jjee2 commited on
Commit
f63d08b
·
verified ·
1 Parent(s): 24951e8

Add chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6

Browse files
.gitattributes CHANGED
@@ -51,3 +51,4 @@ thangla01__6ca44872-2a07-4763-8313-9cdc05879a21/tokenizer.json filter=lfs diff=l
51
  chchen__Llama-3.1-8B-Instruct-PsyCourse-fold8/tokenizer.json filter=lfs diff=lfs merge=lfs -text
52
  denbeo__0fa825d9-4c8a-4e2a-9b9f-40a0591ea08f/tokenizer.json filter=lfs diff=lfs merge=lfs -text
53
  aseratus1__80dde36f-b140-4e57-a010-bebb9584c30b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
51
  chchen__Llama-3.1-8B-Instruct-PsyCourse-fold8/tokenizer.json filter=lfs diff=lfs merge=lfs -text
52
  denbeo__0fa825d9-4c8a-4e2a-9b9f-40a0591ea08f/tokenizer.json filter=lfs diff=lfs merge=lfs -text
53
  aseratus1__80dde36f-b140-4e57-a010-bebb9584c30b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
54
+ chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6/tokenizer.json filter=lfs diff=lfs merge=lfs -text
chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6/.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-PsyCourse-doc-info-fold6/README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: llama3.1
4
+ base_model: meta-llama/Llama-3.1-8B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6
18
+
19
+ 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 course-doc-info-train-fold6 dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.0528
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0001
41
+ - train_batch_size: 1
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 16
45
+ - total_train_batch_size: 16
46
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 5.0
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:------:|:----:|:---------------:|
55
+ | 0.265 | 0.3951 | 10 | 0.2719 |
56
+ | 0.1689 | 0.7901 | 20 | 0.1451 |
57
+ | 0.1027 | 1.1852 | 30 | 0.1037 |
58
+ | 0.0848 | 1.5802 | 40 | 0.0805 |
59
+ | 0.0671 | 1.9753 | 50 | 0.0692 |
60
+ | 0.0635 | 2.3704 | 60 | 0.0614 |
61
+ | 0.0637 | 2.7654 | 70 | 0.0601 |
62
+ | 0.0525 | 3.1605 | 80 | 0.0562 |
63
+ | 0.0567 | 3.5556 | 90 | 0.0555 |
64
+ | 0.0437 | 3.9506 | 100 | 0.0538 |
65
+ | 0.0503 | 4.3457 | 110 | 0.0528 |
66
+ | 0.0521 | 4.7407 | 120 | 0.0528 |
67
+
68
+
69
+ ### Framework versions
70
+
71
+ - PEFT 0.12.0
72
+ - Transformers 4.46.1
73
+ - Pytorch 2.5.1+cu124
74
+ - Datasets 3.1.0
75
+ - Tokenizers 0.20.3
chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6/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
+ "v_proj",
24
+ "k_proj",
25
+ "o_proj",
26
+ "up_proj",
27
+ "q_proj",
28
+ "down_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8546533df3d1d27adc9133eec83364b09ead203b0bd335feb5a54d98ad015814
3
+ size 83945296
chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6/all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.938271604938271,
3
+ "eval_loss": 0.052800051867961884,
4
+ "eval_runtime": 25.4728,
5
+ "eval_samples_per_second": 1.767,
6
+ "eval_steps_per_second": 1.767,
7
+ "total_flos": 1.69590230591275e+17,
8
+ "train_loss": 0.10049069952964783,
9
+ "train_runtime": 4885.3949,
10
+ "train_samples_per_second": 0.415,
11
+ "train_steps_per_second": 0.026
12
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6/eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.938271604938271,
3
+ "eval_loss": 0.052800051867961884,
4
+ "eval_runtime": 25.4728,
5
+ "eval_samples_per_second": 1.767,
6
+ "eval_steps_per_second": 1.767
7
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6/llama3_lora_sft.yaml ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ### model
2
+ model_name_or_path: meta-llama/Llama-3.1-8B-Instruct
3
+ trust_remote_code: true
4
+
5
+ ### method
6
+ stage: sft
7
+ do_train: true
8
+ finetuning_type: lora
9
+ lora_target: all
10
+
11
+ ### dataset
12
+ dataset: course-doc-info-train-fold6
13
+ dataset_dir: data_private
14
+ template: llama3
15
+ cutoff_len: 8192
16
+ # max_samples: 1000
17
+ overwrite_cache: true
18
+ preprocessing_num_workers: 16
19
+
20
+ ### output
21
+ output_dir: saves/psy-course-doc-info/Llama-3.1-8B-Instruct/train/fold6
22
+ logging_steps: 1
23
+ save_steps: 10
24
+ plot_loss: true
25
+ overwrite_output_dir: true
26
+ save_total_limit: 3
27
+ push_to_hub: true
28
+ hub_model_id: chchen/Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6
29
+ load_best_model_at_end: true
30
+
31
+ ### train
32
+ per_device_train_batch_size: 1
33
+ gradient_accumulation_steps: 16
34
+ learning_rate: 1.0e-4
35
+ num_train_epochs: 5.0
36
+ lr_scheduler_type: cosine
37
+ warmup_ratio: 0.1
38
+ bf16: true
39
+ ddp_timeout: 180000000
40
+ enable_liger_kernel: true
41
+
42
+ ### eval
43
+ val_size: 0.1
44
+ per_device_eval_batch_size: 1
45
+ eval_strategy: steps
46
+ eval_steps: 10
chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6/special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eot_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|eom_id|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<|begin_of_text|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "<|eot_id|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": "<|eot_id|>"
33
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6/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-PsyCourse-doc-info-fold6/tokenizer_config.json ADDED
@@ -0,0 +1,2069 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [
2053
+ "<|eot_id|>",
2054
+ "<|eom_id|>"
2055
+ ],
2056
+ "bos_token": "<|begin_of_text|>",
2057
+ "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",
2058
+ "clean_up_tokenization_spaces": true,
2059
+ "eos_token": "<|eot_id|>",
2060
+ "model_input_names": [
2061
+ "input_ids",
2062
+ "attention_mask"
2063
+ ],
2064
+ "model_max_length": 131072,
2065
+ "pad_token": "<|eot_id|>",
2066
+ "padding_side": "right",
2067
+ "split_special_tokens": false,
2068
+ "tokenizer_class": "PreTrainedTokenizerFast"
2069
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.938271604938271,
3
+ "total_flos": 1.69590230591275e+17,
4
+ "train_loss": 0.10049069952964783,
5
+ "train_runtime": 4885.3949,
6
+ "train_samples_per_second": 0.415,
7
+ "train_steps_per_second": 0.026
8
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6/trainer_log.jsonl ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 125, "loss": 0.4084, "lr": 7.692307692307694e-06, "epoch": 0.03950617283950617, "percentage": 0.8, "elapsed_time": "0:00:28", "remaining_time": "0:59:47"}
2
+ {"current_steps": 2, "total_steps": 125, "loss": 0.3408, "lr": 1.5384615384615387e-05, "epoch": 0.07901234567901234, "percentage": 1.6, "elapsed_time": "0:01:05", "remaining_time": "1:06:58"}
3
+ {"current_steps": 3, "total_steps": 125, "loss": 0.3892, "lr": 2.307692307692308e-05, "epoch": 0.11851851851851852, "percentage": 2.4, "elapsed_time": "0:01:33", "remaining_time": "1:03:27"}
4
+ {"current_steps": 4, "total_steps": 125, "loss": 0.3429, "lr": 3.0769230769230774e-05, "epoch": 0.1580246913580247, "percentage": 3.2, "elapsed_time": "0:02:11", "remaining_time": "1:06:18"}
5
+ {"current_steps": 5, "total_steps": 125, "loss": 0.3341, "lr": 3.846153846153846e-05, "epoch": 0.19753086419753085, "percentage": 4.0, "elapsed_time": "0:02:49", "remaining_time": "1:07:58"}
6
+ {"current_steps": 6, "total_steps": 125, "loss": 0.342, "lr": 4.615384615384616e-05, "epoch": 0.23703703703703705, "percentage": 4.8, "elapsed_time": "0:03:28", "remaining_time": "1:09:02"}
7
+ {"current_steps": 7, "total_steps": 125, "loss": 0.3587, "lr": 5.384615384615385e-05, "epoch": 0.2765432098765432, "percentage": 5.6, "elapsed_time": "0:04:06", "remaining_time": "1:09:16"}
8
+ {"current_steps": 8, "total_steps": 125, "loss": 0.2992, "lr": 6.153846153846155e-05, "epoch": 0.3160493827160494, "percentage": 6.4, "elapsed_time": "0:04:48", "remaining_time": "1:10:12"}
9
+ {"current_steps": 9, "total_steps": 125, "loss": 0.2757, "lr": 6.923076923076924e-05, "epoch": 0.35555555555555557, "percentage": 7.2, "elapsed_time": "0:05:29", "remaining_time": "1:10:41"}
10
+ {"current_steps": 10, "total_steps": 125, "loss": 0.265, "lr": 7.692307692307693e-05, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:06:01", "remaining_time": "1:09:22"}
11
+ {"current_steps": 10, "total_steps": 125, "eval_loss": 0.27192339301109314, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:06:27", "remaining_time": "1:14:21"}
12
+ {"current_steps": 11, "total_steps": 125, "loss": 0.2865, "lr": 8.461538461538461e-05, "epoch": 0.4345679012345679, "percentage": 8.8, "elapsed_time": "0:07:09", "remaining_time": "1:14:07"}
13
+ {"current_steps": 12, "total_steps": 125, "loss": 0.2422, "lr": 9.230769230769232e-05, "epoch": 0.4740740740740741, "percentage": 9.6, "elapsed_time": "0:07:44", "remaining_time": "1:12:51"}
14
+ {"current_steps": 13, "total_steps": 125, "loss": 0.2421, "lr": 0.0001, "epoch": 0.5135802469135803, "percentage": 10.4, "elapsed_time": "0:08:18", "remaining_time": "1:11:32"}
15
+ {"current_steps": 14, "total_steps": 125, "loss": 0.2099, "lr": 9.998033131915266e-05, "epoch": 0.5530864197530864, "percentage": 11.2, "elapsed_time": "0:08:50", "remaining_time": "1:10:03"}
16
+ {"current_steps": 15, "total_steps": 125, "loss": 0.209, "lr": 9.992134075089084e-05, "epoch": 0.5925925925925926, "percentage": 12.0, "elapsed_time": "0:09:23", "remaining_time": "1:08:54"}
17
+ {"current_steps": 16, "total_steps": 125, "loss": 0.1967, "lr": 9.982307470588098e-05, "epoch": 0.6320987654320988, "percentage": 12.8, "elapsed_time": "0:10:03", "remaining_time": "1:08:34"}
18
+ {"current_steps": 17, "total_steps": 125, "loss": 0.1765, "lr": 9.968561049466214e-05, "epoch": 0.671604938271605, "percentage": 13.6, "elapsed_time": "0:10:42", "remaining_time": "1:08:01"}
19
+ {"current_steps": 18, "total_steps": 125, "loss": 0.1795, "lr": 9.950905626682228e-05, "epoch": 0.7111111111111111, "percentage": 14.4, "elapsed_time": "0:11:18", "remaining_time": "1:07:11"}
20
+ {"current_steps": 19, "total_steps": 125, "loss": 0.1576, "lr": 9.92935509259118e-05, "epoch": 0.7506172839506173, "percentage": 15.2, "elapsed_time": "0:11:50", "remaining_time": "1:06:05"}
21
+ {"current_steps": 20, "total_steps": 125, "loss": 0.1689, "lr": 9.903926402016153e-05, "epoch": 0.7901234567901234, "percentage": 16.0, "elapsed_time": "0:12:25", "remaining_time": "1:05:15"}
22
+ {"current_steps": 20, "total_steps": 125, "eval_loss": 0.14510378241539001, "epoch": 0.7901234567901234, "percentage": 16.0, "elapsed_time": "0:12:51", "remaining_time": "1:07:31"}
23
+ {"current_steps": 21, "total_steps": 125, "loss": 0.1437, "lr": 9.874639560909117e-05, "epoch": 0.8296296296296296, "percentage": 16.8, "elapsed_time": "0:13:28", "remaining_time": "1:06:45"}
24
+ {"current_steps": 22, "total_steps": 125, "loss": 0.1623, "lr": 9.841517610611309e-05, "epoch": 0.8691358024691358, "percentage": 17.6, "elapsed_time": "0:14:08", "remaining_time": "1:06:13"}
25
+ {"current_steps": 23, "total_steps": 125, "loss": 0.1272, "lr": 9.804586609725499e-05, "epoch": 0.908641975308642, "percentage": 18.4, "elapsed_time": "0:14:48", "remaining_time": "1:05:40"}
26
+ {"current_steps": 24, "total_steps": 125, "loss": 0.1437, "lr": 9.763875613614482e-05, "epoch": 0.9481481481481482, "percentage": 19.2, "elapsed_time": "0:15:18", "remaining_time": "1:04:26"}
27
+ {"current_steps": 25, "total_steps": 125, "loss": 0.138, "lr": 9.719416651541839e-05, "epoch": 0.9876543209876543, "percentage": 20.0, "elapsed_time": "0:16:02", "remaining_time": "1:04:11"}
28
+ {"current_steps": 26, "total_steps": 125, "loss": 0.2049, "lr": 9.671244701472999e-05, "epoch": 1.0271604938271606, "percentage": 20.8, "elapsed_time": "0:16:40", "remaining_time": "1:03:28"}
29
+ {"current_steps": 27, "total_steps": 125, "loss": 0.0987, "lr": 9.619397662556435e-05, "epoch": 1.0666666666666667, "percentage": 21.6, "elapsed_time": "0:17:12", "remaining_time": "1:02:25"}
30
+ {"current_steps": 28, "total_steps": 125, "loss": 0.1196, "lr": 9.563916325306594e-05, "epoch": 1.106172839506173, "percentage": 22.4, "elapsed_time": "0:17:51", "remaining_time": "1:01:52"}
31
+ {"current_steps": 29, "total_steps": 125, "loss": 0.1156, "lr": 9.504844339512095e-05, "epoch": 1.145679012345679, "percentage": 23.2, "elapsed_time": "0:18:27", "remaining_time": "1:01:06"}
32
+ {"current_steps": 30, "total_steps": 125, "loss": 0.1027, "lr": 9.442228179894362e-05, "epoch": 1.1851851851851851, "percentage": 24.0, "elapsed_time": "0:19:00", "remaining_time": "1:00:11"}
33
+ {"current_steps": 30, "total_steps": 125, "eval_loss": 0.10370857268571854, "epoch": 1.1851851851851851, "percentage": 24.0, "elapsed_time": "0:19:26", "remaining_time": "1:01:33"}
34
+ {"current_steps": 31, "total_steps": 125, "loss": 0.1173, "lr": 9.376117109543769e-05, "epoch": 1.2246913580246914, "percentage": 24.8, "elapsed_time": "0:20:06", "remaining_time": "1:00:59"}
35
+ {"current_steps": 32, "total_steps": 125, "loss": 0.1047, "lr": 9.306563141162046e-05, "epoch": 1.2641975308641975, "percentage": 25.6, "elapsed_time": "0:20:44", "remaining_time": "1:00:17"}
36
+ {"current_steps": 33, "total_steps": 125, "loss": 0.0901, "lr": 9.233620996141421e-05, "epoch": 1.3037037037037038, "percentage": 26.4, "elapsed_time": "0:21:24", "remaining_time": "0:59:40"}
37
+ {"current_steps": 34, "total_steps": 125, "loss": 0.0961, "lr": 9.157348061512727e-05, "epoch": 1.34320987654321, "percentage": 27.2, "elapsed_time": "0:22:05", "remaining_time": "0:59:08"}
38
+ {"current_steps": 35, "total_steps": 125, "loss": 0.0986, "lr": 9.077804344796302e-05, "epoch": 1.382716049382716, "percentage": 28.0, "elapsed_time": "0:22:45", "remaining_time": "0:58:30"}
39
+ {"current_steps": 36, "total_steps": 125, "loss": 0.0951, "lr": 8.995052426791247e-05, "epoch": 1.4222222222222223, "percentage": 28.8, "elapsed_time": "0:23:16", "remaining_time": "0:57:31"}
40
+ {"current_steps": 37, "total_steps": 125, "loss": 0.0835, "lr": 8.90915741234015e-05, "epoch": 1.4617283950617284, "percentage": 29.6, "elapsed_time": "0:23:54", "remaining_time": "0:56:52"}
41
+ {"current_steps": 38, "total_steps": 125, "loss": 0.0958, "lr": 8.820186879108038e-05, "epoch": 1.5012345679012347, "percentage": 30.4, "elapsed_time": "0:24:37", "remaining_time": "0:56:21"}
42
+ {"current_steps": 39, "total_steps": 125, "loss": 0.0917, "lr": 8.728210824415827e-05, "epoch": 1.5407407407407407, "percentage": 31.2, "elapsed_time": "0:25:11", "remaining_time": "0:55:32"}
43
+ {"current_steps": 40, "total_steps": 125, "loss": 0.0848, "lr": 8.633301610170135e-05, "epoch": 1.5802469135802468, "percentage": 32.0, "elapsed_time": "0:25:44", "remaining_time": "0:54:42"}
44
+ {"current_steps": 40, "total_steps": 125, "eval_loss": 0.08050418645143509, "epoch": 1.5802469135802468, "percentage": 32.0, "elapsed_time": "0:26:10", "remaining_time": "0:55:38"}
45
+ {"current_steps": 41, "total_steps": 125, "loss": 0.0818, "lr": 8.535533905932738e-05, "epoch": 1.6197530864197531, "percentage": 32.8, "elapsed_time": "0:26:48", "remaining_time": "0:54:55"}
46
+ {"current_steps": 42, "total_steps": 125, "loss": 0.0775, "lr": 8.434984630174509e-05, "epoch": 1.6592592592592592, "percentage": 33.6, "elapsed_time": "0:27:21", "remaining_time": "0:54:04"}
47
+ {"current_steps": 43, "total_steps": 125, "loss": 0.0828, "lr": 8.33173288976002e-05, "epoch": 1.6987654320987655, "percentage": 34.4, "elapsed_time": "0:27:56", "remaining_time": "0:53:17"}
48
+ {"current_steps": 44, "total_steps": 125, "loss": 0.073, "lr": 8.225859917710439e-05, "epoch": 1.7382716049382716, "percentage": 35.2, "elapsed_time": "0:28:29", "remaining_time": "0:52:27"}
49
+ {"current_steps": 45, "total_steps": 125, "loss": 0.087, "lr": 8.117449009293668e-05, "epoch": 1.7777777777777777, "percentage": 36.0, "elapsed_time": "0:29:13", "remaining_time": "0:51:56"}
50
+ {"current_steps": 46, "total_steps": 125, "loss": 0.0595, "lr": 8.006585456492029e-05, "epoch": 1.817283950617284, "percentage": 36.8, "elapsed_time": "0:29:42", "remaining_time": "0:51:01"}
51
+ {"current_steps": 47, "total_steps": 125, "loss": 0.1004, "lr": 7.89335648089903e-05, "epoch": 1.8567901234567903, "percentage": 37.6, "elapsed_time": "0:30:20", "remaining_time": "0:50:21"}
52
+ {"current_steps": 48, "total_steps": 125, "loss": 0.0645, "lr": 7.777851165098012e-05, "epoch": 1.8962962962962964, "percentage": 38.4, "elapsed_time": "0:30:55", "remaining_time": "0:49:37"}
53
+ {"current_steps": 49, "total_steps": 125, "loss": 0.0908, "lr": 7.660160382576683e-05, "epoch": 1.9358024691358025, "percentage": 39.2, "elapsed_time": "0:31:28", "remaining_time": "0:48:49"}
54
+ {"current_steps": 50, "total_steps": 125, "loss": 0.0671, "lr": 7.540376726232648e-05, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:32:02", "remaining_time": "0:48:04"}
55
+ {"current_steps": 50, "total_steps": 125, "eval_loss": 0.06918726116418839, "epoch": 1.9753086419753085, "percentage": 40.0, "elapsed_time": "0:32:28", "remaining_time": "0:48:43"}
56
+ {"current_steps": 51, "total_steps": 125, "loss": 0.1146, "lr": 7.4185944355262e-05, "epoch": 2.0148148148148146, "percentage": 40.8, "elapsed_time": "0:33:10", "remaining_time": "0:48:08"}
57
+ {"current_steps": 52, "total_steps": 125, "loss": 0.055, "lr": 7.294909322337689e-05, "epoch": 2.054320987654321, "percentage": 41.6, "elapsed_time": "0:33:48", "remaining_time": "0:47:27"}
58
+ {"current_steps": 53, "total_steps": 125, "loss": 0.0624, "lr": 7.169418695587791e-05, "epoch": 2.093827160493827, "percentage": 42.4, "elapsed_time": "0:34:27", "remaining_time": "0:46:48"}
59
+ {"current_steps": 54, "total_steps": 125, "loss": 0.0711, "lr": 7.042221284679982e-05, "epoch": 2.1333333333333333, "percentage": 43.2, "elapsed_time": "0:35:06", "remaining_time": "0:46:09"}
60
+ {"current_steps": 55, "total_steps": 125, "loss": 0.0646, "lr": 6.91341716182545e-05, "epoch": 2.1728395061728394, "percentage": 44.0, "elapsed_time": "0:35:46", "remaining_time": "0:45:31"}
61
+ {"current_steps": 56, "total_steps": 125, "loss": 0.0524, "lr": 6.783107663311565e-05, "epoch": 2.212345679012346, "percentage": 44.8, "elapsed_time": "0:36:23", "remaining_time": "0:44:50"}
62
+ {"current_steps": 57, "total_steps": 125, "loss": 0.0686, "lr": 6.651395309775837e-05, "epoch": 2.251851851851852, "percentage": 45.6, "elapsed_time": "0:37:03", "remaining_time": "0:44:12"}
63
+ {"current_steps": 58, "total_steps": 125, "loss": 0.0805, "lr": 6.518383725548074e-05, "epoch": 2.291358024691358, "percentage": 46.4, "elapsed_time": "0:37:42", "remaining_time": "0:43:33"}
64
+ {"current_steps": 59, "total_steps": 125, "loss": 0.0651, "lr": 6.384177557124247e-05, "epoch": 2.330864197530864, "percentage": 47.2, "elapsed_time": "0:38:15", "remaining_time": "0:42:47"}
65
+ {"current_steps": 60, "total_steps": 125, "loss": 0.0635, "lr": 6.248882390836135e-05, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:38:46", "remaining_time": "0:42:00"}
66
+ {"current_steps": 60, "total_steps": 125, "eval_loss": 0.061441570520401, "epoch": 2.3703703703703702, "percentage": 48.0, "elapsed_time": "0:39:12", "remaining_time": "0:42:28"}
67
+ {"current_steps": 61, "total_steps": 125, "loss": 0.0556, "lr": 6.112604669781572e-05, "epoch": 2.4098765432098768, "percentage": 48.8, "elapsed_time": "0:39:50", "remaining_time": "0:41:47"}
68
+ {"current_steps": 62, "total_steps": 125, "loss": 0.0598, "lr": 5.9754516100806423e-05, "epoch": 2.449382716049383, "percentage": 49.6, "elapsed_time": "0:40:25", "remaining_time": "0:41:04"}
69
+ {"current_steps": 63, "total_steps": 125, "loss": 0.074, "lr": 5.837531116523682e-05, "epoch": 2.488888888888889, "percentage": 50.4, "elapsed_time": "0:41:00", "remaining_time": "0:40:21"}
70
+ {"current_steps": 64, "total_steps": 125, "loss": 0.051, "lr": 5.698951697677498e-05, "epoch": 2.528395061728395, "percentage": 51.2, "elapsed_time": "0:41:31", "remaining_time": "0:39:34"}
71
+ {"current_steps": 65, "total_steps": 125, "loss": 0.0612, "lr": 5.559822380516539e-05, "epoch": 2.567901234567901, "percentage": 52.0, "elapsed_time": "0:42:09", "remaining_time": "0:38:55"}
72
+ {"current_steps": 66, "total_steps": 125, "loss": 0.0623, "lr": 5.420252624646238e-05, "epoch": 2.6074074074074076, "percentage": 52.8, "elapsed_time": "0:42:49", "remaining_time": "0:38:17"}
73
+ {"current_steps": 67, "total_steps": 125, "loss": 0.0547, "lr": 5.2803522361859594e-05, "epoch": 2.6469135802469137, "percentage": 53.6, "elapsed_time": "0:43:24", "remaining_time": "0:37:34"}
74
+ {"current_steps": 68, "total_steps": 125, "loss": 0.0555, "lr": 5.140231281379345e-05, "epoch": 2.68641975308642, "percentage": 54.4, "elapsed_time": "0:43:58", "remaining_time": "0:36:51"}
75
+ {"current_steps": 69, "total_steps": 125, "loss": 0.0608, "lr": 5e-05, "epoch": 2.725925925925926, "percentage": 55.2, "elapsed_time": "0:44:31", "remaining_time": "0:36:07"}
76
+ {"current_steps": 70, "total_steps": 125, "loss": 0.0637, "lr": 4.859768718620656e-05, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:45:05", "remaining_time": "0:35:25"}
77
+ {"current_steps": 70, "total_steps": 125, "eval_loss": 0.06007562205195427, "epoch": 2.765432098765432, "percentage": 56.0, "elapsed_time": "0:45:31", "remaining_time": "0:35:45"}
78
+ {"current_steps": 71, "total_steps": 125, "loss": 0.0546, "lr": 4.7196477638140404e-05, "epoch": 2.8049382716049385, "percentage": 56.8, "elapsed_time": "0:46:14", "remaining_time": "0:35:10"}
79
+ {"current_steps": 72, "total_steps": 125, "loss": 0.0456, "lr": 4.579747375353763e-05, "epoch": 2.8444444444444446, "percentage": 57.6, "elapsed_time": "0:46:45", "remaining_time": "0:34:25"}
80
+ {"current_steps": 73, "total_steps": 125, "loss": 0.0608, "lr": 4.4401776194834613e-05, "epoch": 2.8839506172839506, "percentage": 58.4, "elapsed_time": "0:47:24", "remaining_time": "0:33:46"}
81
+ {"current_steps": 74, "total_steps": 125, "loss": 0.0505, "lr": 4.3010483023225045e-05, "epoch": 2.9234567901234567, "percentage": 59.2, "elapsed_time": "0:48:02", "remaining_time": "0:33:06"}
82
+ {"current_steps": 75, "total_steps": 125, "loss": 0.0558, "lr": 4.162468883476319e-05, "epoch": 2.962962962962963, "percentage": 60.0, "elapsed_time": "0:48:36", "remaining_time": "0:32:24"}
83
+ {"current_steps": 76, "total_steps": 125, "loss": 0.0997, "lr": 4.0245483899193595e-05, "epoch": 3.0024691358024693, "percentage": 60.8, "elapsed_time": "0:49:13", "remaining_time": "0:31:44"}
84
+ {"current_steps": 77, "total_steps": 125, "loss": 0.0498, "lr": 3.887395330218429e-05, "epoch": 3.0419753086419754, "percentage": 61.6, "elapsed_time": "0:49:50", "remaining_time": "0:31:04"}
85
+ {"current_steps": 78, "total_steps": 125, "loss": 0.046, "lr": 3.7511176091638653e-05, "epoch": 3.0814814814814815, "percentage": 62.4, "elapsed_time": "0:50:28", "remaining_time": "0:30:24"}
86
+ {"current_steps": 79, "total_steps": 125, "loss": 0.0528, "lr": 3.6158224428757535e-05, "epoch": 3.1209876543209876, "percentage": 63.2, "elapsed_time": "0:51:05", "remaining_time": "0:29:45"}
87
+ {"current_steps": 80, "total_steps": 125, "loss": 0.0525, "lr": 3.4816162744519263e-05, "epoch": 3.1604938271604937, "percentage": 64.0, "elapsed_time": "0:51:36", "remaining_time": "0:29:01"}
88
+ {"current_steps": 80, "total_steps": 125, "eval_loss": 0.05618962645530701, "epoch": 3.1604938271604937, "percentage": 64.0, "elapsed_time": "0:52:02", "remaining_time": "0:29:16"}
89
+ {"current_steps": 81, "total_steps": 125, "loss": 0.0392, "lr": 3.3486046902241664e-05, "epoch": 3.2, "percentage": 64.8, "elapsed_time": "0:52:39", "remaining_time": "0:28:36"}
90
+ {"current_steps": 82, "total_steps": 125, "loss": 0.0474, "lr": 3.216892336688435e-05, "epoch": 3.2395061728395063, "percentage": 65.6, "elapsed_time": "0:53:17", "remaining_time": "0:27:56"}
91
+ {"current_steps": 83, "total_steps": 125, "loss": 0.0513, "lr": 3.086582838174551e-05, "epoch": 3.2790123456790123, "percentage": 66.4, "elapsed_time": "0:53:53", "remaining_time": "0:27:16"}
92
+ {"current_steps": 84, "total_steps": 125, "loss": 0.0502, "lr": 2.9577787153200197e-05, "epoch": 3.3185185185185184, "percentage": 67.2, "elapsed_time": "0:54:29", "remaining_time": "0:26:35"}
93
+ {"current_steps": 85, "total_steps": 125, "loss": 0.0438, "lr": 2.8305813044122097e-05, "epoch": 3.3580246913580245, "percentage": 68.0, "elapsed_time": "0:55:02", "remaining_time": "0:25:54"}
94
+ {"current_steps": 86, "total_steps": 125, "loss": 0.0575, "lr": 2.705090677662311e-05, "epoch": 3.397530864197531, "percentage": 68.8, "elapsed_time": "0:55:35", "remaining_time": "0:25:12"}
95
+ {"current_steps": 87, "total_steps": 125, "loss": 0.0472, "lr": 2.581405564473801e-05, "epoch": 3.437037037037037, "percentage": 69.6, "elapsed_time": "0:56:08", "remaining_time": "0:24:31"}
96
+ {"current_steps": 88, "total_steps": 125, "loss": 0.0479, "lr": 2.459623273767354e-05, "epoch": 3.476543209876543, "percentage": 70.4, "elapsed_time": "0:56:44", "remaining_time": "0:23:51"}
97
+ {"current_steps": 89, "total_steps": 125, "loss": 0.0491, "lr": 2.3398396174233178e-05, "epoch": 3.5160493827160493, "percentage": 71.2, "elapsed_time": "0:57:19", "remaining_time": "0:23:11"}
98
+ {"current_steps": 90, "total_steps": 125, "loss": 0.0567, "lr": 2.2221488349019903e-05, "epoch": 3.5555555555555554, "percentage": 72.0, "elapsed_time": "0:57:57", "remaining_time": "0:22:32"}
99
+ {"current_steps": 90, "total_steps": 125, "eval_loss": 0.0555027574300766, "epoch": 3.5555555555555554, "percentage": 72.0, "elapsed_time": "0:58:23", "remaining_time": "0:22:42"}
100
+ {"current_steps": 91, "total_steps": 125, "loss": 0.0562, "lr": 2.1066435191009715e-05, "epoch": 3.595061728395062, "percentage": 72.8, "elapsed_time": "0:59:06", "remaining_time": "0:22:05"}
101
+ {"current_steps": 92, "total_steps": 125, "loss": 0.0505, "lr": 1.9934145435079702e-05, "epoch": 3.634567901234568, "percentage": 73.6, "elapsed_time": "0:59:41", "remaining_time": "0:21:24"}
102
+ {"current_steps": 93, "total_steps": 125, "loss": 0.045, "lr": 1.8825509907063327e-05, "epoch": 3.674074074074074, "percentage": 74.4, "elapsed_time": "1:00:20", "remaining_time": "0:20:45"}
103
+ {"current_steps": 94, "total_steps": 125, "loss": 0.0475, "lr": 1.774140082289563e-05, "epoch": 3.71358024691358, "percentage": 75.2, "elapsed_time": "1:00:53", "remaining_time": "0:20:04"}
104
+ {"current_steps": 95, "total_steps": 125, "loss": 0.0499, "lr": 1.6682671102399805e-05, "epoch": 3.753086419753086, "percentage": 76.0, "elapsed_time": "1:01:36", "remaining_time": "0:19:27"}
105
+ {"current_steps": 96, "total_steps": 125, "loss": 0.0401, "lr": 1.5650153698254916e-05, "epoch": 3.7925925925925927, "percentage": 76.8, "elapsed_time": "1:02:08", "remaining_time": "0:18:46"}
106
+ {"current_steps": 97, "total_steps": 125, "loss": 0.0449, "lr": 1.4644660940672627e-05, "epoch": 3.832098765432099, "percentage": 77.6, "elapsed_time": "1:02:43", "remaining_time": "0:18:06"}
107
+ {"current_steps": 98, "total_steps": 125, "loss": 0.0633, "lr": 1.3666983898298657e-05, "epoch": 3.871604938271605, "percentage": 78.4, "elapsed_time": "1:03:25", "remaining_time": "0:17:28"}
108
+ {"current_steps": 99, "total_steps": 125, "loss": 0.0488, "lr": 1.2717891755841722e-05, "epoch": 3.911111111111111, "percentage": 79.2, "elapsed_time": "1:04:08", "remaining_time": "0:16:50"}
109
+ {"current_steps": 100, "total_steps": 125, "loss": 0.0437, "lr": 1.1798131208919627e-05, "epoch": 3.950617283950617, "percentage": 80.0, "elapsed_time": "1:04:40", "remaining_time": "0:16:10"}
110
+ {"current_steps": 100, "total_steps": 125, "eval_loss": 0.05377759039402008, "epoch": 3.950617283950617, "percentage": 80.0, "elapsed_time": "1:05:06", "remaining_time": "0:16:16"}
111
+ {"current_steps": 101, "total_steps": 125, "loss": 0.0592, "lr": 1.090842587659851e-05, "epoch": 3.9901234567901236, "percentage": 80.8, "elapsed_time": "1:05:48", "remaining_time": "0:15:38"}
112
+ {"current_steps": 102, "total_steps": 125, "loss": 0.0903, "lr": 1.004947573208756e-05, "epoch": 4.029629629629629, "percentage": 81.6, "elapsed_time": "1:06:25", "remaining_time": "0:14:58"}
113
+ {"current_steps": 103, "total_steps": 125, "loss": 0.0446, "lr": 9.221956552036992e-06, "epoch": 4.069135802469136, "percentage": 82.4, "elapsed_time": "1:07:07", "remaining_time": "0:14:20"}
114
+ {"current_steps": 104, "total_steps": 125, "loss": 0.0383, "lr": 8.426519384872733e-06, "epoch": 4.108641975308642, "percentage": 83.2, "elapsed_time": "1:07:38", "remaining_time": "0:13:39"}
115
+ {"current_steps": 105, "total_steps": 125, "loss": 0.0454, "lr": 7.663790038585793e-06, "epoch": 4.148148148148148, "percentage": 84.0, "elapsed_time": "1:08:18", "remaining_time": "0:13:00"}
116
+ {"current_steps": 106, "total_steps": 125, "loss": 0.0346, "lr": 6.934368588379553e-06, "epoch": 4.187654320987654, "percentage": 84.8, "elapsed_time": "1:08:54", "remaining_time": "0:12:21"}
117
+ {"current_steps": 107, "total_steps": 125, "loss": 0.0465, "lr": 6.238828904562316e-06, "epoch": 4.22716049382716, "percentage": 85.6, "elapsed_time": "1:09:34", "remaining_time": "0:11:42"}
118
+ {"current_steps": 108, "total_steps": 125, "loss": 0.0424, "lr": 5.577718201056392e-06, "epoch": 4.266666666666667, "percentage": 86.4, "elapsed_time": "1:10:08", "remaining_time": "0:11:02"}
119
+ {"current_steps": 109, "total_steps": 125, "loss": 0.0461, "lr": 4.951556604879048e-06, "epoch": 4.306172839506173, "percentage": 87.2, "elapsed_time": "1:10:43", "remaining_time": "0:10:22"}
120
+ {"current_steps": 110, "total_steps": 125, "loss": 0.0503, "lr": 4.360836746934055e-06, "epoch": 4.345679012345679, "percentage": 88.0, "elapsed_time": "1:11:18", "remaining_time": "0:09:43"}
121
+ {"current_steps": 110, "total_steps": 125, "eval_loss": 0.052800051867961884, "epoch": 4.345679012345679, "percentage": 88.0, "elapsed_time": "1:11:44", "remaining_time": "0:09:47"}
122
+ {"current_steps": 111, "total_steps": 125, "loss": 0.0423, "lr": 3.8060233744356633e-06, "epoch": 4.385185185185185, "percentage": 88.8, "elapsed_time": "1:12:24", "remaining_time": "0:09:07"}
123
+ {"current_steps": 112, "total_steps": 125, "loss": 0.0352, "lr": 3.2875529852700147e-06, "epoch": 4.424691358024692, "percentage": 89.6, "elapsed_time": "1:13:01", "remaining_time": "0:08:28"}
124
+ {"current_steps": 113, "total_steps": 125, "loss": 0.0484, "lr": 2.8058334845816213e-06, "epoch": 4.4641975308641975, "percentage": 90.4, "elapsed_time": "1:13:34", "remaining_time": "0:07:48"}
125
+ {"current_steps": 114, "total_steps": 125, "loss": 0.0459, "lr": 2.361243863855184e-06, "epoch": 4.503703703703704, "percentage": 91.2, "elapsed_time": "1:14:15", "remaining_time": "0:07:09"}
126
+ {"current_steps": 115, "total_steps": 125, "loss": 0.049, "lr": 1.9541339027450256e-06, "epoch": 4.54320987654321, "percentage": 92.0, "elapsed_time": "1:14:53", "remaining_time": "0:06:30"}
127
+ {"current_steps": 116, "total_steps": 125, "loss": 0.0509, "lr": 1.584823893886933e-06, "epoch": 4.582716049382716, "percentage": 92.8, "elapsed_time": "1:15:26", "remaining_time": "0:05:51"}
128
+ {"current_steps": 117, "total_steps": 125, "loss": 0.0439, "lr": 1.2536043909088191e-06, "epoch": 4.622222222222222, "percentage": 93.6, "elapsed_time": "1:16:02", "remaining_time": "0:05:11"}
129
+ {"current_steps": 118, "total_steps": 125, "loss": 0.0506, "lr": 9.607359798384785e-07, "epoch": 4.661728395061728, "percentage": 94.4, "elapsed_time": "1:16:34", "remaining_time": "0:04:32"}
130
+ {"current_steps": 119, "total_steps": 125, "loss": 0.0428, "lr": 7.064490740882057e-07, "epoch": 4.701234567901235, "percentage": 95.2, "elapsed_time": "1:17:09", "remaining_time": "0:03:53"}
131
+ {"current_steps": 120, "total_steps": 125, "loss": 0.0521, "lr": 4.909437331777179e-07, "epoch": 4.7407407407407405, "percentage": 96.0, "elapsed_time": "1:17:46", "remaining_time": "0:03:14"}
132
+ {"current_steps": 120, "total_steps": 125, "eval_loss": 0.0528191402554512, "epoch": 4.7407407407407405, "percentage": 96.0, "elapsed_time": "1:18:12", "remaining_time": "0:03:15"}
133
+ {"current_steps": 121, "total_steps": 125, "loss": 0.0453, "lr": 3.143895053378698e-07, "epoch": 4.780246913580247, "percentage": 96.8, "elapsed_time": "1:18:57", "remaining_time": "0:02:36"}
134
+ {"current_steps": 122, "total_steps": 125, "loss": 0.0485, "lr": 1.7692529411904578e-07, "epoch": 4.8197530864197535, "percentage": 97.6, "elapsed_time": "1:19:35", "remaining_time": "0:01:57"}
135
+ {"current_steps": 123, "total_steps": 125, "loss": 0.0533, "lr": 7.865924910916977e-08, "epoch": 4.859259259259259, "percentage": 98.4, "elapsed_time": "1:20:13", "remaining_time": "0:01:18"}
136
+ {"current_steps": 124, "total_steps": 125, "loss": 0.0466, "lr": 1.9668680847356735e-08, "epoch": 4.898765432098766, "percentage": 99.2, "elapsed_time": "1:20:44", "remaining_time": "0:00:39"}
137
+ {"current_steps": 125, "total_steps": 125, "loss": 0.0407, "lr": 0.0, "epoch": 4.938271604938271, "percentage": 100.0, "elapsed_time": "1:21:21", "remaining_time": "0:00:00"}
138
+ {"current_steps": 125, "total_steps": 125, "epoch": 4.938271604938271, "percentage": 100.0, "elapsed_time": "1:21:25", "remaining_time": "0:00:00"}
chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6/trainer_state.json ADDED
@@ -0,0 +1,1013 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.052800051867961884,
3
+ "best_model_checkpoint": "saves/psy-course-doc-info/Llama-3.1-8B-Instruct/train/fold6/checkpoint-110",
4
+ "epoch": 4.938271604938271,
5
+ "eval_steps": 10,
6
+ "global_step": 125,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03950617283950617,
13
+ "grad_norm": 0.5146947503089905,
14
+ "learning_rate": 7.692307692307694e-06,
15
+ "loss": 0.4084,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.07901234567901234,
20
+ "grad_norm": 0.4019896984100342,
21
+ "learning_rate": 1.5384615384615387e-05,
22
+ "loss": 0.3408,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.11851851851851852,
27
+ "grad_norm": 0.5166494846343994,
28
+ "learning_rate": 2.307692307692308e-05,
29
+ "loss": 0.3892,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.1580246913580247,
34
+ "grad_norm": 0.3998715579509735,
35
+ "learning_rate": 3.0769230769230774e-05,
36
+ "loss": 0.3429,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.19753086419753085,
41
+ "grad_norm": 0.45492351055145264,
42
+ "learning_rate": 3.846153846153846e-05,
43
+ "loss": 0.3341,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.23703703703703705,
48
+ "grad_norm": 0.4303339123725891,
49
+ "learning_rate": 4.615384615384616e-05,
50
+ "loss": 0.342,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.2765432098765432,
55
+ "grad_norm": 0.4862079918384552,
56
+ "learning_rate": 5.384615384615385e-05,
57
+ "loss": 0.3587,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.3160493827160494,
62
+ "grad_norm": 0.3997127413749695,
63
+ "learning_rate": 6.153846153846155e-05,
64
+ "loss": 0.2992,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.35555555555555557,
69
+ "grad_norm": 0.3324596881866455,
70
+ "learning_rate": 6.923076923076924e-05,
71
+ "loss": 0.2757,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.3950617283950617,
76
+ "grad_norm": 0.4178152084350586,
77
+ "learning_rate": 7.692307692307693e-05,
78
+ "loss": 0.265,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.3950617283950617,
83
+ "eval_loss": 0.27192339301109314,
84
+ "eval_runtime": 25.982,
85
+ "eval_samples_per_second": 1.732,
86
+ "eval_steps_per_second": 1.732,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.4345679012345679,
91
+ "grad_norm": 0.48562926054000854,
92
+ "learning_rate": 8.461538461538461e-05,
93
+ "loss": 0.2865,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.4740740740740741,
98
+ "grad_norm": 0.4852800965309143,
99
+ "learning_rate": 9.230769230769232e-05,
100
+ "loss": 0.2422,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.5135802469135803,
105
+ "grad_norm": 0.48137393593788147,
106
+ "learning_rate": 0.0001,
107
+ "loss": 0.2421,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.5530864197530864,
112
+ "grad_norm": 0.3652872145175934,
113
+ "learning_rate": 9.998033131915266e-05,
114
+ "loss": 0.2099,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.5925925925925926,
119
+ "grad_norm": 0.34822386503219604,
120
+ "learning_rate": 9.992134075089084e-05,
121
+ "loss": 0.209,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.6320987654320988,
126
+ "grad_norm": 0.3031443655490875,
127
+ "learning_rate": 9.982307470588098e-05,
128
+ "loss": 0.1967,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.671604938271605,
133
+ "grad_norm": 0.31227704882621765,
134
+ "learning_rate": 9.968561049466214e-05,
135
+ "loss": 0.1765,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.7111111111111111,
140
+ "grad_norm": 0.3406769633293152,
141
+ "learning_rate": 9.950905626682228e-05,
142
+ "loss": 0.1795,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.7506172839506173,
147
+ "grad_norm": 0.32388052344322205,
148
+ "learning_rate": 9.92935509259118e-05,
149
+ "loss": 0.1576,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.7901234567901234,
154
+ "grad_norm": 0.2666756212711334,
155
+ "learning_rate": 9.903926402016153e-05,
156
+ "loss": 0.1689,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.7901234567901234,
161
+ "eval_loss": 0.14510378241539001,
162
+ "eval_runtime": 25.986,
163
+ "eval_samples_per_second": 1.732,
164
+ "eval_steps_per_second": 1.732,
165
+ "step": 20
166
+ },
167
+ {
168
+ "epoch": 0.8296296296296296,
169
+ "grad_norm": 0.25905218720436096,
170
+ "learning_rate": 9.874639560909117e-05,
171
+ "loss": 0.1437,
172
+ "step": 21
173
+ },
174
+ {
175
+ "epoch": 0.8691358024691358,
176
+ "grad_norm": 0.3037348687648773,
177
+ "learning_rate": 9.841517610611309e-05,
178
+ "loss": 0.1623,
179
+ "step": 22
180
+ },
181
+ {
182
+ "epoch": 0.908641975308642,
183
+ "grad_norm": 0.34230226278305054,
184
+ "learning_rate": 9.804586609725499e-05,
185
+ "loss": 0.1272,
186
+ "step": 23
187
+ },
188
+ {
189
+ "epoch": 0.9481481481481482,
190
+ "grad_norm": 0.418644517660141,
191
+ "learning_rate": 9.763875613614482e-05,
192
+ "loss": 0.1437,
193
+ "step": 24
194
+ },
195
+ {
196
+ "epoch": 0.9876543209876543,
197
+ "grad_norm": 0.28610771894454956,
198
+ "learning_rate": 9.719416651541839e-05,
199
+ "loss": 0.138,
200
+ "step": 25
201
+ },
202
+ {
203
+ "epoch": 1.0271604938271606,
204
+ "grad_norm": 0.5024089813232422,
205
+ "learning_rate": 9.671244701472999e-05,
206
+ "loss": 0.2049,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 1.0666666666666667,
211
+ "grad_norm": 0.2994146943092346,
212
+ "learning_rate": 9.619397662556435e-05,
213
+ "loss": 0.0987,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 1.106172839506173,
218
+ "grad_norm": 0.3435674011707306,
219
+ "learning_rate": 9.563916325306594e-05,
220
+ "loss": 0.1196,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 1.145679012345679,
225
+ "grad_norm": 0.30092939734458923,
226
+ "learning_rate": 9.504844339512095e-05,
227
+ "loss": 0.1156,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 1.1851851851851851,
232
+ "grad_norm": 0.2616022825241089,
233
+ "learning_rate": 9.442228179894362e-05,
234
+ "loss": 0.1027,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 1.1851851851851851,
239
+ "eval_loss": 0.10370857268571854,
240
+ "eval_runtime": 25.9985,
241
+ "eval_samples_per_second": 1.731,
242
+ "eval_steps_per_second": 1.731,
243
+ "step": 30
244
+ },
245
+ {
246
+ "epoch": 1.2246913580246914,
247
+ "grad_norm": 0.23512841761112213,
248
+ "learning_rate": 9.376117109543769e-05,
249
+ "loss": 0.1173,
250
+ "step": 31
251
+ },
252
+ {
253
+ "epoch": 1.2641975308641975,
254
+ "grad_norm": 0.2797624468803406,
255
+ "learning_rate": 9.306563141162046e-05,
256
+ "loss": 0.1047,
257
+ "step": 32
258
+ },
259
+ {
260
+ "epoch": 1.3037037037037038,
261
+ "grad_norm": 0.21222670376300812,
262
+ "learning_rate": 9.233620996141421e-05,
263
+ "loss": 0.0901,
264
+ "step": 33
265
+ },
266
+ {
267
+ "epoch": 1.34320987654321,
268
+ "grad_norm": 0.22136375308036804,
269
+ "learning_rate": 9.157348061512727e-05,
270
+ "loss": 0.0961,
271
+ "step": 34
272
+ },
273
+ {
274
+ "epoch": 1.382716049382716,
275
+ "grad_norm": 0.2523188292980194,
276
+ "learning_rate": 9.077804344796302e-05,
277
+ "loss": 0.0986,
278
+ "step": 35
279
+ },
280
+ {
281
+ "epoch": 1.4222222222222223,
282
+ "grad_norm": 0.24723868072032928,
283
+ "learning_rate": 8.995052426791247e-05,
284
+ "loss": 0.0951,
285
+ "step": 36
286
+ },
287
+ {
288
+ "epoch": 1.4617283950617284,
289
+ "grad_norm": 0.22367025911808014,
290
+ "learning_rate": 8.90915741234015e-05,
291
+ "loss": 0.0835,
292
+ "step": 37
293
+ },
294
+ {
295
+ "epoch": 1.5012345679012347,
296
+ "grad_norm": 0.3691348433494568,
297
+ "learning_rate": 8.820186879108038e-05,
298
+ "loss": 0.0958,
299
+ "step": 38
300
+ },
301
+ {
302
+ "epoch": 1.5407407407407407,
303
+ "grad_norm": 0.2751408517360687,
304
+ "learning_rate": 8.728210824415827e-05,
305
+ "loss": 0.0917,
306
+ "step": 39
307
+ },
308
+ {
309
+ "epoch": 1.5802469135802468,
310
+ "grad_norm": 0.23567897081375122,
311
+ "learning_rate": 8.633301610170135e-05,
312
+ "loss": 0.0848,
313
+ "step": 40
314
+ },
315
+ {
316
+ "epoch": 1.5802469135802468,
317
+ "eval_loss": 0.08050418645143509,
318
+ "eval_runtime": 25.9982,
319
+ "eval_samples_per_second": 1.731,
320
+ "eval_steps_per_second": 1.731,
321
+ "step": 40
322
+ },
323
+ {
324
+ "epoch": 1.6197530864197531,
325
+ "grad_norm": 0.31919142603874207,
326
+ "learning_rate": 8.535533905932738e-05,
327
+ "loss": 0.0818,
328
+ "step": 41
329
+ },
330
+ {
331
+ "epoch": 1.6592592592592592,
332
+ "grad_norm": 0.2822875678539276,
333
+ "learning_rate": 8.434984630174509e-05,
334
+ "loss": 0.0775,
335
+ "step": 42
336
+ },
337
+ {
338
+ "epoch": 1.6987654320987655,
339
+ "grad_norm": 0.3018384277820587,
340
+ "learning_rate": 8.33173288976002e-05,
341
+ "loss": 0.0828,
342
+ "step": 43
343
+ },
344
+ {
345
+ "epoch": 1.7382716049382716,
346
+ "grad_norm": 0.2712375521659851,
347
+ "learning_rate": 8.225859917710439e-05,
348
+ "loss": 0.073,
349
+ "step": 44
350
+ },
351
+ {
352
+ "epoch": 1.7777777777777777,
353
+ "grad_norm": 0.35071420669555664,
354
+ "learning_rate": 8.117449009293668e-05,
355
+ "loss": 0.087,
356
+ "step": 45
357
+ },
358
+ {
359
+ "epoch": 1.817283950617284,
360
+ "grad_norm": 0.2117828130722046,
361
+ "learning_rate": 8.006585456492029e-05,
362
+ "loss": 0.0595,
363
+ "step": 46
364
+ },
365
+ {
366
+ "epoch": 1.8567901234567903,
367
+ "grad_norm": 0.3012438118457794,
368
+ "learning_rate": 7.89335648089903e-05,
369
+ "loss": 0.1004,
370
+ "step": 47
371
+ },
372
+ {
373
+ "epoch": 1.8962962962962964,
374
+ "grad_norm": 0.21643108129501343,
375
+ "learning_rate": 7.777851165098012e-05,
376
+ "loss": 0.0645,
377
+ "step": 48
378
+ },
379
+ {
380
+ "epoch": 1.9358024691358025,
381
+ "grad_norm": 0.23656418919563293,
382
+ "learning_rate": 7.660160382576683e-05,
383
+ "loss": 0.0908,
384
+ "step": 49
385
+ },
386
+ {
387
+ "epoch": 1.9753086419753085,
388
+ "grad_norm": 0.21919803321361542,
389
+ "learning_rate": 7.540376726232648e-05,
390
+ "loss": 0.0671,
391
+ "step": 50
392
+ },
393
+ {
394
+ "epoch": 1.9753086419753085,
395
+ "eval_loss": 0.06918726116418839,
396
+ "eval_runtime": 26.0005,
397
+ "eval_samples_per_second": 1.731,
398
+ "eval_steps_per_second": 1.731,
399
+ "step": 50
400
+ },
401
+ {
402
+ "epoch": 2.0148148148148146,
403
+ "grad_norm": 0.49693554639816284,
404
+ "learning_rate": 7.4185944355262e-05,
405
+ "loss": 0.1146,
406
+ "step": 51
407
+ },
408
+ {
409
+ "epoch": 2.054320987654321,
410
+ "grad_norm": 0.19470937550067902,
411
+ "learning_rate": 7.294909322337689e-05,
412
+ "loss": 0.055,
413
+ "step": 52
414
+ },
415
+ {
416
+ "epoch": 2.093827160493827,
417
+ "grad_norm": 0.19454921782016754,
418
+ "learning_rate": 7.169418695587791e-05,
419
+ "loss": 0.0624,
420
+ "step": 53
421
+ },
422
+ {
423
+ "epoch": 2.1333333333333333,
424
+ "grad_norm": 0.25666776299476624,
425
+ "learning_rate": 7.042221284679982e-05,
426
+ "loss": 0.0711,
427
+ "step": 54
428
+ },
429
+ {
430
+ "epoch": 2.1728395061728394,
431
+ "grad_norm": 0.2294730246067047,
432
+ "learning_rate": 6.91341716182545e-05,
433
+ "loss": 0.0646,
434
+ "step": 55
435
+ },
436
+ {
437
+ "epoch": 2.212345679012346,
438
+ "grad_norm": 0.20461145043373108,
439
+ "learning_rate": 6.783107663311565e-05,
440
+ "loss": 0.0524,
441
+ "step": 56
442
+ },
443
+ {
444
+ "epoch": 2.251851851851852,
445
+ "grad_norm": 0.2858906686306,
446
+ "learning_rate": 6.651395309775837e-05,
447
+ "loss": 0.0686,
448
+ "step": 57
449
+ },
450
+ {
451
+ "epoch": 2.291358024691358,
452
+ "grad_norm": 0.32071003317832947,
453
+ "learning_rate": 6.518383725548074e-05,
454
+ "loss": 0.0805,
455
+ "step": 58
456
+ },
457
+ {
458
+ "epoch": 2.330864197530864,
459
+ "grad_norm": 0.22127433121204376,
460
+ "learning_rate": 6.384177557124247e-05,
461
+ "loss": 0.0651,
462
+ "step": 59
463
+ },
464
+ {
465
+ "epoch": 2.3703703703703702,
466
+ "grad_norm": 0.2365463823080063,
467
+ "learning_rate": 6.248882390836135e-05,
468
+ "loss": 0.0635,
469
+ "step": 60
470
+ },
471
+ {
472
+ "epoch": 2.3703703703703702,
473
+ "eval_loss": 0.061441570520401,
474
+ "eval_runtime": 26.0166,
475
+ "eval_samples_per_second": 1.73,
476
+ "eval_steps_per_second": 1.73,
477
+ "step": 60
478
+ },
479
+ {
480
+ "epoch": 2.4098765432098768,
481
+ "grad_norm": 0.24754828214645386,
482
+ "learning_rate": 6.112604669781572e-05,
483
+ "loss": 0.0556,
484
+ "step": 61
485
+ },
486
+ {
487
+ "epoch": 2.449382716049383,
488
+ "grad_norm": 0.21690750122070312,
489
+ "learning_rate": 5.9754516100806423e-05,
490
+ "loss": 0.0598,
491
+ "step": 62
492
+ },
493
+ {
494
+ "epoch": 2.488888888888889,
495
+ "grad_norm": 0.2789786458015442,
496
+ "learning_rate": 5.837531116523682e-05,
497
+ "loss": 0.074,
498
+ "step": 63
499
+ },
500
+ {
501
+ "epoch": 2.528395061728395,
502
+ "grad_norm": 0.187678262591362,
503
+ "learning_rate": 5.698951697677498e-05,
504
+ "loss": 0.051,
505
+ "step": 64
506
+ },
507
+ {
508
+ "epoch": 2.567901234567901,
509
+ "grad_norm": 0.17922283709049225,
510
+ "learning_rate": 5.559822380516539e-05,
511
+ "loss": 0.0612,
512
+ "step": 65
513
+ },
514
+ {
515
+ "epoch": 2.6074074074074076,
516
+ "grad_norm": 0.20609335601329803,
517
+ "learning_rate": 5.420252624646238e-05,
518
+ "loss": 0.0623,
519
+ "step": 66
520
+ },
521
+ {
522
+ "epoch": 2.6469135802469137,
523
+ "grad_norm": 0.24197928607463837,
524
+ "learning_rate": 5.2803522361859594e-05,
525
+ "loss": 0.0547,
526
+ "step": 67
527
+ },
528
+ {
529
+ "epoch": 2.68641975308642,
530
+ "grad_norm": 0.20105622708797455,
531
+ "learning_rate": 5.140231281379345e-05,
532
+ "loss": 0.0555,
533
+ "step": 68
534
+ },
535
+ {
536
+ "epoch": 2.725925925925926,
537
+ "grad_norm": 0.2905729115009308,
538
+ "learning_rate": 5e-05,
539
+ "loss": 0.0608,
540
+ "step": 69
541
+ },
542
+ {
543
+ "epoch": 2.765432098765432,
544
+ "grad_norm": 0.22538885474205017,
545
+ "learning_rate": 4.859768718620656e-05,
546
+ "loss": 0.0637,
547
+ "step": 70
548
+ },
549
+ {
550
+ "epoch": 2.765432098765432,
551
+ "eval_loss": 0.06007562205195427,
552
+ "eval_runtime": 26.0197,
553
+ "eval_samples_per_second": 1.729,
554
+ "eval_steps_per_second": 1.729,
555
+ "step": 70
556
+ },
557
+ {
558
+ "epoch": 2.8049382716049385,
559
+ "grad_norm": 0.22092154622077942,
560
+ "learning_rate": 4.7196477638140404e-05,
561
+ "loss": 0.0546,
562
+ "step": 71
563
+ },
564
+ {
565
+ "epoch": 2.8444444444444446,
566
+ "grad_norm": 0.16019904613494873,
567
+ "learning_rate": 4.579747375353763e-05,
568
+ "loss": 0.0456,
569
+ "step": 72
570
+ },
571
+ {
572
+ "epoch": 2.8839506172839506,
573
+ "grad_norm": 0.20831051468849182,
574
+ "learning_rate": 4.4401776194834613e-05,
575
+ "loss": 0.0608,
576
+ "step": 73
577
+ },
578
+ {
579
+ "epoch": 2.9234567901234567,
580
+ "grad_norm": 0.17661935091018677,
581
+ "learning_rate": 4.3010483023225045e-05,
582
+ "loss": 0.0505,
583
+ "step": 74
584
+ },
585
+ {
586
+ "epoch": 2.962962962962963,
587
+ "grad_norm": 0.238091841340065,
588
+ "learning_rate": 4.162468883476319e-05,
589
+ "loss": 0.0558,
590
+ "step": 75
591
+ },
592
+ {
593
+ "epoch": 3.0024691358024693,
594
+ "grad_norm": 0.41548091173171997,
595
+ "learning_rate": 4.0245483899193595e-05,
596
+ "loss": 0.0997,
597
+ "step": 76
598
+ },
599
+ {
600
+ "epoch": 3.0419753086419754,
601
+ "grad_norm": 0.1865716576576233,
602
+ "learning_rate": 3.887395330218429e-05,
603
+ "loss": 0.0498,
604
+ "step": 77
605
+ },
606
+ {
607
+ "epoch": 3.0814814814814815,
608
+ "grad_norm": 0.17337585985660553,
609
+ "learning_rate": 3.7511176091638653e-05,
610
+ "loss": 0.046,
611
+ "step": 78
612
+ },
613
+ {
614
+ "epoch": 3.1209876543209876,
615
+ "grad_norm": 0.20592160522937775,
616
+ "learning_rate": 3.6158224428757535e-05,
617
+ "loss": 0.0528,
618
+ "step": 79
619
+ },
620
+ {
621
+ "epoch": 3.1604938271604937,
622
+ "grad_norm": 0.22112375497817993,
623
+ "learning_rate": 3.4816162744519263e-05,
624
+ "loss": 0.0525,
625
+ "step": 80
626
+ },
627
+ {
628
+ "epoch": 3.1604938271604937,
629
+ "eval_loss": 0.05618962645530701,
630
+ "eval_runtime": 26.0008,
631
+ "eval_samples_per_second": 1.731,
632
+ "eval_steps_per_second": 1.731,
633
+ "step": 80
634
+ },
635
+ {
636
+ "epoch": 3.2,
637
+ "grad_norm": 0.21675719320774078,
638
+ "learning_rate": 3.3486046902241664e-05,
639
+ "loss": 0.0392,
640
+ "step": 81
641
+ },
642
+ {
643
+ "epoch": 3.2395061728395063,
644
+ "grad_norm": 0.17582350969314575,
645
+ "learning_rate": 3.216892336688435e-05,
646
+ "loss": 0.0474,
647
+ "step": 82
648
+ },
649
+ {
650
+ "epoch": 3.2790123456790123,
651
+ "grad_norm": 0.1740693897008896,
652
+ "learning_rate": 3.086582838174551e-05,
653
+ "loss": 0.0513,
654
+ "step": 83
655
+ },
656
+ {
657
+ "epoch": 3.3185185185185184,
658
+ "grad_norm": 0.22133827209472656,
659
+ "learning_rate": 2.9577787153200197e-05,
660
+ "loss": 0.0502,
661
+ "step": 84
662
+ },
663
+ {
664
+ "epoch": 3.3580246913580245,
665
+ "grad_norm": 0.1794731616973877,
666
+ "learning_rate": 2.8305813044122097e-05,
667
+ "loss": 0.0438,
668
+ "step": 85
669
+ },
670
+ {
671
+ "epoch": 3.397530864197531,
672
+ "grad_norm": 0.1969956010580063,
673
+ "learning_rate": 2.705090677662311e-05,
674
+ "loss": 0.0575,
675
+ "step": 86
676
+ },
677
+ {
678
+ "epoch": 3.437037037037037,
679
+ "grad_norm": 0.20567215979099274,
680
+ "learning_rate": 2.581405564473801e-05,
681
+ "loss": 0.0472,
682
+ "step": 87
683
+ },
684
+ {
685
+ "epoch": 3.476543209876543,
686
+ "grad_norm": 0.19513347744941711,
687
+ "learning_rate": 2.459623273767354e-05,
688
+ "loss": 0.0479,
689
+ "step": 88
690
+ },
691
+ {
692
+ "epoch": 3.5160493827160493,
693
+ "grad_norm": 0.19764341413974762,
694
+ "learning_rate": 2.3398396174233178e-05,
695
+ "loss": 0.0491,
696
+ "step": 89
697
+ },
698
+ {
699
+ "epoch": 3.5555555555555554,
700
+ "grad_norm": 0.19821615517139435,
701
+ "learning_rate": 2.2221488349019903e-05,
702
+ "loss": 0.0567,
703
+ "step": 90
704
+ },
705
+ {
706
+ "epoch": 3.5555555555555554,
707
+ "eval_loss": 0.0555027574300766,
708
+ "eval_runtime": 25.9911,
709
+ "eval_samples_per_second": 1.731,
710
+ "eval_steps_per_second": 1.731,
711
+ "step": 90
712
+ },
713
+ {
714
+ "epoch": 3.595061728395062,
715
+ "grad_norm": 0.20487791299819946,
716
+ "learning_rate": 2.1066435191009715e-05,
717
+ "loss": 0.0562,
718
+ "step": 91
719
+ },
720
+ {
721
+ "epoch": 3.634567901234568,
722
+ "grad_norm": 0.18421317636966705,
723
+ "learning_rate": 1.9934145435079702e-05,
724
+ "loss": 0.0505,
725
+ "step": 92
726
+ },
727
+ {
728
+ "epoch": 3.674074074074074,
729
+ "grad_norm": 0.20219753682613373,
730
+ "learning_rate": 1.8825509907063327e-05,
731
+ "loss": 0.045,
732
+ "step": 93
733
+ },
734
+ {
735
+ "epoch": 3.71358024691358,
736
+ "grad_norm": 0.2213960587978363,
737
+ "learning_rate": 1.774140082289563e-05,
738
+ "loss": 0.0475,
739
+ "step": 94
740
+ },
741
+ {
742
+ "epoch": 3.753086419753086,
743
+ "grad_norm": 0.21140997111797333,
744
+ "learning_rate": 1.6682671102399805e-05,
745
+ "loss": 0.0499,
746
+ "step": 95
747
+ },
748
+ {
749
+ "epoch": 3.7925925925925927,
750
+ "grad_norm": 0.18448854982852936,
751
+ "learning_rate": 1.5650153698254916e-05,
752
+ "loss": 0.0401,
753
+ "step": 96
754
+ },
755
+ {
756
+ "epoch": 3.832098765432099,
757
+ "grad_norm": 0.1983409821987152,
758
+ "learning_rate": 1.4644660940672627e-05,
759
+ "loss": 0.0449,
760
+ "step": 97
761
+ },
762
+ {
763
+ "epoch": 3.871604938271605,
764
+ "grad_norm": 0.21478283405303955,
765
+ "learning_rate": 1.3666983898298657e-05,
766
+ "loss": 0.0633,
767
+ "step": 98
768
+ },
769
+ {
770
+ "epoch": 3.911111111111111,
771
+ "grad_norm": 0.18524666130542755,
772
+ "learning_rate": 1.2717891755841722e-05,
773
+ "loss": 0.0488,
774
+ "step": 99
775
+ },
776
+ {
777
+ "epoch": 3.950617283950617,
778
+ "grad_norm": 0.16829054057598114,
779
+ "learning_rate": 1.1798131208919627e-05,
780
+ "loss": 0.0437,
781
+ "step": 100
782
+ },
783
+ {
784
+ "epoch": 3.950617283950617,
785
+ "eval_loss": 0.05377759039402008,
786
+ "eval_runtime": 25.9991,
787
+ "eval_samples_per_second": 1.731,
788
+ "eval_steps_per_second": 1.731,
789
+ "step": 100
790
+ },
791
+ {
792
+ "epoch": 3.9901234567901236,
793
+ "grad_norm": 0.27219635248184204,
794
+ "learning_rate": 1.090842587659851e-05,
795
+ "loss": 0.0592,
796
+ "step": 101
797
+ },
798
+ {
799
+ "epoch": 4.029629629629629,
800
+ "grad_norm": 0.4242662489414215,
801
+ "learning_rate": 1.004947573208756e-05,
802
+ "loss": 0.0903,
803
+ "step": 102
804
+ },
805
+ {
806
+ "epoch": 4.069135802469136,
807
+ "grad_norm": 0.1797526776790619,
808
+ "learning_rate": 9.221956552036992e-06,
809
+ "loss": 0.0446,
810
+ "step": 103
811
+ },
812
+ {
813
+ "epoch": 4.108641975308642,
814
+ "grad_norm": 0.18448083102703094,
815
+ "learning_rate": 8.426519384872733e-06,
816
+ "loss": 0.0383,
817
+ "step": 104
818
+ },
819
+ {
820
+ "epoch": 4.148148148148148,
821
+ "grad_norm": 0.13986733555793762,
822
+ "learning_rate": 7.663790038585793e-06,
823
+ "loss": 0.0454,
824
+ "step": 105
825
+ },
826
+ {
827
+ "epoch": 4.187654320987654,
828
+ "grad_norm": 0.153441920876503,
829
+ "learning_rate": 6.934368588379553e-06,
830
+ "loss": 0.0346,
831
+ "step": 106
832
+ },
833
+ {
834
+ "epoch": 4.22716049382716,
835
+ "grad_norm": 0.19964894652366638,
836
+ "learning_rate": 6.238828904562316e-06,
837
+ "loss": 0.0465,
838
+ "step": 107
839
+ },
840
+ {
841
+ "epoch": 4.266666666666667,
842
+ "grad_norm": 0.17707543075084686,
843
+ "learning_rate": 5.577718201056392e-06,
844
+ "loss": 0.0424,
845
+ "step": 108
846
+ },
847
+ {
848
+ "epoch": 4.306172839506173,
849
+ "grad_norm": 0.16833744943141937,
850
+ "learning_rate": 4.951556604879048e-06,
851
+ "loss": 0.0461,
852
+ "step": 109
853
+ },
854
+ {
855
+ "epoch": 4.345679012345679,
856
+ "grad_norm": 0.19674107432365417,
857
+ "learning_rate": 4.360836746934055e-06,
858
+ "loss": 0.0503,
859
+ "step": 110
860
+ },
861
+ {
862
+ "epoch": 4.345679012345679,
863
+ "eval_loss": 0.052800051867961884,
864
+ "eval_runtime": 26.0016,
865
+ "eval_samples_per_second": 1.731,
866
+ "eval_steps_per_second": 1.731,
867
+ "step": 110
868
+ },
869
+ {
870
+ "epoch": 4.385185185185185,
871
+ "grad_norm": 0.15886488556861877,
872
+ "learning_rate": 3.8060233744356633e-06,
873
+ "loss": 0.0423,
874
+ "step": 111
875
+ },
876
+ {
877
+ "epoch": 4.424691358024692,
878
+ "grad_norm": 0.1287938952445984,
879
+ "learning_rate": 3.2875529852700147e-06,
880
+ "loss": 0.0352,
881
+ "step": 112
882
+ },
883
+ {
884
+ "epoch": 4.4641975308641975,
885
+ "grad_norm": 0.18720778822898865,
886
+ "learning_rate": 2.8058334845816213e-06,
887
+ "loss": 0.0484,
888
+ "step": 113
889
+ },
890
+ {
891
+ "epoch": 4.503703703703704,
892
+ "grad_norm": 0.18879911303520203,
893
+ "learning_rate": 2.361243863855184e-06,
894
+ "loss": 0.0459,
895
+ "step": 114
896
+ },
897
+ {
898
+ "epoch": 4.54320987654321,
899
+ "grad_norm": 0.22935695946216583,
900
+ "learning_rate": 1.9541339027450256e-06,
901
+ "loss": 0.049,
902
+ "step": 115
903
+ },
904
+ {
905
+ "epoch": 4.582716049382716,
906
+ "grad_norm": 0.1820475161075592,
907
+ "learning_rate": 1.584823893886933e-06,
908
+ "loss": 0.0509,
909
+ "step": 116
910
+ },
911
+ {
912
+ "epoch": 4.622222222222222,
913
+ "grad_norm": 0.19951429963111877,
914
+ "learning_rate": 1.2536043909088191e-06,
915
+ "loss": 0.0439,
916
+ "step": 117
917
+ },
918
+ {
919
+ "epoch": 4.661728395061728,
920
+ "grad_norm": 0.19163917005062103,
921
+ "learning_rate": 9.607359798384785e-07,
922
+ "loss": 0.0506,
923
+ "step": 118
924
+ },
925
+ {
926
+ "epoch": 4.701234567901235,
927
+ "grad_norm": 0.18294872343540192,
928
+ "learning_rate": 7.064490740882057e-07,
929
+ "loss": 0.0428,
930
+ "step": 119
931
+ },
932
+ {
933
+ "epoch": 4.7407407407407405,
934
+ "grad_norm": 0.21816276013851166,
935
+ "learning_rate": 4.909437331777179e-07,
936
+ "loss": 0.0521,
937
+ "step": 120
938
+ },
939
+ {
940
+ "epoch": 4.7407407407407405,
941
+ "eval_loss": 0.0528191402554512,
942
+ "eval_runtime": 26.0107,
943
+ "eval_samples_per_second": 1.73,
944
+ "eval_steps_per_second": 1.73,
945
+ "step": 120
946
+ },
947
+ {
948
+ "epoch": 4.780246913580247,
949
+ "grad_norm": 0.1912989616394043,
950
+ "learning_rate": 3.143895053378698e-07,
951
+ "loss": 0.0453,
952
+ "step": 121
953
+ },
954
+ {
955
+ "epoch": 4.8197530864197535,
956
+ "grad_norm": 0.1969219148159027,
957
+ "learning_rate": 1.7692529411904578e-07,
958
+ "loss": 0.0485,
959
+ "step": 122
960
+ },
961
+ {
962
+ "epoch": 4.859259259259259,
963
+ "grad_norm": 0.2046165019273758,
964
+ "learning_rate": 7.865924910916977e-08,
965
+ "loss": 0.0533,
966
+ "step": 123
967
+ },
968
+ {
969
+ "epoch": 4.898765432098766,
970
+ "grad_norm": 0.20170378684997559,
971
+ "learning_rate": 1.9668680847356735e-08,
972
+ "loss": 0.0466,
973
+ "step": 124
974
+ },
975
+ {
976
+ "epoch": 4.938271604938271,
977
+ "grad_norm": 0.15134376287460327,
978
+ "learning_rate": 0.0,
979
+ "loss": 0.0407,
980
+ "step": 125
981
+ },
982
+ {
983
+ "epoch": 4.938271604938271,
984
+ "step": 125,
985
+ "total_flos": 1.69590230591275e+17,
986
+ "train_loss": 0.10049069952964783,
987
+ "train_runtime": 4885.3949,
988
+ "train_samples_per_second": 0.415,
989
+ "train_steps_per_second": 0.026
990
+ }
991
+ ],
992
+ "logging_steps": 1,
993
+ "max_steps": 125,
994
+ "num_input_tokens_seen": 0,
995
+ "num_train_epochs": 5,
996
+ "save_steps": 10,
997
+ "stateful_callbacks": {
998
+ "TrainerControl": {
999
+ "args": {
1000
+ "should_epoch_stop": false,
1001
+ "should_evaluate": false,
1002
+ "should_log": false,
1003
+ "should_save": true,
1004
+ "should_training_stop": true
1005
+ },
1006
+ "attributes": {}
1007
+ }
1008
+ },
1009
+ "total_flos": 1.69590230591275e+17,
1010
+ "train_batch_size": 1,
1011
+ "trial_name": null,
1012
+ "trial_params": null
1013
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca1873310d4eba1fab9c87470c0d536429a8df5ae808938c6667165bbc0726c
3
+ size 5624
chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6/training_eval_loss.png ADDED
chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-info-fold6/training_loss.png ADDED