Hugging Face's logo

jjee2
/
lora_recycle

TensorBoard
Safetensors
GGUF
conversational
Model card Files
xet
 Metrics Community
jjee2 commited on
Commit
5bcfdc4
·
verified ·
1 Parent(s): 386a1a9

Add chchen__Llama-3.1-8B-Instruct-SAA-700

Browse files
Files changed (19) hide show
  1. .gitattributes +1 -0
  2. chchen__Llama-3.1-8B-Instruct-SAA-700/.gitattributes +36 -0
  3. chchen__Llama-3.1-8B-Instruct-SAA-700/.ipynb_checkpoints/lora_orpo-checkpoint.yaml +44 -0
  4. chchen__Llama-3.1-8B-Instruct-SAA-700/README.md +82 -0
  5. chchen__Llama-3.1-8B-Instruct-SAA-700/adapter_config.json +34 -0
  6. chchen__Llama-3.1-8B-Instruct-SAA-700/adapter_model.safetensors +3 -0
  7. chchen__Llama-3.1-8B-Instruct-SAA-700/all_results.json +22 -0
  8. chchen__Llama-3.1-8B-Instruct-SAA-700/eval_results.json +17 -0
  9. chchen__Llama-3.1-8B-Instruct-SAA-700/lora_orpo.yaml +44 -0
  10. chchen__Llama-3.1-8B-Instruct-SAA-700/special_tokens_map.json +17 -0
  11. chchen__Llama-3.1-8B-Instruct-SAA-700/tokenizer.json +3 -0
  12. chchen__Llama-3.1-8B-Instruct-SAA-700/tokenizer_config.json +2065 -0
  13. chchen__Llama-3.1-8B-Instruct-SAA-700/train_results.json +8 -0
  14. chchen__Llama-3.1-8B-Instruct-SAA-700/trainer_log.jsonl +47 -0
  15. chchen__Llama-3.1-8B-Instruct-SAA-700/trainer_state.json +831 -0
  16. chchen__Llama-3.1-8B-Instruct-SAA-700/training_args.bin +3 -0
  17. chchen__Llama-3.1-8B-Instruct-SAA-700/training_eval_loss.png +0 -0
  18. chchen__Llama-3.1-8B-Instruct-SAA-700/training_loss.png +0 -0
  19. chchen__Llama-3.1-8B-Instruct-SAA-700/training_rewards_accuracies.png +0 -0
.gitattributes CHANGED
@@ -583,3 +583,4 @@ eltorio__Llama-3.1-8B-appreciation/tokenizer.json filter=lfs diff=lfs merge=lfs
583
  bane5631__5c5a255d-d71b-4495-b6f6-83741e8f83c0/last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
584
  bane5631__5c5a255d-d71b-4495-b6f6-83741e8f83c0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
585
  clembench-playpen__meta-llama-Meta-Llama-3.1-8B-Instruct_SFT_E1_D60001/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
583
  bane5631__5c5a255d-d71b-4495-b6f6-83741e8f83c0/last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
584
  bane5631__5c5a255d-d71b-4495-b6f6-83741e8f83c0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
585
  clembench-playpen__meta-llama-Meta-Llama-3.1-8B-Instruct_SFT_E1_D60001/tokenizer.json filter=lfs diff=lfs merge=lfs -text
586
+ chchen__Llama-3.1-8B-Instruct-SAA-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
chchen__Llama-3.1-8B-Instruct-SAA-700/.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz 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
+ *.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
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chchen__Llama-3.1-8B-Instruct-SAA-700/.ipynb_checkpoints/lora_orpo-checkpoint.yaml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ### model
2
+ model_name_or_path: meta-llama/Llama-3.1-8B-Instruct
3
+
4
+ ### method
5
+ stage: dpo
6
+ pref_loss: orpo
7
+ do_train: true
8
+ finetuning_type: lora
9
+ lora_target: all
10
+
11
+ ### dataset
12
+ dataset: bct_non_cot_dpo_700
13
+ dataset_dir: data_private
14
+ template: llama3
15
+ cutoff_len: 1024
16
+ # max_samples: 1000
17
+ overwrite_cache: true
18
+ preprocessing_num_workers: 16
19
+
20
+ ### output
21
+ output_dir: saves/Llama-3.1-8B-Instruct/lora/saa-700
22
+ logging_steps: 10
23
+ save_steps: 50
24
+ plot_loss: true
25
+ overwrite_output_dir: true
26
+ save_total_limit: 3
27
+ load_best_model_at_end: true
28
+ push_to_hub: true
29
+ hub_model_id: chchen/Llama-3.1-8B-Instruct-SAA-700
30
+
31
+ ### train
32
+ per_device_train_batch_size: 2
33
+ gradient_accumulation_steps: 8
34
+ learning_rate: 0.000005
35
+ num_train_epochs: 10.0
36
+ lr_scheduler_type: cosine
37
+ warmup_ratio: 0.1
38
+ bf16: true
39
+
40
+ ### eval
41
+ val_size: 0.1
42
+ per_device_eval_batch_size: 2
43
+ evaluation_strategy: steps
44
+ eval_steps: 50
chchen__Llama-3.1-8B-Instruct-SAA-700/README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.1-8B-Instruct
3
+ library_name: peft
4
+ license: llama3.1
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - trl
9
+ - dpo
10
+ - generated_from_trainer
11
+ model-index:
12
+ - name: Llama-3.1-8B-Instruct-SAA-700
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # Llama-3.1-8B-Instruct-SAA-700
20
+
21
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the bct_non_cot_dpo_700 dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.0846
24
+ - Rewards/chosen: -0.0062
25
+ - Rewards/rejected: -0.0635
26
+ - Rewards/accuracies: 0.8857
27
+ - Rewards/margins: 0.0573
28
+ - Logps/rejected: -0.6353
29
+ - Logps/chosen: -0.0623
30
+ - Logits/rejected: -0.4422
31
+ - Logits/chosen: -0.3590
32
+ - Sft Loss: 0.0098
33
+ - Odds Ratio Loss: 0.7473
34
+
35
+ ## Model description
36
+
37
+ More information needed
38
+
39
+ ## Intended uses & limitations
40
+
41
+ More information needed
42
+
43
+ ## Training and evaluation data
44
+
45
+ More information needed
46
+
47
+ ## Training procedure
48
+
49
+ ### Training hyperparameters
50
+
51
+ The following hyperparameters were used during training:
52
+ - learning_rate: 5e-06
53
+ - train_batch_size: 2
54
+ - eval_batch_size: 2
55
+ - seed: 42
56
+ - gradient_accumulation_steps: 8
57
+ - total_train_batch_size: 16
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: cosine
60
+ - lr_scheduler_warmup_ratio: 0.1
61
+ - num_epochs: 10.0
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Sft Loss | Odds Ratio Loss |
66
+ |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:---------------:|
67
+ | 1.3943 | 1.2698 | 50 | 1.1722 | -0.1129 | -0.1708 | 0.8714 | 0.0579 | -1.7085 | -1.1294 | -0.5079 | -0.3998 | 0.1369 | 10.3529 |
68
+ | 0.2668 | 2.5397 | 100 | 0.1508 | -0.0126 | -0.0716 | 0.8857 | 0.0590 | -0.7158 | -0.1261 | -0.4935 | -0.3919 | 0.0160 | 1.3479 |
69
+ | 0.1305 | 3.8095 | 150 | 0.0939 | -0.0069 | -0.0601 | 0.8857 | 0.0531 | -0.6007 | -0.0692 | -0.4467 | -0.3595 | 0.0109 | 0.8298 |
70
+ | 0.126 | 5.0794 | 200 | 0.0885 | -0.0065 | -0.0608 | 0.8857 | 0.0542 | -0.6076 | -0.0653 | -0.4471 | -0.3614 | 0.0103 | 0.7822 |
71
+ | 0.0881 | 6.3492 | 250 | 0.0876 | -0.0064 | -0.0617 | 0.8857 | 0.0553 | -0.6175 | -0.0642 | -0.4433 | -0.3588 | 0.0102 | 0.7739 |
72
+ | 0.1042 | 7.6190 | 300 | 0.0846 | -0.0062 | -0.0635 | 0.8857 | 0.0573 | -0.6353 | -0.0623 | -0.4422 | -0.3590 | 0.0098 | 0.7473 |
73
+ | 0.1405 | 8.8889 | 350 | 0.0853 | -0.0063 | -0.0644 | 0.8857 | 0.0581 | -0.6435 | -0.0627 | -0.4405 | -0.3572 | 0.0099 | 0.7540 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - PEFT 0.12.0
79
+ - Transformers 4.45.2
80
+ - Pytorch 2.3.0
81
+ - Datasets 2.19.0
82
+ - Tokenizers 0.20.0
chchen__Llama-3.1-8B-Instruct-SAA-700/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "down_proj",
25
+ "gate_proj",
26
+ "v_proj",
27
+ "o_proj",
28
+ "q_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
chchen__Llama-3.1-8B-Instruct-SAA-700/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30429c79bbc4a92e87e0eed4a1881de63e1cca7fde88710db1473eebf2ddf090
3
+ size 83945296
chchen__Llama-3.1-8B-Instruct-SAA-700/all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.904761904761905,
3
+ "eval_logits/chosen": -0.3590058982372284,
4
+ "eval_logits/rejected": -0.4422083795070648,
5
+ "eval_logps/chosen": -0.06231304630637169,
6
+ "eval_logps/rejected": -0.635312557220459,
7
+ "eval_loss": 0.08455940335988998,
8
+ "eval_odds_ratio_loss": 0.7473430633544922,
9
+ "eval_rewards/accuracies": 0.8857142925262451,
10
+ "eval_rewards/chosen": -0.006231305189430714,
11
+ "eval_rewards/margins": 0.05729994922876358,
12
+ "eval_rewards/rejected": -0.06353124976158142,
13
+ "eval_runtime": 2.8476,
14
+ "eval_samples_per_second": 24.582,
15
+ "eval_sft_loss": 0.009825083427131176,
16
+ "eval_steps_per_second": 12.291,
17
+ "total_flos": 7.038458947436544e+16,
18
+ "train_loss": 0.3784435097987835,
19
+ "train_runtime": 852.09,
20
+ "train_samples_per_second": 7.394,
21
+ "train_steps_per_second": 0.458
22
+ }
chchen__Llama-3.1-8B-Instruct-SAA-700/eval_results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.904761904761905,
3
+ "eval_logits/chosen": -0.3590058982372284,
4
+ "eval_logits/rejected": -0.4422083795070648,
5
+ "eval_logps/chosen": -0.06231304630637169,
6
+ "eval_logps/rejected": -0.635312557220459,
7
+ "eval_loss": 0.08455940335988998,
8
+ "eval_odds_ratio_loss": 0.7473430633544922,
9
+ "eval_rewards/accuracies": 0.8857142925262451,
10
+ "eval_rewards/chosen": -0.006231305189430714,
11
+ "eval_rewards/margins": 0.05729994922876358,
12
+ "eval_rewards/rejected": -0.06353124976158142,
13
+ "eval_runtime": 2.8476,
14
+ "eval_samples_per_second": 24.582,
15
+ "eval_sft_loss": 0.009825083427131176,
16
+ "eval_steps_per_second": 12.291
17
+ }
chchen__Llama-3.1-8B-Instruct-SAA-700/lora_orpo.yaml ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ### model
2
+ model_name_or_path: meta-llama/Llama-3.1-8B-Instruct
3
+
4
+ ### method
5
+ stage: dpo
6
+ pref_loss: orpo
7
+ do_train: true
8
+ finetuning_type: lora
9
+ lora_target: all
10
+
11
+ ### dataset
12
+ dataset: bct_non_cot_dpo_700
13
+ dataset_dir: data_private
14
+ template: llama3
15
+ cutoff_len: 1024
16
+ # max_samples: 1000
17
+ overwrite_cache: true
18
+ preprocessing_num_workers: 16
19
+
20
+ ### output
21
+ output_dir: saves/Llama-3.1-8B-Instruct/lora/saa-700
22
+ logging_steps: 10
23
+ save_steps: 50
24
+ plot_loss: true
25
+ overwrite_output_dir: true
26
+ save_total_limit: 3
27
+ load_best_model_at_end: true
28
+ push_to_hub: true
29
+ hub_model_id: chchen/Llama-3.1-8B-Instruct-SAA-700
30
+
31
+ ### train
32
+ per_device_train_batch_size: 2
33
+ gradient_accumulation_steps: 8
34
+ learning_rate: 0.000005
35
+ num_train_epochs: 10.0
36
+ lr_scheduler_type: cosine
37
+ warmup_ratio: 0.1
38
+ bf16: true
39
+
40
+ ### eval
41
+ val_size: 0.1
42
+ per_device_eval_batch_size: 2
43
+ evaluation_strategy: steps
44
+ eval_steps: 50
chchen__Llama-3.1-8B-Instruct-SAA-700/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
chchen__Llama-3.1-8B-Instruct-SAA-700/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
chchen__Llama-3.1-8B-Instruct-SAA-700/tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
chchen__Llama-3.1-8B-Instruct-SAA-700/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.904761904761905,
3
+ "total_flos": 7.038458947436544e+16,
4
+ "train_loss": 0.3784435097987835,
5
+ "train_runtime": 852.09,
6
+ "train_samples_per_second": 7.394,
7
+ "train_steps_per_second": 0.458
8
+ }
chchen__Llama-3.1-8B-Instruct-SAA-700/trainer_log.jsonl ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 390, "loss": 1.814, "accuracy": 0.731249988079071, "learning_rate": 1.282051282051282e-06, "epoch": 0.25396825396825395, "percentage": 2.56, "elapsed_time": "0:00:20", "remaining_time": "0:13:11"}
2
+ {"current_steps": 20, "total_steps": 390, "loss": 1.7502, "accuracy": 0.78125, "learning_rate": 2.564102564102564e-06, "epoch": 0.5079365079365079, "percentage": 5.13, "elapsed_time": "0:00:41", "remaining_time": "0:12:45"}
3
+ {"current_steps": 30, "total_steps": 390, "loss": 1.7465, "accuracy": 0.731249988079071, "learning_rate": 3.846153846153847e-06, "epoch": 0.7619047619047619, "percentage": 7.69, "elapsed_time": "0:01:02", "remaining_time": "0:12:34"}
4
+ {"current_steps": 40, "total_steps": 390, "loss": 1.6307, "accuracy": 0.7437499761581421, "learning_rate": 4.999899863449631e-06, "epoch": 1.0158730158730158, "percentage": 10.26, "elapsed_time": "0:01:23", "remaining_time": "0:12:06"}
5
+ {"current_steps": 50, "total_steps": 390, "loss": 1.3943, "accuracy": 0.75, "learning_rate": 4.9878931808274796e-06, "epoch": 1.2698412698412698, "percentage": 12.82, "elapsed_time": "0:01:43", "remaining_time": "0:11:45"}
6
+ {"current_steps": 50, "total_steps": 390, "eval_loss": 1.1722259521484375, "epoch": 1.2698412698412698, "percentage": 12.82, "elapsed_time": "0:01:46", "remaining_time": "0:12:05"}
7
+ {"current_steps": 60, "total_steps": 390, "loss": 1.0229, "accuracy": 0.762499988079071, "learning_rate": 4.955969343539162e-06, "epoch": 1.5238095238095237, "percentage": 15.38, "elapsed_time": "0:02:10", "remaining_time": "0:11:59"}
8
+ {"current_steps": 70, "total_steps": 390, "loss": 0.7628, "accuracy": 0.8062499761581421, "learning_rate": 4.90438392204474e-06, "epoch": 1.7777777777777777, "percentage": 17.95, "elapsed_time": "0:02:31", "remaining_time": "0:11:33"}
9
+ {"current_steps": 80, "total_steps": 390, "loss": 0.5271, "accuracy": 0.8062499761581421, "learning_rate": 4.83354989019146e-06, "epoch": 2.0317460317460316, "percentage": 20.51, "elapsed_time": "0:02:51", "remaining_time": "0:11:06"}
10
+ {"current_steps": 90, "total_steps": 390, "loss": 0.3349, "accuracy": 0.8687499761581421, "learning_rate": 4.744034319097536e-06, "epoch": 2.2857142857142856, "percentage": 23.08, "elapsed_time": "0:03:12", "remaining_time": "0:10:43"}
11
+ {"current_steps": 100, "total_steps": 390, "loss": 0.2668, "accuracy": 0.768750011920929, "learning_rate": 4.636553837390051e-06, "epoch": 2.5396825396825395, "percentage": 25.64, "elapsed_time": "0:03:34", "remaining_time": "0:10:22"}
12
+ {"current_steps": 100, "total_steps": 390, "eval_loss": 0.15076632797718048, "epoch": 2.5396825396825395, "percentage": 25.64, "elapsed_time": "0:03:37", "remaining_time": "0:10:30"}
13
+ {"current_steps": 110, "total_steps": 390, "loss": 0.2015, "accuracy": 0.793749988079071, "learning_rate": 4.511968894140639e-06, "epoch": 2.7936507936507935, "percentage": 28.21, "elapsed_time": "0:04:00", "remaining_time": "0:10:11"}
14
+ {"current_steps": 120, "total_steps": 390, "loss": 0.2015, "accuracy": 0.800000011920929, "learning_rate": 4.3712768704277535e-06, "epoch": 3.0476190476190474, "percentage": 30.77, "elapsed_time": "0:04:20", "remaining_time": "0:09:45"}
15
+ {"current_steps": 130, "total_steps": 390, "loss": 0.1349, "accuracy": 0.8374999761581421, "learning_rate": 4.215604094671835e-06, "epoch": 3.3015873015873014, "percentage": 33.33, "elapsed_time": "0:04:42", "remaining_time": "0:09:24"}
16
+ {"current_steps": 140, "total_steps": 390, "loss": 0.1373, "accuracy": 0.800000011920929, "learning_rate": 4.046196825665638e-06, "epoch": 3.5555555555555554, "percentage": 35.9, "elapsed_time": "0:05:02", "remaining_time": "0:09:01"}
17
+ {"current_steps": 150, "total_steps": 390, "loss": 0.1305, "accuracy": 0.800000011920929, "learning_rate": 3.8644112754862614e-06, "epoch": 3.8095238095238093, "percentage": 38.46, "elapsed_time": "0:05:22", "remaining_time": "0:08:36"}
18
+ {"current_steps": 150, "total_steps": 390, "eval_loss": 0.09387854486703873, "epoch": 3.8095238095238093, "percentage": 38.46, "elapsed_time": "0:05:25", "remaining_time": "0:08:41"}
19
+ {"current_steps": 160, "total_steps": 390, "loss": 0.1756, "accuracy": 0.7749999761581421, "learning_rate": 3.6717027521617593e-06, "epoch": 4.063492063492063, "percentage": 41.03, "elapsed_time": "0:05:48", "remaining_time": "0:08:21"}
20
+ {"current_steps": 170, "total_steps": 390, "loss": 0.1069, "accuracy": 0.824999988079071, "learning_rate": 3.4696140090121377e-06, "epoch": 4.317460317460317, "percentage": 43.59, "elapsed_time": "0:06:08", "remaining_time": "0:07:56"}
21
+ {"current_steps": 180, "total_steps": 390, "loss": 0.1321, "accuracy": 0.8187500238418579, "learning_rate": 3.2597628939356174e-06, "epoch": 4.571428571428571, "percentage": 46.15, "elapsed_time": "0:06:30", "remaining_time": "0:07:35"}
22
+ {"current_steps": 190, "total_steps": 390, "loss": 0.128, "accuracy": 0.824999988079071, "learning_rate": 3.043829397515419e-06, "epoch": 4.825396825396825, "percentage": 48.72, "elapsed_time": "0:06:50", "remaining_time": "0:07:12"}
23
+ {"current_steps": 200, "total_steps": 390, "loss": 0.126, "accuracy": 0.8125, "learning_rate": 2.8235422036351384e-06, "epoch": 5.079365079365079, "percentage": 51.28, "elapsed_time": "0:07:12", "remaining_time": "0:06:50"}
24
+ {"current_steps": 200, "total_steps": 390, "eval_loss": 0.0884871631860733, "epoch": 5.079365079365079, "percentage": 51.28, "elapsed_time": "0:07:14", "remaining_time": "0:06:53"}
25
+ {"current_steps": 210, "total_steps": 390, "loss": 0.1274, "accuracy": 0.8374999761581421, "learning_rate": 2.6006648502735384e-06, "epoch": 5.333333333333333, "percentage": 53.85, "elapsed_time": "0:07:37", "remaining_time": "0:06:32"}
26
+ {"current_steps": 220, "total_steps": 390, "loss": 0.0868, "accuracy": 0.875, "learning_rate": 2.376981611270305e-06, "epoch": 5.587301587301587, "percentage": 56.41, "elapsed_time": "0:07:58", "remaining_time": "0:06:09"}
27
+ {"current_steps": 230, "total_steps": 390, "loss": 0.1317, "accuracy": 0.8125, "learning_rate": 2.154283212088168e-06, "epoch": 5.841269841269841, "percentage": 58.97, "elapsed_time": "0:08:19", "remaining_time": "0:05:47"}
28
+ {"current_steps": 240, "total_steps": 390, "loss": 0.1121, "accuracy": 0.8187500238418579, "learning_rate": 1.934352493925695e-06, "epoch": 6.095238095238095, "percentage": 61.54, "elapsed_time": "0:08:40", "remaining_time": "0:05:25"}
29
+ {"current_steps": 250, "total_steps": 390, "loss": 0.0881, "accuracy": 0.8687499761581421, "learning_rate": 1.7189501409486061e-06, "epoch": 6.349206349206349, "percentage": 64.1, "elapsed_time": "0:09:01", "remaining_time": "0:05:03"}
30
+ {"current_steps": 250, "total_steps": 390, "eval_loss": 0.08761369436979294, "epoch": 6.349206349206349, "percentage": 64.1, "elapsed_time": "0:09:04", "remaining_time": "0:05:04"}
31
+ {"current_steps": 260, "total_steps": 390, "loss": 0.1342, "accuracy": 0.831250011920929, "learning_rate": 1.509800584902108e-06, "epoch": 6.603174603174603, "percentage": 66.67, "elapsed_time": "0:09:26", "remaining_time": "0:04:43"}
32
+ {"current_steps": 270, "total_steps": 390, "loss": 0.0984, "accuracy": 0.8812500238418579, "learning_rate": 1.3085781999467303e-06, "epoch": 6.857142857142857, "percentage": 69.23, "elapsed_time": "0:09:47", "remaining_time": "0:04:21"}
33
+ {"current_steps": 280, "total_steps": 390, "loss": 0.1181, "accuracy": 0.824999988079071, "learning_rate": 1.1168938982367162e-06, "epoch": 7.111111111111111, "percentage": 71.79, "elapsed_time": "0:10:08", "remaining_time": "0:03:59"}
34
+ {"current_steps": 290, "total_steps": 390, "loss": 0.108, "accuracy": 0.8187500238418579, "learning_rate": 9.362822335518062e-07, "epoch": 7.365079365079365, "percentage": 74.36, "elapsed_time": "0:10:29", "remaining_time": "0:03:37"}
35
+ {"current_steps": 300, "total_steps": 390, "loss": 0.1042, "accuracy": 0.8500000238418579, "learning_rate": 7.681891162260016e-07, "epoch": 7.619047619047619, "percentage": 76.92, "elapsed_time": "0:10:50", "remaining_time": "0:03:15"}
36
+ {"current_steps": 300, "total_steps": 390, "eval_loss": 0.08455940335988998, "epoch": 7.619047619047619, "percentage": 76.92, "elapsed_time": "0:10:52", "remaining_time": "0:03:15"}
37
+ {"current_steps": 310, "total_steps": 390, "loss": 0.1001, "accuracy": 0.887499988079071, "learning_rate": 6.139602377230247e-07, "epoch": 7.8730158730158735, "percentage": 79.49, "elapsed_time": "0:11:17", "remaining_time": "0:02:54"}
38
+ {"current_steps": 320, "total_steps": 390, "loss": 0.1097, "accuracy": 0.8187500238418579, "learning_rate": 4.748302975270838e-07, "epoch": 8.126984126984127, "percentage": 82.05, "elapsed_time": "0:11:38", "remaining_time": "0:02:32"}
39
+ {"current_steps": 330, "total_steps": 390, "loss": 0.0902, "accuracy": 0.8812500238418579, "learning_rate": 3.51913118594458e-07, "epoch": 8.380952380952381, "percentage": 84.62, "elapsed_time": "0:11:57", "remaining_time": "0:02:10"}
40
+ {"current_steps": 340, "total_steps": 390, "loss": 0.0848, "accuracy": 0.8812500238418579, "learning_rate": 2.4619273049796e-07, "epoch": 8.634920634920634, "percentage": 87.18, "elapsed_time": "0:12:19", "remaining_time": "0:01:48"}
41
+ {"current_steps": 350, "total_steps": 390, "loss": 0.1405, "accuracy": 0.84375, "learning_rate": 1.5851549164932118e-07, "epoch": 8.88888888888889, "percentage": 89.74, "elapsed_time": "0:12:39", "remaining_time": "0:01:26"}
42
+ {"current_steps": 350, "total_steps": 390, "eval_loss": 0.0852903425693512, "epoch": 8.88888888888889, "percentage": 89.74, "elapsed_time": "0:12:42", "remaining_time": "0:01:27"}
43
+ {"current_steps": 360, "total_steps": 390, "loss": 0.094, "accuracy": 0.862500011920929, "learning_rate": 8.958331366609424e-08, "epoch": 9.142857142857142, "percentage": 92.31, "elapsed_time": "0:13:07", "remaining_time": "0:01:05"}
44
+ {"current_steps": 370, "total_steps": 390, "loss": 0.1036, "accuracy": 0.84375, "learning_rate": 3.994804212627462e-08, "epoch": 9.396825396825397, "percentage": 94.87, "elapsed_time": "0:13:27", "remaining_time": "0:00:43"}
45
+ {"current_steps": 380, "total_steps": 390, "loss": 0.112, "accuracy": 0.856249988079071, "learning_rate": 1.0007038696262517e-08, "epoch": 9.65079365079365, "percentage": 97.44, "elapsed_time": "0:13:48", "remaining_time": "0:00:21"}
46
+ {"current_steps": 390, "total_steps": 390, "loss": 0.0909, "accuracy": 0.8687499761581421, "learning_rate": 0.0, "epoch": 9.904761904761905, "percentage": 100.0, "elapsed_time": "0:14:09", "remaining_time": "0:00:00"}
47
+ {"current_steps": 390, "total_steps": 390, "epoch": 9.904761904761905, "percentage": 100.0, "elapsed_time": "0:14:12", "remaining_time": "0:00:00"}
chchen__Llama-3.1-8B-Instruct-SAA-700/trainer_state.json ADDED
@@ -0,0 +1,831 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.08455940335988998,
3
+ "best_model_checkpoint": "saves/Llama-3.1-8B-Instruct/lora/saa-700/checkpoint-300",
4
+ "epoch": 9.904761904761905,
5
+ "eval_steps": 50,
6
+ "global_step": 390,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.25396825396825395,
13
+ "grad_norm": 6.622786998748779,
14
+ "learning_rate": 1.282051282051282e-06,
15
+ "logits/chosen": -0.43315809965133667,
16
+ "logits/rejected": -0.5123269557952881,
17
+ "logps/chosen": -1.7569204568862915,
18
+ "logps/rejected": -2.1466054916381836,
19
+ "loss": 1.814,
20
+ "odds_ratio_loss": 15.780923843383789,
21
+ "rewards/accuracies": 0.731249988079071,
22
+ "rewards/chosen": -0.17569205164909363,
23
+ "rewards/margins": 0.038968510925769806,
24
+ "rewards/rejected": -0.21466057002544403,
25
+ "sft_loss": 0.23589880764484406,
26
+ "step": 10
27
+ },
28
+ {
29
+ "epoch": 0.5079365079365079,
30
+ "grad_norm": 6.6683030128479,
31
+ "learning_rate": 2.564102564102564e-06,
32
+ "logits/chosen": -0.43245887756347656,
33
+ "logits/rejected": -0.49596747756004333,
34
+ "logps/chosen": -1.697622537612915,
35
+ "logps/rejected": -2.1181578636169434,
36
+ "loss": 1.7502,
37
+ "odds_ratio_loss": 15.375523567199707,
38
+ "rewards/accuracies": 0.78125,
39
+ "rewards/chosen": -0.1697622537612915,
40
+ "rewards/margins": 0.04205355793237686,
41
+ "rewards/rejected": -0.21181580424308777,
42
+ "sft_loss": 0.21262726187705994,
43
+ "step": 20
44
+ },
45
+ {
46
+ "epoch": 0.7619047619047619,
47
+ "grad_norm": 8.463303565979004,
48
+ "learning_rate": 3.846153846153847e-06,
49
+ "logits/chosen": -0.40924006700515747,
50
+ "logits/rejected": -0.48568296432495117,
51
+ "logps/chosen": -1.6889221668243408,
52
+ "logps/rejected": -2.0065219402313232,
53
+ "loss": 1.7465,
54
+ "odds_ratio_loss": 15.427533149719238,
55
+ "rewards/accuracies": 0.731249988079071,
56
+ "rewards/chosen": -0.16889220476150513,
57
+ "rewards/margins": 0.03175998851656914,
58
+ "rewards/rejected": -0.20065219700336456,
59
+ "sft_loss": 0.20373742282390594,
60
+ "step": 30
61
+ },
62
+ {
63
+ "epoch": 1.0158730158730158,
64
+ "grad_norm": 6.983005523681641,
65
+ "learning_rate": 4.999899863449631e-06,
66
+ "logits/chosen": -0.43422746658325195,
67
+ "logits/rejected": -0.5029093027114868,
68
+ "logps/chosen": -1.5778363943099976,
69
+ "logps/rejected": -2.05330228805542,
70
+ "loss": 1.6307,
71
+ "odds_ratio_loss": 14.251497268676758,
72
+ "rewards/accuracies": 0.7437499761581421,
73
+ "rewards/chosen": -0.157783642411232,
74
+ "rewards/margins": 0.04754657670855522,
75
+ "rewards/rejected": -0.20533022284507751,
76
+ "sft_loss": 0.2055801898241043,
77
+ "step": 40
78
+ },
79
+ {
80
+ "epoch": 1.2698412698412698,
81
+ "grad_norm": 6.3808979988098145,
82
+ "learning_rate": 4.9878931808274796e-06,
83
+ "logits/chosen": -0.43995872139930725,
84
+ "logits/rejected": -0.5162149667739868,
85
+ "logps/chosen": -1.3421008586883545,
86
+ "logps/rejected": -1.7787939310073853,
87
+ "loss": 1.3943,
88
+ "odds_ratio_loss": 12.231451034545898,
89
+ "rewards/accuracies": 0.75,
90
+ "rewards/chosen": -0.13421007990837097,
91
+ "rewards/margins": 0.043669313192367554,
92
+ "rewards/rejected": -0.17787939310073853,
93
+ "sft_loss": 0.17115621268749237,
94
+ "step": 50
95
+ },
96
+ {
97
+ "epoch": 1.2698412698412698,
98
+ "eval_logits/chosen": -0.3997752070426941,
99
+ "eval_logits/rejected": -0.5078760385513306,
100
+ "eval_logps/chosen": -1.129433035850525,
101
+ "eval_logps/rejected": -1.708479642868042,
102
+ "eval_loss": 1.1722259521484375,
103
+ "eval_odds_ratio_loss": 10.352947235107422,
104
+ "eval_rewards/accuracies": 0.8714285492897034,
105
+ "eval_rewards/chosen": -0.11294329166412354,
106
+ "eval_rewards/margins": 0.05790466442704201,
107
+ "eval_rewards/rejected": -0.17084796726703644,
108
+ "eval_runtime": 2.8514,
109
+ "eval_samples_per_second": 24.549,
110
+ "eval_sft_loss": 0.1369311660528183,
111
+ "eval_steps_per_second": 12.275,
112
+ "step": 50
113
+ },
114
+ {
115
+ "epoch": 1.5238095238095237,
116
+ "grad_norm": 4.983822822570801,
117
+ "learning_rate": 4.955969343539162e-06,
118
+ "logits/chosen": -0.4064231812953949,
119
+ "logits/rejected": -0.469343364238739,
120
+ "logps/chosen": -0.9726579785346985,
121
+ "logps/rejected": -1.4070051908493042,
122
+ "loss": 1.0229,
123
+ "odds_ratio_loss": 9.085018157958984,
124
+ "rewards/accuracies": 0.762499988079071,
125
+ "rewards/chosen": -0.0972658023238182,
126
+ "rewards/margins": 0.04343472048640251,
127
+ "rewards/rejected": -0.1407005339860916,
128
+ "sft_loss": 0.11443070322275162,
129
+ "step": 60
130
+ },
131
+ {
132
+ "epoch": 1.7777777777777777,
133
+ "grad_norm": 2.7898340225219727,
134
+ "learning_rate": 4.90438392204474e-06,
135
+ "logits/chosen": -0.38613539934158325,
136
+ "logits/rejected": -0.45754584670066833,
137
+ "logps/chosen": -0.7166827917098999,
138
+ "logps/rejected": -1.1386511325836182,
139
+ "loss": 0.7628,
140
+ "odds_ratio_loss": 6.8942084312438965,
141
+ "rewards/accuracies": 0.8062499761581421,
142
+ "rewards/chosen": -0.07166828960180283,
143
+ "rewards/margins": 0.04219682514667511,
144
+ "rewards/rejected": -0.11386511474847794,
145
+ "sft_loss": 0.07338996976613998,
146
+ "step": 70
147
+ },
148
+ {
149
+ "epoch": 2.0317460317460316,
150
+ "grad_norm": 2.5899903774261475,
151
+ "learning_rate": 4.83354989019146e-06,
152
+ "logits/chosen": -0.4129558503627777,
153
+ "logits/rejected": -0.5041948556900024,
154
+ "logps/chosen": -0.4775570333003998,
155
+ "logps/rejected": -0.9863455891609192,
156
+ "loss": 0.5271,
157
+ "odds_ratio_loss": 4.772868633270264,
158
+ "rewards/accuracies": 0.8062499761581421,
159
+ "rewards/chosen": -0.04775569960474968,
160
+ "rewards/margins": 0.050878845155239105,
161
+ "rewards/rejected": -0.09863455593585968,
162
+ "sft_loss": 0.049840252846479416,
163
+ "step": 80
164
+ },
165
+ {
166
+ "epoch": 2.2857142857142856,
167
+ "grad_norm": 1.7005658149719238,
168
+ "learning_rate": 4.744034319097536e-06,
169
+ "logits/chosen": -0.37368327379226685,
170
+ "logits/rejected": -0.4539913535118103,
171
+ "logps/chosen": -0.30150529742240906,
172
+ "logps/rejected": -0.8815568685531616,
173
+ "loss": 0.3349,
174
+ "odds_ratio_loss": 3.050200939178467,
175
+ "rewards/accuracies": 0.8687499761581421,
176
+ "rewards/chosen": -0.030150527134537697,
177
+ "rewards/margins": 0.05800515413284302,
178
+ "rewards/rejected": -0.08815570175647736,
179
+ "sft_loss": 0.029899105429649353,
180
+ "step": 90
181
+ },
182
+ {
183
+ "epoch": 2.5396825396825395,
184
+ "grad_norm": 2.303098440170288,
185
+ "learning_rate": 4.636553837390051e-06,
186
+ "logits/chosen": -0.4066418707370758,
187
+ "logits/rejected": -0.48234590888023376,
188
+ "logps/chosen": -0.21859033405780792,
189
+ "logps/rejected": -0.6556078791618347,
190
+ "loss": 0.2668,
191
+ "odds_ratio_loss": 2.4264979362487793,
192
+ "rewards/accuracies": 0.768750011920929,
193
+ "rewards/chosen": -0.02185903489589691,
194
+ "rewards/margins": 0.04370176047086716,
195
+ "rewards/rejected": -0.06556079536676407,
196
+ "sft_loss": 0.024160917848348618,
197
+ "step": 100
198
+ },
199
+ {
200
+ "epoch": 2.5396825396825395,
201
+ "eval_logits/chosen": -0.3919348120689392,
202
+ "eval_logits/rejected": -0.49354618787765503,
203
+ "eval_logps/chosen": -0.12607190012931824,
204
+ "eval_logps/rejected": -0.7158276438713074,
205
+ "eval_loss": 0.15076632797718048,
206
+ "eval_odds_ratio_loss": 1.3478882312774658,
207
+ "eval_rewards/accuracies": 0.8857142925262451,
208
+ "eval_rewards/chosen": -0.012607189826667309,
209
+ "eval_rewards/margins": 0.058975573629140854,
210
+ "eval_rewards/rejected": -0.07158276438713074,
211
+ "eval_runtime": 2.85,
212
+ "eval_samples_per_second": 24.562,
213
+ "eval_sft_loss": 0.01597750373184681,
214
+ "eval_steps_per_second": 12.281,
215
+ "step": 100
216
+ },
217
+ {
218
+ "epoch": 2.7936507936507935,
219
+ "grad_norm": 2.9208037853240967,
220
+ "learning_rate": 4.511968894140639e-06,
221
+ "logits/chosen": -0.4233960509300232,
222
+ "logits/rejected": -0.49049830436706543,
223
+ "logps/chosen": -0.15838508307933807,
224
+ "logps/rejected": -0.5953269004821777,
225
+ "loss": 0.2015,
226
+ "odds_ratio_loss": 1.83855402469635,
227
+ "rewards/accuracies": 0.793749988079071,
228
+ "rewards/chosen": -0.015838507562875748,
229
+ "rewards/margins": 0.043694186955690384,
230
+ "rewards/rejected": -0.05953269079327583,
231
+ "sft_loss": 0.017660459503531456,
232
+ "step": 110
233
+ },
234
+ {
235
+ "epoch": 3.0476190476190474,
236
+ "grad_norm": 2.1344635486602783,
237
+ "learning_rate": 4.3712768704277535e-06,
238
+ "logits/chosen": -0.382506787776947,
239
+ "logits/rejected": -0.450620174407959,
240
+ "logps/chosen": -0.15453371405601501,
241
+ "logps/rejected": -0.6300913095474243,
242
+ "loss": 0.2015,
243
+ "odds_ratio_loss": 1.8098644018173218,
244
+ "rewards/accuracies": 0.800000011920929,
245
+ "rewards/chosen": -0.015453370288014412,
246
+ "rewards/margins": 0.04755576327443123,
247
+ "rewards/rejected": -0.06300913542509079,
248
+ "sft_loss": 0.020517611876130104,
249
+ "step": 120
250
+ },
251
+ {
252
+ "epoch": 3.3015873015873014,
253
+ "grad_norm": 1.941210389137268,
254
+ "learning_rate": 4.215604094671835e-06,
255
+ "logits/chosen": -0.38204818964004517,
256
+ "logits/rejected": -0.45048651099205017,
257
+ "logps/chosen": -0.09811689704656601,
258
+ "logps/rejected": -0.5908789038658142,
259
+ "loss": 0.1349,
260
+ "odds_ratio_loss": 1.2404112815856934,
261
+ "rewards/accuracies": 0.8374999761581421,
262
+ "rewards/chosen": -0.00981169007718563,
263
+ "rewards/margins": 0.0492762066423893,
264
+ "rewards/rejected": -0.05908789485692978,
265
+ "sft_loss": 0.01083166990429163,
266
+ "step": 130
267
+ },
268
+ {
269
+ "epoch": 3.5555555555555554,
270
+ "grad_norm": 1.2924200296401978,
271
+ "learning_rate": 4.046196825665638e-06,
272
+ "logits/chosen": -0.3512961268424988,
273
+ "logits/rejected": -0.40962281823158264,
274
+ "logps/chosen": -0.09843992441892624,
275
+ "logps/rejected": -0.5608054995536804,
276
+ "loss": 0.1373,
277
+ "odds_ratio_loss": 1.255068063735962,
278
+ "rewards/accuracies": 0.800000011920929,
279
+ "rewards/chosen": -0.009843992069363594,
280
+ "rewards/margins": 0.0462365560233593,
281
+ "rewards/rejected": -0.05608054995536804,
282
+ "sft_loss": 0.011779117397964,
283
+ "step": 140
284
+ },
285
+ {
286
+ "epoch": 3.8095238095238093,
287
+ "grad_norm": 2.3068244457244873,
288
+ "learning_rate": 3.8644112754862614e-06,
289
+ "logits/chosen": -0.3876010775566101,
290
+ "logits/rejected": -0.44387197494506836,
291
+ "logps/chosen": -0.08965662866830826,
292
+ "logps/rejected": -0.5087581872940063,
293
+ "loss": 0.1305,
294
+ "odds_ratio_loss": 1.190866231918335,
295
+ "rewards/accuracies": 0.800000011920929,
296
+ "rewards/chosen": -0.008965663611888885,
297
+ "rewards/margins": 0.04191015660762787,
298
+ "rewards/rejected": -0.05087582394480705,
299
+ "sft_loss": 0.01137098390609026,
300
+ "step": 150
301
+ },
302
+ {
303
+ "epoch": 3.8095238095238093,
304
+ "eval_logits/chosen": -0.35945644974708557,
305
+ "eval_logits/rejected": -0.44672098755836487,
306
+ "eval_logps/chosen": -0.06918758898973465,
307
+ "eval_logps/rejected": -0.6006532907485962,
308
+ "eval_loss": 0.09387854486703873,
309
+ "eval_odds_ratio_loss": 0.8297688961029053,
310
+ "eval_rewards/accuracies": 0.8857142925262451,
311
+ "eval_rewards/chosen": -0.00691875908523798,
312
+ "eval_rewards/margins": 0.05314657464623451,
313
+ "eval_rewards/rejected": -0.060065336525440216,
314
+ "eval_runtime": 2.8482,
315
+ "eval_samples_per_second": 24.577,
316
+ "eval_sft_loss": 0.010901645757257938,
317
+ "eval_steps_per_second": 12.289,
318
+ "step": 150
319
+ },
320
+ {
321
+ "epoch": 4.063492063492063,
322
+ "grad_norm": 2.330451011657715,
323
+ "learning_rate": 3.6717027521617593e-06,
324
+ "logits/chosen": -0.37214913964271545,
325
+ "logits/rejected": -0.40603429079055786,
326
+ "logps/chosen": -0.1277637928724289,
327
+ "logps/rejected": -0.5273887515068054,
328
+ "loss": 0.1756,
329
+ "odds_ratio_loss": 1.603698492050171,
330
+ "rewards/accuracies": 0.7749999761581421,
331
+ "rewards/chosen": -0.012776380404829979,
332
+ "rewards/margins": 0.039962492883205414,
333
+ "rewards/rejected": -0.05273887515068054,
334
+ "sft_loss": 0.01518657524138689,
335
+ "step": 160
336
+ },
337
+ {
338
+ "epoch": 4.317460317460317,
339
+ "grad_norm": 1.3536297082901,
340
+ "learning_rate": 3.4696140090121377e-06,
341
+ "logits/chosen": -0.36368614435195923,
342
+ "logits/rejected": -0.4250513017177582,
343
+ "logps/chosen": -0.07436664402484894,
344
+ "logps/rejected": -0.48485296964645386,
345
+ "loss": 0.1069,
346
+ "odds_ratio_loss": 0.9747287034988403,
347
+ "rewards/accuracies": 0.824999988079071,
348
+ "rewards/chosen": -0.007436663843691349,
349
+ "rewards/margins": 0.04104863479733467,
350
+ "rewards/rejected": -0.04848529398441315,
351
+ "sft_loss": 0.009424617514014244,
352
+ "step": 170
353
+ },
354
+ {
355
+ "epoch": 4.571428571428571,
356
+ "grad_norm": 2.3745017051696777,
357
+ "learning_rate": 3.2597628939356174e-06,
358
+ "logits/chosen": -0.36411547660827637,
359
+ "logits/rejected": -0.4261668622493744,
360
+ "logps/chosen": -0.09986865520477295,
361
+ "logps/rejected": -0.573279857635498,
362
+ "loss": 0.1321,
363
+ "odds_ratio_loss": 1.2067753076553345,
364
+ "rewards/accuracies": 0.8187500238418579,
365
+ "rewards/chosen": -0.00998686533421278,
366
+ "rewards/margins": 0.04734111577272415,
367
+ "rewards/rejected": -0.057327985763549805,
368
+ "sft_loss": 0.011466794647276402,
369
+ "step": 180
370
+ },
371
+ {
372
+ "epoch": 4.825396825396825,
373
+ "grad_norm": 1.3515417575836182,
374
+ "learning_rate": 3.043829397515419e-06,
375
+ "logits/chosen": -0.3659224808216095,
376
+ "logits/rejected": -0.4325219988822937,
377
+ "logps/chosen": -0.09348496794700623,
378
+ "logps/rejected": -0.616773247718811,
379
+ "loss": 0.128,
380
+ "odds_ratio_loss": 1.1637989282608032,
381
+ "rewards/accuracies": 0.824999988079071,
382
+ "rewards/chosen": -0.009348496794700623,
383
+ "rewards/margins": 0.05232882499694824,
384
+ "rewards/rejected": -0.06167732551693916,
385
+ "sft_loss": 0.011618848890066147,
386
+ "step": 190
387
+ },
388
+ {
389
+ "epoch": 5.079365079365079,
390
+ "grad_norm": 1.783627986907959,
391
+ "learning_rate": 2.8235422036351384e-06,
392
+ "logits/chosen": -0.35969123244285583,
393
+ "logits/rejected": -0.4151231646537781,
394
+ "logps/chosen": -0.08597036451101303,
395
+ "logps/rejected": -0.5718755125999451,
396
+ "loss": 0.126,
397
+ "odds_ratio_loss": 1.1704524755477905,
398
+ "rewards/accuracies": 0.8125,
399
+ "rewards/chosen": -0.008597037754952908,
400
+ "rewards/margins": 0.048590514808893204,
401
+ "rewards/rejected": -0.057187557220458984,
402
+ "sft_loss": 0.008975585922598839,
403
+ "step": 200
404
+ },
405
+ {
406
+ "epoch": 5.079365079365079,
407
+ "eval_logits/chosen": -0.36137011647224426,
408
+ "eval_logits/rejected": -0.4470607340335846,
409
+ "eval_logps/chosen": -0.0653248205780983,
410
+ "eval_logps/rejected": -0.6075571179389954,
411
+ "eval_loss": 0.0884871631860733,
412
+ "eval_odds_ratio_loss": 0.7822028398513794,
413
+ "eval_rewards/accuracies": 0.8857142925262451,
414
+ "eval_rewards/chosen": -0.006532481871545315,
415
+ "eval_rewards/margins": 0.05422323942184448,
416
+ "eval_rewards/rejected": -0.06075572222471237,
417
+ "eval_runtime": 2.8488,
418
+ "eval_samples_per_second": 24.572,
419
+ "eval_sft_loss": 0.010266884230077267,
420
+ "eval_steps_per_second": 12.286,
421
+ "step": 200
422
+ },
423
+ {
424
+ "epoch": 5.333333333333333,
425
+ "grad_norm": 1.6064863204956055,
426
+ "learning_rate": 2.6006648502735384e-06,
427
+ "logits/chosen": -0.3677741587162018,
428
+ "logits/rejected": -0.44500789046287537,
429
+ "logps/chosen": -0.09438425302505493,
430
+ "logps/rejected": -0.6154578924179077,
431
+ "loss": 0.1274,
432
+ "odds_ratio_loss": 1.1511874198913574,
433
+ "rewards/accuracies": 0.8374999761581421,
434
+ "rewards/chosen": -0.009438424371182919,
435
+ "rewards/margins": 0.05210735648870468,
436
+ "rewards/rejected": -0.06154578924179077,
437
+ "sft_loss": 0.012264673598110676,
438
+ "step": 210
439
+ },
440
+ {
441
+ "epoch": 5.587301587301587,
442
+ "grad_norm": 1.1026134490966797,
443
+ "learning_rate": 2.376981611270305e-06,
444
+ "logits/chosen": -0.35600247979164124,
445
+ "logits/rejected": -0.41946205496788025,
446
+ "logps/chosen": -0.060617007315158844,
447
+ "logps/rejected": -0.5755067467689514,
448
+ "loss": 0.0868,
449
+ "odds_ratio_loss": 0.7955432534217834,
450
+ "rewards/accuracies": 0.875,
451
+ "rewards/chosen": -0.006061701104044914,
452
+ "rewards/margins": 0.051488976925611496,
453
+ "rewards/rejected": -0.05755067616701126,
454
+ "sft_loss": 0.007234218530356884,
455
+ "step": 220
456
+ },
457
+ {
458
+ "epoch": 5.841269841269841,
459
+ "grad_norm": 1.5417340993881226,
460
+ "learning_rate": 2.154283212088168e-06,
461
+ "logits/chosen": -0.3397272229194641,
462
+ "logits/rejected": -0.4029166102409363,
463
+ "logps/chosen": -0.09258958697319031,
464
+ "logps/rejected": -0.5735796093940735,
465
+ "loss": 0.1317,
466
+ "odds_ratio_loss": 1.2124437093734741,
467
+ "rewards/accuracies": 0.8125,
468
+ "rewards/chosen": -0.009258957579731941,
469
+ "rewards/margins": 0.048099007457494736,
470
+ "rewards/rejected": -0.057357966899871826,
471
+ "sft_loss": 0.010430241003632545,
472
+ "step": 230
473
+ },
474
+ {
475
+ "epoch": 6.095238095238095,
476
+ "grad_norm": 1.7479714155197144,
477
+ "learning_rate": 1.934352493925695e-06,
478
+ "logits/chosen": -0.36627453565597534,
479
+ "logits/rejected": -0.42036452889442444,
480
+ "logps/chosen": -0.08008017390966415,
481
+ "logps/rejected": -0.54417884349823,
482
+ "loss": 0.1121,
483
+ "odds_ratio_loss": 1.0170867443084717,
484
+ "rewards/accuracies": 0.8187500238418579,
485
+ "rewards/chosen": -0.00800801906734705,
486
+ "rewards/margins": 0.046409863978624344,
487
+ "rewards/rejected": -0.05441788583993912,
488
+ "sft_loss": 0.010398345068097115,
489
+ "step": 240
490
+ },
491
+ {
492
+ "epoch": 6.349206349206349,
493
+ "grad_norm": 1.4434510469436646,
494
+ "learning_rate": 1.7189501409486061e-06,
495
+ "logits/chosen": -0.33210882544517517,
496
+ "logits/rejected": -0.39892473816871643,
497
+ "logps/chosen": -0.06178829073905945,
498
+ "logps/rejected": -0.5997610688209534,
499
+ "loss": 0.0881,
500
+ "odds_ratio_loss": 0.8088064193725586,
501
+ "rewards/accuracies": 0.8687499761581421,
502
+ "rewards/chosen": -0.006178829353302717,
503
+ "rewards/margins": 0.05379727482795715,
504
+ "rewards/rejected": -0.05997610092163086,
505
+ "sft_loss": 0.007182084023952484,
506
+ "step": 250
507
+ },
508
+ {
509
+ "epoch": 6.349206349206349,
510
+ "eval_logits/chosen": -0.35881727933883667,
511
+ "eval_logits/rejected": -0.44329720735549927,
512
+ "eval_logps/chosen": -0.0642322227358818,
513
+ "eval_logps/rejected": -0.617460310459137,
514
+ "eval_loss": 0.08761369436979294,
515
+ "eval_odds_ratio_loss": 0.7738510966300964,
516
+ "eval_rewards/accuracies": 0.8857142925262451,
517
+ "eval_rewards/chosen": -0.006423221435397863,
518
+ "eval_rewards/margins": 0.055322811007499695,
519
+ "eval_rewards/rejected": -0.061746031045913696,
520
+ "eval_runtime": 2.85,
521
+ "eval_samples_per_second": 24.561,
522
+ "eval_sft_loss": 0.010228590108454227,
523
+ "eval_steps_per_second": 12.281,
524
+ "step": 250
525
+ },
526
+ {
527
+ "epoch": 6.603174603174603,
528
+ "grad_norm": 1.0927199125289917,
529
+ "learning_rate": 1.509800584902108e-06,
530
+ "logits/chosen": -0.3656907379627228,
531
+ "logits/rejected": -0.4265232980251312,
532
+ "logps/chosen": -0.09537980705499649,
533
+ "logps/rejected": -0.5821040868759155,
534
+ "loss": 0.1342,
535
+ "odds_ratio_loss": 1.2318141460418701,
536
+ "rewards/accuracies": 0.831250011920929,
537
+ "rewards/chosen": -0.009537981823086739,
538
+ "rewards/margins": 0.048672426491975784,
539
+ "rewards/rejected": -0.05821041017770767,
540
+ "sft_loss": 0.01099989004433155,
541
+ "step": 260
542
+ },
543
+ {
544
+ "epoch": 6.857142857142857,
545
+ "grad_norm": 0.9249973893165588,
546
+ "learning_rate": 1.3085781999467303e-06,
547
+ "logits/chosen": -0.35447758436203003,
548
+ "logits/rejected": -0.40749120712280273,
549
+ "logps/chosen": -0.07294099032878876,
550
+ "logps/rejected": -0.629259467124939,
551
+ "loss": 0.0984,
552
+ "odds_ratio_loss": 0.8983978033065796,
553
+ "rewards/accuracies": 0.8812500238418579,
554
+ "rewards/chosen": -0.00729410070925951,
555
+ "rewards/margins": 0.0556318536400795,
556
+ "rewards/rejected": -0.06292594969272614,
557
+ "sft_loss": 0.008602628484368324,
558
+ "step": 270
559
+ },
560
+ {
561
+ "epoch": 7.111111111111111,
562
+ "grad_norm": 2.258975028991699,
563
+ "learning_rate": 1.1168938982367162e-06,
564
+ "logits/chosen": -0.34129127860069275,
565
+ "logits/rejected": -0.4004397392272949,
566
+ "logps/chosen": -0.08433207869529724,
567
+ "logps/rejected": -0.6350318193435669,
568
+ "loss": 0.1181,
569
+ "odds_ratio_loss": 1.0795619487762451,
570
+ "rewards/accuracies": 0.824999988079071,
571
+ "rewards/chosen": -0.008433207869529724,
572
+ "rewards/margins": 0.055069975554943085,
573
+ "rewards/rejected": -0.0635031908750534,
574
+ "sft_loss": 0.010152507573366165,
575
+ "step": 280
576
+ },
577
+ {
578
+ "epoch": 7.365079365079365,
579
+ "grad_norm": 2.165418863296509,
580
+ "learning_rate": 9.362822335518062e-07,
581
+ "logits/chosen": -0.36913567781448364,
582
+ "logits/rejected": -0.4323355555534363,
583
+ "logps/chosen": -0.07687892019748688,
584
+ "logps/rejected": -0.6239712834358215,
585
+ "loss": 0.108,
586
+ "odds_ratio_loss": 0.98408442735672,
587
+ "rewards/accuracies": 0.8187500238418579,
588
+ "rewards/chosen": -0.0076878927648067474,
589
+ "rewards/margins": 0.05470923334360123,
590
+ "rewards/rejected": -0.06239712983369827,
591
+ "sft_loss": 0.009641243144869804,
592
+ "step": 290
593
+ },
594
+ {
595
+ "epoch": 7.619047619047619,
596
+ "grad_norm": 3.004470109939575,
597
+ "learning_rate": 7.681891162260016e-07,
598
+ "logits/chosen": -0.37110036611557007,
599
+ "logits/rejected": -0.42522749304771423,
600
+ "logps/chosen": -0.07615403831005096,
601
+ "logps/rejected": -0.6149039268493652,
602
+ "loss": 0.1042,
603
+ "odds_ratio_loss": 0.963223934173584,
604
+ "rewards/accuracies": 0.8500000238418579,
605
+ "rewards/chosen": -0.007615404669195414,
606
+ "rewards/margins": 0.053874991834163666,
607
+ "rewards/rejected": -0.06149039417505264,
608
+ "sft_loss": 0.007854422554373741,
609
+ "step": 300
610
+ },
611
+ {
612
+ "epoch": 7.619047619047619,
613
+ "eval_logits/chosen": -0.3590058982372284,
614
+ "eval_logits/rejected": -0.4422083795070648,
615
+ "eval_logps/chosen": -0.06231304630637169,
616
+ "eval_logps/rejected": -0.635312557220459,
617
+ "eval_loss": 0.08455940335988998,
618
+ "eval_odds_ratio_loss": 0.7473430633544922,
619
+ "eval_rewards/accuracies": 0.8857142925262451,
620
+ "eval_rewards/chosen": -0.006231305189430714,
621
+ "eval_rewards/margins": 0.05729994922876358,
622
+ "eval_rewards/rejected": -0.06353124976158142,
623
+ "eval_runtime": 2.8479,
624
+ "eval_samples_per_second": 24.58,
625
+ "eval_sft_loss": 0.009825083427131176,
626
+ "eval_steps_per_second": 12.29,
627
+ "step": 300
628
+ },
629
+ {
630
+ "epoch": 7.8730158730158735,
631
+ "grad_norm": 1.533584475517273,
632
+ "learning_rate": 6.139602377230247e-07,
633
+ "logits/chosen": -0.31983453035354614,
634
+ "logits/rejected": -0.382944256067276,
635
+ "logps/chosen": -0.0727442055940628,
636
+ "logps/rejected": -0.624809980392456,
637
+ "loss": 0.1001,
638
+ "odds_ratio_loss": 0.9139682054519653,
639
+ "rewards/accuracies": 0.887499988079071,
640
+ "rewards/chosen": -0.007274420000612736,
641
+ "rewards/margins": 0.05520658567547798,
642
+ "rewards/rejected": -0.06248100847005844,
643
+ "sft_loss": 0.00875190831720829,
644
+ "step": 310
645
+ },
646
+ {
647
+ "epoch": 8.126984126984127,
648
+ "grad_norm": 1.2397465705871582,
649
+ "learning_rate": 4.748302975270838e-07,
650
+ "logits/chosen": -0.36127156019210815,
651
+ "logits/rejected": -0.414104163646698,
652
+ "logps/chosen": -0.07443028688430786,
653
+ "logps/rejected": -0.6057202219963074,
654
+ "loss": 0.1097,
655
+ "odds_ratio_loss": 1.0172044038772583,
656
+ "rewards/accuracies": 0.8187500238418579,
657
+ "rewards/chosen": -0.007443029433488846,
658
+ "rewards/margins": 0.05312899500131607,
659
+ "rewards/rejected": -0.060572028160095215,
660
+ "sft_loss": 0.007985426113009453,
661
+ "step": 320
662
+ },
663
+ {
664
+ "epoch": 8.380952380952381,
665
+ "grad_norm": 0.5725772976875305,
666
+ "learning_rate": 3.51913118594458e-07,
667
+ "logits/chosen": -0.3835681080818176,
668
+ "logits/rejected": -0.43386417627334595,
669
+ "logps/chosen": -0.06635960191488266,
670
+ "logps/rejected": -0.6450189352035522,
671
+ "loss": 0.0902,
672
+ "odds_ratio_loss": 0.8284249305725098,
673
+ "rewards/accuracies": 0.8812500238418579,
674
+ "rewards/chosen": -0.006635960191488266,
675
+ "rewards/margins": 0.057865940034389496,
676
+ "rewards/rejected": -0.06450189650058746,
677
+ "sft_loss": 0.007339561823755503,
678
+ "step": 330
679
+ },
680
+ {
681
+ "epoch": 8.634920634920634,
682
+ "grad_norm": 1.0001157522201538,
683
+ "learning_rate": 2.4619273049796e-07,
684
+ "logits/chosen": -0.33445996046066284,
685
+ "logits/rejected": -0.3972671627998352,
686
+ "logps/chosen": -0.05932674556970596,
687
+ "logps/rejected": -0.6106581091880798,
688
+ "loss": 0.0848,
689
+ "odds_ratio_loss": 0.7749115824699402,
690
+ "rewards/accuracies": 0.8812500238418579,
691
+ "rewards/chosen": -0.005932674743235111,
692
+ "rewards/margins": 0.055133141577243805,
693
+ "rewards/rejected": -0.06106581166386604,
694
+ "sft_loss": 0.007352383341640234,
695
+ "step": 340
696
+ },
697
+ {
698
+ "epoch": 8.88888888888889,
699
+ "grad_norm": 4.11332893371582,
700
+ "learning_rate": 1.5851549164932118e-07,
701
+ "logits/chosen": -0.3571884036064148,
702
+ "logits/rejected": -0.4186948239803314,
703
+ "logps/chosen": -0.10442166030406952,
704
+ "logps/rejected": -0.6717274188995361,
705
+ "loss": 0.1405,
706
+ "odds_ratio_loss": 1.2675970792770386,
707
+ "rewards/accuracies": 0.84375,
708
+ "rewards/chosen": -0.010442165657877922,
709
+ "rewards/margins": 0.05673057585954666,
710
+ "rewards/rejected": -0.06717274338006973,
711
+ "sft_loss": 0.013773849233984947,
712
+ "step": 350
713
+ },
714
+ {
715
+ "epoch": 8.88888888888889,
716
+ "eval_logits/chosen": -0.3572179079055786,
717
+ "eval_logits/rejected": -0.4404871165752411,
718
+ "eval_logps/chosen": -0.06271177530288696,
719
+ "eval_logps/rejected": -0.6435345411300659,
720
+ "eval_loss": 0.0852903425693512,
721
+ "eval_odds_ratio_loss": 0.7539986968040466,
722
+ "eval_rewards/accuracies": 0.8857142925262451,
723
+ "eval_rewards/chosen": -0.006271177902817726,
724
+ "eval_rewards/margins": 0.058082275092601776,
725
+ "eval_rewards/rejected": -0.06435345858335495,
726
+ "eval_runtime": 2.859,
727
+ "eval_samples_per_second": 24.484,
728
+ "eval_sft_loss": 0.009890479035675526,
729
+ "eval_steps_per_second": 12.242,
730
+ "step": 350
731
+ },
732
+ {
733
+ "epoch": 9.142857142857142,
734
+ "grad_norm": 0.9665654897689819,
735
+ "learning_rate": 8.958331366609424e-08,
736
+ "logits/chosen": -0.3107479214668274,
737
+ "logits/rejected": -0.37265530228614807,
738
+ "logps/chosen": -0.06691344082355499,
739
+ "logps/rejected": -0.5724009275436401,
740
+ "loss": 0.094,
741
+ "odds_ratio_loss": 0.8813444972038269,
742
+ "rewards/accuracies": 0.862500011920929,
743
+ "rewards/chosen": -0.006691344082355499,
744
+ "rewards/margins": 0.05054875463247299,
745
+ "rewards/rejected": -0.05724009871482849,
746
+ "sft_loss": 0.0058282362297177315,
747
+ "step": 360
748
+ },
749
+ {
750
+ "epoch": 9.396825396825397,
751
+ "grad_norm": 3.0245769023895264,
752
+ "learning_rate": 3.994804212627462e-08,
753
+ "logits/chosen": -0.34935471415519714,
754
+ "logits/rejected": -0.40634721517562866,
755
+ "logps/chosen": -0.07195556163787842,
756
+ "logps/rejected": -0.6718673706054688,
757
+ "loss": 0.1036,
758
+ "odds_ratio_loss": 0.9533177614212036,
759
+ "rewards/accuracies": 0.84375,
760
+ "rewards/chosen": -0.007195556070655584,
761
+ "rewards/margins": 0.059991173446178436,
762
+ "rewards/rejected": -0.06718672811985016,
763
+ "sft_loss": 0.008246790617704391,
764
+ "step": 370
765
+ },
766
+ {
767
+ "epoch": 9.65079365079365,
768
+ "grad_norm": 0.6890878081321716,
769
+ "learning_rate": 1.0007038696262517e-08,
770
+ "logits/chosen": -0.3386954665184021,
771
+ "logits/rejected": -0.38855743408203125,
772
+ "logps/chosen": -0.08121927082538605,
773
+ "logps/rejected": -0.6734482049942017,
774
+ "loss": 0.112,
775
+ "odds_ratio_loss": 1.0336910486221313,
776
+ "rewards/accuracies": 0.856249988079071,
777
+ "rewards/chosen": -0.00812192726880312,
778
+ "rewards/margins": 0.05922289565205574,
779
+ "rewards/rejected": -0.06734482198953629,
780
+ "sft_loss": 0.00858935434371233,
781
+ "step": 380
782
+ },
783
+ {
784
+ "epoch": 9.904761904761905,
785
+ "grad_norm": 2.2217235565185547,
786
+ "learning_rate": 0.0,
787
+ "logits/chosen": -0.3671117424964905,
788
+ "logits/rejected": -0.4225407540798187,
789
+ "logps/chosen": -0.065305195748806,
790
+ "logps/rejected": -0.5695095062255859,
791
+ "loss": 0.0909,
792
+ "odds_ratio_loss": 0.8265236020088196,
793
+ "rewards/accuracies": 0.8687499761581421,
794
+ "rewards/chosen": -0.006530520506203175,
795
+ "rewards/margins": 0.05042043328285217,
796
+ "rewards/rejected": -0.05695095658302307,
797
+ "sft_loss": 0.008208604529500008,
798
+ "step": 390
799
+ },
800
+ {
801
+ "epoch": 9.904761904761905,
802
+ "step": 390,
803
+ "total_flos": 7.038458947436544e+16,
804
+ "train_loss": 0.3784435097987835,
805
+ "train_runtime": 852.09,
806
+ "train_samples_per_second": 7.394,
807
+ "train_steps_per_second": 0.458
808
+ }
809
+ ],
810
+ "logging_steps": 10,
811
+ "max_steps": 390,
812
+ "num_input_tokens_seen": 0,
813
+ "num_train_epochs": 10,
814
+ "save_steps": 50,
815
+ "stateful_callbacks": {
816
+ "TrainerControl": {
817
+ "args": {
818
+ "should_epoch_stop": false,
819
+ "should_evaluate": false,
820
+ "should_log": false,
821
+ "should_save": true,
822
+ "should_training_stop": true
823
+ },
824
+ "attributes": {}
825
+ }
826
+ },
827
+ "total_flos": 7.038458947436544e+16,
828
+ "train_batch_size": 2,
829
+ "trial_name": null,
830
+ "trial_params": null
831
+ }
chchen__Llama-3.1-8B-Instruct-SAA-700/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3bab49ed184161039e122fb9f7f85f4dec18181b0141974077e95cf59f671f0
3
+ size 5432
chchen__Llama-3.1-8B-Instruct-SAA-700/training_eval_loss.png ADDED
chchen__Llama-3.1-8B-Instruct-SAA-700/training_loss.png ADDED
chchen__Llama-3.1-8B-Instruct-SAA-700/training_rewards_accuracies.png ADDED