jjee2 commited on
Commit
8912029
·
verified ·
1 Parent(s): 458e1a6

Add chchen__Llama-3.1-8B-Instruct-PsyCourse-fold4

Browse files
.gitattributes CHANGED
@@ -74,3 +74,4 @@ trangtrannnnn__eb1213c7-2934-4716-b84c-594b67e3332f/tokenizer.json filter=lfs di
74
  nblinh__d2ca1958-28e8-4e7b-adf9-96cc6be102eb/tokenizer.json filter=lfs diff=lfs merge=lfs -text
75
  chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-fold6/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
  datlaaaaaaa__19add709-458f-469d-87f6-ae780d2125a0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
74
  nblinh__d2ca1958-28e8-4e7b-adf9-96cc6be102eb/tokenizer.json filter=lfs diff=lfs merge=lfs -text
75
  chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-fold6/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
  datlaaaaaaa__19add709-458f-469d-87f6-ae780d2125a0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
77
+ chchen__Llama-3.1-8B-Instruct-PsyCourse-fold4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold4/.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-fold4/README.md ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-fold4
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-fold4
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-train-fold4 dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.0344
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
+ | 0.5681 | 0.0763 | 50 | 0.3814 |
56
+ | 0.122 | 0.1527 | 100 | 0.0796 |
57
+ | 0.0541 | 0.2290 | 150 | 0.0592 |
58
+ | 0.0502 | 0.3053 | 200 | 0.0522 |
59
+ | 0.0666 | 0.3816 | 250 | 0.0539 |
60
+ | 0.046 | 0.4580 | 300 | 0.0493 |
61
+ | 0.0458 | 0.5343 | 350 | 0.0527 |
62
+ | 0.0448 | 0.6106 | 400 | 0.0488 |
63
+ | 0.0567 | 0.6870 | 450 | 0.0462 |
64
+ | 0.0358 | 0.7633 | 500 | 0.0410 |
65
+ | 0.0445 | 0.8396 | 550 | 0.0407 |
66
+ | 0.0462 | 0.9159 | 600 | 0.0407 |
67
+ | 0.0363 | 0.9923 | 650 | 0.0410 |
68
+ | 0.0343 | 1.0686 | 700 | 0.0370 |
69
+ | 0.0413 | 1.1449 | 750 | 0.0378 |
70
+ | 0.0322 | 1.2213 | 800 | 0.0398 |
71
+ | 0.0342 | 1.2976 | 850 | 0.0385 |
72
+ | 0.0337 | 1.3739 | 900 | 0.0436 |
73
+ | 0.0295 | 1.4502 | 950 | 0.0373 |
74
+ | 0.0267 | 1.5266 | 1000 | 0.0386 |
75
+ | 0.0287 | 1.6029 | 1050 | 0.0380 |
76
+ | 0.0504 | 1.6792 | 1100 | 0.0388 |
77
+ | 0.0317 | 1.7556 | 1150 | 0.0391 |
78
+ | 0.0448 | 1.8319 | 1200 | 0.0366 |
79
+ | 0.0278 | 1.9082 | 1250 | 0.0362 |
80
+ | 0.0347 | 1.9845 | 1300 | 0.0344 |
81
+ | 0.0201 | 2.0609 | 1350 | 0.0355 |
82
+ | 0.0238 | 2.1372 | 1400 | 0.0357 |
83
+ | 0.0299 | 2.2135 | 1450 | 0.0371 |
84
+ | 0.0155 | 2.2899 | 1500 | 0.0384 |
85
+ | 0.0157 | 2.3662 | 1550 | 0.0391 |
86
+ | 0.0222 | 2.4425 | 1600 | 0.0370 |
87
+ | 0.0245 | 2.5188 | 1650 | 0.0360 |
88
+ | 0.0206 | 2.5952 | 1700 | 0.0376 |
89
+ | 0.0198 | 2.6715 | 1750 | 0.0363 |
90
+ | 0.0209 | 2.7478 | 1800 | 0.0370 |
91
+ | 0.026 | 2.8242 | 1850 | 0.0362 |
92
+ | 0.0197 | 2.9005 | 1900 | 0.0358 |
93
+ | 0.0291 | 2.9768 | 1950 | 0.0355 |
94
+ | 0.0091 | 3.0531 | 2000 | 0.0416 |
95
+ | 0.0132 | 3.1295 | 2050 | 0.0421 |
96
+ | 0.0115 | 3.2058 | 2100 | 0.0443 |
97
+ | 0.0131 | 3.2821 | 2150 | 0.0459 |
98
+ | 0.0132 | 3.3585 | 2200 | 0.0409 |
99
+ | 0.0077 | 3.4348 | 2250 | 0.0445 |
100
+ | 0.0156 | 3.5111 | 2300 | 0.0444 |
101
+ | 0.0125 | 3.5874 | 2350 | 0.0480 |
102
+ | 0.0089 | 3.6638 | 2400 | 0.0499 |
103
+ | 0.0125 | 3.7401 | 2450 | 0.0467 |
104
+ | 0.0115 | 3.8164 | 2500 | 0.0447 |
105
+ | 0.0062 | 3.8928 | 2550 | 0.0449 |
106
+ | 0.0112 | 3.9691 | 2600 | 0.0462 |
107
+ | 0.005 | 4.0454 | 2650 | 0.0465 |
108
+ | 0.0065 | 4.1217 | 2700 | 0.0502 |
109
+ | 0.0021 | 4.1981 | 2750 | 0.0543 |
110
+ | 0.0033 | 4.2744 | 2800 | 0.0556 |
111
+ | 0.0068 | 4.3507 | 2850 | 0.0572 |
112
+ | 0.0015 | 4.4271 | 2900 | 0.0599 |
113
+ | 0.0036 | 4.5034 | 2950 | 0.0602 |
114
+ | 0.0027 | 4.5797 | 3000 | 0.0615 |
115
+ | 0.0013 | 4.6560 | 3050 | 0.0615 |
116
+ | 0.0056 | 4.7324 | 3100 | 0.0618 |
117
+ | 0.0028 | 4.8087 | 3150 | 0.0618 |
118
+ | 0.0044 | 4.8850 | 3200 | 0.0620 |
119
+ | 0.0061 | 4.9614 | 3250 | 0.0622 |
120
+
121
+
122
+ ### Framework versions
123
+
124
+ - PEFT 0.12.0
125
+ - Transformers 4.46.1
126
+ - Pytorch 2.5.1+cu124
127
+ - Datasets 3.1.0
128
+ - Tokenizers 0.20.3
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold4/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
+ "up_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "gate_proj",
27
+ "q_proj",
28
+ "down_proj",
29
+ "k_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold4/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67e0e2fde6615cf54e629ab0899c6d35da63b9351774dd522e95b2dacd0c21e4
3
+ size 83945296
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold4/all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.999522946283752,
3
+ "eval_loss": 0.03436192870140076,
4
+ "eval_runtime": 157.8575,
5
+ "eval_samples_per_second": 7.38,
6
+ "eval_steps_per_second": 7.38,
7
+ "total_flos": 8.22077121848279e+17,
8
+ "train_loss": 0.04503766617872788,
9
+ "train_runtime": 36493.551,
10
+ "train_samples_per_second": 1.436,
11
+ "train_steps_per_second": 0.09
12
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold4/eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.999522946283752,
3
+ "eval_loss": 0.03436192870140076,
4
+ "eval_runtime": 157.8575,
5
+ "eval_samples_per_second": 7.38,
6
+ "eval_steps_per_second": 7.38
7
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold4/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-train-fold4
13
+ dataset_dir: data_private
14
+ template: llama3
15
+ cutoff_len: 1024
16
+ # max_samples: 1000
17
+ overwrite_cache: true
18
+ preprocessing_num_workers: 16
19
+
20
+ ### output
21
+ output_dir: saves/psy-course/Llama-3.1-8B-Instruct/train/fold4
22
+ logging_steps: 10
23
+ save_steps: 50
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-fold4
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: 50
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold4/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-fold4/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-fold4/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-fold4/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.999522946283752,
3
+ "total_flos": 8.22077121848279e+17,
4
+ "train_loss": 0.04503766617872788,
5
+ "train_runtime": 36493.551,
6
+ "train_samples_per_second": 1.436,
7
+ "train_steps_per_second": 0.09
8
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold4/trainer_log.jsonl ADDED
@@ -0,0 +1,393 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 3275, "loss": 1.6278, "lr": 3.0487804878048782e-06, "epoch": 0.015265718919950386, "percentage": 0.31, "elapsed_time": "0:01:18", "remaining_time": "7:07:16"}
2
+ {"current_steps": 20, "total_steps": 3275, "loss": 1.5554, "lr": 6.0975609756097564e-06, "epoch": 0.030531437839900772, "percentage": 0.61, "elapsed_time": "0:02:35", "remaining_time": "7:02:28"}
3
+ {"current_steps": 30, "total_steps": 3275, "loss": 1.3738, "lr": 9.146341463414634e-06, "epoch": 0.04579715675985116, "percentage": 0.92, "elapsed_time": "0:03:52", "remaining_time": "6:59:48"}
4
+ {"current_steps": 40, "total_steps": 3275, "loss": 1.0174, "lr": 1.2195121951219513e-05, "epoch": 0.061062875679801544, "percentage": 1.22, "elapsed_time": "0:05:10", "remaining_time": "6:58:07"}
5
+ {"current_steps": 50, "total_steps": 3275, "loss": 0.5681, "lr": 1.524390243902439e-05, "epoch": 0.07632859459975193, "percentage": 1.53, "elapsed_time": "0:06:27", "remaining_time": "6:56:54"}
6
+ {"current_steps": 50, "total_steps": 3275, "eval_loss": 0.3813890814781189, "epoch": 0.07632859459975193, "percentage": 1.53, "elapsed_time": "0:09:06", "remaining_time": "9:47:41"}
7
+ {"current_steps": 60, "total_steps": 3275, "loss": 0.3362, "lr": 1.8292682926829268e-05, "epoch": 0.09159431351970232, "percentage": 1.83, "elapsed_time": "0:10:29", "remaining_time": "9:22:25"}
8
+ {"current_steps": 70, "total_steps": 3275, "loss": 0.246, "lr": 2.134146341463415e-05, "epoch": 0.10686003243965271, "percentage": 2.14, "elapsed_time": "0:11:47", "remaining_time": "8:59:42"}
9
+ {"current_steps": 80, "total_steps": 3275, "loss": 0.1841, "lr": 2.4390243902439026e-05, "epoch": 0.12212575135960309, "percentage": 2.44, "elapsed_time": "0:13:04", "remaining_time": "8:41:57"}
10
+ {"current_steps": 90, "total_steps": 3275, "loss": 0.115, "lr": 2.7439024390243906e-05, "epoch": 0.13739147027955348, "percentage": 2.75, "elapsed_time": "0:14:21", "remaining_time": "8:27:53"}
11
+ {"current_steps": 100, "total_steps": 3275, "loss": 0.122, "lr": 3.048780487804878e-05, "epoch": 0.15265718919950386, "percentage": 3.05, "elapsed_time": "0:15:38", "remaining_time": "8:16:44"}
12
+ {"current_steps": 100, "total_steps": 3275, "eval_loss": 0.07960689812898636, "epoch": 0.15265718919950386, "percentage": 3.05, "elapsed_time": "0:18:17", "remaining_time": "9:40:42"}
13
+ {"current_steps": 110, "total_steps": 3275, "loss": 0.0802, "lr": 3.353658536585366e-05, "epoch": 0.16792290811945426, "percentage": 3.36, "elapsed_time": "0:19:38", "remaining_time": "9:25:03"}
14
+ {"current_steps": 120, "total_steps": 3275, "loss": 0.0705, "lr": 3.6585365853658535e-05, "epoch": 0.18318862703940464, "percentage": 3.66, "elapsed_time": "0:20:55", "remaining_time": "9:09:59"}
15
+ {"current_steps": 130, "total_steps": 3275, "loss": 0.08, "lr": 3.9634146341463416e-05, "epoch": 0.19845434595935502, "percentage": 3.97, "elapsed_time": "0:22:12", "remaining_time": "8:57:13"}
16
+ {"current_steps": 140, "total_steps": 3275, "loss": 0.0655, "lr": 4.26829268292683e-05, "epoch": 0.21372006487930542, "percentage": 4.27, "elapsed_time": "0:23:29", "remaining_time": "8:46:04"}
17
+ {"current_steps": 150, "total_steps": 3275, "loss": 0.0541, "lr": 4.573170731707318e-05, "epoch": 0.2289857837992558, "percentage": 4.58, "elapsed_time": "0:24:47", "remaining_time": "8:36:21"}
18
+ {"current_steps": 150, "total_steps": 3275, "eval_loss": 0.059219248592853546, "epoch": 0.2289857837992558, "percentage": 4.58, "elapsed_time": "0:27:25", "remaining_time": "9:31:26"}
19
+ {"current_steps": 160, "total_steps": 3275, "loss": 0.066, "lr": 4.878048780487805e-05, "epoch": 0.24425150271920618, "percentage": 4.89, "elapsed_time": "0:28:47", "remaining_time": "9:20:36"}
20
+ {"current_steps": 170, "total_steps": 3275, "loss": 0.0751, "lr": 5.182926829268293e-05, "epoch": 0.2595172216391566, "percentage": 5.19, "elapsed_time": "0:30:05", "remaining_time": "9:09:30"}
21
+ {"current_steps": 180, "total_steps": 3275, "loss": 0.0772, "lr": 5.487804878048781e-05, "epoch": 0.27478294055910696, "percentage": 5.5, "elapsed_time": "0:31:22", "remaining_time": "8:59:26"}
22
+ {"current_steps": 190, "total_steps": 3275, "loss": 0.0687, "lr": 5.792682926829268e-05, "epoch": 0.29004865947905734, "percentage": 5.8, "elapsed_time": "0:32:39", "remaining_time": "8:50:14"}
23
+ {"current_steps": 200, "total_steps": 3275, "loss": 0.0502, "lr": 6.097560975609756e-05, "epoch": 0.3053143783990077, "percentage": 6.11, "elapsed_time": "0:33:56", "remaining_time": "8:41:51"}
24
+ {"current_steps": 200, "total_steps": 3275, "eval_loss": 0.05221959203481674, "epoch": 0.3053143783990077, "percentage": 6.11, "elapsed_time": "0:36:35", "remaining_time": "9:22:30"}
25
+ {"current_steps": 210, "total_steps": 3275, "loss": 0.0572, "lr": 6.402439024390244e-05, "epoch": 0.3205800973189581, "percentage": 6.41, "elapsed_time": "0:37:56", "remaining_time": "9:13:51"}
26
+ {"current_steps": 220, "total_steps": 3275, "loss": 0.0493, "lr": 6.707317073170732e-05, "epoch": 0.3358458162389085, "percentage": 6.72, "elapsed_time": "0:39:14", "remaining_time": "9:04:51"}
27
+ {"current_steps": 230, "total_steps": 3275, "loss": 0.0421, "lr": 7.012195121951219e-05, "epoch": 0.3511115351588589, "percentage": 7.02, "elapsed_time": "0:40:31", "remaining_time": "8:56:27"}
28
+ {"current_steps": 240, "total_steps": 3275, "loss": 0.0603, "lr": 7.317073170731707e-05, "epoch": 0.3663772540788093, "percentage": 7.33, "elapsed_time": "0:41:48", "remaining_time": "8:48:39"}
29
+ {"current_steps": 250, "total_steps": 3275, "loss": 0.0666, "lr": 7.621951219512195e-05, "epoch": 0.38164297299875966, "percentage": 7.63, "elapsed_time": "0:43:05", "remaining_time": "8:41:23"}
30
+ {"current_steps": 250, "total_steps": 3275, "eval_loss": 0.05392138659954071, "epoch": 0.38164297299875966, "percentage": 7.63, "elapsed_time": "0:45:44", "remaining_time": "9:13:22"}
31
+ {"current_steps": 260, "total_steps": 3275, "loss": 0.0653, "lr": 7.926829268292683e-05, "epoch": 0.39690869191871003, "percentage": 7.94, "elapsed_time": "0:47:05", "remaining_time": "9:06:07"}
32
+ {"current_steps": 270, "total_steps": 3275, "loss": 0.0563, "lr": 8.231707317073171e-05, "epoch": 0.4121744108386604, "percentage": 8.24, "elapsed_time": "0:48:22", "remaining_time": "8:58:25"}
33
+ {"current_steps": 280, "total_steps": 3275, "loss": 0.0576, "lr": 8.53658536585366e-05, "epoch": 0.42744012975861084, "percentage": 8.55, "elapsed_time": "0:49:39", "remaining_time": "8:51:14"}
34
+ {"current_steps": 290, "total_steps": 3275, "loss": 0.0602, "lr": 8.841463414634147e-05, "epoch": 0.4427058486785612, "percentage": 8.85, "elapsed_time": "0:50:56", "remaining_time": "8:44:23"}
35
+ {"current_steps": 300, "total_steps": 3275, "loss": 0.046, "lr": 9.146341463414635e-05, "epoch": 0.4579715675985116, "percentage": 9.16, "elapsed_time": "0:52:14", "remaining_time": "8:38:00"}
36
+ {"current_steps": 300, "total_steps": 3275, "eval_loss": 0.049273185431957245, "epoch": 0.4579715675985116, "percentage": 9.16, "elapsed_time": "0:54:52", "remaining_time": "9:04:11"}
37
+ {"current_steps": 310, "total_steps": 3275, "loss": 0.0649, "lr": 9.451219512195122e-05, "epoch": 0.473237286518462, "percentage": 9.47, "elapsed_time": "0:56:14", "remaining_time": "8:57:59"}
38
+ {"current_steps": 320, "total_steps": 3275, "loss": 0.0436, "lr": 9.75609756097561e-05, "epoch": 0.48850300543841235, "percentage": 9.77, "elapsed_time": "0:57:31", "remaining_time": "8:51:16"}
39
+ {"current_steps": 330, "total_steps": 3275, "loss": 0.0507, "lr": 9.999988635788465e-05, "epoch": 0.5037687243583627, "percentage": 10.08, "elapsed_time": "0:58:48", "remaining_time": "8:44:53"}
40
+ {"current_steps": 340, "total_steps": 3275, "loss": 0.0449, "lr": 9.999590893808788e-05, "epoch": 0.5190344432783132, "percentage": 10.38, "elapsed_time": "1:00:06", "remaining_time": "8:38:50"}
41
+ {"current_steps": 350, "total_steps": 3275, "loss": 0.0458, "lr": 9.998624992909386e-05, "epoch": 0.5343001621982635, "percentage": 10.69, "elapsed_time": "1:01:23", "remaining_time": "8:33:02"}
42
+ {"current_steps": 350, "total_steps": 3275, "eval_loss": 0.05271424353122711, "epoch": 0.5343001621982635, "percentage": 10.69, "elapsed_time": "1:04:01", "remaining_time": "8:55:06"}
43
+ {"current_steps": 360, "total_steps": 3275, "loss": 0.0488, "lr": 9.997091042856284e-05, "epoch": 0.5495658811182139, "percentage": 10.99, "elapsed_time": "1:05:22", "remaining_time": "8:49:23"}
44
+ {"current_steps": 370, "total_steps": 3275, "loss": 0.0646, "lr": 9.994989217969224e-05, "epoch": 0.5648316000381643, "percentage": 11.3, "elapsed_time": "1:06:39", "remaining_time": "8:43:21"}
45
+ {"current_steps": 380, "total_steps": 3275, "loss": 0.0588, "lr": 9.992319757101863e-05, "epoch": 0.5800973189581147, "percentage": 11.6, "elapsed_time": "1:07:56", "remaining_time": "8:37:34"}
46
+ {"current_steps": 390, "total_steps": 3275, "loss": 0.0586, "lr": 9.98908296361462e-05, "epoch": 0.5953630378780651, "percentage": 11.91, "elapsed_time": "1:09:12", "remaining_time": "8:32:01"}
47
+ {"current_steps": 400, "total_steps": 3275, "loss": 0.0448, "lr": 9.98527920534021e-05, "epoch": 0.6106287567980154, "percentage": 12.21, "elapsed_time": "1:10:29", "remaining_time": "8:26:41"}
48
+ {"current_steps": 400, "total_steps": 3275, "eval_loss": 0.048783060163259506, "epoch": 0.6106287567980154, "percentage": 12.21, "elapsed_time": "1:13:07", "remaining_time": "8:45:35"}
49
+ {"current_steps": 410, "total_steps": 3275, "loss": 0.054, "lr": 9.980908914541844e-05, "epoch": 0.6258944757179659, "percentage": 12.52, "elapsed_time": "1:14:29", "remaining_time": "8:40:28"}
50
+ {"current_steps": 420, "total_steps": 3275, "loss": 0.0506, "lr": 9.975972587864095e-05, "epoch": 0.6411601946379162, "percentage": 12.82, "elapsed_time": "1:15:46", "remaining_time": "8:35:02"}
51
+ {"current_steps": 430, "total_steps": 3275, "loss": 0.0369, "lr": 9.970470786276467e-05, "epoch": 0.6564259135578666, "percentage": 13.13, "elapsed_time": "1:17:03", "remaining_time": "8:29:47"}
52
+ {"current_steps": 440, "total_steps": 3275, "loss": 0.0527, "lr": 9.964404135009648e-05, "epoch": 0.671691632477817, "percentage": 13.44, "elapsed_time": "1:18:20", "remaining_time": "8:24:43"}
53
+ {"current_steps": 450, "total_steps": 3275, "loss": 0.0567, "lr": 9.957773323484454e-05, "epoch": 0.6869573513977674, "percentage": 13.74, "elapsed_time": "1:19:36", "remaining_time": "8:19:47"}
54
+ {"current_steps": 450, "total_steps": 3275, "eval_loss": 0.04618264362215996, "epoch": 0.6869573513977674, "percentage": 13.74, "elapsed_time": "1:22:14", "remaining_time": "8:36:17"}
55
+ {"current_steps": 460, "total_steps": 3275, "loss": 0.04, "lr": 9.950579105233483e-05, "epoch": 0.7022230703177178, "percentage": 14.05, "elapsed_time": "1:23:36", "remaining_time": "8:31:36"}
56
+ {"current_steps": 470, "total_steps": 3275, "loss": 0.0383, "lr": 9.94282229781548e-05, "epoch": 0.7174887892376681, "percentage": 14.35, "elapsed_time": "1:24:52", "remaining_time": "8:26:34"}
57
+ {"current_steps": 480, "total_steps": 3275, "loss": 0.0495, "lr": 9.934503782722438e-05, "epoch": 0.7327545081576186, "percentage": 14.66, "elapsed_time": "1:26:09", "remaining_time": "8:21:39"}
58
+ {"current_steps": 490, "total_steps": 3275, "loss": 0.0379, "lr": 9.925624505279411e-05, "epoch": 0.748020227077569, "percentage": 14.96, "elapsed_time": "1:27:25", "remaining_time": "8:16:56"}
59
+ {"current_steps": 500, "total_steps": 3275, "loss": 0.0358, "lr": 9.916185474537098e-05, "epoch": 0.7632859459975193, "percentage": 15.27, "elapsed_time": "1:28:42", "remaining_time": "8:12:22"}
60
+ {"current_steps": 500, "total_steps": 3275, "eval_loss": 0.04097205400466919, "epoch": 0.7632859459975193, "percentage": 15.27, "elapsed_time": "1:31:20", "remaining_time": "8:26:56"}
61
+ {"current_steps": 510, "total_steps": 3275, "loss": 0.0508, "lr": 9.906187763157168e-05, "epoch": 0.7785516649174697, "percentage": 15.57, "elapsed_time": "1:32:41", "remaining_time": "8:22:33"}
62
+ {"current_steps": 520, "total_steps": 3275, "loss": 0.05, "lr": 9.895632507290362e-05, "epoch": 0.7938173838374201, "percentage": 15.88, "elapsed_time": "1:33:58", "remaining_time": "8:17:54"}
63
+ {"current_steps": 530, "total_steps": 3275, "loss": 0.0376, "lr": 9.884520906447379e-05, "epoch": 0.8090831027573705, "percentage": 16.18, "elapsed_time": "1:35:15", "remaining_time": "8:13:20"}
64
+ {"current_steps": 540, "total_steps": 3275, "loss": 0.0482, "lr": 9.872854223362562e-05, "epoch": 0.8243488216773208, "percentage": 16.49, "elapsed_time": "1:36:31", "remaining_time": "8:08:54"}
65
+ {"current_steps": 550, "total_steps": 3275, "loss": 0.0445, "lr": 9.860633783850406e-05, "epoch": 0.8396145405972713, "percentage": 16.79, "elapsed_time": "1:37:48", "remaining_time": "8:04:36"}
66
+ {"current_steps": 550, "total_steps": 3275, "eval_loss": 0.04072929546236992, "epoch": 0.8396145405972713, "percentage": 16.79, "elapsed_time": "1:40:26", "remaining_time": "8:17:36"}
67
+ {"current_steps": 560, "total_steps": 3275, "loss": 0.0501, "lr": 9.847860976654879e-05, "epoch": 0.8548802595172217, "percentage": 17.1, "elapsed_time": "1:41:48", "remaining_time": "8:13:34"}
68
+ {"current_steps": 570, "total_steps": 3275, "loss": 0.0401, "lr": 9.834537253291616e-05, "epoch": 0.870145978437172, "percentage": 17.4, "elapsed_time": "1:43:05", "remaining_time": "8:09:12"}
69
+ {"current_steps": 580, "total_steps": 3275, "loss": 0.0582, "lr": 9.820664127882957e-05, "epoch": 0.8854116973571224, "percentage": 17.71, "elapsed_time": "1:44:21", "remaining_time": "8:04:55"}
70
+ {"current_steps": 590, "total_steps": 3275, "loss": 0.0494, "lr": 9.806243176985888e-05, "epoch": 0.9006774162770728, "percentage": 18.02, "elapsed_time": "1:45:38", "remaining_time": "8:00:44"}
71
+ {"current_steps": 600, "total_steps": 3275, "loss": 0.0462, "lr": 9.791276039412875e-05, "epoch": 0.9159431351970232, "percentage": 18.32, "elapsed_time": "1:46:55", "remaining_time": "7:56:41"}
72
+ {"current_steps": 600, "total_steps": 3275, "eval_loss": 0.040742386132478714, "epoch": 0.9159431351970232, "percentage": 18.32, "elapsed_time": "1:49:32", "remaining_time": "8:08:22"}
73
+ {"current_steps": 610, "total_steps": 3275, "loss": 0.0595, "lr": 9.775764416045628e-05, "epoch": 0.9312088541169735, "percentage": 18.63, "elapsed_time": "1:50:53", "remaining_time": "8:04:29"}
74
+ {"current_steps": 620, "total_steps": 3275, "loss": 0.0463, "lr": 9.759710069641814e-05, "epoch": 0.946474573036924, "percentage": 18.93, "elapsed_time": "1:52:10", "remaining_time": "8:00:22"}
75
+ {"current_steps": 630, "total_steps": 3275, "loss": 0.033, "lr": 9.743114824634734e-05, "epoch": 0.9617402919568744, "percentage": 19.24, "elapsed_time": "1:53:27", "remaining_time": "7:56:21"}
76
+ {"current_steps": 640, "total_steps": 3275, "loss": 0.0497, "lr": 9.725980566925989e-05, "epoch": 0.9770060108768247, "percentage": 19.54, "elapsed_time": "1:54:44", "remaining_time": "7:52:23"}
77
+ {"current_steps": 650, "total_steps": 3275, "loss": 0.0363, "lr": 9.708309243671165e-05, "epoch": 0.9922717297967751, "percentage": 19.85, "elapsed_time": "1:56:00", "remaining_time": "7:48:31"}
78
+ {"current_steps": 650, "total_steps": 3275, "eval_loss": 0.040968675166368484, "epoch": 0.9922717297967751, "percentage": 19.85, "elapsed_time": "1:58:38", "remaining_time": "7:59:07"}
79
+ {"current_steps": 660, "total_steps": 3275, "loss": 0.0343, "lr": 9.690102863058563e-05, "epoch": 1.0075374487167255, "percentage": 20.15, "elapsed_time": "1:59:59", "remaining_time": "7:55:26"}
80
+ {"current_steps": 670, "total_steps": 3275, "loss": 0.0333, "lr": 9.67136349408098e-05, "epoch": 1.0228031676366758, "percentage": 20.46, "elapsed_time": "2:01:16", "remaining_time": "7:51:31"}
81
+ {"current_steps": 680, "total_steps": 3275, "loss": 0.0401, "lr": 9.652093266300583e-05, "epoch": 1.0380688865566263, "percentage": 20.76, "elapsed_time": "2:02:33", "remaining_time": "7:47:41"}
82
+ {"current_steps": 690, "total_steps": 3275, "loss": 0.0271, "lr": 9.632294369606916e-05, "epoch": 1.0533346054765766, "percentage": 21.07, "elapsed_time": "2:03:49", "remaining_time": "7:43:55"}
83
+ {"current_steps": 700, "total_steps": 3275, "loss": 0.0343, "lr": 9.61196905396802e-05, "epoch": 1.068600324396527, "percentage": 21.37, "elapsed_time": "2:05:06", "remaining_time": "7:40:14"}
84
+ {"current_steps": 700, "total_steps": 3275, "eval_loss": 0.03695390745997429, "epoch": 1.068600324396527, "percentage": 21.37, "elapsed_time": "2:07:44", "remaining_time": "7:49:53"}
85
+ {"current_steps": 710, "total_steps": 3275, "loss": 0.0442, "lr": 9.591119629174764e-05, "epoch": 1.0838660433164775, "percentage": 21.68, "elapsed_time": "2:09:06", "remaining_time": "7:46:24"}
86
+ {"current_steps": 720, "total_steps": 3275, "loss": 0.0288, "lr": 9.569748464578343e-05, "epoch": 1.0991317622364278, "percentage": 21.98, "elapsed_time": "2:10:22", "remaining_time": "7:42:39"}
87
+ {"current_steps": 730, "total_steps": 3275, "loss": 0.0273, "lr": 9.54785798882103e-05, "epoch": 1.1143974811563782, "percentage": 22.29, "elapsed_time": "2:11:39", "remaining_time": "7:38:59"}
88
+ {"current_steps": 740, "total_steps": 3275, "loss": 0.0378, "lr": 9.525450689560181e-05, "epoch": 1.1296632000763287, "percentage": 22.6, "elapsed_time": "2:12:56", "remaining_time": "7:35:23"}
89
+ {"current_steps": 750, "total_steps": 3275, "loss": 0.0413, "lr": 9.502529113185532e-05, "epoch": 1.144928918996279, "percentage": 22.9, "elapsed_time": "2:14:12", "remaining_time": "7:31:51"}
90
+ {"current_steps": 750, "total_steps": 3275, "eval_loss": 0.03775772452354431, "epoch": 1.144928918996279, "percentage": 22.9, "elapsed_time": "2:16:50", "remaining_time": "7:40:41"}
91
+ {"current_steps": 760, "total_steps": 3275, "loss": 0.0308, "lr": 9.479095864529828e-05, "epoch": 1.1601946379162293, "percentage": 23.21, "elapsed_time": "2:18:12", "remaining_time": "7:37:21"}
92
+ {"current_steps": 770, "total_steps": 3275, "loss": 0.0316, "lr": 9.455153606572806e-05, "epoch": 1.1754603568361797, "percentage": 23.51, "elapsed_time": "2:19:29", "remaining_time": "7:33:47"}
93
+ {"current_steps": 780, "total_steps": 3275, "loss": 0.0348, "lr": 9.430705060138569e-05, "epoch": 1.1907260757561302, "percentage": 23.82, "elapsed_time": "2:20:45", "remaining_time": "7:30:15"}
94
+ {"current_steps": 790, "total_steps": 3275, "loss": 0.0277, "lr": 9.405753003586395e-05, "epoch": 1.2059917946760805, "percentage": 24.12, "elapsed_time": "2:22:02", "remaining_time": "7:26:49"}
95
+ {"current_steps": 800, "total_steps": 3275, "loss": 0.0322, "lr": 9.38030027249499e-05, "epoch": 1.2212575135960309, "percentage": 24.43, "elapsed_time": "2:23:20", "remaining_time": "7:23:26"}
96
+ {"current_steps": 800, "total_steps": 3275, "eval_loss": 0.03979082778096199, "epoch": 1.2212575135960309, "percentage": 24.43, "elapsed_time": "2:25:57", "remaining_time": "7:31:33"}
97
+ {"current_steps": 810, "total_steps": 3275, "loss": 0.0372, "lr": 9.354349759340263e-05, "epoch": 1.2365232325159814, "percentage": 24.73, "elapsed_time": "2:27:19", "remaining_time": "7:28:21"}
98
+ {"current_steps": 820, "total_steps": 3275, "loss": 0.0338, "lr": 9.327904413166615e-05, "epoch": 1.2517889514359317, "percentage": 25.04, "elapsed_time": "2:28:36", "remaining_time": "7:24:55"}
99
+ {"current_steps": 830, "total_steps": 3275, "loss": 0.0405, "lr": 9.300967239251798e-05, "epoch": 1.267054670355882, "percentage": 25.34, "elapsed_time": "2:29:53", "remaining_time": "7:21:32"}
100
+ {"current_steps": 840, "total_steps": 3275, "loss": 0.0348, "lr": 9.27354129876541e-05, "epoch": 1.2823203892758324, "percentage": 25.65, "elapsed_time": "2:31:10", "remaining_time": "7:18:13"}
101
+ {"current_steps": 850, "total_steps": 3275, "loss": 0.0342, "lr": 9.245629708421008e-05, "epoch": 1.297586108195783, "percentage": 25.95, "elapsed_time": "2:32:27", "remaining_time": "7:14:56"}
102
+ {"current_steps": 850, "total_steps": 3275, "eval_loss": 0.03846587613224983, "epoch": 1.297586108195783, "percentage": 25.95, "elapsed_time": "2:35:04", "remaining_time": "7:22:26"}
103
+ {"current_steps": 860, "total_steps": 3275, "loss": 0.0379, "lr": 9.217235640121926e-05, "epoch": 1.3128518271157332, "percentage": 26.26, "elapsed_time": "2:36:27", "remaining_time": "7:19:20"}
104
+ {"current_steps": 870, "total_steps": 3275, "loss": 0.0425, "lr": 9.188362320600812e-05, "epoch": 1.3281175460356835, "percentage": 26.56, "elapsed_time": "2:37:44", "remaining_time": "7:16:02"}
105
+ {"current_steps": 880, "total_steps": 3275, "loss": 0.0324, "lr": 9.159013031052943e-05, "epoch": 1.343383264955634, "percentage": 26.87, "elapsed_time": "2:39:01", "remaining_time": "7:12:47"}
106
+ {"current_steps": 890, "total_steps": 3275, "loss": 0.0342, "lr": 9.129191106763346e-05, "epoch": 1.3586489838755844, "percentage": 27.18, "elapsed_time": "2:40:18", "remaining_time": "7:09:34"}
107
+ {"current_steps": 900, "total_steps": 3275, "loss": 0.0337, "lr": 9.098899936727771e-05, "epoch": 1.3739147027955347, "percentage": 27.48, "elapsed_time": "2:41:34", "remaining_time": "7:06:23"}
108
+ {"current_steps": 900, "total_steps": 3275, "eval_loss": 0.043599650263786316, "epoch": 1.3739147027955347, "percentage": 27.48, "elapsed_time": "2:44:12", "remaining_time": "7:13:19"}
109
+ {"current_steps": 910, "total_steps": 3275, "loss": 0.029, "lr": 9.068142963267558e-05, "epoch": 1.3891804217154853, "percentage": 27.79, "elapsed_time": "2:45:34", "remaining_time": "7:10:17"}
110
+ {"current_steps": 920, "total_steps": 3275, "loss": 0.0337, "lr": 9.036923681638463e-05, "epoch": 1.4044461406354356, "percentage": 28.09, "elapsed_time": "2:46:50", "remaining_time": "7:07:05"}
111
+ {"current_steps": 930, "total_steps": 3275, "loss": 0.0269, "lr": 9.00524563963343e-05, "epoch": 1.419711859555386, "percentage": 28.4, "elapsed_time": "2:48:07", "remaining_time": "7:03:56"}
112
+ {"current_steps": 940, "total_steps": 3275, "loss": 0.0372, "lr": 8.973112437179436e-05, "epoch": 1.4349775784753362, "percentage": 28.7, "elapsed_time": "2:49:25", "remaining_time": "7:00:50"}
113
+ {"current_steps": 950, "total_steps": 3275, "loss": 0.0295, "lr": 8.940527725928383e-05, "epoch": 1.4502432973952868, "percentage": 29.01, "elapsed_time": "2:50:42", "remaining_time": "6:57:46"}
114
+ {"current_steps": 950, "total_steps": 3275, "eval_loss": 0.037314947694540024, "epoch": 1.4502432973952868, "percentage": 29.01, "elapsed_time": "2:53:19", "remaining_time": "7:04:12"}
115
+ {"current_steps": 960, "total_steps": 3275, "loss": 0.0324, "lr": 8.90749520884212e-05, "epoch": 1.4655090163152371, "percentage": 29.31, "elapsed_time": "2:54:41", "remaining_time": "7:01:15"}
116
+ {"current_steps": 970, "total_steps": 3275, "loss": 0.0357, "lr": 8.874018639771637e-05, "epoch": 1.4807747352351874, "percentage": 29.62, "elapsed_time": "2:55:58", "remaining_time": "6:58:09"}
117
+ {"current_steps": 980, "total_steps": 3275, "loss": 0.0276, "lr": 8.840101823030471e-05, "epoch": 1.4960404541551378, "percentage": 29.92, "elapsed_time": "2:57:15", "remaining_time": "6:55:06"}
118
+ {"current_steps": 990, "total_steps": 3275, "loss": 0.0381, "lr": 8.805748612962382e-05, "epoch": 1.5113061730750883, "percentage": 30.23, "elapsed_time": "2:58:32", "remaining_time": "6:52:04"}
119
+ {"current_steps": 1000, "total_steps": 3275, "loss": 0.0267, "lr": 8.77096291350334e-05, "epoch": 1.5265718919950386, "percentage": 30.53, "elapsed_time": "2:59:48", "remaining_time": "6:49:04"}
120
+ {"current_steps": 1000, "total_steps": 3275, "eval_loss": 0.03864908590912819, "epoch": 1.5265718919950386, "percentage": 30.53, "elapsed_time": "3:02:27", "remaining_time": "6:55:04"}
121
+ {"current_steps": 1010, "total_steps": 3275, "loss": 0.0346, "lr": 8.735748677737874e-05, "epoch": 1.541837610914989, "percentage": 30.84, "elapsed_time": "3:03:51", "remaining_time": "6:52:19"}
122
+ {"current_steps": 1020, "total_steps": 3275, "loss": 0.0296, "lr": 8.700109907449845e-05, "epoch": 1.5571033298349395, "percentage": 31.15, "elapsed_time": "3:05:13", "remaining_time": "6:49:29"}
123
+ {"current_steps": 1030, "total_steps": 3275, "loss": 0.0311, "lr": 8.66405065266768e-05, "epoch": 1.5723690487548898, "percentage": 31.45, "elapsed_time": "3:06:35", "remaining_time": "6:46:42"}
124
+ {"current_steps": 1040, "total_steps": 3275, "loss": 0.0281, "lr": 8.627575011204115e-05, "epoch": 1.5876347676748401, "percentage": 31.76, "elapsed_time": "3:07:58", "remaining_time": "6:43:58"}
125
+ {"current_steps": 1050, "total_steps": 3275, "loss": 0.0287, "lr": 8.590687128190516e-05, "epoch": 1.6029004865947907, "percentage": 32.06, "elapsed_time": "3:09:22", "remaining_time": "6:41:17"}
126
+ {"current_steps": 1050, "total_steps": 3275, "eval_loss": 0.03797018155455589, "epoch": 1.6029004865947907, "percentage": 32.06, "elapsed_time": "3:12:16", "remaining_time": "6:47:25"}
127
+ {"current_steps": 1060, "total_steps": 3275, "loss": 0.0273, "lr": 8.553391195605833e-05, "epoch": 1.618166205514741, "percentage": 32.37, "elapsed_time": "3:13:44", "remaining_time": "6:44:50"}
128
+ {"current_steps": 1070, "total_steps": 3275, "loss": 0.0469, "lr": 8.515691451800205e-05, "epoch": 1.6334319244346913, "percentage": 32.67, "elapsed_time": "3:15:08", "remaining_time": "6:42:07"}
129
+ {"current_steps": 1080, "total_steps": 3275, "loss": 0.0291, "lr": 8.477592181013316e-05, "epoch": 1.6486976433546419, "percentage": 32.98, "elapsed_time": "3:16:32", "remaining_time": "6:39:26"}
130
+ {"current_steps": 1090, "total_steps": 3275, "loss": 0.0297, "lr": 8.439097712887531e-05, "epoch": 1.663963362274592, "percentage": 33.28, "elapsed_time": "3:17:56", "remaining_time": "6:36:46"}
131
+ {"current_steps": 1100, "total_steps": 3275, "loss": 0.0504, "lr": 8.400212421975865e-05, "epoch": 1.6792290811945425, "percentage": 33.59, "elapsed_time": "3:19:20", "remaining_time": "6:34:08"}
132
+ {"current_steps": 1100, "total_steps": 3275, "eval_loss": 0.03881072625517845, "epoch": 1.6792290811945425, "percentage": 33.59, "elapsed_time": "3:22:15", "remaining_time": "6:39:55"}
133
+ {"current_steps": 1110, "total_steps": 3275, "loss": 0.0418, "lr": 8.360940727244859e-05, "epoch": 1.694494800114493, "percentage": 33.89, "elapsed_time": "3:23:42", "remaining_time": "6:37:20"}
134
+ {"current_steps": 1120, "total_steps": 3275, "loss": 0.0285, "lr": 8.321287091572403e-05, "epoch": 1.7097605190344431, "percentage": 34.2, "elapsed_time": "3:25:07", "remaining_time": "6:34:40"}
135
+ {"current_steps": 1130, "total_steps": 3275, "loss": 0.0299, "lr": 8.281256021240566e-05, "epoch": 1.7250262379543937, "percentage": 34.5, "elapsed_time": "3:26:31", "remaining_time": "6:32:02"}
136
+ {"current_steps": 1140, "total_steps": 3275, "loss": 0.0384, "lr": 8.240852065423506e-05, "epoch": 1.740291956874344, "percentage": 34.81, "elapsed_time": "3:27:56", "remaining_time": "6:29:25"}
137
+ {"current_steps": 1150, "total_steps": 3275, "loss": 0.0317, "lr": 8.20007981567048e-05, "epoch": 1.7555576757942943, "percentage": 35.11, "elapsed_time": "3:29:20", "remaining_time": "6:26:50"}
138
+ {"current_steps": 1150, "total_steps": 3275, "eval_loss": 0.03912714123725891, "epoch": 1.7555576757942943, "percentage": 35.11, "elapsed_time": "3:32:17", "remaining_time": "6:32:16"}
139
+ {"current_steps": 1160, "total_steps": 3275, "loss": 0.0384, "lr": 8.158943905384082e-05, "epoch": 1.7708233947142449, "percentage": 35.42, "elapsed_time": "3:33:45", "remaining_time": "6:29:44"}
140
+ {"current_steps": 1170, "total_steps": 3275, "loss": 0.0305, "lr": 8.117449009293668e-05, "epoch": 1.7860891136341952, "percentage": 35.73, "elapsed_time": "3:35:10", "remaining_time": "6:27:07"}
141
+ {"current_steps": 1180, "total_steps": 3275, "loss": 0.0306, "lr": 8.075599842924139e-05, "epoch": 1.8013548325541455, "percentage": 36.03, "elapsed_time": "3:36:34", "remaining_time": "6:24:30"}
142
+ {"current_steps": 1190, "total_steps": 3275, "loss": 0.0361, "lr": 8.033401162060049e-05, "epoch": 1.816620551474096, "percentage": 36.34, "elapsed_time": "3:37:59", "remaining_time": "6:21:56"}
143
+ {"current_steps": 1200, "total_steps": 3275, "loss": 0.0448, "lr": 7.990857762205157e-05, "epoch": 1.8318862703940464, "percentage": 36.64, "elapsed_time": "3:39:24", "remaining_time": "6:19:23"}
144
+ {"current_steps": 1200, "total_steps": 3275, "eval_loss": 0.03655826300382614, "epoch": 1.8318862703940464, "percentage": 36.64, "elapsed_time": "3:42:20", "remaining_time": "6:24:28"}
145
+ {"current_steps": 1210, "total_steps": 3275, "loss": 0.0378, "lr": 7.947974478037468e-05, "epoch": 1.8471519893139967, "percentage": 36.95, "elapsed_time": "3:43:50", "remaining_time": "6:22:00"}
146
+ {"current_steps": 1220, "total_steps": 3275, "loss": 0.0309, "lr": 7.904756182859797e-05, "epoch": 1.8624177082339473, "percentage": 37.25, "elapsed_time": "3:45:15", "remaining_time": "6:19:25"}
147
+ {"current_steps": 1230, "total_steps": 3275, "loss": 0.0318, "lr": 7.861207788045984e-05, "epoch": 1.8776834271538976, "percentage": 37.56, "elapsed_time": "3:46:39", "remaining_time": "6:16:51"}
148
+ {"current_steps": 1240, "total_steps": 3275, "loss": 0.0322, "lr": 7.817334242482738e-05, "epoch": 1.892949146073848, "percentage": 37.86, "elapsed_time": "3:48:04", "remaining_time": "6:14:18"}
149
+ {"current_steps": 1250, "total_steps": 3275, "loss": 0.0278, "lr": 7.773140532007262e-05, "epoch": 1.9082148649937984, "percentage": 38.17, "elapsed_time": "3:49:30", "remaining_time": "6:11:47"}
150
+ {"current_steps": 1250, "total_steps": 3275, "eval_loss": 0.036195144057273865, "epoch": 1.9082148649937984, "percentage": 38.17, "elapsed_time": "3:52:27", "remaining_time": "6:16:34"}
151
+ {"current_steps": 1260, "total_steps": 3275, "loss": 0.0294, "lr": 7.728631678840638e-05, "epoch": 1.9234805839137485, "percentage": 38.47, "elapsed_time": "3:53:56", "remaining_time": "6:14:06"}
152
+ {"current_steps": 1270, "total_steps": 3275, "loss": 0.0319, "lr": 7.683812741017112e-05, "epoch": 1.938746302833699, "percentage": 38.78, "elapsed_time": "3:55:21", "remaining_time": "6:11:33"}
153
+ {"current_steps": 1280, "total_steps": 3275, "loss": 0.0388, "lr": 7.638688811809274e-05, "epoch": 1.9540120217536494, "percentage": 39.08, "elapsed_time": "3:56:46", "remaining_time": "6:09:02"}
154
+ {"current_steps": 1290, "total_steps": 3275, "loss": 0.0267, "lr": 7.593265019149275e-05, "epoch": 1.9692777406735997, "percentage": 39.39, "elapsed_time": "3:58:09", "remaining_time": "6:06:28"}
155
+ {"current_steps": 1300, "total_steps": 3275, "loss": 0.0347, "lr": 7.547546525046073e-05, "epoch": 1.9845434595935503, "percentage": 39.69, "elapsed_time": "3:59:32", "remaining_time": "6:03:54"}
156
+ {"current_steps": 1300, "total_steps": 3275, "eval_loss": 0.03436192870140076, "epoch": 1.9845434595935503, "percentage": 39.69, "elapsed_time": "4:02:28", "remaining_time": "6:08:21"}
157
+ {"current_steps": 1310, "total_steps": 3275, "loss": 0.0353, "lr": 7.501538524998812e-05, "epoch": 1.9998091785135006, "percentage": 40.0, "elapsed_time": "4:03:57", "remaining_time": "6:05:56"}
158
+ {"current_steps": 1320, "total_steps": 3275, "loss": 0.0161, "lr": 7.455246247406406e-05, "epoch": 2.015074897433451, "percentage": 40.31, "elapsed_time": "4:05:22", "remaining_time": "6:03:24"}
159
+ {"current_steps": 1330, "total_steps": 3275, "loss": 0.0256, "lr": 7.408674952973382e-05, "epoch": 2.0303406163534015, "percentage": 40.61, "elapsed_time": "4:06:47", "remaining_time": "6:00:53"}
160
+ {"current_steps": 1340, "total_steps": 3275, "loss": 0.0235, "lr": 7.361829934112036e-05, "epoch": 2.0456063352733516, "percentage": 40.92, "elapsed_time": "4:08:12", "remaining_time": "5:58:24"}
161
+ {"current_steps": 1350, "total_steps": 3275, "loss": 0.0201, "lr": 7.314716514341006e-05, "epoch": 2.060872054193302, "percentage": 41.22, "elapsed_time": "4:09:37", "remaining_time": "5:55:57"}
162
+ {"current_steps": 1350, "total_steps": 3275, "eval_loss": 0.035528797656297684, "epoch": 2.060872054193302, "percentage": 41.22, "elapsed_time": "4:12:35", "remaining_time": "6:00:10"}
163
+ {"current_steps": 1360, "total_steps": 3275, "loss": 0.0164, "lr": 7.267340047680305e-05, "epoch": 2.0761377731132526, "percentage": 41.53, "elapsed_time": "4:14:04", "remaining_time": "5:57:45"}
164
+ {"current_steps": 1370, "total_steps": 3275, "loss": 0.0182, "lr": 7.21970591804287e-05, "epoch": 2.0914034920332027, "percentage": 41.83, "elapsed_time": "4:15:29", "remaining_time": "5:55:15"}
165
+ {"current_steps": 1380, "total_steps": 3275, "loss": 0.0254, "lr": 7.171819538622747e-05, "epoch": 2.1066692109531533, "percentage": 42.14, "elapsed_time": "4:16:54", "remaining_time": "5:52:46"}
166
+ {"current_steps": 1390, "total_steps": 3275, "loss": 0.0231, "lr": 7.123686351279914e-05, "epoch": 2.121934929873104, "percentage": 42.44, "elapsed_time": "4:18:19", "remaining_time": "5:50:18"}
167
+ {"current_steps": 1400, "total_steps": 3275, "loss": 0.0238, "lr": 7.07531182592187e-05, "epoch": 2.137200648793054, "percentage": 42.75, "elapsed_time": "4:19:44", "remaining_time": "5:47:52"}
168
+ {"current_steps": 1400, "total_steps": 3275, "eval_loss": 0.03574272617697716, "epoch": 2.137200648793054, "percentage": 42.75, "elapsed_time": "4:22:42", "remaining_time": "5:51:50"}
169
+ {"current_steps": 1410, "total_steps": 3275, "loss": 0.0315, "lr": 7.026701459882026e-05, "epoch": 2.1524663677130045, "percentage": 43.05, "elapsed_time": "4:24:12", "remaining_time": "5:49:27"}
170
+ {"current_steps": 1420, "total_steps": 3275, "loss": 0.0227, "lr": 6.977860777294988e-05, "epoch": 2.167732086632955, "percentage": 43.36, "elapsed_time": "4:25:37", "remaining_time": "5:46:59"}
171
+ {"current_steps": 1430, "total_steps": 3275, "loss": 0.0175, "lr": 6.92879532846878e-05, "epoch": 2.182997805552905, "percentage": 43.66, "elapsed_time": "4:27:02", "remaining_time": "5:44:32"}
172
+ {"current_steps": 1440, "total_steps": 3275, "loss": 0.0187, "lr": 6.879510689254104e-05, "epoch": 2.1982635244728557, "percentage": 43.97, "elapsed_time": "4:28:27", "remaining_time": "5:42:05"}
173
+ {"current_steps": 1450, "total_steps": 3275, "loss": 0.0299, "lr": 6.830012460410697e-05, "epoch": 2.213529243392806, "percentage": 44.27, "elapsed_time": "4:29:52", "remaining_time": "5:39:40"}
174
+ {"current_steps": 1450, "total_steps": 3275, "eval_loss": 0.037096813321113586, "epoch": 2.213529243392806, "percentage": 44.27, "elapsed_time": "4:32:49", "remaining_time": "5:43:22"}
175
+ {"current_steps": 1460, "total_steps": 3275, "loss": 0.017, "lr": 6.780306266970851e-05, "epoch": 2.2287949623127563, "percentage": 44.58, "elapsed_time": "4:34:17", "remaining_time": "5:40:58"}
176
+ {"current_steps": 1470, "total_steps": 3275, "loss": 0.0209, "lr": 6.73039775760018e-05, "epoch": 2.244060681232707, "percentage": 44.89, "elapsed_time": "4:35:41", "remaining_time": "5:38:31"}
177
+ {"current_steps": 1480, "total_steps": 3275, "loss": 0.0201, "lr": 6.680292603955702e-05, "epoch": 2.2593264001526574, "percentage": 45.19, "elapsed_time": "4:37:06", "remaining_time": "5:36:05"}
178
+ {"current_steps": 1490, "total_steps": 3275, "loss": 0.022, "lr": 6.629996500041299e-05, "epoch": 2.2745921190726075, "percentage": 45.5, "elapsed_time": "4:38:30", "remaining_time": "5:33:38"}
179
+ {"current_steps": 1500, "total_steps": 3275, "loss": 0.0155, "lr": 6.579515161560649e-05, "epoch": 2.289857837992558, "percentage": 45.8, "elapsed_time": "4:39:54", "remaining_time": "5:31:13"}
180
+ {"current_steps": 1500, "total_steps": 3275, "eval_loss": 0.038406338542699814, "epoch": 2.289857837992558, "percentage": 45.8, "elapsed_time": "4:42:50", "remaining_time": "5:34:41"}
181
+ {"current_steps": 1510, "total_steps": 3275, "loss": 0.0268, "lr": 6.528854325267692e-05, "epoch": 2.305123556912508, "percentage": 46.11, "elapsed_time": "4:44:18", "remaining_time": "5:32:19"}
182
+ {"current_steps": 1520, "total_steps": 3275, "loss": 0.0213, "lr": 6.478019748314686e-05, "epoch": 2.3203892758324587, "percentage": 46.41, "elapsed_time": "4:45:43", "remaining_time": "5:29:53"}
183
+ {"current_steps": 1530, "total_steps": 3275, "loss": 0.0238, "lr": 6.42701720759797e-05, "epoch": 2.3356549947524092, "percentage": 46.72, "elapsed_time": "4:47:06", "remaining_time": "5:27:27"}
184
+ {"current_steps": 1540, "total_steps": 3275, "loss": 0.019, "lr": 6.375852499101467e-05, "epoch": 2.3509207136723593, "percentage": 47.02, "elapsed_time": "4:48:30", "remaining_time": "5:25:02"}
185
+ {"current_steps": 1550, "total_steps": 3275, "loss": 0.0157, "lr": 6.324531437238019e-05, "epoch": 2.36618643259231, "percentage": 47.33, "elapsed_time": "4:49:54", "remaining_time": "5:22:38"}
186
+ {"current_steps": 1550, "total_steps": 3275, "eval_loss": 0.03914285823702812, "epoch": 2.36618643259231, "percentage": 47.33, "elapsed_time": "4:52:49", "remaining_time": "5:25:53"}
187
+ {"current_steps": 1560, "total_steps": 3275, "loss": 0.025, "lr": 6.273059854188636e-05, "epoch": 2.3814521515122604, "percentage": 47.63, "elapsed_time": "4:54:16", "remaining_time": "5:23:30"}
188
+ {"current_steps": 1570, "total_steps": 3275, "loss": 0.0242, "lr": 6.221443599239721e-05, "epoch": 2.3967178704322105, "percentage": 47.94, "elapsed_time": "4:55:38", "remaining_time": "5:21:03"}
189
+ {"current_steps": 1580, "total_steps": 3275, "loss": 0.028, "lr": 6.169688538118342e-05, "epoch": 2.411983589352161, "percentage": 48.24, "elapsed_time": "4:57:00", "remaining_time": "5:18:37"}
190
+ {"current_steps": 1590, "total_steps": 3275, "loss": 0.0232, "lr": 6.117800552325655e-05, "epoch": 2.4272493082721116, "percentage": 48.55, "elapsed_time": "4:58:24", "remaining_time": "5:16:13"}
191
+ {"current_steps": 1600, "total_steps": 3275, "loss": 0.0222, "lr": 6.06578553846852e-05, "epoch": 2.4425150271920617, "percentage": 48.85, "elapsed_time": "4:59:48", "remaining_time": "5:13:51"}
192
+ {"current_steps": 1600, "total_steps": 3275, "eval_loss": 0.03701253607869148, "epoch": 2.4425150271920617, "percentage": 48.85, "elapsed_time": "5:02:43", "remaining_time": "5:16:54"}
193
+ {"current_steps": 1610, "total_steps": 3275, "loss": 0.0228, "lr": 6.013649407589401e-05, "epoch": 2.4577807461120122, "percentage": 49.16, "elapsed_time": "5:04:07", "remaining_time": "5:14:30"}
194
+ {"current_steps": 1620, "total_steps": 3275, "loss": 0.0246, "lr": 5.961398084494634e-05, "epoch": 2.473046465031963, "percentage": 49.47, "elapsed_time": "5:05:29", "remaining_time": "5:12:05"}
195
+ {"current_steps": 1630, "total_steps": 3275, "loss": 0.0283, "lr": 5.909037507081121e-05, "epoch": 2.488312183951913, "percentage": 49.77, "elapsed_time": "5:06:53", "remaining_time": "5:09:43"}
196
+ {"current_steps": 1640, "total_steps": 3275, "loss": 0.029, "lr": 5.8565736256615434e-05, "epoch": 2.5035779028718634, "percentage": 50.08, "elapsed_time": "5:08:18", "remaining_time": "5:07:21"}
197
+ {"current_steps": 1650, "total_steps": 3275, "loss": 0.0245, "lr": 5.8040124022881625e-05, "epoch": 2.518843621791814, "percentage": 50.38, "elapsed_time": "5:09:42", "remaining_time": "5:05:00"}
198
+ {"current_steps": 1650, "total_steps": 3275, "eval_loss": 0.035995036363601685, "epoch": 2.518843621791814, "percentage": 50.38, "elapsed_time": "5:12:32", "remaining_time": "5:07:48"}
199
+ {"current_steps": 1660, "total_steps": 3275, "loss": 0.0173, "lr": 5.751359810075284e-05, "epoch": 2.534109340711764, "percentage": 50.69, "elapsed_time": "5:13:55", "remaining_time": "5:05:24"}
200
+ {"current_steps": 1670, "total_steps": 3275, "loss": 0.0125, "lr": 5.6986218325204676e-05, "epoch": 2.5493750596317146, "percentage": 50.99, "elapsed_time": "5:15:12", "remaining_time": "5:02:56"}
201
+ {"current_steps": 1680, "total_steps": 3275, "loss": 0.0158, "lr": 5.645804462824556e-05, "epoch": 2.5646407785516647, "percentage": 51.3, "elapsed_time": "5:16:29", "remaining_time": "5:00:29"}
202
+ {"current_steps": 1690, "total_steps": 3275, "loss": 0.0247, "lr": 5.5929137032106005e-05, "epoch": 2.5799064974716153, "percentage": 51.6, "elapsed_time": "5:17:46", "remaining_time": "4:58:02"}
203
+ {"current_steps": 1700, "total_steps": 3275, "loss": 0.0206, "lr": 5.53995556424176e-05, "epoch": 2.595172216391566, "percentage": 51.91, "elapsed_time": "5:19:03", "remaining_time": "4:55:36"}
204
+ {"current_steps": 1700, "total_steps": 3275, "eval_loss": 0.03758452460169792, "epoch": 2.595172216391566, "percentage": 51.91, "elapsed_time": "5:21:42", "remaining_time": "4:58:02"}
205
+ {"current_steps": 1710, "total_steps": 3275, "loss": 0.0175, "lr": 5.4869360641382615e-05, "epoch": 2.610437935311516, "percentage": 52.21, "elapsed_time": "5:23:03", "remaining_time": "4:55:39"}
206
+ {"current_steps": 1720, "total_steps": 3275, "loss": 0.0225, "lr": 5.433861228093471e-05, "epoch": 2.6257036542314665, "percentage": 52.52, "elapsed_time": "5:24:20", "remaining_time": "4:53:13"}
207
+ {"current_steps": 1730, "total_steps": 3275, "loss": 0.0179, "lr": 5.380737087589197e-05, "epoch": 2.640969373151417, "percentage": 52.82, "elapsed_time": "5:25:36", "remaining_time": "4:50:47"}
208
+ {"current_steps": 1740, "total_steps": 3275, "loss": 0.032, "lr": 5.327569679710256e-05, "epoch": 2.656235092071367, "percentage": 53.13, "elapsed_time": "5:26:53", "remaining_time": "4:48:23"}
209
+ {"current_steps": 1750, "total_steps": 3275, "loss": 0.0198, "lr": 5.274365046458416e-05, "epoch": 2.6715008109913176, "percentage": 53.44, "elapsed_time": "5:28:10", "remaining_time": "4:45:59"}
210
+ {"current_steps": 1750, "total_steps": 3275, "eval_loss": 0.036341313272714615, "epoch": 2.6715008109913176, "percentage": 53.44, "elapsed_time": "5:30:48", "remaining_time": "4:48:16"}
211
+ {"current_steps": 1760, "total_steps": 3275, "loss": 0.0256, "lr": 5.2211292340657804e-05, "epoch": 2.686766529911268, "percentage": 53.74, "elapsed_time": "5:32:09", "remaining_time": "4:45:55"}
212
+ {"current_steps": 1770, "total_steps": 3275, "loss": 0.0274, "lr": 5.167868292307678e-05, "epoch": 2.7020322488312183, "percentage": 54.05, "elapsed_time": "5:33:26", "remaining_time": "4:43:31"}
213
+ {"current_steps": 1780, "total_steps": 3275, "loss": 0.0184, "lr": 5.114588273815173e-05, "epoch": 2.717297967751169, "percentage": 54.35, "elapsed_time": "5:34:43", "remaining_time": "4:41:07"}
214
+ {"current_steps": 1790, "total_steps": 3275, "loss": 0.0272, "lr": 5.061295233387223e-05, "epoch": 2.732563686671119, "percentage": 54.66, "elapsed_time": "5:36:00", "remaining_time": "4:38:45"}
215
+ {"current_steps": 1800, "total_steps": 3275, "loss": 0.0209, "lr": 5.007995227302617e-05, "epoch": 2.7478294055910695, "percentage": 54.96, "elapsed_time": "5:37:17", "remaining_time": "4:36:23"}
216
+ {"current_steps": 1800, "total_steps": 3275, "eval_loss": 0.037039320915937424, "epoch": 2.7478294055910695, "percentage": 54.96, "elapsed_time": "5:39:55", "remaining_time": "4:38:33"}
217
+ {"current_steps": 1810, "total_steps": 3275, "loss": 0.022, "lr": 4.954694312631729e-05, "epoch": 2.76309512451102, "percentage": 55.27, "elapsed_time": "5:41:17", "remaining_time": "4:36:14"}
218
+ {"current_steps": 1820, "total_steps": 3275, "loss": 0.0205, "lr": 4.901398546548181e-05, "epoch": 2.7783608434309706, "percentage": 55.57, "elapsed_time": "5:42:34", "remaining_time": "4:33:51"}
219
+ {"current_steps": 1830, "total_steps": 3275, "loss": 0.0213, "lr": 4.848113985640513e-05, "epoch": 2.7936265623509207, "percentage": 55.88, "elapsed_time": "5:43:50", "remaining_time": "4:31:30"}
220
+ {"current_steps": 1840, "total_steps": 3275, "loss": 0.0231, "lr": 4.794846685223884e-05, "epoch": 2.808892281270871, "percentage": 56.18, "elapsed_time": "5:45:07", "remaining_time": "4:29:09"}
221
+ {"current_steps": 1850, "total_steps": 3275, "loss": 0.026, "lr": 4.741602698651966e-05, "epoch": 2.8241580001908213, "percentage": 56.49, "elapsed_time": "5:46:24", "remaining_time": "4:26:49"}
222
+ {"current_steps": 1850, "total_steps": 3275, "eval_loss": 0.036198943853378296, "epoch": 2.8241580001908213, "percentage": 56.49, "elapsed_time": "5:49:02", "remaining_time": "4:28:51"}
223
+ {"current_steps": 1860, "total_steps": 3275, "loss": 0.0276, "lr": 4.6883880766290086e-05, "epoch": 2.839423719110772, "percentage": 56.79, "elapsed_time": "5:50:23", "remaining_time": "4:26:34"}
224
+ {"current_steps": 1870, "total_steps": 3275, "loss": 0.0188, "lr": 4.635208866522251e-05, "epoch": 2.8546894380307224, "percentage": 57.1, "elapsed_time": "5:51:40", "remaining_time": "4:24:13"}
225
+ {"current_steps": 1880, "total_steps": 3275, "loss": 0.0193, "lr": 4.5820711116746785e-05, "epoch": 2.8699551569506725, "percentage": 57.4, "elapsed_time": "5:52:57", "remaining_time": "4:21:54"}
226
+ {"current_steps": 1890, "total_steps": 3275, "loss": 0.0237, "lr": 4.528980850718255e-05, "epoch": 2.885220875870623, "percentage": 57.71, "elapsed_time": "5:54:14", "remaining_time": "4:19:35"}
227
+ {"current_steps": 1900, "total_steps": 3275, "loss": 0.0197, "lr": 4.475944116887695e-05, "epoch": 2.9004865947905736, "percentage": 58.02, "elapsed_time": "5:55:31", "remaining_time": "4:17:17"}
228
+ {"current_steps": 1900, "total_steps": 3275, "eval_loss": 0.03581969812512398, "epoch": 2.9004865947905736, "percentage": 58.02, "elapsed_time": "5:58:09", "remaining_time": "4:19:11"}
229
+ {"current_steps": 1910, "total_steps": 3275, "loss": 0.0278, "lr": 4.4229669373348226e-05, "epoch": 2.9157523137105237, "percentage": 58.32, "elapsed_time": "5:59:31", "remaining_time": "4:16:56"}
230
+ {"current_steps": 1920, "total_steps": 3275, "loss": 0.0216, "lr": 4.3700553324436575e-05, "epoch": 2.9310180326304742, "percentage": 58.63, "elapsed_time": "6:00:48", "remaining_time": "4:14:37"}
231
+ {"current_steps": 1930, "total_steps": 3275, "loss": 0.0277, "lr": 4.317215315146238e-05, "epoch": 2.9462837515504248, "percentage": 58.93, "elapsed_time": "6:02:05", "remaining_time": "4:12:20"}
232
+ {"current_steps": 1940, "total_steps": 3275, "loss": 0.0242, "lr": 4.264452890239315e-05, "epoch": 2.961549470470375, "percentage": 59.24, "elapsed_time": "6:03:22", "remaining_time": "4:10:03"}
233
+ {"current_steps": 1950, "total_steps": 3275, "loss": 0.0291, "lr": 4.211774053701952e-05, "epoch": 2.9768151893903254, "percentage": 59.54, "elapsed_time": "6:04:39", "remaining_time": "4:07:46"}
234
+ {"current_steps": 1950, "total_steps": 3275, "eval_loss": 0.03554380312561989, "epoch": 2.9768151893903254, "percentage": 59.54, "elapsed_time": "6:07:17", "remaining_time": "4:09:34"}
235
+ {"current_steps": 1960, "total_steps": 3275, "loss": 0.0155, "lr": 4.159184792014145e-05, "epoch": 2.9920809083102755, "percentage": 59.85, "elapsed_time": "6:08:38", "remaining_time": "4:07:20"}
236
+ {"current_steps": 1970, "total_steps": 3275, "loss": 0.0118, "lr": 4.1066910814765016e-05, "epoch": 3.007346627230226, "percentage": 60.15, "elapsed_time": "6:09:55", "remaining_time": "4:05:03"}
237
+ {"current_steps": 1980, "total_steps": 3275, "loss": 0.0148, "lr": 4.0542988875310995e-05, "epoch": 3.0226123461501766, "percentage": 60.46, "elapsed_time": "6:11:12", "remaining_time": "4:02:47"}
238
+ {"current_steps": 1990, "total_steps": 3275, "loss": 0.0136, "lr": 4.002014164083552e-05, "epoch": 3.0378780650701267, "percentage": 60.76, "elapsed_time": "6:12:29", "remaining_time": "4:00:31"}
239
+ {"current_steps": 2000, "total_steps": 3275, "loss": 0.0091, "lr": 3.9498428528264204e-05, "epoch": 3.0531437839900772, "percentage": 61.07, "elapsed_time": "6:13:46", "remaining_time": "3:58:17"}
240
+ {"current_steps": 2000, "total_steps": 3275, "eval_loss": 0.04159301891922951, "epoch": 3.0531437839900772, "percentage": 61.07, "elapsed_time": "6:16:25", "remaining_time": "3:59:58"}
241
+ {"current_steps": 2010, "total_steps": 3275, "loss": 0.0092, "lr": 3.89779088256397e-05, "epoch": 3.068409502910028, "percentage": 61.37, "elapsed_time": "6:17:46", "remaining_time": "3:57:45"}
242
+ {"current_steps": 2020, "total_steps": 3275, "loss": 0.0097, "lr": 3.845864168538437e-05, "epoch": 3.083675221829978, "percentage": 61.68, "elapsed_time": "6:19:04", "remaining_time": "3:55:30"}
243
+ {"current_steps": 2030, "total_steps": 3275, "loss": 0.0117, "lr": 3.794068611757794e-05, "epoch": 3.0989409407499284, "percentage": 61.98, "elapsed_time": "6:20:20", "remaining_time": "3:53:16"}
244
+ {"current_steps": 2040, "total_steps": 3275, "loss": 0.0157, "lr": 3.7424100983251695e-05, "epoch": 3.114206659669879, "percentage": 62.29, "elapsed_time": "6:21:38", "remaining_time": "3:51:02"}
245
+ {"current_steps": 2050, "total_steps": 3275, "loss": 0.0132, "lr": 3.6908944987699345e-05, "epoch": 3.129472378589829, "percentage": 62.6, "elapsed_time": "6:22:55", "remaining_time": "3:48:49"}
246
+ {"current_steps": 2050, "total_steps": 3275, "eval_loss": 0.042059410363435745, "epoch": 3.129472378589829, "percentage": 62.6, "elapsed_time": "6:25:33", "remaining_time": "3:50:23"}
247
+ {"current_steps": 2060, "total_steps": 3275, "loss": 0.0087, "lr": 3.639527667380571e-05, "epoch": 3.1447380975097796, "percentage": 62.9, "elapsed_time": "6:26:55", "remaining_time": "3:48:12"}
248
+ {"current_steps": 2070, "total_steps": 3275, "loss": 0.0086, "lr": 3.5883154415393885e-05, "epoch": 3.16000381642973, "percentage": 63.21, "elapsed_time": "6:28:12", "remaining_time": "3:45:59"}
249
+ {"current_steps": 2080, "total_steps": 3275, "loss": 0.0111, "lr": 3.537263641059152e-05, "epoch": 3.1752695353496803, "percentage": 63.51, "elapsed_time": "6:29:29", "remaining_time": "3:43:46"}
250
+ {"current_steps": 2090, "total_steps": 3275, "loss": 0.01, "lr": 3.486378067521718e-05, "epoch": 3.190535254269631, "percentage": 63.82, "elapsed_time": "6:30:46", "remaining_time": "3:41:33"}
251
+ {"current_steps": 2100, "total_steps": 3275, "loss": 0.0115, "lr": 3.435664503618732e-05, "epoch": 3.2058009731895813, "percentage": 64.12, "elapsed_time": "6:32:03", "remaining_time": "3:39:22"}
252
+ {"current_steps": 2100, "total_steps": 3275, "eval_loss": 0.04429946094751358, "epoch": 3.2058009731895813, "percentage": 64.12, "elapsed_time": "6:34:42", "remaining_time": "3:40:50"}
253
+ {"current_steps": 2110, "total_steps": 3275, "loss": 0.0108, "lr": 3.3851287124944756e-05, "epoch": 3.2210666921095314, "percentage": 64.43, "elapsed_time": "6:36:03", "remaining_time": "3:38:40"}
254
+ {"current_steps": 2120, "total_steps": 3275, "loss": 0.0086, "lr": 3.334776437090944e-05, "epoch": 3.236332411029482, "percentage": 64.73, "elapsed_time": "6:37:21", "remaining_time": "3:36:28"}
255
+ {"current_steps": 2130, "total_steps": 3275, "loss": 0.0101, "lr": 3.2846133994952046e-05, "epoch": 3.251598129949432, "percentage": 65.04, "elapsed_time": "6:38:38", "remaining_time": "3:34:17"}
256
+ {"current_steps": 2140, "total_steps": 3275, "loss": 0.0061, "lr": 3.234645300289136e-05, "epoch": 3.2668638488693826, "percentage": 65.34, "elapsed_time": "6:39:55", "remaining_time": "3:32:06"}
257
+ {"current_steps": 2150, "total_steps": 3275, "loss": 0.0131, "lr": 3.1848778179016075e-05, "epoch": 3.282129567789333, "percentage": 65.65, "elapsed_time": "6:41:12", "remaining_time": "3:29:55"}
258
+ {"current_steps": 2150, "total_steps": 3275, "eval_loss": 0.04585850238800049, "epoch": 3.282129567789333, "percentage": 65.65, "elapsed_time": "6:43:50", "remaining_time": "3:31:18"}
259
+ {"current_steps": 2160, "total_steps": 3275, "loss": 0.0127, "lr": 3.135316607963176e-05, "epoch": 3.2973952867092833, "percentage": 65.95, "elapsed_time": "6:45:11", "remaining_time": "3:29:09"}
260
+ {"current_steps": 2170, "total_steps": 3275, "loss": 0.0108, "lr": 3.085967302663375e-05, "epoch": 3.312661005629234, "percentage": 66.26, "elapsed_time": "6:46:28", "remaining_time": "3:26:59"}
261
+ {"current_steps": 2180, "total_steps": 3275, "loss": 0.0168, "lr": 3.0368355101106615e-05, "epoch": 3.3279267245491844, "percentage": 66.56, "elapsed_time": "6:47:45", "remaining_time": "3:24:48"}
262
+ {"current_steps": 2190, "total_steps": 3275, "loss": 0.0095, "lr": 2.987926813695116e-05, "epoch": 3.3431924434691345, "percentage": 66.87, "elapsed_time": "6:49:02", "remaining_time": "3:22:39"}
263
+ {"current_steps": 2200, "total_steps": 3275, "loss": 0.0132, "lr": 2.939246771453924e-05, "epoch": 3.358458162389085, "percentage": 67.18, "elapsed_time": "6:50:19", "remaining_time": "3:20:30"}
264
+ {"current_steps": 2200, "total_steps": 3275, "eval_loss": 0.04094408452510834, "epoch": 3.358458162389085, "percentage": 67.18, "elapsed_time": "6:52:58", "remaining_time": "3:21:47"}
265
+ {"current_steps": 2210, "total_steps": 3275, "loss": 0.0136, "lr": 2.890800915439772e-05, "epoch": 3.3737238813090356, "percentage": 67.48, "elapsed_time": "6:54:19", "remaining_time": "3:19:39"}
266
+ {"current_steps": 2220, "total_steps": 3275, "loss": 0.0094, "lr": 2.842594751092159e-05, "epoch": 3.3889896002289857, "percentage": 67.79, "elapsed_time": "6:55:36", "remaining_time": "3:17:30"}
267
+ {"current_steps": 2230, "total_steps": 3275, "loss": 0.0111, "lr": 2.794633756611776e-05, "epoch": 3.404255319148936, "percentage": 68.09, "elapsed_time": "6:56:53", "remaining_time": "3:15:21"}
268
+ {"current_steps": 2240, "total_steps": 3275, "loss": 0.0106, "lr": 2.7469233823379347e-05, "epoch": 3.4195210380688867, "percentage": 68.4, "elapsed_time": "6:58:10", "remaining_time": "3:13:13"}
269
+ {"current_steps": 2250, "total_steps": 3275, "loss": 0.0077, "lr": 2.6994690501292032e-05, "epoch": 3.434786756988837, "percentage": 68.7, "elapsed_time": "6:59:27", "remaining_time": "3:11:05"}
270
+ {"current_steps": 2250, "total_steps": 3275, "eval_loss": 0.04445834830403328, "epoch": 3.434786756988837, "percentage": 68.7, "elapsed_time": "7:02:06", "remaining_time": "3:12:17"}
271
+ {"current_steps": 2260, "total_steps": 3275, "loss": 0.0073, "lr": 2.652276152747246e-05, "epoch": 3.4500524759087874, "percentage": 69.01, "elapsed_time": "7:03:27", "remaining_time": "3:10:11"}
272
+ {"current_steps": 2270, "total_steps": 3275, "loss": 0.0058, "lr": 2.6053500532439968e-05, "epoch": 3.465318194828738, "percentage": 69.31, "elapsed_time": "7:04:45", "remaining_time": "3:08:03"}
273
+ {"current_steps": 2280, "total_steps": 3275, "loss": 0.0135, "lr": 2.5586960843521824e-05, "epoch": 3.480583913748688, "percentage": 69.62, "elapsed_time": "7:06:02", "remaining_time": "3:05:55"}
274
+ {"current_steps": 2290, "total_steps": 3275, "loss": 0.0137, "lr": 2.5123195478793217e-05, "epoch": 3.4958496326686386, "percentage": 69.92, "elapsed_time": "7:07:19", "remaining_time": "3:03:48"}
275
+ {"current_steps": 2300, "total_steps": 3275, "loss": 0.0156, "lr": 2.466225714105202e-05, "epoch": 3.5111153515885887, "percentage": 70.23, "elapsed_time": "7:08:36", "remaining_time": "3:01:41"}
276
+ {"current_steps": 2300, "total_steps": 3275, "eval_loss": 0.04438282549381256, "epoch": 3.5111153515885887, "percentage": 70.23, "elapsed_time": "7:11:14", "remaining_time": "3:02:48"}
277
+ {"current_steps": 2310, "total_steps": 3275, "loss": 0.014, "lr": 2.420419821182982e-05, "epoch": 3.526381070508539, "percentage": 70.53, "elapsed_time": "7:12:36", "remaining_time": "3:00:43"}
278
+ {"current_steps": 2320, "total_steps": 3275, "loss": 0.0097, "lr": 2.3749070745438996e-05, "epoch": 3.5416467894284898, "percentage": 70.84, "elapsed_time": "7:13:53", "remaining_time": "2:58:36"}
279
+ {"current_steps": 2330, "total_steps": 3275, "loss": 0.0092, "lr": 2.3296926463057396e-05, "epoch": 3.5569125083484403, "percentage": 71.15, "elapsed_time": "7:15:10", "remaining_time": "2:56:29"}
280
+ {"current_steps": 2340, "total_steps": 3275, "loss": 0.0076, "lr": 2.284781674685058e-05, "epoch": 3.5721782272683904, "percentage": 71.45, "elapsed_time": "7:16:27", "remaining_time": "2:54:23"}
281
+ {"current_steps": 2350, "total_steps": 3275, "loss": 0.0125, "lr": 2.2401792634132708e-05, "epoch": 3.587443946188341, "percentage": 71.76, "elapsed_time": "7:17:45", "remaining_time": "2:52:18"}
282
+ {"current_steps": 2350, "total_steps": 3275, "eval_loss": 0.048045314848423004, "epoch": 3.587443946188341, "percentage": 71.76, "elapsed_time": "7:20:23", "remaining_time": "2:53:20"}
283
+ {"current_steps": 2360, "total_steps": 3275, "loss": 0.0094, "lr": 2.195890481156666e-05, "epoch": 3.602709665108291, "percentage": 72.06, "elapsed_time": "7:21:45", "remaining_time": "2:51:16"}
284
+ {"current_steps": 2370, "total_steps": 3275, "loss": 0.0122, "lr": 2.151920360940387e-05, "epoch": 3.6179753840282416, "percentage": 72.37, "elapsed_time": "7:23:02", "remaining_time": "2:49:10"}
285
+ {"current_steps": 2380, "total_steps": 3275, "loss": 0.0075, "lr": 2.1082738995764785e-05, "epoch": 3.633241102948192, "percentage": 72.67, "elapsed_time": "7:24:19", "remaining_time": "2:47:05"}
286
+ {"current_steps": 2390, "total_steps": 3275, "loss": 0.0063, "lr": 2.0649560570960465e-05, "epoch": 3.6485068218681422, "percentage": 72.98, "elapsed_time": "7:25:36", "remaining_time": "2:45:00"}
287
+ {"current_steps": 2400, "total_steps": 3275, "loss": 0.0089, "lr": 2.0219717561855855e-05, "epoch": 3.663772540788093, "percentage": 73.28, "elapsed_time": "7:26:53", "remaining_time": "2:42:55"}
288
+ {"current_steps": 2400, "total_steps": 3275, "eval_loss": 0.049949660897254944, "epoch": 3.663772540788093, "percentage": 73.28, "elapsed_time": "7:29:32", "remaining_time": "2:43:53"}
289
+ {"current_steps": 2410, "total_steps": 3275, "loss": 0.0168, "lr": 1.9793258816275728e-05, "epoch": 3.679038259708043, "percentage": 73.59, "elapsed_time": "7:30:53", "remaining_time": "2:41:50"}
290
+ {"current_steps": 2420, "total_steps": 3275, "loss": 0.0106, "lr": 1.9370232797453402e-05, "epoch": 3.6943039786279934, "percentage": 73.89, "elapsed_time": "7:32:10", "remaining_time": "2:39:45"}
291
+ {"current_steps": 2430, "total_steps": 3275, "loss": 0.01, "lr": 1.8950687578523502e-05, "epoch": 3.709569697547944, "percentage": 74.2, "elapsed_time": "7:33:27", "remaining_time": "2:37:41"}
292
+ {"current_steps": 2440, "total_steps": 3275, "loss": 0.0067, "lr": 1.853467083705869e-05, "epoch": 3.7248354164678945, "percentage": 74.5, "elapsed_time": "7:34:44", "remaining_time": "2:35:37"}
293
+ {"current_steps": 2450, "total_steps": 3275, "loss": 0.0125, "lr": 1.8122229849651716e-05, "epoch": 3.7401011353878446, "percentage": 74.81, "elapsed_time": "7:36:01", "remaining_time": "2:33:33"}
294
+ {"current_steps": 2450, "total_steps": 3275, "eval_loss": 0.04671522229909897, "epoch": 3.7401011353878446, "percentage": 74.81, "elapsed_time": "7:38:39", "remaining_time": "2:34:26"}
295
+ {"current_steps": 2460, "total_steps": 3275, "loss": 0.014, "lr": 1.7713411486542707e-05, "epoch": 3.755366854307795, "percentage": 75.11, "elapsed_time": "7:40:01", "remaining_time": "2:32:24"}
296
+ {"current_steps": 2470, "total_steps": 3275, "loss": 0.0076, "lr": 1.7308262206292897e-05, "epoch": 3.7706325732277453, "percentage": 75.42, "elapsed_time": "7:41:19", "remaining_time": "2:30:21"}
297
+ {"current_steps": 2480, "total_steps": 3275, "loss": 0.015, "lr": 1.6906828050504907e-05, "epoch": 3.785898292147696, "percentage": 75.73, "elapsed_time": "7:42:36", "remaining_time": "2:28:17"}
298
+ {"current_steps": 2490, "total_steps": 3275, "loss": 0.0096, "lr": 1.650915463859068e-05, "epoch": 3.8011640110676463, "percentage": 76.03, "elapsed_time": "7:43:53", "remaining_time": "2:26:14"}
299
+ {"current_steps": 2500, "total_steps": 3275, "loss": 0.0115, "lr": 1.6115287162587055e-05, "epoch": 3.8164297299875964, "percentage": 76.34, "elapsed_time": "7:45:10", "remaining_time": "2:24:12"}
300
+ {"current_steps": 2500, "total_steps": 3275, "eval_loss": 0.04467522352933884, "epoch": 3.8164297299875964, "percentage": 76.34, "elapsed_time": "7:47:49", "remaining_time": "2:25:01"}
301
+ {"current_steps": 2510, "total_steps": 3275, "loss": 0.0064, "lr": 1.57252703820203e-05, "epoch": 3.831695448907547, "percentage": 76.64, "elapsed_time": "7:49:10", "remaining_time": "2:22:59"}
302
+ {"current_steps": 2520, "total_steps": 3275, "loss": 0.0159, "lr": 1.5339148618819393e-05, "epoch": 3.8469611678274975, "percentage": 76.95, "elapsed_time": "7:50:27", "remaining_time": "2:20:57"}
303
+ {"current_steps": 2530, "total_steps": 3275, "loss": 0.0135, "lr": 1.4956965752279395e-05, "epoch": 3.8622268867474476, "percentage": 77.25, "elapsed_time": "7:51:44", "remaining_time": "2:18:54"}
304
+ {"current_steps": 2540, "total_steps": 3275, "loss": 0.0103, "lr": 1.457876521407484e-05, "epoch": 3.877492605667398, "percentage": 77.56, "elapsed_time": "7:53:02", "remaining_time": "2:16:52"}
305
+ {"current_steps": 2550, "total_steps": 3275, "loss": 0.0062, "lr": 1.4204589983324173e-05, "epoch": 3.8927583245873487, "percentage": 77.86, "elapsed_time": "7:54:18", "remaining_time": "2:14:51"}
306
+ {"current_steps": 2550, "total_steps": 3275, "eval_loss": 0.044938329607248306, "epoch": 3.8927583245873487, "percentage": 77.86, "elapsed_time": "7:56:56", "remaining_time": "2:15:36"}
307
+ {"current_steps": 2560, "total_steps": 3275, "loss": 0.0095, "lr": 1.383448258170557e-05, "epoch": 3.908024043507299, "percentage": 78.17, "elapsed_time": "7:58:18", "remaining_time": "2:13:35"}
308
+ {"current_steps": 2570, "total_steps": 3275, "loss": 0.0069, "lr": 1.3468485068624653e-05, "epoch": 3.9232897624272494, "percentage": 78.47, "elapsed_time": "7:59:35", "remaining_time": "2:11:33"}
309
+ {"current_steps": 2580, "total_steps": 3275, "loss": 0.0119, "lr": 1.310663903643492e-05, "epoch": 3.9385554813471995, "percentage": 78.78, "elapsed_time": "8:00:52", "remaining_time": "2:09:32"}
310
+ {"current_steps": 2590, "total_steps": 3275, "loss": 0.0109, "lr": 1.2748985605711028e-05, "epoch": 3.95382120026715, "percentage": 79.08, "elapsed_time": "8:02:10", "remaining_time": "2:07:31"}
311
+ {"current_steps": 2600, "total_steps": 3275, "loss": 0.0112, "lr": 1.2395565420575932e-05, "epoch": 3.9690869191871005, "percentage": 79.39, "elapsed_time": "8:03:27", "remaining_time": "2:05:30"}
312
+ {"current_steps": 2600, "total_steps": 3275, "eval_loss": 0.046159546822309494, "epoch": 3.9690869191871005, "percentage": 79.39, "elapsed_time": "8:06:05", "remaining_time": "2:06:11"}
313
+ {"current_steps": 2610, "total_steps": 3275, "loss": 0.0194, "lr": 1.2046418644081903e-05, "epoch": 3.984352638107051, "percentage": 79.69, "elapsed_time": "8:07:26", "remaining_time": "2:04:11"}
314
+ {"current_steps": 2620, "total_steps": 3275, "loss": 0.0084, "lr": 1.1701584953646505e-05, "epoch": 3.999618357027001, "percentage": 80.0, "elapsed_time": "8:08:43", "remaining_time": "2:02:10"}
315
+ {"current_steps": 2630, "total_steps": 3275, "loss": 0.006, "lr": 1.1361103536543466e-05, "epoch": 4.014884075946951, "percentage": 80.31, "elapsed_time": "8:10:00", "remaining_time": "2:00:10"}
316
+ {"current_steps": 2640, "total_steps": 3275, "loss": 0.0033, "lr": 1.1025013085449527e-05, "epoch": 4.030149794866902, "percentage": 80.61, "elapsed_time": "8:11:17", "remaining_time": "1:58:10"}
317
+ {"current_steps": 2650, "total_steps": 3275, "loss": 0.005, "lr": 1.0693351794047224e-05, "epoch": 4.045415513786852, "percentage": 80.92, "elapsed_time": "8:12:34", "remaining_time": "1:56:10"}
318
+ {"current_steps": 2650, "total_steps": 3275, "eval_loss": 0.04647543653845787, "epoch": 4.045415513786852, "percentage": 80.92, "elapsed_time": "8:15:12", "remaining_time": "1:56:47"}
319
+ {"current_steps": 2660, "total_steps": 3275, "loss": 0.0043, "lr": 1.036615735268468e-05, "epoch": 4.060681232706803, "percentage": 81.22, "elapsed_time": "8:16:33", "remaining_time": "1:54:48"}
320
+ {"current_steps": 2670, "total_steps": 3275, "loss": 0.0058, "lr": 1.0043466944092272e-05, "epoch": 4.0759469516267535, "percentage": 81.53, "elapsed_time": "8:17:50", "remaining_time": "1:52:48"}
321
+ {"current_steps": 2680, "total_steps": 3275, "loss": 0.0081, "lr": 9.72531723915726e-06, "epoch": 4.091212670546703, "percentage": 81.83, "elapsed_time": "8:19:07", "remaining_time": "1:50:48"}
322
+ {"current_steps": 2690, "total_steps": 3275, "loss": 0.0055, "lr": 9.411744392756405e-06, "epoch": 4.106478389466654, "percentage": 82.14, "elapsed_time": "8:20:24", "remaining_time": "1:48:49"}
323
+ {"current_steps": 2700, "total_steps": 3275, "loss": 0.0065, "lr": 9.102784039647339e-06, "epoch": 4.121744108386604, "percentage": 82.44, "elapsed_time": "8:21:41", "remaining_time": "1:46:50"}
324
+ {"current_steps": 2700, "total_steps": 3275, "eval_loss": 0.050155650824308395, "epoch": 4.121744108386604, "percentage": 82.44, "elapsed_time": "8:24:19", "remaining_time": "1:47:24"}
325
+ {"current_steps": 2710, "total_steps": 3275, "loss": 0.007, "lr": 8.79847129041893e-06, "epoch": 4.137009827306555, "percentage": 82.75, "elapsed_time": "8:25:41", "remaining_time": "1:45:25"}
326
+ {"current_steps": 2720, "total_steps": 3275, "loss": 0.0032, "lr": 8.498840727501316e-06, "epoch": 4.152275546226505, "percentage": 83.05, "elapsed_time": "8:26:58", "remaining_time": "1:43:26"}
327
+ {"current_steps": 2730, "total_steps": 3275, "loss": 0.0028, "lr": 8.203926401235957e-06, "epoch": 4.167541265146456, "percentage": 83.36, "elapsed_time": "8:28:15", "remaining_time": "1:41:27"}
328
+ {"current_steps": 2740, "total_steps": 3275, "loss": 0.0029, "lr": 7.913761826006017e-06, "epoch": 4.1828069840664055, "percentage": 83.66, "elapsed_time": "8:29:32", "remaining_time": "1:39:29"}
329
+ {"current_steps": 2750, "total_steps": 3275, "loss": 0.0021, "lr": 7.628379976427868e-06, "epoch": 4.198072702986356, "percentage": 83.97, "elapsed_time": "8:30:49", "remaining_time": "1:37:31"}
330
+ {"current_steps": 2750, "total_steps": 3275, "eval_loss": 0.054289042949676514, "epoch": 4.198072702986356, "percentage": 83.97, "elapsed_time": "8:33:27", "remaining_time": "1:38:01"}
331
+ {"current_steps": 2760, "total_steps": 3275, "loss": 0.008, "lr": 7.347813283603705e-06, "epoch": 4.213338421906307, "percentage": 84.27, "elapsed_time": "8:34:49", "remaining_time": "1:36:03"}
332
+ {"current_steps": 2770, "total_steps": 3275, "loss": 0.0041, "lr": 7.072093631436161e-06, "epoch": 4.228604140826257, "percentage": 84.58, "elapsed_time": "8:36:06", "remaining_time": "1:34:05"}
333
+ {"current_steps": 2780, "total_steps": 3275, "loss": 0.0035, "lr": 6.801252353004867e-06, "epoch": 4.243869859746208, "percentage": 84.89, "elapsed_time": "8:37:23", "remaining_time": "1:32:07"}
334
+ {"current_steps": 2790, "total_steps": 3275, "loss": 0.0037, "lr": 6.535320227005826e-06, "epoch": 4.259135578666158, "percentage": 85.19, "elapsed_time": "8:38:40", "remaining_time": "1:30:09"}
335
+ {"current_steps": 2800, "total_steps": 3275, "loss": 0.0033, "lr": 6.274327474253611e-06, "epoch": 4.274401297586108, "percentage": 85.5, "elapsed_time": "8:39:58", "remaining_time": "1:28:12"}
336
+ {"current_steps": 2800, "total_steps": 3275, "eval_loss": 0.055618129670619965, "epoch": 4.274401297586108, "percentage": 85.5, "elapsed_time": "8:42:36", "remaining_time": "1:28:39"}
337
+ {"current_steps": 2810, "total_steps": 3275, "loss": 0.004, "lr": 6.018303754247112e-06, "epoch": 4.289667016506058, "percentage": 85.8, "elapsed_time": "8:43:57", "remaining_time": "1:26:42"}
338
+ {"current_steps": 2820, "total_steps": 3275, "loss": 0.0045, "lr": 5.767278161798911e-06, "epoch": 4.304932735426009, "percentage": 86.11, "elapsed_time": "8:45:14", "remaining_time": "1:24:44"}
339
+ {"current_steps": 2830, "total_steps": 3275, "loss": 0.0018, "lr": 5.521279223729026e-06, "epoch": 4.3201984543459595, "percentage": 86.41, "elapsed_time": "8:46:32", "remaining_time": "1:22:47"}
340
+ {"current_steps": 2840, "total_steps": 3275, "loss": 0.0036, "lr": 5.280334895622968e-06, "epoch": 4.33546417326591, "percentage": 86.72, "elapsed_time": "8:47:48", "remaining_time": "1:20:50"}
341
+ {"current_steps": 2850, "total_steps": 3275, "loss": 0.0068, "lr": 5.044472558654961e-06, "epoch": 4.350729892185861, "percentage": 87.02, "elapsed_time": "8:49:05", "remaining_time": "1:18:53"}
342
+ {"current_steps": 2850, "total_steps": 3275, "eval_loss": 0.057221900671720505, "epoch": 4.350729892185861, "percentage": 87.02, "elapsed_time": "8:51:43", "remaining_time": "1:19:17"}
343
+ {"current_steps": 2860, "total_steps": 3275, "loss": 0.0024, "lr": 4.813719016476203e-06, "epoch": 4.36599561110581, "percentage": 87.33, "elapsed_time": "8:53:05", "remaining_time": "1:17:21"}
344
+ {"current_steps": 2870, "total_steps": 3275, "loss": 0.0017, "lr": 4.588100492168973e-06, "epoch": 4.381261330025761, "percentage": 87.63, "elapsed_time": "8:54:22", "remaining_time": "1:15:24"}
345
+ {"current_steps": 2880, "total_steps": 3275, "loss": 0.0029, "lr": 4.367642625266511e-06, "epoch": 4.396527048945711, "percentage": 87.94, "elapsed_time": "8:55:39", "remaining_time": "1:13:27"}
346
+ {"current_steps": 2890, "total_steps": 3275, "loss": 0.0023, "lr": 4.1523704688394176e-06, "epoch": 4.411792767865662, "percentage": 88.24, "elapsed_time": "8:56:56", "remaining_time": "1:11:31"}
347
+ {"current_steps": 2900, "total_steps": 3275, "loss": 0.0015, "lr": 3.9423084866484884e-06, "epoch": 4.427058486785612, "percentage": 88.55, "elapsed_time": "8:58:13", "remaining_time": "1:09:35"}
348
+ {"current_steps": 2900, "total_steps": 3275, "eval_loss": 0.05985542759299278, "epoch": 4.427058486785612, "percentage": 88.55, "elapsed_time": "9:00:51", "remaining_time": "1:09:56"}
349
+ {"current_steps": 2910, "total_steps": 3275, "loss": 0.0071, "lr": 3.737480550364736e-06, "epoch": 4.442324205705562, "percentage": 88.85, "elapsed_time": "9:02:12", "remaining_time": "1:08:00"}
350
+ {"current_steps": 2920, "total_steps": 3275, "loss": 0.0041, "lr": 3.5379099368564817e-06, "epoch": 4.457589924625513, "percentage": 89.16, "elapsed_time": "9:03:29", "remaining_time": "1:06:04"}
351
+ {"current_steps": 2930, "total_steps": 3275, "loss": 0.0026, "lr": 3.3436193255442396e-06, "epoch": 4.472855643545463, "percentage": 89.47, "elapsed_time": "9:04:47", "remaining_time": "1:04:08"}
352
+ {"current_steps": 2940, "total_steps": 3275, "loss": 0.0031, "lr": 3.1546307958233214e-06, "epoch": 4.488121362465414, "percentage": 89.77, "elapsed_time": "9:06:03", "remaining_time": "1:02:13"}
353
+ {"current_steps": 2950, "total_steps": 3275, "loss": 0.0036, "lr": 2.9709658245547834e-06, "epoch": 4.503387081385364, "percentage": 90.08, "elapsed_time": "9:07:21", "remaining_time": "1:00:18"}
354
+ {"current_steps": 2950, "total_steps": 3275, "eval_loss": 0.060201384127140045, "epoch": 4.503387081385364, "percentage": 90.08, "elapsed_time": "9:09:59", "remaining_time": "1:00:35"}
355
+ {"current_steps": 2960, "total_steps": 3275, "loss": 0.0027, "lr": 2.792645283624712e-06, "epoch": 4.518652800305315, "percentage": 90.38, "elapsed_time": "9:11:20", "remaining_time": "0:58:40"}
356
+ {"current_steps": 2970, "total_steps": 3275, "loss": 0.0014, "lr": 2.6196894375723645e-06, "epoch": 4.5339185192252645, "percentage": 90.69, "elapsed_time": "9:12:37", "remaining_time": "0:56:45"}
357
+ {"current_steps": 2980, "total_steps": 3275, "loss": 0.0064, "lr": 2.452117941287246e-06, "epoch": 4.549184238145215, "percentage": 90.99, "elapsed_time": "9:13:55", "remaining_time": "0:54:50"}
358
+ {"current_steps": 2990, "total_steps": 3275, "loss": 0.0012, "lr": 2.2899498377755566e-06, "epoch": 4.5644499570651655, "percentage": 91.3, "elapsed_time": "9:15:12", "remaining_time": "0:52:55"}
359
+ {"current_steps": 3000, "total_steps": 3275, "loss": 0.0027, "lr": 2.1332035559960663e-06, "epoch": 4.579715675985116, "percentage": 91.6, "elapsed_time": "9:16:29", "remaining_time": "0:51:00"}
360
+ {"current_steps": 3000, "total_steps": 3275, "eval_loss": 0.06145218014717102, "epoch": 4.579715675985116, "percentage": 91.6, "elapsed_time": "9:19:07", "remaining_time": "0:51:15"}
361
+ {"current_steps": 3010, "total_steps": 3275, "loss": 0.0043, "lr": 1.9818969087658735e-06, "epoch": 4.594981394905067, "percentage": 91.91, "elapsed_time": "9:20:29", "remaining_time": "0:49:20"}
362
+ {"current_steps": 3020, "total_steps": 3275, "loss": 0.0011, "lr": 1.8360470907361093e-06, "epoch": 4.610247113825016, "percentage": 92.21, "elapsed_time": "9:21:45", "remaining_time": "0:47:26"}
363
+ {"current_steps": 3030, "total_steps": 3275, "loss": 0.0056, "lr": 1.6956706764379438e-06, "epoch": 4.625512832744967, "percentage": 92.52, "elapsed_time": "9:23:03", "remaining_time": "0:45:31"}
364
+ {"current_steps": 3040, "total_steps": 3275, "loss": 0.0028, "lr": 1.5607836183989921e-06, "epoch": 4.640778551664917, "percentage": 92.82, "elapsed_time": "9:24:20", "remaining_time": "0:43:37"}
365
+ {"current_steps": 3050, "total_steps": 3275, "loss": 0.0013, "lr": 1.4314012453305215e-06, "epoch": 4.656044270584868, "percentage": 93.13, "elapsed_time": "9:25:37", "remaining_time": "0:41:43"}
366
+ {"current_steps": 3050, "total_steps": 3275, "eval_loss": 0.061488546431064606, "epoch": 4.656044270584868, "percentage": 93.13, "elapsed_time": "9:28:15", "remaining_time": "0:41:55"}
367
+ {"current_steps": 3060, "total_steps": 3275, "loss": 0.0028, "lr": 1.3075382603854157e-06, "epoch": 4.6713099895048185, "percentage": 93.44, "elapsed_time": "9:29:37", "remaining_time": "0:40:01"}
368
+ {"current_steps": 3070, "total_steps": 3275, "loss": 0.0027, "lr": 1.1892087394873353e-06, "epoch": 4.686575708424769, "percentage": 93.74, "elapsed_time": "9:30:54", "remaining_time": "0:38:07"}
369
+ {"current_steps": 3080, "total_steps": 3275, "loss": 0.0038, "lr": 1.076426129731084e-06, "epoch": 4.701841427344719, "percentage": 94.05, "elapsed_time": "9:32:11", "remaining_time": "0:36:13"}
370
+ {"current_steps": 3090, "total_steps": 3275, "loss": 0.005, "lr": 9.692032478545e-07, "epoch": 4.717107146264669, "percentage": 94.35, "elapsed_time": "9:33:28", "remaining_time": "0:34:20"}
371
+ {"current_steps": 3100, "total_steps": 3275, "loss": 0.0056, "lr": 8.675522787819023e-07, "epoch": 4.73237286518462, "percentage": 94.66, "elapsed_time": "9:34:45", "remaining_time": "0:32:26"}
372
+ {"current_steps": 3100, "total_steps": 3275, "eval_loss": 0.061799220740795135, "epoch": 4.73237286518462, "percentage": 94.66, "elapsed_time": "9:37:24", "remaining_time": "0:32:35"}
373
+ {"current_steps": 3110, "total_steps": 3275, "loss": 0.0051, "lr": 7.714847742394337e-07, "epoch": 4.74763858410457, "percentage": 94.96, "elapsed_time": "9:38:45", "remaining_time": "0:30:42"}
374
+ {"current_steps": 3120, "total_steps": 3275, "loss": 0.0089, "lr": 6.810116514422593e-07, "epoch": 4.762904303024521, "percentage": 95.27, "elapsed_time": "9:40:02", "remaining_time": "0:28:48"}
375
+ {"current_steps": 3130, "total_steps": 3275, "loss": 0.0031, "lr": 5.961431918539817e-07, "epoch": 4.7781700219444705, "percentage": 95.57, "elapsed_time": "9:41:19", "remaining_time": "0:26:55"}
376
+ {"current_steps": 3140, "total_steps": 3275, "loss": 0.0058, "lr": 5.16889040018187e-07, "epoch": 4.793435740864421, "percentage": 95.88, "elapsed_time": "9:42:36", "remaining_time": "0:25:02"}
377
+ {"current_steps": 3150, "total_steps": 3275, "loss": 0.0028, "lr": 4.432582024624543e-07, "epoch": 4.808701459784372, "percentage": 96.18, "elapsed_time": "9:43:53", "remaining_time": "0:23:10"}
378
+ {"current_steps": 3150, "total_steps": 3275, "eval_loss": 0.06179770454764366, "epoch": 4.808701459784372, "percentage": 96.18, "elapsed_time": "9:46:32", "remaining_time": "0:23:16"}
379
+ {"current_steps": 3160, "total_steps": 3275, "loss": 0.0028, "lr": 3.7525904667484737e-07, "epoch": 4.823967178704322, "percentage": 96.49, "elapsed_time": "9:47:56", "remaining_time": "0:21:23"}
380
+ {"current_steps": 3170, "total_steps": 3275, "loss": 0.0037, "lr": 3.128993001530245e-07, "epoch": 4.839232897624273, "percentage": 96.79, "elapsed_time": "9:49:13", "remaining_time": "0:19:31"}
381
+ {"current_steps": 3180, "total_steps": 3275, "loss": 0.003, "lr": 2.5618604952605816e-07, "epoch": 4.854498616544223, "percentage": 97.1, "elapsed_time": "9:50:31", "remaining_time": "0:17:38"}
382
+ {"current_steps": 3190, "total_steps": 3275, "loss": 0.0034, "lr": 2.0512573974912908e-07, "epoch": 4.869764335464174, "percentage": 97.4, "elapsed_time": "9:51:48", "remaining_time": "0:15:46"}
383
+ {"current_steps": 3200, "total_steps": 3275, "loss": 0.0044, "lr": 1.597241733711008e-07, "epoch": 4.885030054384123, "percentage": 97.71, "elapsed_time": "9:53:05", "remaining_time": "0:13:54"}
384
+ {"current_steps": 3200, "total_steps": 3275, "eval_loss": 0.06198294460773468, "epoch": 4.885030054384123, "percentage": 97.71, "elapsed_time": "9:55:43", "remaining_time": "0:13:57"}
385
+ {"current_steps": 3210, "total_steps": 3275, "loss": 0.0077, "lr": 1.1998650987510295e-07, "epoch": 4.900295773304074, "percentage": 98.02, "elapsed_time": "9:57:05", "remaining_time": "0:12:05"}
386
+ {"current_steps": 3220, "total_steps": 3275, "loss": 0.0097, "lr": 8.591726509222242e-08, "epoch": 4.9155614922240245, "percentage": 98.32, "elapsed_time": "9:58:21", "remaining_time": "0:10:13"}
387
+ {"current_steps": 3230, "total_steps": 3275, "loss": 0.0048, "lr": 5.752031068830266e-08, "epoch": 4.930827211143975, "percentage": 98.63, "elapsed_time": "9:59:38", "remaining_time": "0:08:21"}
388
+ {"current_steps": 3240, "total_steps": 3275, "loss": 0.0013, "lr": 3.4798873723984605e-08, "epoch": 4.946092930063926, "percentage": 98.93, "elapsed_time": "10:00:55", "remaining_time": "0:06:29"}
389
+ {"current_steps": 3250, "total_steps": 3275, "loss": 0.0061, "lr": 1.7755536287944464e-08, "epoch": 4.961358648983875, "percentage": 99.24, "elapsed_time": "10:02:12", "remaining_time": "0:04:37"}
390
+ {"current_steps": 3250, "total_steps": 3275, "eval_loss": 0.06215130165219307, "epoch": 4.961358648983875, "percentage": 99.24, "elapsed_time": "10:04:51", "remaining_time": "0:04:39"}
391
+ {"current_steps": 3260, "total_steps": 3275, "loss": 0.0082, "lr": 6.3922352034895276e-09, "epoch": 4.976624367903826, "percentage": 99.54, "elapsed_time": "10:06:13", "remaining_time": "0:02:47"}
392
+ {"current_steps": 3270, "total_steps": 3275, "loss": 0.005, "lr": 7.102618084620094e-10, "epoch": 4.991890086823776, "percentage": 99.85, "elapsed_time": "10:07:30", "remaining_time": "0:00:55"}
393
+ {"current_steps": 3275, "total_steps": 3275, "epoch": 4.999522946283752, "percentage": 100.0, "elapsed_time": "10:08:13", "remaining_time": "0:00:00"}
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold4/trainer_state.json ADDED
@@ -0,0 +1,2851 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.03436192870140076,
3
+ "best_model_checkpoint": "saves/psy-course/Llama-3.1-8B-Instruct/train/fold4/checkpoint-1300",
4
+ "epoch": 4.999522946283752,
5
+ "eval_steps": 50,
6
+ "global_step": 3275,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.015265718919950386,
13
+ "grad_norm": 4.221195220947266,
14
+ "learning_rate": 3.0487804878048782e-06,
15
+ "loss": 1.6278,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.030531437839900772,
20
+ "grad_norm": 5.125793933868408,
21
+ "learning_rate": 6.0975609756097564e-06,
22
+ "loss": 1.5554,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.04579715675985116,
27
+ "grad_norm": 6.733878135681152,
28
+ "learning_rate": 9.146341463414634e-06,
29
+ "loss": 1.3738,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.061062875679801544,
34
+ "grad_norm": 2.5405797958374023,
35
+ "learning_rate": 1.2195121951219513e-05,
36
+ "loss": 1.0174,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.07632859459975193,
41
+ "grad_norm": 1.4538228511810303,
42
+ "learning_rate": 1.524390243902439e-05,
43
+ "loss": 0.5681,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.07632859459975193,
48
+ "eval_loss": 0.3813890814781189,
49
+ "eval_runtime": 158.8708,
50
+ "eval_samples_per_second": 7.333,
51
+ "eval_steps_per_second": 7.333,
52
+ "step": 50
53
+ },
54
+ {
55
+ "epoch": 0.09159431351970232,
56
+ "grad_norm": 1.5504209995269775,
57
+ "learning_rate": 1.8292682926829268e-05,
58
+ "loss": 0.3362,
59
+ "step": 60
60
+ },
61
+ {
62
+ "epoch": 0.10686003243965271,
63
+ "grad_norm": 1.2897658348083496,
64
+ "learning_rate": 2.134146341463415e-05,
65
+ "loss": 0.246,
66
+ "step": 70
67
+ },
68
+ {
69
+ "epoch": 0.12212575135960309,
70
+ "grad_norm": 1.0303564071655273,
71
+ "learning_rate": 2.4390243902439026e-05,
72
+ "loss": 0.1841,
73
+ "step": 80
74
+ },
75
+ {
76
+ "epoch": 0.13739147027955348,
77
+ "grad_norm": 0.9430064558982849,
78
+ "learning_rate": 2.7439024390243906e-05,
79
+ "loss": 0.115,
80
+ "step": 90
81
+ },
82
+ {
83
+ "epoch": 0.15265718919950386,
84
+ "grad_norm": 0.9477012157440186,
85
+ "learning_rate": 3.048780487804878e-05,
86
+ "loss": 0.122,
87
+ "step": 100
88
+ },
89
+ {
90
+ "epoch": 0.15265718919950386,
91
+ "eval_loss": 0.07960689812898636,
92
+ "eval_runtime": 158.7007,
93
+ "eval_samples_per_second": 7.341,
94
+ "eval_steps_per_second": 7.341,
95
+ "step": 100
96
+ },
97
+ {
98
+ "epoch": 0.16792290811945426,
99
+ "grad_norm": 0.690284788608551,
100
+ "learning_rate": 3.353658536585366e-05,
101
+ "loss": 0.0802,
102
+ "step": 110
103
+ },
104
+ {
105
+ "epoch": 0.18318862703940464,
106
+ "grad_norm": 0.651168704032898,
107
+ "learning_rate": 3.6585365853658535e-05,
108
+ "loss": 0.0705,
109
+ "step": 120
110
+ },
111
+ {
112
+ "epoch": 0.19845434595935502,
113
+ "grad_norm": 0.766960084438324,
114
+ "learning_rate": 3.9634146341463416e-05,
115
+ "loss": 0.08,
116
+ "step": 130
117
+ },
118
+ {
119
+ "epoch": 0.21372006487930542,
120
+ "grad_norm": 0.49084338545799255,
121
+ "learning_rate": 4.26829268292683e-05,
122
+ "loss": 0.0655,
123
+ "step": 140
124
+ },
125
+ {
126
+ "epoch": 0.2289857837992558,
127
+ "grad_norm": 0.6232007145881653,
128
+ "learning_rate": 4.573170731707318e-05,
129
+ "loss": 0.0541,
130
+ "step": 150
131
+ },
132
+ {
133
+ "epoch": 0.2289857837992558,
134
+ "eval_loss": 0.059219248592853546,
135
+ "eval_runtime": 158.6529,
136
+ "eval_samples_per_second": 7.343,
137
+ "eval_steps_per_second": 7.343,
138
+ "step": 150
139
+ },
140
+ {
141
+ "epoch": 0.24425150271920618,
142
+ "grad_norm": 0.6613311767578125,
143
+ "learning_rate": 4.878048780487805e-05,
144
+ "loss": 0.066,
145
+ "step": 160
146
+ },
147
+ {
148
+ "epoch": 0.2595172216391566,
149
+ "grad_norm": 1.2490918636322021,
150
+ "learning_rate": 5.182926829268293e-05,
151
+ "loss": 0.0751,
152
+ "step": 170
153
+ },
154
+ {
155
+ "epoch": 0.27478294055910696,
156
+ "grad_norm": 0.5701612234115601,
157
+ "learning_rate": 5.487804878048781e-05,
158
+ "loss": 0.0772,
159
+ "step": 180
160
+ },
161
+ {
162
+ "epoch": 0.29004865947905734,
163
+ "grad_norm": 0.8585615754127502,
164
+ "learning_rate": 5.792682926829268e-05,
165
+ "loss": 0.0687,
166
+ "step": 190
167
+ },
168
+ {
169
+ "epoch": 0.3053143783990077,
170
+ "grad_norm": 0.5563382506370544,
171
+ "learning_rate": 6.097560975609756e-05,
172
+ "loss": 0.0502,
173
+ "step": 200
174
+ },
175
+ {
176
+ "epoch": 0.3053143783990077,
177
+ "eval_loss": 0.05221959203481674,
178
+ "eval_runtime": 158.6341,
179
+ "eval_samples_per_second": 7.344,
180
+ "eval_steps_per_second": 7.344,
181
+ "step": 200
182
+ },
183
+ {
184
+ "epoch": 0.3205800973189581,
185
+ "grad_norm": 0.6384761929512024,
186
+ "learning_rate": 6.402439024390244e-05,
187
+ "loss": 0.0572,
188
+ "step": 210
189
+ },
190
+ {
191
+ "epoch": 0.3358458162389085,
192
+ "grad_norm": 0.5302607417106628,
193
+ "learning_rate": 6.707317073170732e-05,
194
+ "loss": 0.0493,
195
+ "step": 220
196
+ },
197
+ {
198
+ "epoch": 0.3511115351588589,
199
+ "grad_norm": 0.7148872017860413,
200
+ "learning_rate": 7.012195121951219e-05,
201
+ "loss": 0.0421,
202
+ "step": 230
203
+ },
204
+ {
205
+ "epoch": 0.3663772540788093,
206
+ "grad_norm": 0.6102215051651001,
207
+ "learning_rate": 7.317073170731707e-05,
208
+ "loss": 0.0603,
209
+ "step": 240
210
+ },
211
+ {
212
+ "epoch": 0.38164297299875966,
213
+ "grad_norm": 0.552837610244751,
214
+ "learning_rate": 7.621951219512195e-05,
215
+ "loss": 0.0666,
216
+ "step": 250
217
+ },
218
+ {
219
+ "epoch": 0.38164297299875966,
220
+ "eval_loss": 0.05392138659954071,
221
+ "eval_runtime": 158.5738,
222
+ "eval_samples_per_second": 7.347,
223
+ "eval_steps_per_second": 7.347,
224
+ "step": 250
225
+ },
226
+ {
227
+ "epoch": 0.39690869191871003,
228
+ "grad_norm": 0.6186545491218567,
229
+ "learning_rate": 7.926829268292683e-05,
230
+ "loss": 0.0653,
231
+ "step": 260
232
+ },
233
+ {
234
+ "epoch": 0.4121744108386604,
235
+ "grad_norm": 0.5888819098472595,
236
+ "learning_rate": 8.231707317073171e-05,
237
+ "loss": 0.0563,
238
+ "step": 270
239
+ },
240
+ {
241
+ "epoch": 0.42744012975861084,
242
+ "grad_norm": 0.36493584513664246,
243
+ "learning_rate": 8.53658536585366e-05,
244
+ "loss": 0.0576,
245
+ "step": 280
246
+ },
247
+ {
248
+ "epoch": 0.4427058486785612,
249
+ "grad_norm": 0.506234347820282,
250
+ "learning_rate": 8.841463414634147e-05,
251
+ "loss": 0.0602,
252
+ "step": 290
253
+ },
254
+ {
255
+ "epoch": 0.4579715675985116,
256
+ "grad_norm": 0.5001620650291443,
257
+ "learning_rate": 9.146341463414635e-05,
258
+ "loss": 0.046,
259
+ "step": 300
260
+ },
261
+ {
262
+ "epoch": 0.4579715675985116,
263
+ "eval_loss": 0.049273185431957245,
264
+ "eval_runtime": 158.5042,
265
+ "eval_samples_per_second": 7.35,
266
+ "eval_steps_per_second": 7.35,
267
+ "step": 300
268
+ },
269
+ {
270
+ "epoch": 0.473237286518462,
271
+ "grad_norm": 0.56379634141922,
272
+ "learning_rate": 9.451219512195122e-05,
273
+ "loss": 0.0649,
274
+ "step": 310
275
+ },
276
+ {
277
+ "epoch": 0.48850300543841235,
278
+ "grad_norm": 0.4352799355983734,
279
+ "learning_rate": 9.75609756097561e-05,
280
+ "loss": 0.0436,
281
+ "step": 320
282
+ },
283
+ {
284
+ "epoch": 0.5037687243583627,
285
+ "grad_norm": 0.6286426186561584,
286
+ "learning_rate": 9.999988635788465e-05,
287
+ "loss": 0.0507,
288
+ "step": 330
289
+ },
290
+ {
291
+ "epoch": 0.5190344432783132,
292
+ "grad_norm": 0.7499465346336365,
293
+ "learning_rate": 9.999590893808788e-05,
294
+ "loss": 0.0449,
295
+ "step": 340
296
+ },
297
+ {
298
+ "epoch": 0.5343001621982635,
299
+ "grad_norm": 0.6524621248245239,
300
+ "learning_rate": 9.998624992909386e-05,
301
+ "loss": 0.0458,
302
+ "step": 350
303
+ },
304
+ {
305
+ "epoch": 0.5343001621982635,
306
+ "eval_loss": 0.05271424353122711,
307
+ "eval_runtime": 158.5134,
308
+ "eval_samples_per_second": 7.35,
309
+ "eval_steps_per_second": 7.35,
310
+ "step": 350
311
+ },
312
+ {
313
+ "epoch": 0.5495658811182139,
314
+ "grad_norm": 0.3585219979286194,
315
+ "learning_rate": 9.997091042856284e-05,
316
+ "loss": 0.0488,
317
+ "step": 360
318
+ },
319
+ {
320
+ "epoch": 0.5648316000381643,
321
+ "grad_norm": 0.2826538681983948,
322
+ "learning_rate": 9.994989217969224e-05,
323
+ "loss": 0.0646,
324
+ "step": 370
325
+ },
326
+ {
327
+ "epoch": 0.5800973189581147,
328
+ "grad_norm": 1.2497502565383911,
329
+ "learning_rate": 9.992319757101863e-05,
330
+ "loss": 0.0588,
331
+ "step": 380
332
+ },
333
+ {
334
+ "epoch": 0.5953630378780651,
335
+ "grad_norm": 0.4816202223300934,
336
+ "learning_rate": 9.98908296361462e-05,
337
+ "loss": 0.0586,
338
+ "step": 390
339
+ },
340
+ {
341
+ "epoch": 0.6106287567980154,
342
+ "grad_norm": 0.349490225315094,
343
+ "learning_rate": 9.98527920534021e-05,
344
+ "loss": 0.0448,
345
+ "step": 400
346
+ },
347
+ {
348
+ "epoch": 0.6106287567980154,
349
+ "eval_loss": 0.048783060163259506,
350
+ "eval_runtime": 157.7617,
351
+ "eval_samples_per_second": 7.385,
352
+ "eval_steps_per_second": 7.385,
353
+ "step": 400
354
+ },
355
+ {
356
+ "epoch": 0.6258944757179659,
357
+ "grad_norm": 0.6848151683807373,
358
+ "learning_rate": 9.980908914541844e-05,
359
+ "loss": 0.054,
360
+ "step": 410
361
+ },
362
+ {
363
+ "epoch": 0.6411601946379162,
364
+ "grad_norm": 0.5100162625312805,
365
+ "learning_rate": 9.975972587864095e-05,
366
+ "loss": 0.0506,
367
+ "step": 420
368
+ },
369
+ {
370
+ "epoch": 0.6564259135578666,
371
+ "grad_norm": 0.41106978058815,
372
+ "learning_rate": 9.970470786276467e-05,
373
+ "loss": 0.0369,
374
+ "step": 430
375
+ },
376
+ {
377
+ "epoch": 0.671691632477817,
378
+ "grad_norm": 0.29269176721572876,
379
+ "learning_rate": 9.964404135009648e-05,
380
+ "loss": 0.0527,
381
+ "step": 440
382
+ },
383
+ {
384
+ "epoch": 0.6869573513977674,
385
+ "grad_norm": 0.23321561515331268,
386
+ "learning_rate": 9.957773323484454e-05,
387
+ "loss": 0.0567,
388
+ "step": 450
389
+ },
390
+ {
391
+ "epoch": 0.6869573513977674,
392
+ "eval_loss": 0.04618264362215996,
393
+ "eval_runtime": 157.632,
394
+ "eval_samples_per_second": 7.391,
395
+ "eval_steps_per_second": 7.391,
396
+ "step": 450
397
+ },
398
+ {
399
+ "epoch": 0.7022230703177178,
400
+ "grad_norm": 0.22461284697055817,
401
+ "learning_rate": 9.950579105233483e-05,
402
+ "loss": 0.04,
403
+ "step": 460
404
+ },
405
+ {
406
+ "epoch": 0.7174887892376681,
407
+ "grad_norm": 0.41304975748062134,
408
+ "learning_rate": 9.94282229781548e-05,
409
+ "loss": 0.0383,
410
+ "step": 470
411
+ },
412
+ {
413
+ "epoch": 0.7327545081576186,
414
+ "grad_norm": 0.8002622723579407,
415
+ "learning_rate": 9.934503782722438e-05,
416
+ "loss": 0.0495,
417
+ "step": 480
418
+ },
419
+ {
420
+ "epoch": 0.748020227077569,
421
+ "grad_norm": 0.27543845772743225,
422
+ "learning_rate": 9.925624505279411e-05,
423
+ "loss": 0.0379,
424
+ "step": 490
425
+ },
426
+ {
427
+ "epoch": 0.7632859459975193,
428
+ "grad_norm": 0.19786208868026733,
429
+ "learning_rate": 9.916185474537098e-05,
430
+ "loss": 0.0358,
431
+ "step": 500
432
+ },
433
+ {
434
+ "epoch": 0.7632859459975193,
435
+ "eval_loss": 0.04097205400466919,
436
+ "eval_runtime": 157.5197,
437
+ "eval_samples_per_second": 7.396,
438
+ "eval_steps_per_second": 7.396,
439
+ "step": 500
440
+ },
441
+ {
442
+ "epoch": 0.7785516649174697,
443
+ "grad_norm": 0.7004953622817993,
444
+ "learning_rate": 9.906187763157168e-05,
445
+ "loss": 0.0508,
446
+ "step": 510
447
+ },
448
+ {
449
+ "epoch": 0.7938173838374201,
450
+ "grad_norm": 0.28915488719940186,
451
+ "learning_rate": 9.895632507290362e-05,
452
+ "loss": 0.05,
453
+ "step": 520
454
+ },
455
+ {
456
+ "epoch": 0.8090831027573705,
457
+ "grad_norm": 0.38373371958732605,
458
+ "learning_rate": 9.884520906447379e-05,
459
+ "loss": 0.0376,
460
+ "step": 530
461
+ },
462
+ {
463
+ "epoch": 0.8243488216773208,
464
+ "grad_norm": 0.5942443609237671,
465
+ "learning_rate": 9.872854223362562e-05,
466
+ "loss": 0.0482,
467
+ "step": 540
468
+ },
469
+ {
470
+ "epoch": 0.8396145405972713,
471
+ "grad_norm": 0.44209200143814087,
472
+ "learning_rate": 9.860633783850406e-05,
473
+ "loss": 0.0445,
474
+ "step": 550
475
+ },
476
+ {
477
+ "epoch": 0.8396145405972713,
478
+ "eval_loss": 0.04072929546236992,
479
+ "eval_runtime": 157.4739,
480
+ "eval_samples_per_second": 7.398,
481
+ "eval_steps_per_second": 7.398,
482
+ "step": 550
483
+ },
484
+ {
485
+ "epoch": 0.8548802595172217,
486
+ "grad_norm": 0.14016468822956085,
487
+ "learning_rate": 9.847860976654879e-05,
488
+ "loss": 0.0501,
489
+ "step": 560
490
+ },
491
+ {
492
+ "epoch": 0.870145978437172,
493
+ "grad_norm": 0.32843533158302307,
494
+ "learning_rate": 9.834537253291616e-05,
495
+ "loss": 0.0401,
496
+ "step": 570
497
+ },
498
+ {
499
+ "epoch": 0.8854116973571224,
500
+ "grad_norm": 0.7663369178771973,
501
+ "learning_rate": 9.820664127882957e-05,
502
+ "loss": 0.0582,
503
+ "step": 580
504
+ },
505
+ {
506
+ "epoch": 0.9006774162770728,
507
+ "grad_norm": 0.40339088439941406,
508
+ "learning_rate": 9.806243176985888e-05,
509
+ "loss": 0.0494,
510
+ "step": 590
511
+ },
512
+ {
513
+ "epoch": 0.9159431351970232,
514
+ "grad_norm": 0.4325726628303528,
515
+ "learning_rate": 9.791276039412875e-05,
516
+ "loss": 0.0462,
517
+ "step": 600
518
+ },
519
+ {
520
+ "epoch": 0.9159431351970232,
521
+ "eval_loss": 0.040742386132478714,
522
+ "eval_runtime": 157.4061,
523
+ "eval_samples_per_second": 7.401,
524
+ "eval_steps_per_second": 7.401,
525
+ "step": 600
526
+ },
527
+ {
528
+ "epoch": 0.9312088541169735,
529
+ "grad_norm": 0.39752867817878723,
530
+ "learning_rate": 9.775764416045628e-05,
531
+ "loss": 0.0595,
532
+ "step": 610
533
+ },
534
+ {
535
+ "epoch": 0.946474573036924,
536
+ "grad_norm": 0.37356245517730713,
537
+ "learning_rate": 9.759710069641814e-05,
538
+ "loss": 0.0463,
539
+ "step": 620
540
+ },
541
+ {
542
+ "epoch": 0.9617402919568744,
543
+ "grad_norm": 0.3723120391368866,
544
+ "learning_rate": 9.743114824634734e-05,
545
+ "loss": 0.033,
546
+ "step": 630
547
+ },
548
+ {
549
+ "epoch": 0.9770060108768247,
550
+ "grad_norm": 0.4107719659805298,
551
+ "learning_rate": 9.725980566925989e-05,
552
+ "loss": 0.0497,
553
+ "step": 640
554
+ },
555
+ {
556
+ "epoch": 0.9922717297967751,
557
+ "grad_norm": 0.31700581312179565,
558
+ "learning_rate": 9.708309243671165e-05,
559
+ "loss": 0.0363,
560
+ "step": 650
561
+ },
562
+ {
563
+ "epoch": 0.9922717297967751,
564
+ "eval_loss": 0.040968675166368484,
565
+ "eval_runtime": 157.3806,
566
+ "eval_samples_per_second": 7.402,
567
+ "eval_steps_per_second": 7.402,
568
+ "step": 650
569
+ },
570
+ {
571
+ "epoch": 1.0075374487167255,
572
+ "grad_norm": 0.18884813785552979,
573
+ "learning_rate": 9.690102863058563e-05,
574
+ "loss": 0.0343,
575
+ "step": 660
576
+ },
577
+ {
578
+ "epoch": 1.0228031676366758,
579
+ "grad_norm": 0.3541209399700165,
580
+ "learning_rate": 9.67136349408098e-05,
581
+ "loss": 0.0333,
582
+ "step": 670
583
+ },
584
+ {
585
+ "epoch": 1.0380688865566263,
586
+ "grad_norm": 0.17939338088035583,
587
+ "learning_rate": 9.652093266300583e-05,
588
+ "loss": 0.0401,
589
+ "step": 680
590
+ },
591
+ {
592
+ "epoch": 1.0533346054765766,
593
+ "grad_norm": 0.20926208794116974,
594
+ "learning_rate": 9.632294369606916e-05,
595
+ "loss": 0.0271,
596
+ "step": 690
597
+ },
598
+ {
599
+ "epoch": 1.068600324396527,
600
+ "grad_norm": 0.2087617814540863,
601
+ "learning_rate": 9.61196905396802e-05,
602
+ "loss": 0.0343,
603
+ "step": 700
604
+ },
605
+ {
606
+ "epoch": 1.068600324396527,
607
+ "eval_loss": 0.03695390745997429,
608
+ "eval_runtime": 157.4136,
609
+ "eval_samples_per_second": 7.401,
610
+ "eval_steps_per_second": 7.401,
611
+ "step": 700
612
+ },
613
+ {
614
+ "epoch": 1.0838660433164775,
615
+ "grad_norm": 0.46884167194366455,
616
+ "learning_rate": 9.591119629174764e-05,
617
+ "loss": 0.0442,
618
+ "step": 710
619
+ },
620
+ {
621
+ "epoch": 1.0991317622364278,
622
+ "grad_norm": 0.2890946865081787,
623
+ "learning_rate": 9.569748464578343e-05,
624
+ "loss": 0.0288,
625
+ "step": 720
626
+ },
627
+ {
628
+ "epoch": 1.1143974811563782,
629
+ "grad_norm": 0.20250333845615387,
630
+ "learning_rate": 9.54785798882103e-05,
631
+ "loss": 0.0273,
632
+ "step": 730
633
+ },
634
+ {
635
+ "epoch": 1.1296632000763287,
636
+ "grad_norm": 0.26456066966056824,
637
+ "learning_rate": 9.525450689560181e-05,
638
+ "loss": 0.0378,
639
+ "step": 740
640
+ },
641
+ {
642
+ "epoch": 1.144928918996279,
643
+ "grad_norm": 0.3689366281032562,
644
+ "learning_rate": 9.502529113185532e-05,
645
+ "loss": 0.0413,
646
+ "step": 750
647
+ },
648
+ {
649
+ "epoch": 1.144928918996279,
650
+ "eval_loss": 0.03775772452354431,
651
+ "eval_runtime": 157.6202,
652
+ "eval_samples_per_second": 7.391,
653
+ "eval_steps_per_second": 7.391,
654
+ "step": 750
655
+ },
656
+ {
657
+ "epoch": 1.1601946379162293,
658
+ "grad_norm": 0.21495144069194794,
659
+ "learning_rate": 9.479095864529828e-05,
660
+ "loss": 0.0308,
661
+ "step": 760
662
+ },
663
+ {
664
+ "epoch": 1.1754603568361797,
665
+ "grad_norm": 0.17624302208423615,
666
+ "learning_rate": 9.455153606572806e-05,
667
+ "loss": 0.0316,
668
+ "step": 770
669
+ },
670
+ {
671
+ "epoch": 1.1907260757561302,
672
+ "grad_norm": 0.26850008964538574,
673
+ "learning_rate": 9.430705060138569e-05,
674
+ "loss": 0.0348,
675
+ "step": 780
676
+ },
677
+ {
678
+ "epoch": 1.2059917946760805,
679
+ "grad_norm": 0.633297860622406,
680
+ "learning_rate": 9.405753003586395e-05,
681
+ "loss": 0.0277,
682
+ "step": 790
683
+ },
684
+ {
685
+ "epoch": 1.2212575135960309,
686
+ "grad_norm": 0.2546226978302002,
687
+ "learning_rate": 9.38030027249499e-05,
688
+ "loss": 0.0322,
689
+ "step": 800
690
+ },
691
+ {
692
+ "epoch": 1.2212575135960309,
693
+ "eval_loss": 0.03979082778096199,
694
+ "eval_runtime": 157.5322,
695
+ "eval_samples_per_second": 7.395,
696
+ "eval_steps_per_second": 7.395,
697
+ "step": 800
698
+ },
699
+ {
700
+ "epoch": 1.2365232325159814,
701
+ "grad_norm": 0.3185233175754547,
702
+ "learning_rate": 9.354349759340263e-05,
703
+ "loss": 0.0372,
704
+ "step": 810
705
+ },
706
+ {
707
+ "epoch": 1.2517889514359317,
708
+ "grad_norm": 0.32911208271980286,
709
+ "learning_rate": 9.327904413166615e-05,
710
+ "loss": 0.0338,
711
+ "step": 820
712
+ },
713
+ {
714
+ "epoch": 1.267054670355882,
715
+ "grad_norm": 0.5364266037940979,
716
+ "learning_rate": 9.300967239251798e-05,
717
+ "loss": 0.0405,
718
+ "step": 830
719
+ },
720
+ {
721
+ "epoch": 1.2823203892758324,
722
+ "grad_norm": 0.1836143583059311,
723
+ "learning_rate": 9.27354129876541e-05,
724
+ "loss": 0.0348,
725
+ "step": 840
726
+ },
727
+ {
728
+ "epoch": 1.297586108195783,
729
+ "grad_norm": 0.18749667704105377,
730
+ "learning_rate": 9.245629708421008e-05,
731
+ "loss": 0.0342,
732
+ "step": 850
733
+ },
734
+ {
735
+ "epoch": 1.297586108195783,
736
+ "eval_loss": 0.03846587613224983,
737
+ "eval_runtime": 157.7572,
738
+ "eval_samples_per_second": 7.385,
739
+ "eval_steps_per_second": 7.385,
740
+ "step": 850
741
+ },
742
+ {
743
+ "epoch": 1.3128518271157332,
744
+ "grad_norm": 0.473058819770813,
745
+ "learning_rate": 9.217235640121926e-05,
746
+ "loss": 0.0379,
747
+ "step": 860
748
+ },
749
+ {
750
+ "epoch": 1.3281175460356835,
751
+ "grad_norm": 0.5135864019393921,
752
+ "learning_rate": 9.188362320600812e-05,
753
+ "loss": 0.0425,
754
+ "step": 870
755
+ },
756
+ {
757
+ "epoch": 1.343383264955634,
758
+ "grad_norm": 0.46343910694122314,
759
+ "learning_rate": 9.159013031052943e-05,
760
+ "loss": 0.0324,
761
+ "step": 880
762
+ },
763
+ {
764
+ "epoch": 1.3586489838755844,
765
+ "grad_norm": 0.3623945116996765,
766
+ "learning_rate": 9.129191106763346e-05,
767
+ "loss": 0.0342,
768
+ "step": 890
769
+ },
770
+ {
771
+ "epoch": 1.3739147027955347,
772
+ "grad_norm": 0.3033890724182129,
773
+ "learning_rate": 9.098899936727771e-05,
774
+ "loss": 0.0337,
775
+ "step": 900
776
+ },
777
+ {
778
+ "epoch": 1.3739147027955347,
779
+ "eval_loss": 0.043599650263786316,
780
+ "eval_runtime": 157.7841,
781
+ "eval_samples_per_second": 7.384,
782
+ "eval_steps_per_second": 7.384,
783
+ "step": 900
784
+ },
785
+ {
786
+ "epoch": 1.3891804217154853,
787
+ "grad_norm": 0.4166663587093353,
788
+ "learning_rate": 9.068142963267558e-05,
789
+ "loss": 0.029,
790
+ "step": 910
791
+ },
792
+ {
793
+ "epoch": 1.4044461406354356,
794
+ "grad_norm": 0.273224413394928,
795
+ "learning_rate": 9.036923681638463e-05,
796
+ "loss": 0.0337,
797
+ "step": 920
798
+ },
799
+ {
800
+ "epoch": 1.419711859555386,
801
+ "grad_norm": 0.2528637647628784,
802
+ "learning_rate": 9.00524563963343e-05,
803
+ "loss": 0.0269,
804
+ "step": 930
805
+ },
806
+ {
807
+ "epoch": 1.4349775784753362,
808
+ "grad_norm": 0.3691759407520294,
809
+ "learning_rate": 8.973112437179436e-05,
810
+ "loss": 0.0372,
811
+ "step": 940
812
+ },
813
+ {
814
+ "epoch": 1.4502432973952868,
815
+ "grad_norm": 0.30305129289627075,
816
+ "learning_rate": 8.940527725928383e-05,
817
+ "loss": 0.0295,
818
+ "step": 950
819
+ },
820
+ {
821
+ "epoch": 1.4502432973952868,
822
+ "eval_loss": 0.037314947694540024,
823
+ "eval_runtime": 157.8345,
824
+ "eval_samples_per_second": 7.381,
825
+ "eval_steps_per_second": 7.381,
826
+ "step": 950
827
+ },
828
+ {
829
+ "epoch": 1.4655090163152371,
830
+ "grad_norm": 0.26650476455688477,
831
+ "learning_rate": 8.90749520884212e-05,
832
+ "loss": 0.0324,
833
+ "step": 960
834
+ },
835
+ {
836
+ "epoch": 1.4807747352351874,
837
+ "grad_norm": 0.34022459387779236,
838
+ "learning_rate": 8.874018639771637e-05,
839
+ "loss": 0.0357,
840
+ "step": 970
841
+ },
842
+ {
843
+ "epoch": 1.4960404541551378,
844
+ "grad_norm": 0.22096742689609528,
845
+ "learning_rate": 8.840101823030471e-05,
846
+ "loss": 0.0276,
847
+ "step": 980
848
+ },
849
+ {
850
+ "epoch": 1.5113061730750883,
851
+ "grad_norm": 0.3219353258609772,
852
+ "learning_rate": 8.805748612962382e-05,
853
+ "loss": 0.0381,
854
+ "step": 990
855
+ },
856
+ {
857
+ "epoch": 1.5265718919950386,
858
+ "grad_norm": 0.12673026323318481,
859
+ "learning_rate": 8.77096291350334e-05,
860
+ "loss": 0.0267,
861
+ "step": 1000
862
+ },
863
+ {
864
+ "epoch": 1.5265718919950386,
865
+ "eval_loss": 0.03864908590912819,
866
+ "eval_runtime": 158.4803,
867
+ "eval_samples_per_second": 7.351,
868
+ "eval_steps_per_second": 7.351,
869
+ "step": 1000
870
+ },
871
+ {
872
+ "epoch": 1.541837610914989,
873
+ "grad_norm": 0.2603205442428589,
874
+ "learning_rate": 8.735748677737874e-05,
875
+ "loss": 0.0346,
876
+ "step": 1010
877
+ },
878
+ {
879
+ "epoch": 1.5571033298349395,
880
+ "grad_norm": 0.3782278001308441,
881
+ "learning_rate": 8.700109907449845e-05,
882
+ "loss": 0.0296,
883
+ "step": 1020
884
+ },
885
+ {
886
+ "epoch": 1.5723690487548898,
887
+ "grad_norm": 0.18346253037452698,
888
+ "learning_rate": 8.66405065266768e-05,
889
+ "loss": 0.0311,
890
+ "step": 1030
891
+ },
892
+ {
893
+ "epoch": 1.5876347676748401,
894
+ "grad_norm": 0.20292475819587708,
895
+ "learning_rate": 8.627575011204115e-05,
896
+ "loss": 0.0281,
897
+ "step": 1040
898
+ },
899
+ {
900
+ "epoch": 1.6029004865947907,
901
+ "grad_norm": 0.17125393450260162,
902
+ "learning_rate": 8.590687128190516e-05,
903
+ "loss": 0.0287,
904
+ "step": 1050
905
+ },
906
+ {
907
+ "epoch": 1.6029004865947907,
908
+ "eval_loss": 0.03797018155455589,
909
+ "eval_runtime": 174.0303,
910
+ "eval_samples_per_second": 6.694,
911
+ "eval_steps_per_second": 6.694,
912
+ "step": 1050
913
+ },
914
+ {
915
+ "epoch": 1.618166205514741,
916
+ "grad_norm": 0.10430210083723068,
917
+ "learning_rate": 8.553391195605833e-05,
918
+ "loss": 0.0273,
919
+ "step": 1060
920
+ },
921
+ {
922
+ "epoch": 1.6334319244346913,
923
+ "grad_norm": 0.5334872007369995,
924
+ "learning_rate": 8.515691451800205e-05,
925
+ "loss": 0.0469,
926
+ "step": 1070
927
+ },
928
+ {
929
+ "epoch": 1.6486976433546419,
930
+ "grad_norm": 0.2953313887119293,
931
+ "learning_rate": 8.477592181013316e-05,
932
+ "loss": 0.0291,
933
+ "step": 1080
934
+ },
935
+ {
936
+ "epoch": 1.663963362274592,
937
+ "grad_norm": 0.19991376996040344,
938
+ "learning_rate": 8.439097712887531e-05,
939
+ "loss": 0.0297,
940
+ "step": 1090
941
+ },
942
+ {
943
+ "epoch": 1.6792290811945425,
944
+ "grad_norm": 0.37268176674842834,
945
+ "learning_rate": 8.400212421975865e-05,
946
+ "loss": 0.0504,
947
+ "step": 1100
948
+ },
949
+ {
950
+ "epoch": 1.6792290811945425,
951
+ "eval_loss": 0.03881072625517845,
952
+ "eval_runtime": 175.3493,
953
+ "eval_samples_per_second": 6.644,
954
+ "eval_steps_per_second": 6.644,
955
+ "step": 1100
956
+ },
957
+ {
958
+ "epoch": 1.694494800114493,
959
+ "grad_norm": 0.2996631860733032,
960
+ "learning_rate": 8.360940727244859e-05,
961
+ "loss": 0.0418,
962
+ "step": 1110
963
+ },
964
+ {
965
+ "epoch": 1.7097605190344431,
966
+ "grad_norm": 0.2608354687690735,
967
+ "learning_rate": 8.321287091572403e-05,
968
+ "loss": 0.0285,
969
+ "step": 1120
970
+ },
971
+ {
972
+ "epoch": 1.7250262379543937,
973
+ "grad_norm": 0.45164602994918823,
974
+ "learning_rate": 8.281256021240566e-05,
975
+ "loss": 0.0299,
976
+ "step": 1130
977
+ },
978
+ {
979
+ "epoch": 1.740291956874344,
980
+ "grad_norm": 0.21513421833515167,
981
+ "learning_rate": 8.240852065423506e-05,
982
+ "loss": 0.0384,
983
+ "step": 1140
984
+ },
985
+ {
986
+ "epoch": 1.7555576757942943,
987
+ "grad_norm": 0.2836594879627228,
988
+ "learning_rate": 8.20007981567048e-05,
989
+ "loss": 0.0317,
990
+ "step": 1150
991
+ },
992
+ {
993
+ "epoch": 1.7555576757942943,
994
+ "eval_loss": 0.03912714123725891,
995
+ "eval_runtime": 176.2466,
996
+ "eval_samples_per_second": 6.61,
997
+ "eval_steps_per_second": 6.61,
998
+ "step": 1150
999
+ },
1000
+ {
1001
+ "epoch": 1.7708233947142449,
1002
+ "grad_norm": 0.25921815633773804,
1003
+ "learning_rate": 8.158943905384082e-05,
1004
+ "loss": 0.0384,
1005
+ "step": 1160
1006
+ },
1007
+ {
1008
+ "epoch": 1.7860891136341952,
1009
+ "grad_norm": 0.18497350811958313,
1010
+ "learning_rate": 8.117449009293668e-05,
1011
+ "loss": 0.0305,
1012
+ "step": 1170
1013
+ },
1014
+ {
1015
+ "epoch": 1.8013548325541455,
1016
+ "grad_norm": 0.16409793496131897,
1017
+ "learning_rate": 8.075599842924139e-05,
1018
+ "loss": 0.0306,
1019
+ "step": 1180
1020
+ },
1021
+ {
1022
+ "epoch": 1.816620551474096,
1023
+ "grad_norm": 0.16807886958122253,
1024
+ "learning_rate": 8.033401162060049e-05,
1025
+ "loss": 0.0361,
1026
+ "step": 1190
1027
+ },
1028
+ {
1029
+ "epoch": 1.8318862703940464,
1030
+ "grad_norm": 0.4135243594646454,
1031
+ "learning_rate": 7.990857762205157e-05,
1032
+ "loss": 0.0448,
1033
+ "step": 1200
1034
+ },
1035
+ {
1036
+ "epoch": 1.8318862703940464,
1037
+ "eval_loss": 0.03655826300382614,
1038
+ "eval_runtime": 176.7043,
1039
+ "eval_samples_per_second": 6.593,
1040
+ "eval_steps_per_second": 6.593,
1041
+ "step": 1200
1042
+ },
1043
+ {
1044
+ "epoch": 1.8471519893139967,
1045
+ "grad_norm": 0.28721022605895996,
1046
+ "learning_rate": 7.947974478037468e-05,
1047
+ "loss": 0.0378,
1048
+ "step": 1210
1049
+ },
1050
+ {
1051
+ "epoch": 1.8624177082339473,
1052
+ "grad_norm": 0.5347437262535095,
1053
+ "learning_rate": 7.904756182859797e-05,
1054
+ "loss": 0.0309,
1055
+ "step": 1220
1056
+ },
1057
+ {
1058
+ "epoch": 1.8776834271538976,
1059
+ "grad_norm": 0.10005893558263779,
1060
+ "learning_rate": 7.861207788045984e-05,
1061
+ "loss": 0.0318,
1062
+ "step": 1230
1063
+ },
1064
+ {
1065
+ "epoch": 1.892949146073848,
1066
+ "grad_norm": 0.355914443731308,
1067
+ "learning_rate": 7.817334242482738e-05,
1068
+ "loss": 0.0322,
1069
+ "step": 1240
1070
+ },
1071
+ {
1072
+ "epoch": 1.9082148649937984,
1073
+ "grad_norm": 0.1554553210735321,
1074
+ "learning_rate": 7.773140532007262e-05,
1075
+ "loss": 0.0278,
1076
+ "step": 1250
1077
+ },
1078
+ {
1079
+ "epoch": 1.9082148649937984,
1080
+ "eval_loss": 0.036195144057273865,
1081
+ "eval_runtime": 177.2966,
1082
+ "eval_samples_per_second": 6.571,
1083
+ "eval_steps_per_second": 6.571,
1084
+ "step": 1250
1085
+ },
1086
+ {
1087
+ "epoch": 1.9234805839137485,
1088
+ "grad_norm": 0.13769276440143585,
1089
+ "learning_rate": 7.728631678840638e-05,
1090
+ "loss": 0.0294,
1091
+ "step": 1260
1092
+ },
1093
+ {
1094
+ "epoch": 1.938746302833699,
1095
+ "grad_norm": 0.21283772587776184,
1096
+ "learning_rate": 7.683812741017112e-05,
1097
+ "loss": 0.0319,
1098
+ "step": 1270
1099
+ },
1100
+ {
1101
+ "epoch": 1.9540120217536494,
1102
+ "grad_norm": 0.5776203274726868,
1103
+ "learning_rate": 7.638688811809274e-05,
1104
+ "loss": 0.0388,
1105
+ "step": 1280
1106
+ },
1107
+ {
1108
+ "epoch": 1.9692777406735997,
1109
+ "grad_norm": 0.21127784252166748,
1110
+ "learning_rate": 7.593265019149275e-05,
1111
+ "loss": 0.0267,
1112
+ "step": 1290
1113
+ },
1114
+ {
1115
+ "epoch": 1.9845434595935503,
1116
+ "grad_norm": 0.4357820153236389,
1117
+ "learning_rate": 7.547546525046073e-05,
1118
+ "loss": 0.0347,
1119
+ "step": 1300
1120
+ },
1121
+ {
1122
+ "epoch": 1.9845434595935503,
1123
+ "eval_loss": 0.03436192870140076,
1124
+ "eval_runtime": 175.7034,
1125
+ "eval_samples_per_second": 6.63,
1126
+ "eval_steps_per_second": 6.63,
1127
+ "step": 1300
1128
+ },
1129
+ {
1130
+ "epoch": 1.9998091785135006,
1131
+ "grad_norm": 0.10159356147050858,
1132
+ "learning_rate": 7.501538524998812e-05,
1133
+ "loss": 0.0353,
1134
+ "step": 1310
1135
+ },
1136
+ {
1137
+ "epoch": 2.015074897433451,
1138
+ "grad_norm": 0.18945099413394928,
1139
+ "learning_rate": 7.455246247406406e-05,
1140
+ "loss": 0.0161,
1141
+ "step": 1320
1142
+ },
1143
+ {
1144
+ "epoch": 2.0303406163534015,
1145
+ "grad_norm": 0.3977908790111542,
1146
+ "learning_rate": 7.408674952973382e-05,
1147
+ "loss": 0.0256,
1148
+ "step": 1330
1149
+ },
1150
+ {
1151
+ "epoch": 2.0456063352733516,
1152
+ "grad_norm": 0.2554134428501129,
1153
+ "learning_rate": 7.361829934112036e-05,
1154
+ "loss": 0.0235,
1155
+ "step": 1340
1156
+ },
1157
+ {
1158
+ "epoch": 2.060872054193302,
1159
+ "grad_norm": 0.2563072144985199,
1160
+ "learning_rate": 7.314716514341006e-05,
1161
+ "loss": 0.0201,
1162
+ "step": 1350
1163
+ },
1164
+ {
1165
+ "epoch": 2.060872054193302,
1166
+ "eval_loss": 0.035528797656297684,
1167
+ "eval_runtime": 177.4606,
1168
+ "eval_samples_per_second": 6.565,
1169
+ "eval_steps_per_second": 6.565,
1170
+ "step": 1350
1171
+ },
1172
+ {
1173
+ "epoch": 2.0761377731132526,
1174
+ "grad_norm": 0.1881485879421234,
1175
+ "learning_rate": 7.267340047680305e-05,
1176
+ "loss": 0.0164,
1177
+ "step": 1360
1178
+ },
1179
+ {
1180
+ "epoch": 2.0914034920332027,
1181
+ "grad_norm": 0.29883432388305664,
1182
+ "learning_rate": 7.21970591804287e-05,
1183
+ "loss": 0.0182,
1184
+ "step": 1370
1185
+ },
1186
+ {
1187
+ "epoch": 2.1066692109531533,
1188
+ "grad_norm": 0.36703965067863464,
1189
+ "learning_rate": 7.171819538622747e-05,
1190
+ "loss": 0.0254,
1191
+ "step": 1380
1192
+ },
1193
+ {
1194
+ "epoch": 2.121934929873104,
1195
+ "grad_norm": 0.1899896115064621,
1196
+ "learning_rate": 7.123686351279914e-05,
1197
+ "loss": 0.0231,
1198
+ "step": 1390
1199
+ },
1200
+ {
1201
+ "epoch": 2.137200648793054,
1202
+ "grad_norm": 0.1549081802368164,
1203
+ "learning_rate": 7.07531182592187e-05,
1204
+ "loss": 0.0238,
1205
+ "step": 1400
1206
+ },
1207
+ {
1208
+ "epoch": 2.137200648793054,
1209
+ "eval_loss": 0.03574272617697716,
1210
+ "eval_runtime": 177.5378,
1211
+ "eval_samples_per_second": 6.562,
1212
+ "eval_steps_per_second": 6.562,
1213
+ "step": 1400
1214
+ },
1215
+ {
1216
+ "epoch": 2.1524663677130045,
1217
+ "grad_norm": 0.4319554567337036,
1218
+ "learning_rate": 7.026701459882026e-05,
1219
+ "loss": 0.0315,
1220
+ "step": 1410
1221
+ },
1222
+ {
1223
+ "epoch": 2.167732086632955,
1224
+ "grad_norm": 0.19883885979652405,
1225
+ "learning_rate": 6.977860777294988e-05,
1226
+ "loss": 0.0227,
1227
+ "step": 1420
1228
+ },
1229
+ {
1230
+ "epoch": 2.182997805552905,
1231
+ "grad_norm": 0.18116509914398193,
1232
+ "learning_rate": 6.92879532846878e-05,
1233
+ "loss": 0.0175,
1234
+ "step": 1430
1235
+ },
1236
+ {
1237
+ "epoch": 2.1982635244728557,
1238
+ "grad_norm": 0.43378233909606934,
1239
+ "learning_rate": 6.879510689254104e-05,
1240
+ "loss": 0.0187,
1241
+ "step": 1440
1242
+ },
1243
+ {
1244
+ "epoch": 2.213529243392806,
1245
+ "grad_norm": 0.3628329038619995,
1246
+ "learning_rate": 6.830012460410697e-05,
1247
+ "loss": 0.0299,
1248
+ "step": 1450
1249
+ },
1250
+ {
1251
+ "epoch": 2.213529243392806,
1252
+ "eval_loss": 0.037096813321113586,
1253
+ "eval_runtime": 176.5754,
1254
+ "eval_samples_per_second": 6.598,
1255
+ "eval_steps_per_second": 6.598,
1256
+ "step": 1450
1257
+ },
1258
+ {
1259
+ "epoch": 2.2287949623127563,
1260
+ "grad_norm": 0.28517764806747437,
1261
+ "learning_rate": 6.780306266970851e-05,
1262
+ "loss": 0.017,
1263
+ "step": 1460
1264
+ },
1265
+ {
1266
+ "epoch": 2.244060681232707,
1267
+ "grad_norm": 0.3066461682319641,
1268
+ "learning_rate": 6.73039775760018e-05,
1269
+ "loss": 0.0209,
1270
+ "step": 1470
1271
+ },
1272
+ {
1273
+ "epoch": 2.2593264001526574,
1274
+ "grad_norm": 0.22259260714054108,
1275
+ "learning_rate": 6.680292603955702e-05,
1276
+ "loss": 0.0201,
1277
+ "step": 1480
1278
+ },
1279
+ {
1280
+ "epoch": 2.2745921190726075,
1281
+ "grad_norm": 0.6137614846229553,
1282
+ "learning_rate": 6.629996500041299e-05,
1283
+ "loss": 0.022,
1284
+ "step": 1490
1285
+ },
1286
+ {
1287
+ "epoch": 2.289857837992558,
1288
+ "grad_norm": 0.11755680292844772,
1289
+ "learning_rate": 6.579515161560649e-05,
1290
+ "loss": 0.0155,
1291
+ "step": 1500
1292
+ },
1293
+ {
1294
+ "epoch": 2.289857837992558,
1295
+ "eval_loss": 0.038406338542699814,
1296
+ "eval_runtime": 175.5413,
1297
+ "eval_samples_per_second": 6.637,
1298
+ "eval_steps_per_second": 6.637,
1299
+ "step": 1500
1300
+ },
1301
+ {
1302
+ "epoch": 2.305123556912508,
1303
+ "grad_norm": 0.2847287058830261,
1304
+ "learning_rate": 6.528854325267692e-05,
1305
+ "loss": 0.0268,
1306
+ "step": 1510
1307
+ },
1308
+ {
1309
+ "epoch": 2.3203892758324587,
1310
+ "grad_norm": 0.412030965089798,
1311
+ "learning_rate": 6.478019748314686e-05,
1312
+ "loss": 0.0213,
1313
+ "step": 1520
1314
+ },
1315
+ {
1316
+ "epoch": 2.3356549947524092,
1317
+ "grad_norm": 0.31995999813079834,
1318
+ "learning_rate": 6.42701720759797e-05,
1319
+ "loss": 0.0238,
1320
+ "step": 1530
1321
+ },
1322
+ {
1323
+ "epoch": 2.3509207136723593,
1324
+ "grad_norm": 0.2422753870487213,
1325
+ "learning_rate": 6.375852499101467e-05,
1326
+ "loss": 0.019,
1327
+ "step": 1540
1328
+ },
1329
+ {
1330
+ "epoch": 2.36618643259231,
1331
+ "grad_norm": 0.10162404924631119,
1332
+ "learning_rate": 6.324531437238019e-05,
1333
+ "loss": 0.0157,
1334
+ "step": 1550
1335
+ },
1336
+ {
1337
+ "epoch": 2.36618643259231,
1338
+ "eval_loss": 0.03914285823702812,
1339
+ "eval_runtime": 174.6144,
1340
+ "eval_samples_per_second": 6.672,
1341
+ "eval_steps_per_second": 6.672,
1342
+ "step": 1550
1343
+ },
1344
+ {
1345
+ "epoch": 2.3814521515122604,
1346
+ "grad_norm": 0.27880334854125977,
1347
+ "learning_rate": 6.273059854188636e-05,
1348
+ "loss": 0.025,
1349
+ "step": 1560
1350
+ },
1351
+ {
1352
+ "epoch": 2.3967178704322105,
1353
+ "grad_norm": 0.4933589994907379,
1354
+ "learning_rate": 6.221443599239721e-05,
1355
+ "loss": 0.0242,
1356
+ "step": 1570
1357
+ },
1358
+ {
1359
+ "epoch": 2.411983589352161,
1360
+ "grad_norm": 0.5834177136421204,
1361
+ "learning_rate": 6.169688538118342e-05,
1362
+ "loss": 0.028,
1363
+ "step": 1580
1364
+ },
1365
+ {
1366
+ "epoch": 2.4272493082721116,
1367
+ "grad_norm": 0.4436355233192444,
1368
+ "learning_rate": 6.117800552325655e-05,
1369
+ "loss": 0.0232,
1370
+ "step": 1590
1371
+ },
1372
+ {
1373
+ "epoch": 2.4425150271920617,
1374
+ "grad_norm": 0.19233737885951996,
1375
+ "learning_rate": 6.06578553846852e-05,
1376
+ "loss": 0.0222,
1377
+ "step": 1600
1378
+ },
1379
+ {
1380
+ "epoch": 2.4425150271920617,
1381
+ "eval_loss": 0.03701253607869148,
1382
+ "eval_runtime": 175.2711,
1383
+ "eval_samples_per_second": 6.647,
1384
+ "eval_steps_per_second": 6.647,
1385
+ "step": 1600
1386
+ },
1387
+ {
1388
+ "epoch": 2.4577807461120122,
1389
+ "grad_norm": 0.22640623152256012,
1390
+ "learning_rate": 6.013649407589401e-05,
1391
+ "loss": 0.0228,
1392
+ "step": 1610
1393
+ },
1394
+ {
1395
+ "epoch": 2.473046465031963,
1396
+ "grad_norm": 0.19025041162967682,
1397
+ "learning_rate": 5.961398084494634e-05,
1398
+ "loss": 0.0246,
1399
+ "step": 1620
1400
+ },
1401
+ {
1402
+ "epoch": 2.488312183951913,
1403
+ "grad_norm": 0.5301237106323242,
1404
+ "learning_rate": 5.909037507081121e-05,
1405
+ "loss": 0.0283,
1406
+ "step": 1630
1407
+ },
1408
+ {
1409
+ "epoch": 2.5035779028718634,
1410
+ "grad_norm": 0.13809001445770264,
1411
+ "learning_rate": 5.8565736256615434e-05,
1412
+ "loss": 0.029,
1413
+ "step": 1640
1414
+ },
1415
+ {
1416
+ "epoch": 2.518843621791814,
1417
+ "grad_norm": 0.17507204413414001,
1418
+ "learning_rate": 5.8040124022881625e-05,
1419
+ "loss": 0.0245,
1420
+ "step": 1650
1421
+ },
1422
+ {
1423
+ "epoch": 2.518843621791814,
1424
+ "eval_loss": 0.035995036363601685,
1425
+ "eval_runtime": 170.1729,
1426
+ "eval_samples_per_second": 6.846,
1427
+ "eval_steps_per_second": 6.846,
1428
+ "step": 1650
1429
+ },
1430
+ {
1431
+ "epoch": 2.534109340711764,
1432
+ "grad_norm": 0.5437776446342468,
1433
+ "learning_rate": 5.751359810075284e-05,
1434
+ "loss": 0.0173,
1435
+ "step": 1660
1436
+ },
1437
+ {
1438
+ "epoch": 2.5493750596317146,
1439
+ "grad_norm": 0.21639682352542877,
1440
+ "learning_rate": 5.6986218325204676e-05,
1441
+ "loss": 0.0125,
1442
+ "step": 1670
1443
+ },
1444
+ {
1445
+ "epoch": 2.5646407785516647,
1446
+ "grad_norm": 0.36389076709747314,
1447
+ "learning_rate": 5.645804462824556e-05,
1448
+ "loss": 0.0158,
1449
+ "step": 1680
1450
+ },
1451
+ {
1452
+ "epoch": 2.5799064974716153,
1453
+ "grad_norm": 0.1342177391052246,
1454
+ "learning_rate": 5.5929137032106005e-05,
1455
+ "loss": 0.0247,
1456
+ "step": 1690
1457
+ },
1458
+ {
1459
+ "epoch": 2.595172216391566,
1460
+ "grad_norm": 0.2882712483406067,
1461
+ "learning_rate": 5.53995556424176e-05,
1462
+ "loss": 0.0206,
1463
+ "step": 1700
1464
+ },
1465
+ {
1466
+ "epoch": 2.595172216391566,
1467
+ "eval_loss": 0.03758452460169792,
1468
+ "eval_runtime": 158.0975,
1469
+ "eval_samples_per_second": 7.369,
1470
+ "eval_steps_per_second": 7.369,
1471
+ "step": 1700
1472
+ },
1473
+ {
1474
+ "epoch": 2.610437935311516,
1475
+ "grad_norm": 0.31510451436042786,
1476
+ "learning_rate": 5.4869360641382615e-05,
1477
+ "loss": 0.0175,
1478
+ "step": 1710
1479
+ },
1480
+ {
1481
+ "epoch": 2.6257036542314665,
1482
+ "grad_norm": 0.22791199386119843,
1483
+ "learning_rate": 5.433861228093471e-05,
1484
+ "loss": 0.0225,
1485
+ "step": 1720
1486
+ },
1487
+ {
1488
+ "epoch": 2.640969373151417,
1489
+ "grad_norm": 0.16334158182144165,
1490
+ "learning_rate": 5.380737087589197e-05,
1491
+ "loss": 0.0179,
1492
+ "step": 1730
1493
+ },
1494
+ {
1495
+ "epoch": 2.656235092071367,
1496
+ "grad_norm": 0.4029809534549713,
1497
+ "learning_rate": 5.327569679710256e-05,
1498
+ "loss": 0.032,
1499
+ "step": 1740
1500
+ },
1501
+ {
1502
+ "epoch": 2.6715008109913176,
1503
+ "grad_norm": 0.17828147113323212,
1504
+ "learning_rate": 5.274365046458416e-05,
1505
+ "loss": 0.0198,
1506
+ "step": 1750
1507
+ },
1508
+ {
1509
+ "epoch": 2.6715008109913176,
1510
+ "eval_loss": 0.036341313272714615,
1511
+ "eval_runtime": 157.9022,
1512
+ "eval_samples_per_second": 7.378,
1513
+ "eval_steps_per_second": 7.378,
1514
+ "step": 1750
1515
+ },
1516
+ {
1517
+ "epoch": 2.686766529911268,
1518
+ "grad_norm": 0.3760712742805481,
1519
+ "learning_rate": 5.2211292340657804e-05,
1520
+ "loss": 0.0256,
1521
+ "step": 1760
1522
+ },
1523
+ {
1524
+ "epoch": 2.7020322488312183,
1525
+ "grad_norm": 0.18362978100776672,
1526
+ "learning_rate": 5.167868292307678e-05,
1527
+ "loss": 0.0274,
1528
+ "step": 1770
1529
+ },
1530
+ {
1531
+ "epoch": 2.717297967751169,
1532
+ "grad_norm": 0.18960805237293243,
1533
+ "learning_rate": 5.114588273815173e-05,
1534
+ "loss": 0.0184,
1535
+ "step": 1780
1536
+ },
1537
+ {
1538
+ "epoch": 2.732563686671119,
1539
+ "grad_norm": 0.3714582622051239,
1540
+ "learning_rate": 5.061295233387223e-05,
1541
+ "loss": 0.0272,
1542
+ "step": 1790
1543
+ },
1544
+ {
1545
+ "epoch": 2.7478294055910695,
1546
+ "grad_norm": 0.3221634328365326,
1547
+ "learning_rate": 5.007995227302617e-05,
1548
+ "loss": 0.0209,
1549
+ "step": 1800
1550
+ },
1551
+ {
1552
+ "epoch": 2.7478294055910695,
1553
+ "eval_loss": 0.037039320915937424,
1554
+ "eval_runtime": 158.1041,
1555
+ "eval_samples_per_second": 7.369,
1556
+ "eval_steps_per_second": 7.369,
1557
+ "step": 1800
1558
+ },
1559
+ {
1560
+ "epoch": 2.76309512451102,
1561
+ "grad_norm": 0.13622955977916718,
1562
+ "learning_rate": 4.954694312631729e-05,
1563
+ "loss": 0.022,
1564
+ "step": 1810
1565
+ },
1566
+ {
1567
+ "epoch": 2.7783608434309706,
1568
+ "grad_norm": 0.2798239290714264,
1569
+ "learning_rate": 4.901398546548181e-05,
1570
+ "loss": 0.0205,
1571
+ "step": 1820
1572
+ },
1573
+ {
1574
+ "epoch": 2.7936265623509207,
1575
+ "grad_norm": 0.34951063990592957,
1576
+ "learning_rate": 4.848113985640513e-05,
1577
+ "loss": 0.0213,
1578
+ "step": 1830
1579
+ },
1580
+ {
1581
+ "epoch": 2.808892281270871,
1582
+ "grad_norm": 0.19509588181972504,
1583
+ "learning_rate": 4.794846685223884e-05,
1584
+ "loss": 0.0231,
1585
+ "step": 1840
1586
+ },
1587
+ {
1588
+ "epoch": 2.8241580001908213,
1589
+ "grad_norm": 0.4014818072319031,
1590
+ "learning_rate": 4.741602698651966e-05,
1591
+ "loss": 0.026,
1592
+ "step": 1850
1593
+ },
1594
+ {
1595
+ "epoch": 2.8241580001908213,
1596
+ "eval_loss": 0.036198943853378296,
1597
+ "eval_runtime": 157.9325,
1598
+ "eval_samples_per_second": 7.377,
1599
+ "eval_steps_per_second": 7.377,
1600
+ "step": 1850
1601
+ },
1602
+ {
1603
+ "epoch": 2.839423719110772,
1604
+ "grad_norm": 0.5051618814468384,
1605
+ "learning_rate": 4.6883880766290086e-05,
1606
+ "loss": 0.0276,
1607
+ "step": 1860
1608
+ },
1609
+ {
1610
+ "epoch": 2.8546894380307224,
1611
+ "grad_norm": 0.2065005749464035,
1612
+ "learning_rate": 4.635208866522251e-05,
1613
+ "loss": 0.0188,
1614
+ "step": 1870
1615
+ },
1616
+ {
1617
+ "epoch": 2.8699551569506725,
1618
+ "grad_norm": 0.27732136845588684,
1619
+ "learning_rate": 4.5820711116746785e-05,
1620
+ "loss": 0.0193,
1621
+ "step": 1880
1622
+ },
1623
+ {
1624
+ "epoch": 2.885220875870623,
1625
+ "grad_norm": 0.35616669058799744,
1626
+ "learning_rate": 4.528980850718255e-05,
1627
+ "loss": 0.0237,
1628
+ "step": 1890
1629
+ },
1630
+ {
1631
+ "epoch": 2.9004865947905736,
1632
+ "grad_norm": 0.30379197001457214,
1633
+ "learning_rate": 4.475944116887695e-05,
1634
+ "loss": 0.0197,
1635
+ "step": 1900
1636
+ },
1637
+ {
1638
+ "epoch": 2.9004865947905736,
1639
+ "eval_loss": 0.03581969812512398,
1640
+ "eval_runtime": 158.3121,
1641
+ "eval_samples_per_second": 7.359,
1642
+ "eval_steps_per_second": 7.359,
1643
+ "step": 1900
1644
+ },
1645
+ {
1646
+ "epoch": 2.9157523137105237,
1647
+ "grad_norm": 0.3760513365268707,
1648
+ "learning_rate": 4.4229669373348226e-05,
1649
+ "loss": 0.0278,
1650
+ "step": 1910
1651
+ },
1652
+ {
1653
+ "epoch": 2.9310180326304742,
1654
+ "grad_norm": 0.14965511858463287,
1655
+ "learning_rate": 4.3700553324436575e-05,
1656
+ "loss": 0.0216,
1657
+ "step": 1920
1658
+ },
1659
+ {
1660
+ "epoch": 2.9462837515504248,
1661
+ "grad_norm": 0.3847552537918091,
1662
+ "learning_rate": 4.317215315146238e-05,
1663
+ "loss": 0.0277,
1664
+ "step": 1930
1665
+ },
1666
+ {
1667
+ "epoch": 2.961549470470375,
1668
+ "grad_norm": 0.21934816241264343,
1669
+ "learning_rate": 4.264452890239315e-05,
1670
+ "loss": 0.0242,
1671
+ "step": 1940
1672
+ },
1673
+ {
1674
+ "epoch": 2.9768151893903254,
1675
+ "grad_norm": 0.347125768661499,
1676
+ "learning_rate": 4.211774053701952e-05,
1677
+ "loss": 0.0291,
1678
+ "step": 1950
1679
+ },
1680
+ {
1681
+ "epoch": 2.9768151893903254,
1682
+ "eval_loss": 0.03554380312561989,
1683
+ "eval_runtime": 158.3407,
1684
+ "eval_samples_per_second": 7.358,
1685
+ "eval_steps_per_second": 7.358,
1686
+ "step": 1950
1687
+ },
1688
+ {
1689
+ "epoch": 2.9920809083102755,
1690
+ "grad_norm": 0.09311053901910782,
1691
+ "learning_rate": 4.159184792014145e-05,
1692
+ "loss": 0.0155,
1693
+ "step": 1960
1694
+ },
1695
+ {
1696
+ "epoch": 3.007346627230226,
1697
+ "grad_norm": 0.094869464635849,
1698
+ "learning_rate": 4.1066910814765016e-05,
1699
+ "loss": 0.0118,
1700
+ "step": 1970
1701
+ },
1702
+ {
1703
+ "epoch": 3.0226123461501766,
1704
+ "grad_norm": 0.2167072743177414,
1705
+ "learning_rate": 4.0542988875310995e-05,
1706
+ "loss": 0.0148,
1707
+ "step": 1980
1708
+ },
1709
+ {
1710
+ "epoch": 3.0378780650701267,
1711
+ "grad_norm": 0.14555399119853973,
1712
+ "learning_rate": 4.002014164083552e-05,
1713
+ "loss": 0.0136,
1714
+ "step": 1990
1715
+ },
1716
+ {
1717
+ "epoch": 3.0531437839900772,
1718
+ "grad_norm": 0.1664235144853592,
1719
+ "learning_rate": 3.9498428528264204e-05,
1720
+ "loss": 0.0091,
1721
+ "step": 2000
1722
+ },
1723
+ {
1724
+ "epoch": 3.0531437839900772,
1725
+ "eval_loss": 0.04159301891922951,
1726
+ "eval_runtime": 158.3202,
1727
+ "eval_samples_per_second": 7.359,
1728
+ "eval_steps_per_second": 7.359,
1729
+ "step": 2000
1730
+ },
1731
+ {
1732
+ "epoch": 3.068409502910028,
1733
+ "grad_norm": 0.2766287326812744,
1734
+ "learning_rate": 3.89779088256397e-05,
1735
+ "loss": 0.0092,
1736
+ "step": 2010
1737
+ },
1738
+ {
1739
+ "epoch": 3.083675221829978,
1740
+ "grad_norm": 0.38887709379196167,
1741
+ "learning_rate": 3.845864168538437e-05,
1742
+ "loss": 0.0097,
1743
+ "step": 2020
1744
+ },
1745
+ {
1746
+ "epoch": 3.0989409407499284,
1747
+ "grad_norm": 0.35072392225265503,
1748
+ "learning_rate": 3.794068611757794e-05,
1749
+ "loss": 0.0117,
1750
+ "step": 2030
1751
+ },
1752
+ {
1753
+ "epoch": 3.114206659669879,
1754
+ "grad_norm": 0.2347632646560669,
1755
+ "learning_rate": 3.7424100983251695e-05,
1756
+ "loss": 0.0157,
1757
+ "step": 2040
1758
+ },
1759
+ {
1760
+ "epoch": 3.129472378589829,
1761
+ "grad_norm": 0.6192054748535156,
1762
+ "learning_rate": 3.6908944987699345e-05,
1763
+ "loss": 0.0132,
1764
+ "step": 2050
1765
+ },
1766
+ {
1767
+ "epoch": 3.129472378589829,
1768
+ "eval_loss": 0.042059410363435745,
1769
+ "eval_runtime": 158.4528,
1770
+ "eval_samples_per_second": 7.352,
1771
+ "eval_steps_per_second": 7.352,
1772
+ "step": 2050
1773
+ },
1774
+ {
1775
+ "epoch": 3.1447380975097796,
1776
+ "grad_norm": 0.07461170107126236,
1777
+ "learning_rate": 3.639527667380571e-05,
1778
+ "loss": 0.0087,
1779
+ "step": 2060
1780
+ },
1781
+ {
1782
+ "epoch": 3.16000381642973,
1783
+ "grad_norm": 0.24892112612724304,
1784
+ "learning_rate": 3.5883154415393885e-05,
1785
+ "loss": 0.0086,
1786
+ "step": 2070
1787
+ },
1788
+ {
1789
+ "epoch": 3.1752695353496803,
1790
+ "grad_norm": 0.25514039397239685,
1791
+ "learning_rate": 3.537263641059152e-05,
1792
+ "loss": 0.0111,
1793
+ "step": 2080
1794
+ },
1795
+ {
1796
+ "epoch": 3.190535254269631,
1797
+ "grad_norm": 0.3669221103191376,
1798
+ "learning_rate": 3.486378067521718e-05,
1799
+ "loss": 0.01,
1800
+ "step": 2090
1801
+ },
1802
+ {
1803
+ "epoch": 3.2058009731895813,
1804
+ "grad_norm": 0.24360391497612,
1805
+ "learning_rate": 3.435664503618732e-05,
1806
+ "loss": 0.0115,
1807
+ "step": 2100
1808
+ },
1809
+ {
1810
+ "epoch": 3.2058009731895813,
1811
+ "eval_loss": 0.04429946094751358,
1812
+ "eval_runtime": 158.3749,
1813
+ "eval_samples_per_second": 7.356,
1814
+ "eval_steps_per_second": 7.356,
1815
+ "step": 2100
1816
+ },
1817
+ {
1818
+ "epoch": 3.2210666921095314,
1819
+ "grad_norm": 0.14438766241073608,
1820
+ "learning_rate": 3.3851287124944756e-05,
1821
+ "loss": 0.0108,
1822
+ "step": 2110
1823
+ },
1824
+ {
1825
+ "epoch": 3.236332411029482,
1826
+ "grad_norm": 0.21432369947433472,
1827
+ "learning_rate": 3.334776437090944e-05,
1828
+ "loss": 0.0086,
1829
+ "step": 2120
1830
+ },
1831
+ {
1832
+ "epoch": 3.251598129949432,
1833
+ "grad_norm": 0.030950259417295456,
1834
+ "learning_rate": 3.2846133994952046e-05,
1835
+ "loss": 0.0101,
1836
+ "step": 2130
1837
+ },
1838
+ {
1839
+ "epoch": 3.2668638488693826,
1840
+ "grad_norm": 0.3596804440021515,
1841
+ "learning_rate": 3.234645300289136e-05,
1842
+ "loss": 0.0061,
1843
+ "step": 2140
1844
+ },
1845
+ {
1846
+ "epoch": 3.282129567789333,
1847
+ "grad_norm": 0.9810014963150024,
1848
+ "learning_rate": 3.1848778179016075e-05,
1849
+ "loss": 0.0131,
1850
+ "step": 2150
1851
+ },
1852
+ {
1853
+ "epoch": 3.282129567789333,
1854
+ "eval_loss": 0.04585850238800049,
1855
+ "eval_runtime": 158.4392,
1856
+ "eval_samples_per_second": 7.353,
1857
+ "eval_steps_per_second": 7.353,
1858
+ "step": 2150
1859
+ },
1860
+ {
1861
+ "epoch": 3.2973952867092833,
1862
+ "grad_norm": 0.48682817816734314,
1863
+ "learning_rate": 3.135316607963176e-05,
1864
+ "loss": 0.0127,
1865
+ "step": 2160
1866
+ },
1867
+ {
1868
+ "epoch": 3.312661005629234,
1869
+ "grad_norm": 0.23697037994861603,
1870
+ "learning_rate": 3.085967302663375e-05,
1871
+ "loss": 0.0108,
1872
+ "step": 2170
1873
+ },
1874
+ {
1875
+ "epoch": 3.3279267245491844,
1876
+ "grad_norm": 0.5131348371505737,
1877
+ "learning_rate": 3.0368355101106615e-05,
1878
+ "loss": 0.0168,
1879
+ "step": 2180
1880
+ },
1881
+ {
1882
+ "epoch": 3.3431924434691345,
1883
+ "grad_norm": 0.4184378981590271,
1884
+ "learning_rate": 2.987926813695116e-05,
1885
+ "loss": 0.0095,
1886
+ "step": 2190
1887
+ },
1888
+ {
1889
+ "epoch": 3.358458162389085,
1890
+ "grad_norm": 0.14508870244026184,
1891
+ "learning_rate": 2.939246771453924e-05,
1892
+ "loss": 0.0132,
1893
+ "step": 2200
1894
+ },
1895
+ {
1896
+ "epoch": 3.358458162389085,
1897
+ "eval_loss": 0.04094408452510834,
1898
+ "eval_runtime": 158.4285,
1899
+ "eval_samples_per_second": 7.353,
1900
+ "eval_steps_per_second": 7.353,
1901
+ "step": 2200
1902
+ },
1903
+ {
1904
+ "epoch": 3.3737238813090356,
1905
+ "grad_norm": 0.41974306106567383,
1906
+ "learning_rate": 2.890800915439772e-05,
1907
+ "loss": 0.0136,
1908
+ "step": 2210
1909
+ },
1910
+ {
1911
+ "epoch": 3.3889896002289857,
1912
+ "grad_norm": 0.24298487603664398,
1913
+ "learning_rate": 2.842594751092159e-05,
1914
+ "loss": 0.0094,
1915
+ "step": 2220
1916
+ },
1917
+ {
1918
+ "epoch": 3.404255319148936,
1919
+ "grad_norm": 0.2780051827430725,
1920
+ "learning_rate": 2.794633756611776e-05,
1921
+ "loss": 0.0111,
1922
+ "step": 2230
1923
+ },
1924
+ {
1925
+ "epoch": 3.4195210380688867,
1926
+ "grad_norm": 0.4046504497528076,
1927
+ "learning_rate": 2.7469233823379347e-05,
1928
+ "loss": 0.0106,
1929
+ "step": 2240
1930
+ },
1931
+ {
1932
+ "epoch": 3.434786756988837,
1933
+ "grad_norm": 0.5508965849876404,
1934
+ "learning_rate": 2.6994690501292032e-05,
1935
+ "loss": 0.0077,
1936
+ "step": 2250
1937
+ },
1938
+ {
1939
+ "epoch": 3.434786756988837,
1940
+ "eval_loss": 0.04445834830403328,
1941
+ "eval_runtime": 158.3347,
1942
+ "eval_samples_per_second": 7.358,
1943
+ "eval_steps_per_second": 7.358,
1944
+ "step": 2250
1945
+ },
1946
+ {
1947
+ "epoch": 3.4500524759087874,
1948
+ "grad_norm": 0.1673806607723236,
1949
+ "learning_rate": 2.652276152747246e-05,
1950
+ "loss": 0.0073,
1951
+ "step": 2260
1952
+ },
1953
+ {
1954
+ "epoch": 3.465318194828738,
1955
+ "grad_norm": 0.11956673860549927,
1956
+ "learning_rate": 2.6053500532439968e-05,
1957
+ "loss": 0.0058,
1958
+ "step": 2270
1959
+ },
1960
+ {
1961
+ "epoch": 3.480583913748688,
1962
+ "grad_norm": 0.08597150444984436,
1963
+ "learning_rate": 2.5586960843521824e-05,
1964
+ "loss": 0.0135,
1965
+ "step": 2280
1966
+ },
1967
+ {
1968
+ "epoch": 3.4958496326686386,
1969
+ "grad_norm": 0.456600159406662,
1970
+ "learning_rate": 2.5123195478793217e-05,
1971
+ "loss": 0.0137,
1972
+ "step": 2290
1973
+ },
1974
+ {
1975
+ "epoch": 3.5111153515885887,
1976
+ "grad_norm": 0.10607762634754181,
1977
+ "learning_rate": 2.466225714105202e-05,
1978
+ "loss": 0.0156,
1979
+ "step": 2300
1980
+ },
1981
+ {
1982
+ "epoch": 3.5111153515885887,
1983
+ "eval_loss": 0.04438282549381256,
1984
+ "eval_runtime": 158.4663,
1985
+ "eval_samples_per_second": 7.352,
1986
+ "eval_steps_per_second": 7.352,
1987
+ "step": 2300
1988
+ },
1989
+ {
1990
+ "epoch": 3.526381070508539,
1991
+ "grad_norm": 0.2712307572364807,
1992
+ "learning_rate": 2.420419821182982e-05,
1993
+ "loss": 0.014,
1994
+ "step": 2310
1995
+ },
1996
+ {
1997
+ "epoch": 3.5416467894284898,
1998
+ "grad_norm": 0.34561389684677124,
1999
+ "learning_rate": 2.3749070745438996e-05,
2000
+ "loss": 0.0097,
2001
+ "step": 2320
2002
+ },
2003
+ {
2004
+ "epoch": 3.5569125083484403,
2005
+ "grad_norm": 0.1999119520187378,
2006
+ "learning_rate": 2.3296926463057396e-05,
2007
+ "loss": 0.0092,
2008
+ "step": 2330
2009
+ },
2010
+ {
2011
+ "epoch": 3.5721782272683904,
2012
+ "grad_norm": 0.24684706330299377,
2013
+ "learning_rate": 2.284781674685058e-05,
2014
+ "loss": 0.0076,
2015
+ "step": 2340
2016
+ },
2017
+ {
2018
+ "epoch": 3.587443946188341,
2019
+ "grad_norm": 0.13131554424762726,
2020
+ "learning_rate": 2.2401792634132708e-05,
2021
+ "loss": 0.0125,
2022
+ "step": 2350
2023
+ },
2024
+ {
2025
+ "epoch": 3.587443946188341,
2026
+ "eval_loss": 0.048045314848423004,
2027
+ "eval_runtime": 158.5084,
2028
+ "eval_samples_per_second": 7.35,
2029
+ "eval_steps_per_second": 7.35,
2030
+ "step": 2350
2031
+ },
2032
+ {
2033
+ "epoch": 3.602709665108291,
2034
+ "grad_norm": 0.5896148085594177,
2035
+ "learning_rate": 2.195890481156666e-05,
2036
+ "loss": 0.0094,
2037
+ "step": 2360
2038
+ },
2039
+ {
2040
+ "epoch": 3.6179753840282416,
2041
+ "grad_norm": 0.13258546590805054,
2042
+ "learning_rate": 2.151920360940387e-05,
2043
+ "loss": 0.0122,
2044
+ "step": 2370
2045
+ },
2046
+ {
2047
+ "epoch": 3.633241102948192,
2048
+ "grad_norm": 0.40482622385025024,
2049
+ "learning_rate": 2.1082738995764785e-05,
2050
+ "loss": 0.0075,
2051
+ "step": 2380
2052
+ },
2053
+ {
2054
+ "epoch": 3.6485068218681422,
2055
+ "grad_norm": 0.34933677315711975,
2056
+ "learning_rate": 2.0649560570960465e-05,
2057
+ "loss": 0.0063,
2058
+ "step": 2390
2059
+ },
2060
+ {
2061
+ "epoch": 3.663772540788093,
2062
+ "grad_norm": 0.37669917941093445,
2063
+ "learning_rate": 2.0219717561855855e-05,
2064
+ "loss": 0.0089,
2065
+ "step": 2400
2066
+ },
2067
+ {
2068
+ "epoch": 3.663772540788093,
2069
+ "eval_loss": 0.049949660897254944,
2070
+ "eval_runtime": 158.5713,
2071
+ "eval_samples_per_second": 7.347,
2072
+ "eval_steps_per_second": 7.347,
2073
+ "step": 2400
2074
+ },
2075
+ {
2076
+ "epoch": 3.679038259708043,
2077
+ "grad_norm": 0.26693466305732727,
2078
+ "learning_rate": 1.9793258816275728e-05,
2079
+ "loss": 0.0168,
2080
+ "step": 2410
2081
+ },
2082
+ {
2083
+ "epoch": 3.6943039786279934,
2084
+ "grad_norm": 0.3945235311985016,
2085
+ "learning_rate": 1.9370232797453402e-05,
2086
+ "loss": 0.0106,
2087
+ "step": 2420
2088
+ },
2089
+ {
2090
+ "epoch": 3.709569697547944,
2091
+ "grad_norm": 0.529176652431488,
2092
+ "learning_rate": 1.8950687578523502e-05,
2093
+ "loss": 0.01,
2094
+ "step": 2430
2095
+ },
2096
+ {
2097
+ "epoch": 3.7248354164678945,
2098
+ "grad_norm": 0.22456000745296478,
2099
+ "learning_rate": 1.853467083705869e-05,
2100
+ "loss": 0.0067,
2101
+ "step": 2440
2102
+ },
2103
+ {
2104
+ "epoch": 3.7401011353878446,
2105
+ "grad_norm": 0.406535267829895,
2106
+ "learning_rate": 1.8122229849651716e-05,
2107
+ "loss": 0.0125,
2108
+ "step": 2450
2109
+ },
2110
+ {
2111
+ "epoch": 3.7401011353878446,
2112
+ "eval_loss": 0.04671522229909897,
2113
+ "eval_runtime": 158.5667,
2114
+ "eval_samples_per_second": 7.347,
2115
+ "eval_steps_per_second": 7.347,
2116
+ "step": 2450
2117
+ },
2118
+ {
2119
+ "epoch": 3.755366854307795,
2120
+ "grad_norm": 0.24689412117004395,
2121
+ "learning_rate": 1.7713411486542707e-05,
2122
+ "loss": 0.014,
2123
+ "step": 2460
2124
+ },
2125
+ {
2126
+ "epoch": 3.7706325732277453,
2127
+ "grad_norm": 0.27206507325172424,
2128
+ "learning_rate": 1.7308262206292897e-05,
2129
+ "loss": 0.0076,
2130
+ "step": 2470
2131
+ },
2132
+ {
2133
+ "epoch": 3.785898292147696,
2134
+ "grad_norm": 0.6516662240028381,
2135
+ "learning_rate": 1.6906828050504907e-05,
2136
+ "loss": 0.015,
2137
+ "step": 2480
2138
+ },
2139
+ {
2140
+ "epoch": 3.8011640110676463,
2141
+ "grad_norm": 0.7136443853378296,
2142
+ "learning_rate": 1.650915463859068e-05,
2143
+ "loss": 0.0096,
2144
+ "step": 2490
2145
+ },
2146
+ {
2147
+ "epoch": 3.8164297299875964,
2148
+ "grad_norm": 0.08043626695871353,
2149
+ "learning_rate": 1.6115287162587055e-05,
2150
+ "loss": 0.0115,
2151
+ "step": 2500
2152
+ },
2153
+ {
2154
+ "epoch": 3.8164297299875964,
2155
+ "eval_loss": 0.04467522352933884,
2156
+ "eval_runtime": 158.5106,
2157
+ "eval_samples_per_second": 7.35,
2158
+ "eval_steps_per_second": 7.35,
2159
+ "step": 2500
2160
+ },
2161
+ {
2162
+ "epoch": 3.831695448907547,
2163
+ "grad_norm": 0.37196823954582214,
2164
+ "learning_rate": 1.57252703820203e-05,
2165
+ "loss": 0.0064,
2166
+ "step": 2510
2167
+ },
2168
+ {
2169
+ "epoch": 3.8469611678274975,
2170
+ "grad_norm": 0.5090697407722473,
2171
+ "learning_rate": 1.5339148618819393e-05,
2172
+ "loss": 0.0159,
2173
+ "step": 2520
2174
+ },
2175
+ {
2176
+ "epoch": 3.8622268867474476,
2177
+ "grad_norm": 0.317979633808136,
2178
+ "learning_rate": 1.4956965752279395e-05,
2179
+ "loss": 0.0135,
2180
+ "step": 2530
2181
+ },
2182
+ {
2183
+ "epoch": 3.877492605667398,
2184
+ "grad_norm": 0.30272015929222107,
2185
+ "learning_rate": 1.457876521407484e-05,
2186
+ "loss": 0.0103,
2187
+ "step": 2540
2188
+ },
2189
+ {
2190
+ "epoch": 3.8927583245873487,
2191
+ "grad_norm": 0.33453094959259033,
2192
+ "learning_rate": 1.4204589983324173e-05,
2193
+ "loss": 0.0062,
2194
+ "step": 2550
2195
+ },
2196
+ {
2197
+ "epoch": 3.8927583245873487,
2198
+ "eval_loss": 0.044938329607248306,
2199
+ "eval_runtime": 158.251,
2200
+ "eval_samples_per_second": 7.362,
2201
+ "eval_steps_per_second": 7.362,
2202
+ "step": 2550
2203
+ },
2204
+ {
2205
+ "epoch": 3.908024043507299,
2206
+ "grad_norm": 0.22449414432048798,
2207
+ "learning_rate": 1.383448258170557e-05,
2208
+ "loss": 0.0095,
2209
+ "step": 2560
2210
+ },
2211
+ {
2212
+ "epoch": 3.9232897624272494,
2213
+ "grad_norm": 0.35782113671302795,
2214
+ "learning_rate": 1.3468485068624653e-05,
2215
+ "loss": 0.0069,
2216
+ "step": 2570
2217
+ },
2218
+ {
2219
+ "epoch": 3.9385554813471995,
2220
+ "grad_norm": 0.019237499684095383,
2221
+ "learning_rate": 1.310663903643492e-05,
2222
+ "loss": 0.0119,
2223
+ "step": 2580
2224
+ },
2225
+ {
2226
+ "epoch": 3.95382120026715,
2227
+ "grad_norm": 0.19343972206115723,
2228
+ "learning_rate": 1.2748985605711028e-05,
2229
+ "loss": 0.0109,
2230
+ "step": 2590
2231
+ },
2232
+ {
2233
+ "epoch": 3.9690869191871005,
2234
+ "grad_norm": 0.3041229844093323,
2235
+ "learning_rate": 1.2395565420575932e-05,
2236
+ "loss": 0.0112,
2237
+ "step": 2600
2238
+ },
2239
+ {
2240
+ "epoch": 3.9690869191871005,
2241
+ "eval_loss": 0.046159546822309494,
2242
+ "eval_runtime": 158.163,
2243
+ "eval_samples_per_second": 7.366,
2244
+ "eval_steps_per_second": 7.366,
2245
+ "step": 2600
2246
+ },
2247
+ {
2248
+ "epoch": 3.984352638107051,
2249
+ "grad_norm": 0.18217749893665314,
2250
+ "learning_rate": 1.2046418644081903e-05,
2251
+ "loss": 0.0194,
2252
+ "step": 2610
2253
+ },
2254
+ {
2255
+ "epoch": 3.999618357027001,
2256
+ "grad_norm": 0.40362730622291565,
2257
+ "learning_rate": 1.1701584953646505e-05,
2258
+ "loss": 0.0084,
2259
+ "step": 2620
2260
+ },
2261
+ {
2262
+ "epoch": 4.014884075946951,
2263
+ "grad_norm": 0.20328281819820404,
2264
+ "learning_rate": 1.1361103536543466e-05,
2265
+ "loss": 0.006,
2266
+ "step": 2630
2267
+ },
2268
+ {
2269
+ "epoch": 4.030149794866902,
2270
+ "grad_norm": 0.03458496183156967,
2271
+ "learning_rate": 1.1025013085449527e-05,
2272
+ "loss": 0.0033,
2273
+ "step": 2640
2274
+ },
2275
+ {
2276
+ "epoch": 4.045415513786852,
2277
+ "grad_norm": 0.24609656631946564,
2278
+ "learning_rate": 1.0693351794047224e-05,
2279
+ "loss": 0.005,
2280
+ "step": 2650
2281
+ },
2282
+ {
2283
+ "epoch": 4.045415513786852,
2284
+ "eval_loss": 0.04647543653845787,
2285
+ "eval_runtime": 158.0997,
2286
+ "eval_samples_per_second": 7.369,
2287
+ "eval_steps_per_second": 7.369,
2288
+ "step": 2650
2289
+ },
2290
+ {
2291
+ "epoch": 4.060681232706803,
2292
+ "grad_norm": 0.12650443613529205,
2293
+ "learning_rate": 1.036615735268468e-05,
2294
+ "loss": 0.0043,
2295
+ "step": 2660
2296
+ },
2297
+ {
2298
+ "epoch": 4.0759469516267535,
2299
+ "grad_norm": 0.06227023899555206,
2300
+ "learning_rate": 1.0043466944092272e-05,
2301
+ "loss": 0.0058,
2302
+ "step": 2670
2303
+ },
2304
+ {
2305
+ "epoch": 4.091212670546703,
2306
+ "grad_norm": 0.09046266973018646,
2307
+ "learning_rate": 9.72531723915726e-06,
2308
+ "loss": 0.0081,
2309
+ "step": 2680
2310
+ },
2311
+ {
2312
+ "epoch": 4.106478389466654,
2313
+ "grad_norm": 0.09273139387369156,
2314
+ "learning_rate": 9.411744392756405e-06,
2315
+ "loss": 0.0055,
2316
+ "step": 2690
2317
+ },
2318
+ {
2319
+ "epoch": 4.121744108386604,
2320
+ "grad_norm": 0.07838311046361923,
2321
+ "learning_rate": 9.102784039647339e-06,
2322
+ "loss": 0.0065,
2323
+ "step": 2700
2324
+ },
2325
+ {
2326
+ "epoch": 4.121744108386604,
2327
+ "eval_loss": 0.050155650824308395,
2328
+ "eval_runtime": 158.2759,
2329
+ "eval_samples_per_second": 7.361,
2330
+ "eval_steps_per_second": 7.361,
2331
+ "step": 2700
2332
+ },
2333
+ {
2334
+ "epoch": 4.137009827306555,
2335
+ "grad_norm": 1.3356140851974487,
2336
+ "learning_rate": 8.79847129041893e-06,
2337
+ "loss": 0.007,
2338
+ "step": 2710
2339
+ },
2340
+ {
2341
+ "epoch": 4.152275546226505,
2342
+ "grad_norm": 0.06380099803209305,
2343
+ "learning_rate": 8.498840727501316e-06,
2344
+ "loss": 0.0032,
2345
+ "step": 2720
2346
+ },
2347
+ {
2348
+ "epoch": 4.167541265146456,
2349
+ "grad_norm": 0.05524059012532234,
2350
+ "learning_rate": 8.203926401235957e-06,
2351
+ "loss": 0.0028,
2352
+ "step": 2730
2353
+ },
2354
+ {
2355
+ "epoch": 4.1828069840664055,
2356
+ "grad_norm": 0.048491813242435455,
2357
+ "learning_rate": 7.913761826006017e-06,
2358
+ "loss": 0.0029,
2359
+ "step": 2740
2360
+ },
2361
+ {
2362
+ "epoch": 4.198072702986356,
2363
+ "grad_norm": 0.07295604050159454,
2364
+ "learning_rate": 7.628379976427868e-06,
2365
+ "loss": 0.0021,
2366
+ "step": 2750
2367
+ },
2368
+ {
2369
+ "epoch": 4.198072702986356,
2370
+ "eval_loss": 0.054289042949676514,
2371
+ "eval_runtime": 158.2341,
2372
+ "eval_samples_per_second": 7.363,
2373
+ "eval_steps_per_second": 7.363,
2374
+ "step": 2750
2375
+ },
2376
+ {
2377
+ "epoch": 4.213338421906307,
2378
+ "grad_norm": 0.10423220694065094,
2379
+ "learning_rate": 7.347813283603705e-06,
2380
+ "loss": 0.008,
2381
+ "step": 2760
2382
+ },
2383
+ {
2384
+ "epoch": 4.228604140826257,
2385
+ "grad_norm": 0.07456283271312714,
2386
+ "learning_rate": 7.072093631436161e-06,
2387
+ "loss": 0.0041,
2388
+ "step": 2770
2389
+ },
2390
+ {
2391
+ "epoch": 4.243869859746208,
2392
+ "grad_norm": 0.01388398464769125,
2393
+ "learning_rate": 6.801252353004867e-06,
2394
+ "loss": 0.0035,
2395
+ "step": 2780
2396
+ },
2397
+ {
2398
+ "epoch": 4.259135578666158,
2399
+ "grad_norm": 0.2674631178379059,
2400
+ "learning_rate": 6.535320227005826e-06,
2401
+ "loss": 0.0037,
2402
+ "step": 2790
2403
+ },
2404
+ {
2405
+ "epoch": 4.274401297586108,
2406
+ "grad_norm": 0.028004569932818413,
2407
+ "learning_rate": 6.274327474253611e-06,
2408
+ "loss": 0.0033,
2409
+ "step": 2800
2410
+ },
2411
+ {
2412
+ "epoch": 4.274401297586108,
2413
+ "eval_loss": 0.055618129670619965,
2414
+ "eval_runtime": 158.2941,
2415
+ "eval_samples_per_second": 7.36,
2416
+ "eval_steps_per_second": 7.36,
2417
+ "step": 2800
2418
+ },
2419
+ {
2420
+ "epoch": 4.289667016506058,
2421
+ "grad_norm": 0.02966715581715107,
2422
+ "learning_rate": 6.018303754247112e-06,
2423
+ "loss": 0.004,
2424
+ "step": 2810
2425
+ },
2426
+ {
2427
+ "epoch": 4.304932735426009,
2428
+ "grad_norm": 0.07398536056280136,
2429
+ "learning_rate": 5.767278161798911e-06,
2430
+ "loss": 0.0045,
2431
+ "step": 2820
2432
+ },
2433
+ {
2434
+ "epoch": 4.3201984543459595,
2435
+ "grad_norm": 0.06184925138950348,
2436
+ "learning_rate": 5.521279223729026e-06,
2437
+ "loss": 0.0018,
2438
+ "step": 2830
2439
+ },
2440
+ {
2441
+ "epoch": 4.33546417326591,
2442
+ "grad_norm": 0.10655587166547775,
2443
+ "learning_rate": 5.280334895622968e-06,
2444
+ "loss": 0.0036,
2445
+ "step": 2840
2446
+ },
2447
+ {
2448
+ "epoch": 4.350729892185861,
2449
+ "grad_norm": 0.2469986528158188,
2450
+ "learning_rate": 5.044472558654961e-06,
2451
+ "loss": 0.0068,
2452
+ "step": 2850
2453
+ },
2454
+ {
2455
+ "epoch": 4.350729892185861,
2456
+ "eval_loss": 0.057221900671720505,
2457
+ "eval_runtime": 158.3313,
2458
+ "eval_samples_per_second": 7.358,
2459
+ "eval_steps_per_second": 7.358,
2460
+ "step": 2850
2461
+ },
2462
+ {
2463
+ "epoch": 4.36599561110581,
2464
+ "grad_norm": 0.07252271473407745,
2465
+ "learning_rate": 4.813719016476203e-06,
2466
+ "loss": 0.0024,
2467
+ "step": 2860
2468
+ },
2469
+ {
2470
+ "epoch": 4.381261330025761,
2471
+ "grad_norm": 0.3494785726070404,
2472
+ "learning_rate": 4.588100492168973e-06,
2473
+ "loss": 0.0017,
2474
+ "step": 2870
2475
+ },
2476
+ {
2477
+ "epoch": 4.396527048945711,
2478
+ "grad_norm": 0.10995281487703323,
2479
+ "learning_rate": 4.367642625266511e-06,
2480
+ "loss": 0.0029,
2481
+ "step": 2880
2482
+ },
2483
+ {
2484
+ "epoch": 4.411792767865662,
2485
+ "grad_norm": 0.01004809606820345,
2486
+ "learning_rate": 4.1523704688394176e-06,
2487
+ "loss": 0.0023,
2488
+ "step": 2890
2489
+ },
2490
+ {
2491
+ "epoch": 4.427058486785612,
2492
+ "grad_norm": 0.11159130930900574,
2493
+ "learning_rate": 3.9423084866484884e-06,
2494
+ "loss": 0.0015,
2495
+ "step": 2900
2496
+ },
2497
+ {
2498
+ "epoch": 4.427058486785612,
2499
+ "eval_loss": 0.05985542759299278,
2500
+ "eval_runtime": 158.3929,
2501
+ "eval_samples_per_second": 7.355,
2502
+ "eval_steps_per_second": 7.355,
2503
+ "step": 2900
2504
+ },
2505
+ {
2506
+ "epoch": 4.442324205705562,
2507
+ "grad_norm": 0.35261520743370056,
2508
+ "learning_rate": 3.737480550364736e-06,
2509
+ "loss": 0.0071,
2510
+ "step": 2910
2511
+ },
2512
+ {
2513
+ "epoch": 4.457589924625513,
2514
+ "grad_norm": 0.26947641372680664,
2515
+ "learning_rate": 3.5379099368564817e-06,
2516
+ "loss": 0.0041,
2517
+ "step": 2920
2518
+ },
2519
+ {
2520
+ "epoch": 4.472855643545463,
2521
+ "grad_norm": 0.24151833355426788,
2522
+ "learning_rate": 3.3436193255442396e-06,
2523
+ "loss": 0.0026,
2524
+ "step": 2930
2525
+ },
2526
+ {
2527
+ "epoch": 4.488121362465414,
2528
+ "grad_norm": 0.007592054083943367,
2529
+ "learning_rate": 3.1546307958233214e-06,
2530
+ "loss": 0.0031,
2531
+ "step": 2940
2532
+ },
2533
+ {
2534
+ "epoch": 4.503387081385364,
2535
+ "grad_norm": 0.16517309844493866,
2536
+ "learning_rate": 2.9709658245547834e-06,
2537
+ "loss": 0.0036,
2538
+ "step": 2950
2539
+ },
2540
+ {
2541
+ "epoch": 4.503387081385364,
2542
+ "eval_loss": 0.060201384127140045,
2543
+ "eval_runtime": 158.4197,
2544
+ "eval_samples_per_second": 7.354,
2545
+ "eval_steps_per_second": 7.354,
2546
+ "step": 2950
2547
+ },
2548
+ {
2549
+ "epoch": 4.518652800305315,
2550
+ "grad_norm": 0.08729831874370575,
2551
+ "learning_rate": 2.792645283624712e-06,
2552
+ "loss": 0.0027,
2553
+ "step": 2960
2554
+ },
2555
+ {
2556
+ "epoch": 4.5339185192252645,
2557
+ "grad_norm": 0.11076062172651291,
2558
+ "learning_rate": 2.6196894375723645e-06,
2559
+ "loss": 0.0014,
2560
+ "step": 2970
2561
+ },
2562
+ {
2563
+ "epoch": 4.549184238145215,
2564
+ "grad_norm": 0.009186147712171078,
2565
+ "learning_rate": 2.452117941287246e-06,
2566
+ "loss": 0.0064,
2567
+ "step": 2980
2568
+ },
2569
+ {
2570
+ "epoch": 4.5644499570651655,
2571
+ "grad_norm": 0.14165641367435455,
2572
+ "learning_rate": 2.2899498377755566e-06,
2573
+ "loss": 0.0012,
2574
+ "step": 2990
2575
+ },
2576
+ {
2577
+ "epoch": 4.579715675985116,
2578
+ "grad_norm": 0.09586022794246674,
2579
+ "learning_rate": 2.1332035559960663e-06,
2580
+ "loss": 0.0027,
2581
+ "step": 3000
2582
+ },
2583
+ {
2584
+ "epoch": 4.579715675985116,
2585
+ "eval_loss": 0.06145218014717102,
2586
+ "eval_runtime": 158.4209,
2587
+ "eval_samples_per_second": 7.354,
2588
+ "eval_steps_per_second": 7.354,
2589
+ "step": 3000
2590
+ },
2591
+ {
2592
+ "epoch": 4.594981394905067,
2593
+ "grad_norm": 0.12076330184936523,
2594
+ "learning_rate": 1.9818969087658735e-06,
2595
+ "loss": 0.0043,
2596
+ "step": 3010
2597
+ },
2598
+ {
2599
+ "epoch": 4.610247113825016,
2600
+ "grad_norm": 0.002956979675218463,
2601
+ "learning_rate": 1.8360470907361093e-06,
2602
+ "loss": 0.0011,
2603
+ "step": 3020
2604
+ },
2605
+ {
2606
+ "epoch": 4.625512832744967,
2607
+ "grad_norm": 0.022843187674880028,
2608
+ "learning_rate": 1.6956706764379438e-06,
2609
+ "loss": 0.0056,
2610
+ "step": 3030
2611
+ },
2612
+ {
2613
+ "epoch": 4.640778551664917,
2614
+ "grad_norm": 0.12420812249183655,
2615
+ "learning_rate": 1.5607836183989921e-06,
2616
+ "loss": 0.0028,
2617
+ "step": 3040
2618
+ },
2619
+ {
2620
+ "epoch": 4.656044270584868,
2621
+ "grad_norm": 0.23208186030387878,
2622
+ "learning_rate": 1.4314012453305215e-06,
2623
+ "loss": 0.0013,
2624
+ "step": 3050
2625
+ },
2626
+ {
2627
+ "epoch": 4.656044270584868,
2628
+ "eval_loss": 0.061488546431064606,
2629
+ "eval_runtime": 158.5492,
2630
+ "eval_samples_per_second": 7.348,
2631
+ "eval_steps_per_second": 7.348,
2632
+ "step": 3050
2633
+ },
2634
+ {
2635
+ "epoch": 4.6713099895048185,
2636
+ "grad_norm": 0.36894094944000244,
2637
+ "learning_rate": 1.3075382603854157e-06,
2638
+ "loss": 0.0028,
2639
+ "step": 3060
2640
+ },
2641
+ {
2642
+ "epoch": 4.686575708424769,
2643
+ "grad_norm": 0.011954453773796558,
2644
+ "learning_rate": 1.1892087394873353e-06,
2645
+ "loss": 0.0027,
2646
+ "step": 3070
2647
+ },
2648
+ {
2649
+ "epoch": 4.701841427344719,
2650
+ "grad_norm": 0.025959955528378487,
2651
+ "learning_rate": 1.076426129731084e-06,
2652
+ "loss": 0.0038,
2653
+ "step": 3080
2654
+ },
2655
+ {
2656
+ "epoch": 4.717107146264669,
2657
+ "grad_norm": 0.13131509721279144,
2658
+ "learning_rate": 9.692032478545e-07,
2659
+ "loss": 0.005,
2660
+ "step": 3090
2661
+ },
2662
+ {
2663
+ "epoch": 4.73237286518462,
2664
+ "grad_norm": 0.2080388367176056,
2665
+ "learning_rate": 8.675522787819023e-07,
2666
+ "loss": 0.0056,
2667
+ "step": 3100
2668
+ },
2669
+ {
2670
+ "epoch": 4.73237286518462,
2671
+ "eval_loss": 0.061799220740795135,
2672
+ "eval_runtime": 158.5326,
2673
+ "eval_samples_per_second": 7.349,
2674
+ "eval_steps_per_second": 7.349,
2675
+ "step": 3100
2676
+ },
2677
+ {
2678
+ "epoch": 4.74763858410457,
2679
+ "grad_norm": 0.04518610239028931,
2680
+ "learning_rate": 7.714847742394337e-07,
2681
+ "loss": 0.0051,
2682
+ "step": 3110
2683
+ },
2684
+ {
2685
+ "epoch": 4.762904303024521,
2686
+ "grad_norm": 0.613032877445221,
2687
+ "learning_rate": 6.810116514422593e-07,
2688
+ "loss": 0.0089,
2689
+ "step": 3120
2690
+ },
2691
+ {
2692
+ "epoch": 4.7781700219444705,
2693
+ "grad_norm": 0.09960233420133591,
2694
+ "learning_rate": 5.961431918539817e-07,
2695
+ "loss": 0.0031,
2696
+ "step": 3130
2697
+ },
2698
+ {
2699
+ "epoch": 4.793435740864421,
2700
+ "grad_norm": 0.15351538360118866,
2701
+ "learning_rate": 5.16889040018187e-07,
2702
+ "loss": 0.0058,
2703
+ "step": 3140
2704
+ },
2705
+ {
2706
+ "epoch": 4.808701459784372,
2707
+ "grad_norm": 0.039991118013858795,
2708
+ "learning_rate": 4.432582024624543e-07,
2709
+ "loss": 0.0028,
2710
+ "step": 3150
2711
+ },
2712
+ {
2713
+ "epoch": 4.808701459784372,
2714
+ "eval_loss": 0.06179770454764366,
2715
+ "eval_runtime": 158.4692,
2716
+ "eval_samples_per_second": 7.352,
2717
+ "eval_steps_per_second": 7.352,
2718
+ "step": 3150
2719
+ },
2720
+ {
2721
+ "epoch": 4.823967178704322,
2722
+ "grad_norm": 0.03549914062023163,
2723
+ "learning_rate": 3.7525904667484737e-07,
2724
+ "loss": 0.0028,
2725
+ "step": 3160
2726
+ },
2727
+ {
2728
+ "epoch": 4.839232897624273,
2729
+ "grad_norm": 0.3593372702598572,
2730
+ "learning_rate": 3.128993001530245e-07,
2731
+ "loss": 0.0037,
2732
+ "step": 3170
2733
+ },
2734
+ {
2735
+ "epoch": 4.854498616544223,
2736
+ "grad_norm": 0.10235150158405304,
2737
+ "learning_rate": 2.5618604952605816e-07,
2738
+ "loss": 0.003,
2739
+ "step": 3180
2740
+ },
2741
+ {
2742
+ "epoch": 4.869764335464174,
2743
+ "grad_norm": 0.029046185314655304,
2744
+ "learning_rate": 2.0512573974912908e-07,
2745
+ "loss": 0.0034,
2746
+ "step": 3190
2747
+ },
2748
+ {
2749
+ "epoch": 4.885030054384123,
2750
+ "grad_norm": 0.3789989948272705,
2751
+ "learning_rate": 1.597241733711008e-07,
2752
+ "loss": 0.0044,
2753
+ "step": 3200
2754
+ },
2755
+ {
2756
+ "epoch": 4.885030054384123,
2757
+ "eval_loss": 0.06198294460773468,
2758
+ "eval_runtime": 158.4955,
2759
+ "eval_samples_per_second": 7.35,
2760
+ "eval_steps_per_second": 7.35,
2761
+ "step": 3200
2762
+ },
2763
+ {
2764
+ "epoch": 4.900295773304074,
2765
+ "grad_norm": 0.03306398168206215,
2766
+ "learning_rate": 1.1998650987510295e-07,
2767
+ "loss": 0.0077,
2768
+ "step": 3210
2769
+ },
2770
+ {
2771
+ "epoch": 4.9155614922240245,
2772
+ "grad_norm": 0.06163898482918739,
2773
+ "learning_rate": 8.591726509222242e-08,
2774
+ "loss": 0.0097,
2775
+ "step": 3220
2776
+ },
2777
+ {
2778
+ "epoch": 4.930827211143975,
2779
+ "grad_norm": 0.7225600481033325,
2780
+ "learning_rate": 5.752031068830266e-08,
2781
+ "loss": 0.0048,
2782
+ "step": 3230
2783
+ },
2784
+ {
2785
+ "epoch": 4.946092930063926,
2786
+ "grad_norm": 0.07761527597904205,
2787
+ "learning_rate": 3.4798873723984605e-08,
2788
+ "loss": 0.0013,
2789
+ "step": 3240
2790
+ },
2791
+ {
2792
+ "epoch": 4.961358648983875,
2793
+ "grad_norm": 0.5555828213691711,
2794
+ "learning_rate": 1.7755536287944464e-08,
2795
+ "loss": 0.0061,
2796
+ "step": 3250
2797
+ },
2798
+ {
2799
+ "epoch": 4.961358648983875,
2800
+ "eval_loss": 0.06215130165219307,
2801
+ "eval_runtime": 158.5647,
2802
+ "eval_samples_per_second": 7.347,
2803
+ "eval_steps_per_second": 7.347,
2804
+ "step": 3250
2805
+ },
2806
+ {
2807
+ "epoch": 4.976624367903826,
2808
+ "grad_norm": 0.009183814749121666,
2809
+ "learning_rate": 6.3922352034895276e-09,
2810
+ "loss": 0.0082,
2811
+ "step": 3260
2812
+ },
2813
+ {
2814
+ "epoch": 4.991890086823776,
2815
+ "grad_norm": 0.18164366483688354,
2816
+ "learning_rate": 7.102618084620094e-10,
2817
+ "loss": 0.005,
2818
+ "step": 3270
2819
+ },
2820
+ {
2821
+ "epoch": 4.999522946283752,
2822
+ "step": 3275,
2823
+ "total_flos": 8.22077121848279e+17,
2824
+ "train_loss": 0.04503766617872788,
2825
+ "train_runtime": 36493.551,
2826
+ "train_samples_per_second": 1.436,
2827
+ "train_steps_per_second": 0.09
2828
+ }
2829
+ ],
2830
+ "logging_steps": 10,
2831
+ "max_steps": 3275,
2832
+ "num_input_tokens_seen": 0,
2833
+ "num_train_epochs": 5,
2834
+ "save_steps": 50,
2835
+ "stateful_callbacks": {
2836
+ "TrainerControl": {
2837
+ "args": {
2838
+ "should_epoch_stop": false,
2839
+ "should_evaluate": false,
2840
+ "should_log": false,
2841
+ "should_save": true,
2842
+ "should_training_stop": true
2843
+ },
2844
+ "attributes": {}
2845
+ }
2846
+ },
2847
+ "total_flos": 8.22077121848279e+17,
2848
+ "train_batch_size": 1,
2849
+ "trial_name": null,
2850
+ "trial_params": null
2851
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold4/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db10fcb36c11fe6e3f77bd5560ff600fa59fe13096095c3a662e0904c23543d3
3
+ size 5624
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold4/training_eval_loss.png ADDED
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold4/training_loss.png ADDED