842801308651e-06, "epoch": 1.5335463258785942, "percentage": 51.12, "elapsed_time": "0:04:07", "remaining_time": "0:03:56"}
49
+ {"current_steps": 490, "total_steps": 939, "loss": 0.3259, "lr": 5.510315742589042e-06, "epoch": 1.5654952076677318, "percentage": 52.18, "elapsed_time": "0:04:12", "remaining_time": "0:03:51"}
50
+ {"current_steps": 500, "total_steps": 939, "loss": 0.3428, "lr": 5.325083381622165e-06, "epoch": 1.5974440894568689, "percentage": 53.25, "elapsed_time": "0:04:17", "remaining_time": "0:03:46"}
51
+ {"current_steps": 510, "total_steps": 939, "loss": 0.3764, "lr": 5.139401726188208e-06, "epoch": 1.6293929712460065, "percentage": 54.31, "elapsed_time": "0:04:22", "remaining_time": "0:03:41"}
52
+ {"current_steps": 520, "total_steps": 939, "loss": 0.383, "lr": 4.953527405032723e-06, "epoch": 1.6613418530351438, "percentage": 55.38, "elapsed_time": "0:04:27", "remaining_time": "0:03:35"}
53
+ {"current_steps": 530, "total_steps": 939, "loss": 0.3533, "lr": 4.767717313182611e-06, "epoch": 1.6932907348242812, "percentage": 56.44, "elapsed_time": "0:04:33", "remaining_time": "0:03:30"}
54
+ {"current_steps": 540, "total_steps": 939, "loss": 0.3652, "lr": 4.582228256894093e-06, "epoch": 1.7252396166134185, "percentage": 57.51, "elapsed_time": "0:04:38", "remaining_time": "0:03:25"}
55
+ {"current_steps": 550, "total_steps": 939, "loss": 0.3213, "lr": 4.397316598723385e-06, "epoch": 1.7571884984025559, "percentage": 58.57, "elapsed_time": "0:04:43", "remaining_time": "0:03:20"}
56
+ {"current_steps": 560, "total_steps": 939, "loss": 0.3486, "lr": 4.2132379032105695e-06, "epoch": 1.7891373801916934, "percentage": 59.64, "elapsed_time": "0:04:48", "remaining_time": "0:03:15"}
57
+ {"current_steps": 570, "total_steps": 939, "loss": 0.3161, "lr": 4.030246583666437e-06, "epoch": 1.8210862619808306, "percentage": 60.7, "elapsed_time": "0:04:53", "remaining_time": "0:03:10"}
58
+ {"current_steps": 580, "total_steps": 939, "loss": 0.3472, "lr": 3.848595550550401e-06, "epoch": 1.8530351437699681, "percentage": 61.77, "elapsed_time": "0:04:59", "remaining_time": "0:03:05"}
59
+ {"current_steps": 590, "total_steps": 939, "loss": 0.3888, "lr": 3.668535861925509e-06, "epoch": 1.8849840255591053, "percentage": 62.83, "elapsed_time": "0:05:04", "remaining_time": "0:03:00"}
60
+ {"current_steps": 600, "total_steps": 939, "loss": 0.3225, "lr": 3.4903163764736104e-06, "epoch": 1.9169329073482428, "percentage": 63.9, "elapsed_time": "0:05:09", "remaining_time": "0:02:54"}
61
+ {"current_steps": 610, "total_steps": 939, "loss": 0.3637, "lr": 3.314183409550293e-06, "epoch": 1.9488817891373802, "percentage": 64.96, "elapsed_time": "0:05:14", "remaining_time": "0:02:49"}
62
+ {"current_steps": 620, "total_steps": 939, "loss": 0.3309, "lr": 3.140380392754901e-06, "epoch": 1.9808306709265175, "percentage": 66.03, "elapsed_time": "0:05:19", "remaining_time": "0:02:44"}
63
+ {"current_steps": 630, "total_steps": 939, "loss": 0.3188, "lr": 2.969147537486175e-06, "epoch": 2.012779552715655, "percentage": 67.09, "elapsed_time": "0:05:25", "remaining_time": "0:02:39"}
64
+ {"current_steps": 640, "total_steps": 939, "loss": 0.3058, "lr": 2.800721502948506e-06, "epoch": 2.0447284345047922, "percentage": 68.16, "elapsed_time": "0:05:30", "remaining_time": "0:02:34"}
65
+ {"current_steps": 650, "total_steps": 939, "loss": 0.3417, "lr": 2.635335069067617e-06, "epoch": 2.07667731629393, "percentage": 69.22, "elapsed_time": "0:05:35", "remaining_time": "0:02:29"}
66
+ {"current_steps": 660, "total_steps": 939, "loss": 0.3195, "lr": 2.4732168147677927e-06, "epoch": 2.108626198083067, "percentage": 70.29, "elapsed_time": "0:05:40", "remaining_time": "0:02:24"}
67
+ {"current_steps": 670, "total_steps": 939, "loss": 0.2989, "lr": 2.314590802055232e-06, "epoch": 2.1405750798722045, "percentage": 71.35, "elapsed_time": "0:05:45", "remaining_time": "0:02:18"}
68
+ {"current_steps": 680, "total_steps": 939, "loss": 0.3187, "lr": 2.159676266344222e-06, "epoch": 2.1725239616613417, "percentage": 72.42, "elapsed_time": "0:05:50", "remaining_time": "0:02:13"}
69
+ {"current_steps": 690, "total_steps": 939, "loss": 0.3064, "lr": 2.0086873134540626e-06, "epoch": 2.2044728434504792, "percentage": 73.48, "elapsed_time": "0:05:56", "remaining_time": "0:02:08"}
70
+ {"current_steps": 700, "total_steps": 939, "loss": 0.3114, "lr": 1.8618326236955908e-06, "epoch": 2.236421725239617, "percentage": 74.55, "elapsed_time": "0:06:01", "remaining_time": "0:02:03"}
71
+ {"current_steps": 710, "total_steps": 939, "loss": 0.2955, "lr": 1.7193151634562071e-06, "epoch": 2.268370607028754, "percentage": 75.61, "elapsed_time": "0:06:06", "remaining_time": "0:01:58"}
72
+ {"current_steps": 720, "total_steps": 939, "loss": 0.2825, "lr": 1.581331904682089e-06, "epoch": 2.3003194888178915, "percentage": 76.68, "elapsed_time": "0:06:11", "remaining_time": "0:01:53"}
73
+ {"current_steps": 730, "total_steps": 939, "loss": 0.2928, "lr": 1.4480735526452427e-06, "epoch": 2.3322683706070286, "percentage": 77.74, "elapsed_time": "0:06:16", "remaining_time": "0:01:47"}
74
+ {"current_steps": 740, "total_steps": 939, "loss": 0.3024, "lr": 1.319724282371664e-06, "epoch": 2.364217252396166, "percentage": 78.81, "elapsed_time": "0:06:22", "remaining_time": "0:01:42"}
75
+ {"current_steps": 750, "total_steps": 939, "loss": 0.3522, "lr": 1.1964614840949002e-06, "epoch": 2.3961661341853033, "percentage": 79.87, "elapsed_time": "0:06:27", "remaining_time": "0:01:37"}
76
+ {"current_steps": 760, "total_steps": 939, "loss": 0.2863, "lr": 1.078455518086784e-06, "epoch": 2.428115015974441, "percentage": 80.94, "elapsed_time": "0:06:32", "remaining_time": "0:01:32"}
77
+ {"current_steps": 770, "total_steps": 939, "loss": 0.273, "lr": 9.658694792042284e-07, "epoch": 2.460063897763578, "percentage": 82.0, "elapsed_time": "0:06:37", "remaining_time": "0:01:27"}
78
+ {"current_steps": 780, "total_steps": 939, "loss": 0.2948, "lr": 8.58858971477457e-07, "epoch": 2.4920127795527156, "percentage": 83.07, "elapsed_time": "0:06:42", "remaining_time": "0:01:22"}
79
+ {"current_steps": 790, "total_steps": 939, "loss": 0.2945, "lr": 7.575718930512516e-07, "epoch": 2.523961661341853, "percentage": 84.13, "elapsed_time": "0:06:47", "remaining_time": "0:01:16"}
80
+ {"current_steps": 800, "total_steps": 939, "loss": 0.2694, "lr": 6.621482317764105e-07, "epoch": 2.5559105431309903, "percentage": 85.2, "elapsed_time": "0:06:52", "remaining_time": "0:01:11"}
81
+ {"current_steps": 810, "total_steps": 939, "loss": 0.2632, "lr": 5.727198717339511e-07, "epoch": 2.587859424920128, "percentage": 86.26, "elapsed_time": "0:06:57", "remaining_time": "0:01:06"}
82
+ {"current_steps": 820, "total_steps": 939, "loss": 0.2781, "lr": 4.894104109594466e-07, "epoch": 2.619808306709265, "percentage": 87.33, "elapsed_time": "0:07:02", "remaining_time": "0:01:01"}
83
+ {"current_steps": 830, "total_steps": 939, "loss": 0.3137, "lr": 4.123349906194357e-07, "epoch": 2.6517571884984026, "percentage": 88.39, "elapsed_time": "0:07:08", "remaining_time": "0:00:56"}
84
+ {"current_steps": 840, "total_steps": 939, "loss": 0.2815, "lr": 3.416001358759635e-07, "epoch": 2.68370607028754, "percentage": 89.46, "elapsed_time": "0:07:13", "remaining_time": "0:00:51"}
85
+ {"current_steps": 850, "total_steps": 939, "loss": 0.3089, "lr": 2.7730360865923954e-07, "epoch": 2.7156549520766773, "percentage": 90.52, "elapsed_time": "0:07:18", "remaining_time": "0:00:45"}
86
+ {"current_steps": 860, "total_steps": 939, "loss": 0.3243, "lr": 2.1953427255185122e-07, "epoch": 2.747603833865815, "percentage": 91.59, "elapsed_time": "0:07:23", "remaining_time": "0:00:40"}
87
+ {"current_steps": 870, "total_steps": 939, "loss": 0.2945, "lr": 1.6837196997130434e-07, "epoch": 2.779552715654952, "percentage": 92.65, "elapsed_time": "0:07:28", "remaining_time": "0:00:35"}
88
+ {"current_steps": 880, "total_steps": 939, "loss": 0.3142, "lr": 1.2388741182062348e-07, "epoch": 2.8115015974440896, "percentage": 93.72, "elapsed_time": "0:07:33", "remaining_time": "0:00:30"}
89
+ {"current_steps": 890, "total_steps": 939, "loss": 0.2833, "lr": 8.614207975952083e-08, "epoch": 2.8434504792332267, "percentage": 94.78, "elapsed_time": "0:07:38", "remaining_time": "0:00:25"}
90
+ {"current_steps": 900, "total_steps": 939, "loss": 0.3235, "lr": 5.518814123121885e-08, "epoch": 2.8753993610223643, "percentage": 95.85, "elapsed_time": "0:07:43", "remaining_time": "0:00:20"}
91
+ {"current_steps": 910, "total_steps": 939, "loss": 0.3097, "lr": 3.10683773623488e-08, "epoch": 2.9073482428115014, "percentage": 96.91, "elapsed_time": "0:07:48", "remaining_time": "0:00:14"}
92
+ {"current_steps": 920, "total_steps": 939, "loss": 0.2829, "lr": 1.3816123835588835e-08, "epoch": 2.939297124600639, "percentage": 97.98, "elapsed_time": "0:07:54", "remaining_time": "0:00:09"}
93
+ {"current_steps": 930, "total_steps": 939, "loss": 0.3004, "lr": 3.4552248167507576e-09, "epoch": 2.9712460063897765, "percentage": 99.04, "elapsed_time": "0:07:59", "remaining_time": "0:00:04"}
94
+ {"current_steps": 939, "total_steps": 939, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:08:04", "remaining_time": "0:00:00"}
gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/trainer_state.json ADDED
@@ -0,0 +1,694 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 939,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.03194888178913738,
14
+ "grad_norm": 10.445302963256836,
15
+ "learning_rate": 9.574468085106384e-07,
16
+ "loss": 1.1215,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.06389776357827476,
21
+ "grad_norm": 6.524072170257568,
22
+ "learning_rate": 2.021276595744681e-06,
23
+ "loss": 1.0612,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.09584664536741214,
28
+ "grad_norm": 9.06125259399414,
29
+ "learning_rate": 3.0851063829787237e-06,
30
+ "loss": 1.1456,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.12779552715654952,
35
+ "grad_norm": 7.754812240600586,
36
+ "learning_rate": 4.148936170212766e-06,
37
+ "loss": 1.167,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.1597444089456869,
42
+ "grad_norm": 6.150674343109131,
43
+ "learning_rate": 5.212765957446809e-06,
44
+ "loss": 0.8876,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.19169329073482427,
49
+ "grad_norm": 3.6968953609466553,
50
+ "learning_rate": 6.276595744680851e-06,
51
+ "loss": 0.6745,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.22364217252396165,
56
+ "grad_norm": 2.0117056369781494,
57
+ "learning_rate": 7.340425531914894e-06,
58
+ "loss": 0.5948,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.25559105431309903,
63
+ "grad_norm": 2.015714406967163,
64
+ "learning_rate": 8.404255319148937e-06,
65
+ "loss": 0.5838,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.28753993610223644,
70
+ "grad_norm": 2.0278899669647217,
71
+ "learning_rate": 9.46808510638298e-06,
72
+ "loss": 0.5852,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.3194888178913738,
77
+ "grad_norm": 1.7055463790893555,
78
+ "learning_rate": 9.999136119166803e-06,
79
+ "loss": 0.5371,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.3514376996805112,
84
+ "grad_norm": 2.0075223445892334,
85
+ "learning_rate": 9.9922268634943e-06,
86
+ "loss": 0.5588,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.38338658146964855,
91
+ "grad_norm": 2.5569844245910645,
92
+ "learning_rate": 9.978417901361958e-06,
93
+ "loss": 0.5363,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.41533546325878595,
98
+ "grad_norm": 3.164818286895752,
99
+ "learning_rate": 9.95772831799724e-06,
100
+ "loss": 0.4908,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.4472843450479233,
105
+ "grad_norm": 2.094508171081543,
106
+ "learning_rate": 9.930186708264902e-06,
107
+ "loss": 0.4938,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.4792332268370607,
112
+ "grad_norm": 2.319535970687866,
113
+ "learning_rate": 9.895831137146319e-06,
114
+ "loss": 0.4804,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.5111821086261981,
119
+ "grad_norm": 2.136704683303833,
120
+ "learning_rate": 9.854709087130261e-06,
121
+ "loss": 0.5004,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.5431309904153354,
126
+ "grad_norm": 1.9635846614837646,
127
+ "learning_rate": 9.80687739258782e-06,
128
+ "loss": 0.4596,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.5750798722044729,
133
+ "grad_norm": 2.6207661628723145,
134
+ "learning_rate": 9.7524021612222e-06,
135
+ "loss": 0.4839,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.6070287539936102,
140
+ "grad_norm": 2.431267023086548,
141
+ "learning_rate": 9.691358682701927e-06,
142
+ "loss": 0.4526,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.6389776357827476,
147
+ "grad_norm": 2.977464199066162,
148
+ "learning_rate": 9.623831324603755e-06,
149
+ "loss": 0.4709,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.670926517571885,
154
+ "grad_norm": 2.57798171043396,
155
+ "learning_rate": 9.549913415809084e-06,
156
+ "loss": 0.4471,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.7028753993610224,
161
+ "grad_norm": 2.74763560295105,
162
+ "learning_rate": 9.469707117515068e-06,
163
+ "loss": 0.4229,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.7348242811501597,
168
+ "grad_norm": 3.0384881496429443,
169
+ "learning_rate": 9.383323282038632e-06,
170
+ "loss": 0.4018,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.7667731629392971,
175
+ "grad_norm": 2.6778738498687744,
176
+ "learning_rate": 9.29088129960862e-06,
177
+ "loss": 0.4784,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.7987220447284346,
182
+ "grad_norm": 3.22487735748291,
183
+ "learning_rate": 9.192508933357753e-06,
184
+ "loss": 0.4493,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.8306709265175719,
189
+ "grad_norm": 2.5190269947052,
190
+ "learning_rate": 9.088342142742493e-06,
191
+ "loss": 0.4492,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.8626198083067093,
196
+ "grad_norm": 2.3401877880096436,
197
+ "learning_rate": 8.978524895634842e-06,
198
+ "loss": 0.4557,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.8945686900958466,
203
+ "grad_norm": 2.725109100341797,
204
+ "learning_rate": 8.86320896934581e-06,
205
+ "loss": 0.4353,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.9265175718849841,
210
+ "grad_norm": 3.324842691421509,
211
+ "learning_rate": 8.742553740855507e-06,
212
+ "loss": 0.4475,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.9584664536741214,
217
+ "grad_norm": 2.9460716247558594,
218
+ "learning_rate": 8.616725966539831e-06,
219
+ "loss": 0.4585,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.9904153354632588,
224
+ "grad_norm": 3.3959391117095947,
225
+ "learning_rate": 8.485899551698166e-06,
226
+ "loss": 0.4099,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 1.0223642172523961,
231
+ "grad_norm": 3.2734692096710205,
232
+ "learning_rate": 8.350255310200611e-06,
233
+ "loss": 0.4175,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 1.0543130990415335,
238
+ "grad_norm": 4.019186496734619,
239
+ "learning_rate": 8.209980714586955e-06,
240
+ "loss": 0.3992,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 1.0862619808306708,
245
+ "grad_norm": 3.6706490516662598,
246
+ "learning_rate": 8.065269636962765e-06,
247
+ "loss": 0.3998,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 1.1182108626198084,
252
+ "grad_norm": 3.0696253776550293,
253
+ "learning_rate": 7.916322081050708e-06,
254
+ "loss": 0.3891,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 1.1501597444089458,
259
+ "grad_norm": 2.8689801692962646,
260
+ "learning_rate": 7.76334390576742e-06,
261
+ "loss": 0.3915,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 1.182108626198083,
266
+ "grad_norm": 2.8732635974884033,
267
+ "learning_rate": 7.60654654070796e-06,
268
+ "loss": 0.3798,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 1.2140575079872205,
273
+ "grad_norm": 4.922475814819336,
274
+ "learning_rate": 7.446146693931111e-06,
275
+ "loss": 0.3801,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 1.2460063897763578,
280
+ "grad_norm": 3.499190330505371,
281
+ "learning_rate": 7.282366052449351e-06,
282
+ "loss": 0.3691,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 1.2779552715654952,
287
+ "grad_norm": 3.9021763801574707,
288
+ "learning_rate": 7.115430975837457e-06,
289
+ "loss": 0.3794,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 1.3099041533546325,
294
+ "grad_norm": 4.84491491317749,
295
+ "learning_rate": 6.945572183383229e-06,
296
+ "loss": 0.3479,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 1.34185303514377,
301
+ "grad_norm": 4.468801021575928,
302
+ "learning_rate": 6.773024435212678e-06,
303
+ "loss": 0.3492,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 1.3738019169329074,
308
+ "grad_norm": 4.482706069946289,
309
+ "learning_rate": 6.598026207830428e-06,
310
+ "loss": 0.3569,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 1.4057507987220448,
315
+ "grad_norm": 3.455061197280884,
316
+ "learning_rate": 6.4208193645237314e-06,
317
+ "loss": 0.3987,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 1.4376996805111821,
322
+ "grad_norm": 3.639888286590576,
323
+ "learning_rate": 6.241648821085666e-06,
324
+ "loss": 0.3589,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 1.4696485623003195,
329
+ "grad_norm": 6.02905797958374,
330
+ "learning_rate": 6.060762207319479e-06,
331
+ "loss": 0.4122,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 1.5015974440894568,
336
+ "grad_norm": 4.491400241851807,
337
+ "learning_rate": 5.878409524791931e-06,
338
+ "loss": 0.3542,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 1.5335463258785942,
343
+ "grad_norm": 3.850947618484497,
344
+ "learning_rate": 5.694842801308651e-06,
345
+ "loss": 0.3719,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 1.5654952076677318,
350
+ "grad_norm": 3.6334033012390137,
351
+ "learning_rate": 5.510315742589042e-06,
352
+ "loss": 0.3259,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.5974440894568689,
357
+ "grad_norm": 5.071944236755371,
358
+ "learning_rate": 5.325083381622165e-06,
359
+ "loss": 0.3428,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.6293929712460065,
364
+ "grad_norm": 3.8090009689331055,
365
+ "learning_rate": 5.139401726188208e-06,
366
+ "loss": 0.3764,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 1.6613418530351438,
371
+ "grad_norm": 3.925981283187866,
372
+ "learning_rate": 4.953527405032723e-06,
373
+ "loss": 0.383,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 1.6932907348242812,
378
+ "grad_norm": 6.125942230224609,
379
+ "learning_rate": 4.767717313182611e-06,
380
+ "loss": 0.3533,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 1.7252396166134185,
385
+ "grad_norm": 3.9766414165496826,
386
+ "learning_rate": 4.582228256894093e-06,
387
+ "loss": 0.3652,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.7571884984025559,
392
+ "grad_norm": 7.139044284820557,
393
+ "learning_rate": 4.397316598723385e-06,
394
+ "loss": 0.3213,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 1.7891373801916934,
399
+ "grad_norm": 4.280309200286865,
400
+ "learning_rate": 4.2132379032105695e-06,
401
+ "loss": 0.3486,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 1.8210862619808306,
406
+ "grad_norm": 3.9839210510253906,
407
+ "learning_rate": 4.030246583666437e-06,
408
+ "loss": 0.3161,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 1.8530351437699681,
413
+ "grad_norm": 5.437602519989014,
414
+ "learning_rate": 3.848595550550401e-06,
415
+ "loss": 0.3472,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 1.8849840255591053,
420
+ "grad_norm": 5.817410469055176,
421
+ "learning_rate": 3.668535861925509e-06,
422
+ "loss": 0.3888,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 1.9169329073482428,
427
+ "grad_norm": 5.5709381103515625,
428
+ "learning_rate": 3.4903163764736104e-06,
429
+ "loss": 0.3225,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 1.9488817891373802,
434
+ "grad_norm": 4.854086399078369,
435
+ "learning_rate": 3.314183409550293e-06,
436
+ "loss": 0.3637,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 1.9808306709265175,
441
+ "grad_norm": 5.341320037841797,
442
+ "learning_rate": 3.140380392754901e-06,
443
+ "loss": 0.3309,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 2.012779552715655,
448
+ "grad_norm": 4.052433013916016,
449
+ "learning_rate": 2.969147537486175e-06,
450
+ "loss": 0.3188,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 2.0447284345047922,
455
+ "grad_norm": 6.213695049285889,
456
+ "learning_rate": 2.800721502948506e-06,
457
+ "loss": 0.3058,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 2.07667731629393,
462
+ "grad_norm": 5.307283878326416,
463
+ "learning_rate": 2.635335069067617e-06,
464
+ "loss": 0.3417,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 2.108626198083067,
469
+ "grad_norm": 5.063953876495361,
470
+ "learning_rate": 2.4732168147677927e-06,
471
+ "loss": 0.3195,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 2.1405750798722045,
476
+ "grad_norm": 7.373411655426025,
477
+ "learning_rate": 2.314590802055232e-06,
478
+ "loss": 0.2989,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 2.1725239616613417,
483
+ "grad_norm": 9.082876205444336,
484
+ "learning_rate": 2.159676266344222e-06,
485
+ "loss": 0.3187,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 2.2044728434504792,
490
+ "grad_norm": 7.071778297424316,
491
+ "learning_rate": 2.0086873134540626e-06,
492
+ "loss": 0.3064,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 2.236421725239617,
497
+ "grad_norm": 4.376129627227783,
498
+ "learning_rate": 1.8618326236955908e-06,
499
+ "loss": 0.3114,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 2.268370607028754,
504
+ "grad_norm": 6.112962245941162,
505
+ "learning_rate": 1.7193151634562071e-06,
506
+ "loss": 0.2955,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 2.3003194888178915,
511
+ "grad_norm": 5.760268688201904,
512
+ "learning_rate": 1.581331904682089e-06,
513
+ "loss": 0.2825,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 2.3322683706070286,
518
+ "grad_norm": 6.972622394561768,
519
+ "learning_rate": 1.4480735526452427e-06,
520
+ "loss": 0.2928,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 2.364217252396166,
525
+ "grad_norm": 8.442282676696777,
526
+ "learning_rate": 1.319724282371664e-06,
527
+ "loss": 0.3024,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 2.3961661341853033,
532
+ "grad_norm": 4.642228603363037,
533
+ "learning_rate": 1.1964614840949002e-06,
534
+ "loss": 0.3522,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 2.428115015974441,
539
+ "grad_norm": 4.407663822174072,
540
+ "learning_rate": 1.078455518086784e-06,
541
+ "loss": 0.2863,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 2.460063897763578,
546
+ "grad_norm": 5.7068986892700195,
547
+ "learning_rate": 9.658694792042284e-07,
548
+ "loss": 0.273,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 2.4920127795527156,
553
+ "grad_norm": 9.480902671813965,
554
+ "learning_rate": 8.58858971477457e-07,
555
+ "loss": 0.2948,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 2.523961661341853,
560
+ "grad_norm": 6.3506693840026855,
561
+ "learning_rate": 7.575718930512516e-07,
562
+ "loss": 0.2945,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 2.5559105431309903,
567
+ "grad_norm": 4.636996269226074,
568
+ "learning_rate": 6.621482317764105e-07,
569
+ "loss": 0.2694,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 2.587859424920128,
574
+ "grad_norm": 6.740283489227295,
575
+ "learning_rate": 5.727198717339511e-07,
576
+ "loss": 0.2632,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 2.619808306709265,
581
+ "grad_norm": 5.469799518585205,
582
+ "learning_rate": 4.894104109594466e-07,
583
+ "loss": 0.2781,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 2.6517571884984026,
588
+ "grad_norm": 8.596780776977539,
589
+ "learning_rate": 4.123349906194357e-07,
590
+ "loss": 0.3137,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 2.68370607028754,
595
+ "grad_norm": 6.271667957305908,
596
+ "learning_rate": 3.416001358759635e-07,
597
+ "loss": 0.2815,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 2.7156549520766773,
602
+ "grad_norm": 10.2745361328125,
603
+ "learning_rate": 2.7730360865923954e-07,
604
+ "loss": 0.3089,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 2.747603833865815,
609
+ "grad_norm": 5.311823844909668,
610
+ "learning_rate": 2.1953427255185122e-07,
611
+ "loss": 0.3243,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 2.779552715654952,
616
+ "grad_norm": 5.055395126342773,
617
+ "learning_rate": 1.6837196997130434e-07,
618
+ "loss": 0.2945,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 2.8115015974440896,
623
+ "grad_norm": 9.366786003112793,
624
+ "learning_rate": 1.2388741182062348e-07,
625
+ "loss": 0.3142,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 2.8434504792332267,
630
+ "grad_norm": 6.428186416625977,
631
+ "learning_rate": 8.614207975952083e-08,
632
+ "loss": 0.2833,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 2.8753993610223643,
637
+ "grad_norm": 6.8983612060546875,
638
+ "learning_rate": 5.518814123121885e-08,
639
+ "loss": 0.3235,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 2.9073482428115014,
644
+ "grad_norm": 6.682745933532715,
645
+ "learning_rate": 3.10683773623488e-08,
646
+ "loss": 0.3097,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 2.939297124600639,
651
+ "grad_norm": 7.35684871673584,
652
+ "learning_rate": 1.3816123835588835e-08,
653
+ "loss": 0.2829,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 2.9712460063897765,
658
+ "grad_norm": 5.339282035827637,
659
+ "learning_rate": 3.4552248167507576e-09,
660
+ "loss": 0.3004,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 3.0,
665
+ "step": 939,
666
+ "total_flos": 2.4342577580448154e+17,
667
+ "train_loss": 0.41667796907841337,
668
+ "train_runtime": 499.1967,
669
+ "train_samples_per_second": 60.097,
670
+ "train_steps_per_second": 1.881
671
+ }
672
+ ],
673
+ "logging_steps": 10,
674
+ "max_steps": 939,
675
+ "num_input_tokens_seen": 0,
676
+ "num_train_epochs": 3,
677
+ "save_steps": 2000,
678
+ "stateful_callbacks": {
679
+ "TrainerControl": {
680
+ "args": {
681
+ "should_epoch_stop": false,
682
+ "should_evaluate": false,
683
+ "should_log": false,
684
+ "should_save": true,
685
+ "should_training_stop": true
686
+ },
687
+ "attributes": {}
688
+ }
689
+ },
690
+ "total_flos": 2.4342577580448154e+17,
691
+ "train_batch_size": 4,
692
+ "trial_name": null,
693
+ "trial_params": null
694
+ }
gsm8k__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: sft
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # sft
18
+
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the gsm8k__llama3_8b_instruct__n5000_t1t2_s0_bare_100_r8_bs4_lr1e5_e3_f_lora_sft dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 8
44
+ - total_train_batch_size: 32
45
+ - total_eval_batch_size: 64
46
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 3
50
+
51
+ ### Training results
52
+
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - PEFT 0.15.2
58
+ - Transformers 4.52.4
59
+ - Pytorch 2.7.0+cu126
60
+ - Datasets 3.6.0
61
+ - Tokenizers 0.21.1
gsm8k__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "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": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "k_proj",
28
+ "down_proj",
29
+ "gate_proj",
30
+ "up_proj",
31
+ "v_proj",
32
+ "o_proj",
33
+ "q_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
gsm8k__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 2.1400181022916608e+17,
4
+ "train_loss": 0.44269738639124667,
5
+ "train_runtime": 464.0428,
6
+ "train_samples_per_second": 64.649,
7
+ "train_steps_per_second": 2.024
8
+ }
gsm8k__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
gsm8k__llama3_8b_instruct__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2