jjee2 commited on
Commit
1470207
·
verified ·
1 Parent(s): ea94442

Add chchen__Llama-3.1-8B-Instruct-PsyCourse-fold8

Browse files
.gitattributes CHANGED
@@ -48,3 +48,4 @@ chchen__Llama-3.1-8B-Instruct-PsyCourse-fold3/tokenizer.json filter=lfs diff=lfs
48
  cunghoctienganh__a7b71eb1-db0f-4c12-ae7f-75544046c341/tokenizer.json filter=lfs diff=lfs merge=lfs -text
49
  denbeo__62ffaa8b-b61d-4281-8bf1-d1626c4e6ea7/tokenizer.json filter=lfs diff=lfs merge=lfs -text
50
  thangla01__6ca44872-2a07-4763-8313-9cdc05879a21/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
48
  cunghoctienganh__a7b71eb1-db0f-4c12-ae7f-75544046c341/tokenizer.json filter=lfs diff=lfs merge=lfs -text
49
  denbeo__62ffaa8b-b61d-4281-8bf1-d1626c4e6ea7/tokenizer.json filter=lfs diff=lfs merge=lfs -text
50
  thangla01__6ca44872-2a07-4763-8313-9cdc05879a21/tokenizer.json filter=lfs diff=lfs merge=lfs -text
51
+ chchen__Llama-3.1-8B-Instruct-PsyCourse-fold8/tokenizer.json filter=lfs diff=lfs merge=lfs -text
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold8/.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-fold8/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-fold8
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-fold8
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-fold8 dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.0354
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
+ | 0.6782 | 0.0758 | 50 | 0.4323 |
56
+ | 0.1528 | 0.1516 | 100 | 0.0901 |
57
+ | 0.0741 | 0.2275 | 150 | 0.0665 |
58
+ | 0.0544 | 0.3033 | 200 | 0.0563 |
59
+ | 0.053 | 0.3791 | 250 | 0.0572 |
60
+ | 0.0626 | 0.4549 | 300 | 0.0589 |
61
+ | 0.0646 | 0.5308 | 350 | 0.0462 |
62
+ | 0.0336 | 0.6066 | 400 | 0.0449 |
63
+ | 0.0426 | 0.6824 | 450 | 0.0435 |
64
+ | 0.0354 | 0.7582 | 500 | 0.0468 |
65
+ | 0.0506 | 0.8340 | 550 | 0.0444 |
66
+ | 0.0346 | 0.9099 | 600 | 0.0411 |
67
+ | 0.0514 | 0.9857 | 650 | 0.0443 |
68
+ | 0.0323 | 1.0615 | 700 | 0.0412 |
69
+ | 0.0261 | 1.1373 | 750 | 0.0431 |
70
+ | 0.0307 | 1.2132 | 800 | 0.0398 |
71
+ | 0.0284 | 1.2890 | 850 | 0.0416 |
72
+ | 0.0316 | 1.3648 | 900 | 0.0398 |
73
+ | 0.0288 | 1.4406 | 950 | 0.0397 |
74
+ | 0.0306 | 1.5164 | 1000 | 0.0411 |
75
+ | 0.0449 | 1.5923 | 1050 | 0.0384 |
76
+ | 0.0281 | 1.6681 | 1100 | 0.0385 |
77
+ | 0.038 | 1.7439 | 1150 | 0.0376 |
78
+ | 0.0277 | 1.8197 | 1200 | 0.0354 |
79
+ | 0.0381 | 1.8956 | 1250 | 0.0377 |
80
+ | 0.0278 | 1.9714 | 1300 | 0.0359 |
81
+ | 0.0194 | 2.0472 | 1350 | 0.0393 |
82
+ | 0.0149 | 2.1230 | 1400 | 0.0375 |
83
+ | 0.0243 | 2.1988 | 1450 | 0.0402 |
84
+ | 0.0234 | 2.2747 | 1500 | 0.0396 |
85
+ | 0.0189 | 2.3505 | 1550 | 0.0392 |
86
+ | 0.0195 | 2.4263 | 1600 | 0.0396 |
87
+ | 0.0221 | 2.5021 | 1650 | 0.0475 |
88
+ | 0.0179 | 2.5780 | 1700 | 0.0408 |
89
+ | 0.0225 | 2.6538 | 1750 | 0.0386 |
90
+ | 0.0207 | 2.7296 | 1800 | 0.0398 |
91
+ | 0.015 | 2.8054 | 1850 | 0.0410 |
92
+ | 0.0295 | 2.8812 | 1900 | 0.0372 |
93
+ | 0.0227 | 2.9571 | 1950 | 0.0380 |
94
+ | 0.0128 | 3.0329 | 2000 | 0.0398 |
95
+ | 0.0096 | 3.1087 | 2050 | 0.0432 |
96
+ | 0.0076 | 3.1845 | 2100 | 0.0488 |
97
+ | 0.0122 | 3.2604 | 2150 | 0.0451 |
98
+ | 0.0101 | 3.3362 | 2200 | 0.0467 |
99
+ | 0.0124 | 3.4120 | 2250 | 0.0464 |
100
+ | 0.0113 | 3.4878 | 2300 | 0.0480 |
101
+ | 0.0126 | 3.5636 | 2350 | 0.0480 |
102
+ | 0.0114 | 3.6395 | 2400 | 0.0436 |
103
+ | 0.0071 | 3.7153 | 2450 | 0.0472 |
104
+ | 0.0117 | 3.7911 | 2500 | 0.0490 |
105
+ | 0.0145 | 3.8669 | 2550 | 0.0475 |
106
+ | 0.008 | 3.9428 | 2600 | 0.0459 |
107
+ | 0.0044 | 4.0186 | 2650 | 0.0480 |
108
+ | 0.0061 | 4.0944 | 2700 | 0.0542 |
109
+ | 0.0048 | 4.1702 | 2750 | 0.0556 |
110
+ | 0.0043 | 4.2460 | 2800 | 0.0557 |
111
+ | 0.0049 | 4.3219 | 2850 | 0.0570 |
112
+ | 0.0019 | 4.3977 | 2900 | 0.0587 |
113
+ | 0.0053 | 4.4735 | 2950 | 0.0595 |
114
+ | 0.0072 | 4.5493 | 3000 | 0.0597 |
115
+ | 0.0047 | 4.6252 | 3050 | 0.0599 |
116
+ | 0.003 | 4.7010 | 3100 | 0.0602 |
117
+ | 0.0025 | 4.7768 | 3150 | 0.0603 |
118
+ | 0.0027 | 4.8526 | 3200 | 0.0604 |
119
+ | 0.0022 | 4.9284 | 3250 | 0.0604 |
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-fold8/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
+ "down_proj",
25
+ "o_proj",
26
+ "q_proj",
27
+ "gate_proj",
28
+ "v_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-fold8/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8802731e188ee4e218cfc53219a500cf08561e558a93d330f73cd9e14ef5bf9a
3
+ size 83945296
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold8/all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.996682778883518,
3
+ "eval_loss": 0.03543492406606674,
4
+ "eval_runtime": 160.5577,
5
+ "eval_samples_per_second": 7.306,
6
+ "eval_steps_per_second": 7.306,
7
+ "total_flos": 8.269502901505229e+17,
8
+ "train_loss": 0.04518177697310657,
9
+ "train_runtime": 36119.4942,
10
+ "train_samples_per_second": 1.461,
11
+ "train_steps_per_second": 0.091
12
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold8/eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.996682778883518,
3
+ "eval_loss": 0.03543492406606674,
4
+ "eval_runtime": 160.5577,
5
+ "eval_samples_per_second": 7.306,
6
+ "eval_steps_per_second": 7.306
7
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold8/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-fold8
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/fold8
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-fold8
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-fold8/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-fold8/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-fold8/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-fold8/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.996682778883518,
3
+ "total_flos": 8.269502901505229e+17,
4
+ "train_loss": 0.04518177697310657,
5
+ "train_runtime": 36119.4942,
6
+ "train_samples_per_second": 1.461,
7
+ "train_steps_per_second": 0.091
8
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold8/trainer_log.jsonl ADDED
@@ -0,0 +1,395 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 3295, "loss": 1.59, "lr": 3.0303030303030305e-06, "epoch": 0.015164439389631315, "percentage": 0.3, "elapsed_time": "0:01:16", "remaining_time": "6:59:27"}
2
+ {"current_steps": 20, "total_steps": 3295, "loss": 1.5951, "lr": 6.060606060606061e-06, "epoch": 0.03032887877926263, "percentage": 0.61, "elapsed_time": "0:02:33", "remaining_time": "6:58:57"}
3
+ {"current_steps": 30, "total_steps": 3295, "loss": 1.2503, "lr": 9.090909090909091e-06, "epoch": 0.045493318168893945, "percentage": 0.91, "elapsed_time": "0:03:50", "remaining_time": "6:58:06"}
4
+ {"current_steps": 40, "total_steps": 3295, "loss": 0.9145, "lr": 1.2121212121212122e-05, "epoch": 0.06065775755852526, "percentage": 1.21, "elapsed_time": "0:05:07", "remaining_time": "6:57:06"}
5
+ {"current_steps": 50, "total_steps": 3295, "loss": 0.6782, "lr": 1.5151515151515153e-05, "epoch": 0.07582219694815658, "percentage": 1.52, "elapsed_time": "0:06:24", "remaining_time": "6:56:06"}
6
+ {"current_steps": 50, "total_steps": 3295, "eval_loss": 0.43230628967285156, "epoch": 0.07582219694815658, "percentage": 1.52, "elapsed_time": "0:09:04", "remaining_time": "9:48:45"}
7
+ {"current_steps": 60, "total_steps": 3295, "loss": 0.3929, "lr": 1.8181818181818182e-05, "epoch": 0.09098663633778789, "percentage": 1.82, "elapsed_time": "0:10:28", "remaining_time": "9:24:34"}
8
+ {"current_steps": 70, "total_steps": 3295, "loss": 0.2232, "lr": 2.1212121212121215e-05, "epoch": 0.1061510757274192, "percentage": 2.12, "elapsed_time": "0:11:45", "remaining_time": "9:01:33"}
9
+ {"current_steps": 80, "total_steps": 3295, "loss": 0.2301, "lr": 2.4242424242424244e-05, "epoch": 0.12131551511705052, "percentage": 2.43, "elapsed_time": "0:13:02", "remaining_time": "8:43:56"}
10
+ {"current_steps": 90, "total_steps": 3295, "loss": 0.127, "lr": 2.7272727272727273e-05, "epoch": 0.13647995450668182, "percentage": 2.73, "elapsed_time": "0:14:19", "remaining_time": "8:29:58"}
11
+ {"current_steps": 100, "total_steps": 3295, "loss": 0.1528, "lr": 3.0303030303030306e-05, "epoch": 0.15164439389631315, "percentage": 3.03, "elapsed_time": "0:15:36", "remaining_time": "8:18:29"}
12
+ {"current_steps": 100, "total_steps": 3295, "eval_loss": 0.0901423990726471, "epoch": 0.15164439389631315, "percentage": 3.03, "elapsed_time": "0:18:15", "remaining_time": "9:43:30"}
13
+ {"current_steps": 110, "total_steps": 3295, "loss": 0.0945, "lr": 3.3333333333333335e-05, "epoch": 0.16680883328594445, "percentage": 3.34, "elapsed_time": "0:19:37", "remaining_time": "9:28:08"}
14
+ {"current_steps": 120, "total_steps": 3295, "loss": 0.0798, "lr": 3.6363636363636364e-05, "epoch": 0.18197327267557578, "percentage": 3.64, "elapsed_time": "0:20:54", "remaining_time": "9:13:11"}
15
+ {"current_steps": 130, "total_steps": 3295, "loss": 0.0769, "lr": 3.939393939393939e-05, "epoch": 0.19713771206520708, "percentage": 3.95, "elapsed_time": "0:22:11", "remaining_time": "9:00:16"}
16
+ {"current_steps": 140, "total_steps": 3295, "loss": 0.0684, "lr": 4.242424242424243e-05, "epoch": 0.2123021514548384, "percentage": 4.25, "elapsed_time": "0:23:28", "remaining_time": "8:49:04"}
17
+ {"current_steps": 150, "total_steps": 3295, "loss": 0.0741, "lr": 4.545454545454546e-05, "epoch": 0.2274665908444697, "percentage": 4.55, "elapsed_time": "0:24:45", "remaining_time": "8:39:00"}
18
+ {"current_steps": 150, "total_steps": 3295, "eval_loss": 0.06654910743236542, "epoch": 0.2274665908444697, "percentage": 4.55, "elapsed_time": "0:27:24", "remaining_time": "9:34:49"}
19
+ {"current_steps": 160, "total_steps": 3295, "loss": 0.0795, "lr": 4.848484848484849e-05, "epoch": 0.24263103023410104, "percentage": 4.86, "elapsed_time": "0:28:47", "remaining_time": "9:24:08"}
20
+ {"current_steps": 170, "total_steps": 3295, "loss": 0.0702, "lr": 5.151515151515152e-05, "epoch": 0.25779546962373234, "percentage": 5.16, "elapsed_time": "0:30:04", "remaining_time": "9:12:52"}
21
+ {"current_steps": 180, "total_steps": 3295, "loss": 0.0818, "lr": 5.4545454545454546e-05, "epoch": 0.27295990901336364, "percentage": 5.46, "elapsed_time": "0:31:21", "remaining_time": "9:02:38"}
22
+ {"current_steps": 190, "total_steps": 3295, "loss": 0.0682, "lr": 5.757575757575758e-05, "epoch": 0.288124348402995, "percentage": 5.77, "elapsed_time": "0:32:38", "remaining_time": "8:53:27"}
23
+ {"current_steps": 200, "total_steps": 3295, "loss": 0.0544, "lr": 6.060606060606061e-05, "epoch": 0.3032887877926263, "percentage": 6.07, "elapsed_time": "0:33:55", "remaining_time": "8:45:03"}
24
+ {"current_steps": 200, "total_steps": 3295, "eval_loss": 0.05628184229135513, "epoch": 0.3032887877926263, "percentage": 6.07, "elapsed_time": "0:36:35", "remaining_time": "9:26:15"}
25
+ {"current_steps": 210, "total_steps": 3295, "loss": 0.0538, "lr": 6.363636363636364e-05, "epoch": 0.3184532271822576, "percentage": 6.37, "elapsed_time": "0:37:59", "remaining_time": "9:18:10"}
26
+ {"current_steps": 220, "total_steps": 3295, "loss": 0.0571, "lr": 6.666666666666667e-05, "epoch": 0.3336176665718889, "percentage": 6.68, "elapsed_time": "0:39:17", "remaining_time": "9:09:08"}
27
+ {"current_steps": 230, "total_steps": 3295, "loss": 0.0628, "lr": 6.96969696969697e-05, "epoch": 0.34878210596152026, "percentage": 6.98, "elapsed_time": "0:40:34", "remaining_time": "9:00:38"}
28
+ {"current_steps": 240, "total_steps": 3295, "loss": 0.0476, "lr": 7.272727272727273e-05, "epoch": 0.36394654535115156, "percentage": 7.28, "elapsed_time": "0:41:51", "remaining_time": "8:52:46"}
29
+ {"current_steps": 250, "total_steps": 3295, "loss": 0.053, "lr": 7.575757575757576e-05, "epoch": 0.37911098474078286, "percentage": 7.59, "elapsed_time": "0:43:08", "remaining_time": "8:45:25"}
30
+ {"current_steps": 250, "total_steps": 3295, "eval_loss": 0.0572020523250103, "epoch": 0.37911098474078286, "percentage": 7.59, "elapsed_time": "0:45:48", "remaining_time": "9:17:52"}
31
+ {"current_steps": 260, "total_steps": 3295, "loss": 0.0516, "lr": 7.878787878787879e-05, "epoch": 0.39427542413041416, "percentage": 7.89, "elapsed_time": "0:47:09", "remaining_time": "9:10:32"}
32
+ {"current_steps": 270, "total_steps": 3295, "loss": 0.0712, "lr": 8.181818181818183e-05, "epoch": 0.40943986352004547, "percentage": 8.19, "elapsed_time": "0:48:27", "remaining_time": "9:02:52"}
33
+ {"current_steps": 280, "total_steps": 3295, "loss": 0.0531, "lr": 8.484848484848486e-05, "epoch": 0.4246043029096768, "percentage": 8.5, "elapsed_time": "0:49:44", "remaining_time": "8:55:32"}
34
+ {"current_steps": 290, "total_steps": 3295, "loss": 0.0466, "lr": 8.787878787878789e-05, "epoch": 0.4397687422993081, "percentage": 8.8, "elapsed_time": "0:51:01", "remaining_time": "8:48:41"}
35
+ {"current_steps": 300, "total_steps": 3295, "loss": 0.0626, "lr": 9.090909090909092e-05, "epoch": 0.4549331816889394, "percentage": 9.1, "elapsed_time": "0:52:18", "remaining_time": "8:42:12"}
36
+ {"current_steps": 300, "total_steps": 3295, "eval_loss": 0.05890120193362236, "epoch": 0.4549331816889394, "percentage": 9.1, "elapsed_time": "0:54:58", "remaining_time": "9:08:47"}
37
+ {"current_steps": 310, "total_steps": 3295, "loss": 0.0501, "lr": 9.393939393939395e-05, "epoch": 0.4700976210785707, "percentage": 9.41, "elapsed_time": "0:56:19", "remaining_time": "9:02:25"}
38
+ {"current_steps": 320, "total_steps": 3295, "loss": 0.0443, "lr": 9.696969696969698e-05, "epoch": 0.4852620604682021, "percentage": 9.71, "elapsed_time": "0:57:37", "remaining_time": "8:55:40"}
39
+ {"current_steps": 330, "total_steps": 3295, "loss": 0.0479, "lr": 0.0001, "epoch": 0.5004264998578334, "percentage": 10.02, "elapsed_time": "0:58:54", "remaining_time": "8:49:14"}
40
+ {"current_steps": 340, "total_steps": 3295, "loss": 0.0507, "lr": 9.999719336268101e-05, "epoch": 0.5155909392474647, "percentage": 10.32, "elapsed_time": "1:00:11", "remaining_time": "8:43:04"}
41
+ {"current_steps": 350, "total_steps": 3295, "loss": 0.0646, "lr": 9.998877376581251e-05, "epoch": 0.530755378637096, "percentage": 10.62, "elapsed_time": "1:01:28", "remaining_time": "8:37:16"}
42
+ {"current_steps": 350, "total_steps": 3295, "eval_loss": 0.04616093635559082, "epoch": 0.530755378637096, "percentage": 10.62, "elapsed_time": "1:04:08", "remaining_time": "8:59:41"}
43
+ {"current_steps": 360, "total_steps": 3295, "loss": 0.0549, "lr": 9.997474215462472e-05, "epoch": 0.5459198180267273, "percentage": 10.93, "elapsed_time": "1:05:30", "remaining_time": "8:54:08"}
44
+ {"current_steps": 370, "total_steps": 3295, "loss": 0.0442, "lr": 9.995510010438337e-05, "epoch": 0.5610842574163586, "percentage": 11.23, "elapsed_time": "1:06:48", "remaining_time": "8:48:07"}
45
+ {"current_steps": 380, "total_steps": 3295, "loss": 0.0607, "lr": 9.992984982021295e-05, "epoch": 0.57624869680599, "percentage": 11.53, "elapsed_time": "1:08:05", "remaining_time": "8:42:20"}
46
+ {"current_steps": 390, "total_steps": 3295, "loss": 0.0526, "lr": 9.9898994136849e-05, "epoch": 0.5914131361956213, "percentage": 11.84, "elapsed_time": "1:09:22", "remaining_time": "8:36:47"}
47
+ {"current_steps": 400, "total_steps": 3295, "loss": 0.0336, "lr": 9.986253651832005e-05, "epoch": 0.6065775755852526, "percentage": 12.14, "elapsed_time": "1:10:39", "remaining_time": "8:31:24"}
48
+ {"current_steps": 400, "total_steps": 3295, "eval_loss": 0.04486996307969093, "epoch": 0.6065775755852526, "percentage": 12.14, "elapsed_time": "1:13:19", "remaining_time": "8:50:41"}
49
+ {"current_steps": 410, "total_steps": 3295, "loss": 0.0409, "lr": 9.982048105755859e-05, "epoch": 0.6217420149748839, "percentage": 12.44, "elapsed_time": "1:14:41", "remaining_time": "8:45:34"}
50
+ {"current_steps": 420, "total_steps": 3295, "loss": 0.052, "lr": 9.977283247594166e-05, "epoch": 0.6369064543645152, "percentage": 12.75, "elapsed_time": "1:15:58", "remaining_time": "8:40:06"}
51
+ {"current_steps": 430, "total_steps": 3295, "loss": 0.047, "lr": 9.971959612276076e-05, "epoch": 0.6520708937541465, "percentage": 13.05, "elapsed_time": "1:17:16", "remaining_time": "8:34:49"}
52
+ {"current_steps": 440, "total_steps": 3295, "loss": 0.0456, "lr": 9.966077797462129e-05, "epoch": 0.6672353331437778, "percentage": 13.35, "elapsed_time": "1:18:33", "remaining_time": "8:29:44"}
53
+ {"current_steps": 450, "total_steps": 3295, "loss": 0.0426, "lr": 9.959638463477165e-05, "epoch": 0.6823997725334091, "percentage": 13.66, "elapsed_time": "1:19:50", "remaining_time": "8:24:48"}
54
+ {"current_steps": 450, "total_steps": 3295, "eval_loss": 0.043455954641103745, "epoch": 0.6823997725334091, "percentage": 13.66, "elapsed_time": "1:22:30", "remaining_time": "8:41:38"}
55
+ {"current_steps": 460, "total_steps": 3295, "loss": 0.0471, "lr": 9.952642333236186e-05, "epoch": 0.6975642119230405, "percentage": 13.96, "elapsed_time": "1:23:52", "remaining_time": "8:36:54"}
56
+ {"current_steps": 470, "total_steps": 3295, "loss": 0.0514, "lr": 9.945090192163202e-05, "epoch": 0.7127286513126718, "percentage": 14.26, "elapsed_time": "1:25:09", "remaining_time": "8:31:53"}
57
+ {"current_steps": 480, "total_steps": 3295, "loss": 0.0372, "lr": 9.936982888103051e-05, "epoch": 0.7278930907023031, "percentage": 14.57, "elapsed_time": "1:26:26", "remaining_time": "8:26:56"}
58
+ {"current_steps": 490, "total_steps": 3295, "loss": 0.036, "lr": 9.928321331226219e-05, "epoch": 0.7430575300919344, "percentage": 14.87, "elapsed_time": "1:27:43", "remaining_time": "8:22:13"}
59
+ {"current_steps": 500, "total_steps": 3295, "loss": 0.0354, "lr": 9.919106493926655e-05, "epoch": 0.7582219694815657, "percentage": 15.17, "elapsed_time": "1:29:01", "remaining_time": "8:17:37"}
60
+ {"current_steps": 500, "total_steps": 3295, "eval_loss": 0.04678919166326523, "epoch": 0.7582219694815657, "percentage": 15.17, "elapsed_time": "1:31:41", "remaining_time": "8:32:31"}
61
+ {"current_steps": 510, "total_steps": 3295, "loss": 0.0463, "lr": 9.909339410712612e-05, "epoch": 0.773386408871197, "percentage": 15.48, "elapsed_time": "1:33:02", "remaining_time": "8:28:07"}
62
+ {"current_steps": 520, "total_steps": 3295, "loss": 0.0388, "lr": 9.8990211780905e-05, "epoch": 0.7885508482608283, "percentage": 15.78, "elapsed_time": "1:34:20", "remaining_time": "8:23:26"}
63
+ {"current_steps": 530, "total_steps": 3295, "loss": 0.0368, "lr": 9.888152954441785e-05, "epoch": 0.8037152876504596, "percentage": 16.08, "elapsed_time": "1:35:37", "remaining_time": "8:18:50"}
64
+ {"current_steps": 540, "total_steps": 3295, "loss": 0.039, "lr": 9.876735959892953e-05, "epoch": 0.8188797270400909, "percentage": 16.39, "elapsed_time": "1:36:54", "remaining_time": "8:14:23"}
65
+ {"current_steps": 550, "total_steps": 3295, "loss": 0.0506, "lr": 9.864771476178522e-05, "epoch": 0.8340441664297223, "percentage": 16.69, "elapsed_time": "1:38:11", "remaining_time": "8:10:03"}
66
+ {"current_steps": 550, "total_steps": 3295, "eval_loss": 0.04438818246126175, "epoch": 0.8340441664297223, "percentage": 16.69, "elapsed_time": "1:40:51", "remaining_time": "8:23:21"}
67
+ {"current_steps": 560, "total_steps": 3295, "loss": 0.0515, "lr": 9.852260846497153e-05, "epoch": 0.8492086058193536, "percentage": 17.0, "elapsed_time": "1:42:13", "remaining_time": "8:19:14"}
68
+ {"current_steps": 570, "total_steps": 3295, "loss": 0.0537, "lr": 9.839205475360851e-05, "epoch": 0.864373045208985, "percentage": 17.3, "elapsed_time": "1:43:30", "remaining_time": "8:14:50"}
69
+ {"current_steps": 580, "total_steps": 3295, "loss": 0.0497, "lr": 9.825606828437291e-05, "epoch": 0.8795374845986162, "percentage": 17.6, "elapsed_time": "1:44:47", "remaining_time": "8:10:30"}
70
+ {"current_steps": 590, "total_steps": 3295, "loss": 0.0392, "lr": 9.811466432385267e-05, "epoch": 0.8947019239882475, "percentage": 17.91, "elapsed_time": "1:46:04", "remaining_time": "8:06:18"}
71
+ {"current_steps": 600, "total_steps": 3295, "loss": 0.0346, "lr": 9.796785874683314e-05, "epoch": 0.9098663633778789, "percentage": 18.21, "elapsed_time": "1:47:21", "remaining_time": "8:02:12"}
72
+ {"current_steps": 600, "total_steps": 3295, "eval_loss": 0.04112881049513817, "epoch": 0.9098663633778789, "percentage": 18.21, "elapsed_time": "1:50:01", "remaining_time": "8:14:10"}
73
+ {"current_steps": 610, "total_steps": 3295, "loss": 0.05, "lr": 9.781566803451475e-05, "epoch": 0.9250308027675102, "percentage": 18.51, "elapsed_time": "1:51:23", "remaining_time": "8:10:17"}
74
+ {"current_steps": 620, "total_steps": 3295, "loss": 0.0414, "lr": 9.765810927266281e-05, "epoch": 0.9401952421571415, "percentage": 18.82, "elapsed_time": "1:52:40", "remaining_time": "8:06:09"}
75
+ {"current_steps": 630, "total_steps": 3295, "loss": 0.0389, "lr": 9.749520014968934e-05, "epoch": 0.9553596815467729, "percentage": 19.12, "elapsed_time": "1:53:57", "remaining_time": "8:02:05"}
76
+ {"current_steps": 640, "total_steps": 3295, "loss": 0.0449, "lr": 9.732695895466735e-05, "epoch": 0.9705241209364042, "percentage": 19.42, "elapsed_time": "1:55:15", "remaining_time": "7:58:07"}
77
+ {"current_steps": 650, "total_steps": 3295, "loss": 0.0514, "lr": 9.715340457527746e-05, "epoch": 0.9856885603260355, "percentage": 19.73, "elapsed_time": "1:56:32", "remaining_time": "7:54:14"}
78
+ {"current_steps": 650, "total_steps": 3295, "eval_loss": 0.04426902160048485, "epoch": 0.9856885603260355, "percentage": 19.73, "elapsed_time": "1:59:12", "remaining_time": "8:05:04"}
79
+ {"current_steps": 660, "total_steps": 3295, "loss": 0.04, "lr": 9.697455649568761e-05, "epoch": 1.0008529997156668, "percentage": 20.03, "elapsed_time": "2:00:34", "remaining_time": "8:01:21"}
80
+ {"current_steps": 670, "total_steps": 3295, "loss": 0.0294, "lr": 9.679043479436556e-05, "epoch": 1.016017439105298, "percentage": 20.33, "elapsed_time": "2:01:51", "remaining_time": "7:57:26"}
81
+ {"current_steps": 680, "total_steps": 3295, "loss": 0.0277, "lr": 9.660106014182489e-05, "epoch": 1.0311818784949294, "percentage": 20.64, "elapsed_time": "2:03:08", "remaining_time": "7:53:32"}
82
+ {"current_steps": 690, "total_steps": 3295, "loss": 0.0444, "lr": 9.640645379830424e-05, "epoch": 1.0463463178845607, "percentage": 20.94, "elapsed_time": "2:04:25", "remaining_time": "7:49:45"}
83
+ {"current_steps": 700, "total_steps": 3295, "loss": 0.0323, "lr": 9.620663761138067e-05, "epoch": 1.061510757274192, "percentage": 21.24, "elapsed_time": "2:05:42", "remaining_time": "7:46:01"}
84
+ {"current_steps": 700, "total_steps": 3295, "eval_loss": 0.041203178465366364, "epoch": 1.061510757274192, "percentage": 21.24, "elapsed_time": "2:08:22", "remaining_time": "7:55:54"}
85
+ {"current_steps": 710, "total_steps": 3295, "loss": 0.0261, "lr": 9.600163401351688e-05, "epoch": 1.0766751966638233, "percentage": 21.55, "elapsed_time": "2:09:44", "remaining_time": "7:52:23"}
86
+ {"current_steps": 720, "total_steps": 3295, "loss": 0.0453, "lr": 9.579146601954276e-05, "epoch": 1.0918396360534546, "percentage": 21.85, "elapsed_time": "2:11:02", "remaining_time": "7:48:38"}
87
+ {"current_steps": 730, "total_steps": 3295, "loss": 0.0364, "lr": 9.557615722407177e-05, "epoch": 1.1070040754430859, "percentage": 22.15, "elapsed_time": "2:12:19", "remaining_time": "7:44:55"}
88
+ {"current_steps": 740, "total_steps": 3295, "loss": 0.0279, "lr": 9.535573179885191e-05, "epoch": 1.1221685148327172, "percentage": 22.46, "elapsed_time": "2:13:35", "remaining_time": "7:41:15"}
89
+ {"current_steps": 750, "total_steps": 3295, "loss": 0.0261, "lr": 9.513021449005214e-05, "epoch": 1.1373329542223485, "percentage": 22.76, "elapsed_time": "2:14:52", "remaining_time": "7:37:40"}
90
+ {"current_steps": 750, "total_steps": 3295, "eval_loss": 0.04307902976870537, "epoch": 1.1373329542223485, "percentage": 22.76, "elapsed_time": "2:17:32", "remaining_time": "7:46:42"}
91
+ {"current_steps": 760, "total_steps": 3295, "loss": 0.0326, "lr": 9.489963061548428e-05, "epoch": 1.15249739361198, "percentage": 23.07, "elapsed_time": "2:18:54", "remaining_time": "7:43:20"}
92
+ {"current_steps": 770, "total_steps": 3295, "loss": 0.0232, "lr": 9.466400606176062e-05, "epoch": 1.1676618330016113, "percentage": 23.37, "elapsed_time": "2:20:12", "remaining_time": "7:39:44"}
93
+ {"current_steps": 780, "total_steps": 3295, "loss": 0.0235, "lr": 9.442336728138779e-05, "epoch": 1.1828262723912426, "percentage": 23.67, "elapsed_time": "2:21:28", "remaining_time": "7:36:11"}
94
+ {"current_steps": 790, "total_steps": 3295, "loss": 0.0364, "lr": 9.417774128979706e-05, "epoch": 1.197990711780874, "percentage": 23.98, "elapsed_time": "2:22:45", "remaining_time": "7:32:41"}
95
+ {"current_steps": 800, "total_steps": 3295, "loss": 0.0307, "lr": 9.39271556623114e-05, "epoch": 1.2131551511705052, "percentage": 24.28, "elapsed_time": "2:24:03", "remaining_time": "7:29:16"}
96
+ {"current_steps": 800, "total_steps": 3295, "eval_loss": 0.03978438675403595, "epoch": 1.2131551511705052, "percentage": 24.28, "elapsed_time": "2:26:43", "remaining_time": "7:37:34"}
97
+ {"current_steps": 810, "total_steps": 3295, "loss": 0.039, "lr": 9.367163853104975e-05, "epoch": 1.2283195905601365, "percentage": 24.58, "elapsed_time": "2:28:05", "remaining_time": "7:34:19"}
98
+ {"current_steps": 820, "total_steps": 3295, "loss": 0.0413, "lr": 9.341121858176876e-05, "epoch": 1.2434840299497678, "percentage": 24.89, "elapsed_time": "2:29:22", "remaining_time": "7:30:50"}
99
+ {"current_steps": 830, "total_steps": 3295, "loss": 0.036, "lr": 9.314592505064239e-05, "epoch": 1.2586484693393991, "percentage": 25.19, "elapsed_time": "2:30:39", "remaining_time": "7:27:25"}
100
+ {"current_steps": 840, "total_steps": 3295, "loss": 0.0258, "lr": 9.28757877209796e-05, "epoch": 1.2738129087290304, "percentage": 25.49, "elapsed_time": "2:31:56", "remaining_time": "7:24:03"}
101
+ {"current_steps": 850, "total_steps": 3295, "loss": 0.0284, "lr": 9.260083691988084e-05, "epoch": 1.2889773481186617, "percentage": 25.8, "elapsed_time": "2:33:12", "remaining_time": "7:20:43"}
102
+ {"current_steps": 850, "total_steps": 3295, "eval_loss": 0.04156646877527237, "epoch": 1.2889773481186617, "percentage": 25.8, "elapsed_time": "2:35:52", "remaining_time": "7:28:22"}
103
+ {"current_steps": 860, "total_steps": 3295, "loss": 0.0368, "lr": 9.232110351483327e-05, "epoch": 1.304141787508293, "percentage": 26.1, "elapsed_time": "2:37:14", "remaining_time": "7:25:12"}
104
+ {"current_steps": 870, "total_steps": 3295, "loss": 0.0369, "lr": 9.203661891024547e-05, "epoch": 1.3193062268979243, "percentage": 26.4, "elapsed_time": "2:38:31", "remaining_time": "7:21:51"}
105
+ {"current_steps": 880, "total_steps": 3295, "loss": 0.0345, "lr": 9.174741504392173e-05, "epoch": 1.3344706662875556, "percentage": 26.71, "elapsed_time": "2:39:48", "remaining_time": "7:18:33"}
106
+ {"current_steps": 890, "total_steps": 3295, "loss": 0.0413, "lr": 9.145352438347662e-05, "epoch": 1.349635105677187, "percentage": 27.01, "elapsed_time": "2:41:05", "remaining_time": "7:15:18"}
107
+ {"current_steps": 900, "total_steps": 3295, "loss": 0.0316, "lr": 9.115497992268995e-05, "epoch": 1.3647995450668184, "percentage": 27.31, "elapsed_time": "2:42:22", "remaining_time": "7:12:06"}
108
+ {"current_steps": 900, "total_steps": 3295, "eval_loss": 0.03982315585017204, "epoch": 1.3647995450668184, "percentage": 27.31, "elapsed_time": "2:45:02", "remaining_time": "7:19:11"}
109
+ {"current_steps": 910, "total_steps": 3295, "loss": 0.0309, "lr": 9.085181517780273e-05, "epoch": 1.3799639844564497, "percentage": 27.62, "elapsed_time": "2:46:25", "remaining_time": "7:16:10"}
110
+ {"current_steps": 920, "total_steps": 3295, "loss": 0.0355, "lr": 9.054406418375443e-05, "epoch": 1.395128423846081, "percentage": 27.92, "elapsed_time": "2:47:42", "remaining_time": "7:12:57"}
111
+ {"current_steps": 930, "total_steps": 3295, "loss": 0.0299, "lr": 9.023176149036203e-05, "epoch": 1.4102928632357123, "percentage": 28.22, "elapsed_time": "2:49:00", "remaining_time": "7:09:46"}
112
+ {"current_steps": 940, "total_steps": 3295, "loss": 0.0416, "lr": 8.991494215844132e-05, "epoch": 1.4254573026253436, "percentage": 28.53, "elapsed_time": "2:50:17", "remaining_time": "7:06:37"}
113
+ {"current_steps": 950, "total_steps": 3295, "loss": 0.0288, "lr": 8.959364175587069e-05, "epoch": 1.440621742014975, "percentage": 28.83, "elapsed_time": "2:51:34", "remaining_time": "7:03:30"}
114
+ {"current_steps": 950, "total_steps": 3295, "eval_loss": 0.039692338556051254, "epoch": 1.440621742014975, "percentage": 28.83, "elapsed_time": "2:54:14", "remaining_time": "7:10:05"}
115
+ {"current_steps": 960, "total_steps": 3295, "loss": 0.0448, "lr": 8.926789635359817e-05, "epoch": 1.4557861814046062, "percentage": 29.14, "elapsed_time": "2:55:35", "remaining_time": "7:07:04"}
116
+ {"current_steps": 970, "total_steps": 3295, "loss": 0.0294, "lr": 8.893774252159187e-05, "epoch": 1.4709506207942376, "percentage": 29.44, "elapsed_time": "2:56:52", "remaining_time": "7:03:57"}
117
+ {"current_steps": 980, "total_steps": 3295, "loss": 0.0396, "lr": 8.860321732473439e-05, "epoch": 1.4861150601838689, "percentage": 29.74, "elapsed_time": "2:58:09", "remaining_time": "7:00:51"}
118
+ {"current_steps": 990, "total_steps": 3295, "loss": 0.0389, "lr": 8.826435831866184e-05, "epoch": 1.5012794995735002, "percentage": 30.05, "elapsed_time": "2:59:26", "remaining_time": "6:57:47"}
119
+ {"current_steps": 1000, "total_steps": 3295, "loss": 0.0306, "lr": 8.79212035455475e-05, "epoch": 1.5164439389631315, "percentage": 30.35, "elapsed_time": "3:00:43", "remaining_time": "6:54:46"}
120
+ {"current_steps": 1000, "total_steps": 3295, "eval_loss": 0.041055887937545776, "epoch": 1.5164439389631315, "percentage": 30.35, "elapsed_time": "3:03:23", "remaining_time": "7:00:53"}
121
+ {"current_steps": 1010, "total_steps": 3295, "loss": 0.03, "lr": 8.757379152983103e-05, "epoch": 1.5316083783527628, "percentage": 30.65, "elapsed_time": "3:04:45", "remaining_time": "6:58:00"}
122
+ {"current_steps": 1020, "total_steps": 3295, "loss": 0.0335, "lr": 8.722216127389363e-05, "epoch": 1.546772817742394, "percentage": 30.96, "elapsed_time": "3:06:02", "remaining_time": "6:54:57"}
123
+ {"current_steps": 1030, "total_steps": 3295, "loss": 0.0361, "lr": 8.686635225367919e-05, "epoch": 1.5619372571320254, "percentage": 31.26, "elapsed_time": "3:07:20", "remaining_time": "6:51:57"}
124
+ {"current_steps": 1040, "total_steps": 3295, "loss": 0.038, "lr": 8.650640441426274e-05, "epoch": 1.5771016965216567, "percentage": 31.56, "elapsed_time": "3:08:37", "remaining_time": "6:48:58"}
125
+ {"current_steps": 1050, "total_steps": 3295, "loss": 0.0449, "lr": 8.614235816536582e-05, "epoch": 1.592266135911288, "percentage": 31.87, "elapsed_time": "3:09:54", "remaining_time": "6:46:01"}
126
+ {"current_steps": 1050, "total_steps": 3295, "eval_loss": 0.03836758807301521, "epoch": 1.592266135911288, "percentage": 31.87, "elapsed_time": "3:12:34", "remaining_time": "6:51:43"}
127
+ {"current_steps": 1060, "total_steps": 3295, "loss": 0.0377, "lr": 8.577425437681994e-05, "epoch": 1.6074305753009193, "percentage": 32.17, "elapsed_time": "3:13:55", "remaining_time": "6:48:54"}
128
+ {"current_steps": 1070, "total_steps": 3295, "loss": 0.0322, "lr": 8.540213437397833e-05, "epoch": 1.6225950146905506, "percentage": 32.47, "elapsed_time": "3:15:13", "remaining_time": "6:45:56"}
129
+ {"current_steps": 1080, "total_steps": 3295, "loss": 0.0273, "lr": 8.502603993307647e-05, "epoch": 1.6377594540801819, "percentage": 32.78, "elapsed_time": "3:16:30", "remaining_time": "6:43:01"}
130
+ {"current_steps": 1090, "total_steps": 3295, "loss": 0.0251, "lr": 8.464601327654207e-05, "epoch": 1.6529238934698132, "percentage": 33.08, "elapsed_time": "3:17:47", "remaining_time": "6:40:06"}
131
+ {"current_steps": 1100, "total_steps": 3295, "loss": 0.0281, "lr": 8.4262097068255e-05, "epoch": 1.6680883328594445, "percentage": 33.38, "elapsed_time": "3:19:04", "remaining_time": "6:37:14"}
132
+ {"current_steps": 1100, "total_steps": 3295, "eval_loss": 0.038478951901197433, "epoch": 1.6680883328594445, "percentage": 33.38, "elapsed_time": "3:21:44", "remaining_time": "6:42:33"}
133
+ {"current_steps": 1110, "total_steps": 3295, "loss": 0.0331, "lr": 8.387433440875758e-05, "epoch": 1.6832527722490758, "percentage": 33.69, "elapsed_time": "3:23:05", "remaining_time": "6:39:47"}
134
+ {"current_steps": 1120, "total_steps": 3295, "loss": 0.0336, "lr": 8.348276883041583e-05, "epoch": 1.698417211638707, "percentage": 33.99, "elapsed_time": "3:24:23", "remaining_time": "6:36:54"}
135
+ {"current_steps": 1130, "total_steps": 3295, "loss": 0.0464, "lr": 8.308744429253238e-05, "epoch": 1.7135816510283386, "percentage": 34.29, "elapsed_time": "3:25:40", "remaining_time": "6:34:02"}
136
+ {"current_steps": 1140, "total_steps": 3295, "loss": 0.0345, "lr": 8.268840517641123e-05, "epoch": 1.72874609041797, "percentage": 34.6, "elapsed_time": "3:26:57", "remaining_time": "6:31:12"}
137
+ {"current_steps": 1150, "total_steps": 3295, "loss": 0.038, "lr": 8.228569628037543e-05, "epoch": 1.7439105298076012, "percentage": 34.9, "elapsed_time": "3:28:14", "remaining_time": "6:28:24"}
138
+ {"current_steps": 1150, "total_steps": 3295, "eval_loss": 0.03758051246404648, "epoch": 1.7439105298076012, "percentage": 34.9, "elapsed_time": "3:30:54", "remaining_time": "6:33:22"}
139
+ {"current_steps": 1160, "total_steps": 3295, "loss": 0.0325, "lr": 8.187936281473758e-05, "epoch": 1.7590749691972325, "percentage": 35.2, "elapsed_time": "3:32:16", "remaining_time": "6:30:41"}
140
+ {"current_steps": 1170, "total_steps": 3295, "loss": 0.0276, "lr": 8.146945039672446e-05, "epoch": 1.7742394085868638, "percentage": 35.51, "elapsed_time": "3:33:33", "remaining_time": "6:27:52"}
141
+ {"current_steps": 1180, "total_steps": 3295, "loss": 0.0306, "lr": 8.105600504535567e-05, "epoch": 1.789403847976495, "percentage": 35.81, "elapsed_time": "3:34:50", "remaining_time": "6:25:04"}
142
+ {"current_steps": 1190, "total_steps": 3295, "loss": 0.0416, "lr": 8.06390731762773e-05, "epoch": 1.8045682873661264, "percentage": 36.12, "elapsed_time": "3:36:07", "remaining_time": "6:22:18"}
143
+ {"current_steps": 1200, "total_steps": 3295, "loss": 0.0277, "lr": 8.021870159655109e-05, "epoch": 1.8197327267557577, "percentage": 36.42, "elapsed_time": "3:37:25", "remaining_time": "6:19:34"}
144
+ {"current_steps": 1200, "total_steps": 3295, "eval_loss": 0.03543492406606674, "epoch": 1.8197327267557577, "percentage": 36.42, "elapsed_time": "3:40:04", "remaining_time": "6:24:13"}
145
+ {"current_steps": 1210, "total_steps": 3295, "loss": 0.0335, "lr": 7.979493749939955e-05, "epoch": 1.8348971661453892, "percentage": 36.72, "elapsed_time": "3:41:27", "remaining_time": "6:21:35"}
146
+ {"current_steps": 1220, "total_steps": 3295, "loss": 0.0421, "lr": 7.93678284589079e-05, "epoch": 1.8500616055350205, "percentage": 37.03, "elapsed_time": "3:42:44", "remaining_time": "6:18:50"}
147
+ {"current_steps": 1230, "total_steps": 3295, "loss": 0.0282, "lr": 7.893742242468301e-05, "epoch": 1.8652260449246518, "percentage": 37.33, "elapsed_time": "3:44:01", "remaining_time": "6:16:06"}
148
+ {"current_steps": 1240, "total_steps": 3295, "loss": 0.0386, "lr": 7.850376771647038e-05, "epoch": 1.8803904843142831, "percentage": 37.63, "elapsed_time": "3:45:18", "remaining_time": "6:13:24"}
149
+ {"current_steps": 1250, "total_steps": 3295, "loss": 0.0381, "lr": 7.806691301872958e-05, "epoch": 1.8955549237039144, "percentage": 37.94, "elapsed_time": "3:46:36", "remaining_time": "6:10:43"}
150
+ {"current_steps": 1250, "total_steps": 3295, "eval_loss": 0.037748388946056366, "epoch": 1.8955549237039144, "percentage": 37.94, "elapsed_time": "3:49:15", "remaining_time": "6:15:04"}
151
+ {"current_steps": 1260, "total_steps": 3295, "loss": 0.0359, "lr": 7.762690737516846e-05, "epoch": 1.9107193630935457, "percentage": 38.24, "elapsed_time": "3:50:38", "remaining_time": "6:12:29"}
152
+ {"current_steps": 1270, "total_steps": 3295, "loss": 0.0326, "lr": 7.718380018323742e-05, "epoch": 1.925883802483177, "percentage": 38.54, "elapsed_time": "3:51:55", "remaining_time": "6:09:47"}
153
+ {"current_steps": 1280, "total_steps": 3295, "loss": 0.0279, "lr": 7.673764118858371e-05, "epoch": 1.9410482418728083, "percentage": 38.85, "elapsed_time": "3:53:12", "remaining_time": "6:07:07"}
154
+ {"current_steps": 1290, "total_steps": 3295, "loss": 0.0408, "lr": 7.628848047946675e-05, "epoch": 1.9562126812624396, "percentage": 39.15, "elapsed_time": "3:54:29", "remaining_time": "6:04:27"}
155
+ {"current_steps": 1300, "total_steps": 3295, "loss": 0.0278, "lr": 7.583636848113483e-05, "epoch": 1.971377120652071, "percentage": 39.45, "elapsed_time": "3:55:46", "remaining_time": "6:01:49"}
156
+ {"current_steps": 1300, "total_steps": 3295, "eval_loss": 0.03594334051012993, "epoch": 1.971377120652071, "percentage": 39.45, "elapsed_time": "3:58:26", "remaining_time": "6:05:54"}
157
+ {"current_steps": 1310, "total_steps": 3295, "loss": 0.0322, "lr": 7.538135595016423e-05, "epoch": 1.9865415600417022, "percentage": 39.76, "elapsed_time": "3:59:47", "remaining_time": "6:03:21"}
158
+ {"current_steps": 1320, "total_steps": 3295, "loss": 0.0292, "lr": 7.492349396876096e-05, "epoch": 2.0017059994313335, "percentage": 40.06, "elapsed_time": "4:01:05", "remaining_time": "6:00:43"}
159
+ {"current_steps": 1330, "total_steps": 3295, "loss": 0.0237, "lr": 7.4462833939026e-05, "epoch": 2.016870438820965, "percentage": 40.36, "elapsed_time": "4:02:22", "remaining_time": "5:58:05"}
160
+ {"current_steps": 1340, "total_steps": 3295, "loss": 0.0219, "lr": 7.399942757718455e-05, "epoch": 2.032034878210596, "percentage": 40.67, "elapsed_time": "4:03:39", "remaining_time": "5:55:28"}
161
+ {"current_steps": 1350, "total_steps": 3295, "loss": 0.0194, "lr": 7.35333269077802e-05, "epoch": 2.0471993176002274, "percentage": 40.97, "elapsed_time": "4:04:56", "remaining_time": "5:52:53"}
162
+ {"current_steps": 1350, "total_steps": 3295, "eval_loss": 0.03932846337556839, "epoch": 2.0471993176002274, "percentage": 40.97, "elapsed_time": "4:07:36", "remaining_time": "5:56:44"}
163
+ {"current_steps": 1360, "total_steps": 3295, "loss": 0.0287, "lr": 7.306458425783426e-05, "epoch": 2.0623637569898587, "percentage": 41.27, "elapsed_time": "4:08:58", "remaining_time": "5:54:14"}
164
+ {"current_steps": 1370, "total_steps": 3295, "loss": 0.02, "lr": 7.25932522509713e-05, "epoch": 2.07752819637949, "percentage": 41.58, "elapsed_time": "4:10:15", "remaining_time": "5:51:38"}
165
+ {"current_steps": 1380, "total_steps": 3295, "loss": 0.0244, "lr": 7.211938380151133e-05, "epoch": 2.0926926357691213, "percentage": 41.88, "elapsed_time": "4:11:31", "remaining_time": "5:49:02"}
166
+ {"current_steps": 1390, "total_steps": 3295, "loss": 0.0309, "lr": 7.164303210852934e-05, "epoch": 2.1078570751587526, "percentage": 42.19, "elapsed_time": "4:12:48", "remaining_time": "5:46:29"}
167
+ {"current_steps": 1400, "total_steps": 3295, "loss": 0.0149, "lr": 7.116425064988286e-05, "epoch": 2.123021514548384, "percentage": 42.49, "elapsed_time": "4:14:05", "remaining_time": "5:43:56"}
168
+ {"current_steps": 1400, "total_steps": 3295, "eval_loss": 0.03746328130364418, "epoch": 2.123021514548384, "percentage": 42.49, "elapsed_time": "4:16:45", "remaining_time": "5:47:32"}
169
+ {"current_steps": 1410, "total_steps": 3295, "loss": 0.0244, "lr": 7.068309317620827e-05, "epoch": 2.1381859539380152, "percentage": 42.79, "elapsed_time": "4:18:08", "remaining_time": "5:45:06"}
170
+ {"current_steps": 1420, "total_steps": 3295, "loss": 0.0211, "lr": 7.019961370488645e-05, "epoch": 2.1533503933276466, "percentage": 43.1, "elapsed_time": "4:19:26", "remaining_time": "5:42:33"}
171
+ {"current_steps": 1430, "total_steps": 3295, "loss": 0.02, "lr": 6.971386651397849e-05, "epoch": 2.168514832717278, "percentage": 43.4, "elapsed_time": "4:20:43", "remaining_time": "5:40:01"}
172
+ {"current_steps": 1440, "total_steps": 3295, "loss": 0.0169, "lr": 6.922590613613211e-05, "epoch": 2.183679272106909, "percentage": 43.7, "elapsed_time": "4:22:00", "remaining_time": "5:37:31"}
173
+ {"current_steps": 1450, "total_steps": 3295, "loss": 0.0243, "lr": 6.873578735245961e-05, "epoch": 2.1988437114965405, "percentage": 44.01, "elapsed_time": "4:23:18", "remaining_time": "5:35:02"}
174
+ {"current_steps": 1450, "total_steps": 3295, "eval_loss": 0.04021035507321358, "epoch": 2.1988437114965405, "percentage": 44.01, "elapsed_time": "4:25:58", "remaining_time": "5:38:25"}
175
+ {"current_steps": 1460, "total_steps": 3295, "loss": 0.021, "lr": 6.824356518638775e-05, "epoch": 2.2140081508861718, "percentage": 44.31, "elapsed_time": "4:27:20", "remaining_time": "5:36:00"}
176
+ {"current_steps": 1470, "total_steps": 3295, "loss": 0.0198, "lr": 6.774929489748052e-05, "epoch": 2.229172590275803, "percentage": 44.61, "elapsed_time": "4:28:37", "remaining_time": "5:33:30"}
177
+ {"current_steps": 1480, "total_steps": 3295, "loss": 0.0302, "lr": 6.725303197523548e-05, "epoch": 2.2443370296654344, "percentage": 44.92, "elapsed_time": "4:29:54", "remaining_time": "5:31:00"}
178
+ {"current_steps": 1490, "total_steps": 3295, "loss": 0.0225, "lr": 6.675483213285412e-05, "epoch": 2.259501469055066, "percentage": 45.22, "elapsed_time": "4:31:11", "remaining_time": "5:28:31"}
179
+ {"current_steps": 1500, "total_steps": 3295, "loss": 0.0234, "lr": 6.625475130098728e-05, "epoch": 2.274665908444697, "percentage": 45.52, "elapsed_time": "4:32:28", "remaining_time": "5:26:03"}
180
+ {"current_steps": 1500, "total_steps": 3295, "eval_loss": 0.039622507989406586, "epoch": 2.274665908444697, "percentage": 45.52, "elapsed_time": "4:35:08", "remaining_time": "5:29:15"}
181
+ {"current_steps": 1510, "total_steps": 3295, "loss": 0.0213, "lr": 6.575284562145593e-05, "epoch": 2.2898303478343287, "percentage": 45.83, "elapsed_time": "4:36:30", "remaining_time": "5:26:52"}
182
+ {"current_steps": 1520, "total_steps": 3295, "loss": 0.0258, "lr": 6.524917144094851e-05, "epoch": 2.30499478722396, "percentage": 46.13, "elapsed_time": "4:37:47", "remaining_time": "5:24:24"}
183
+ {"current_steps": 1530, "total_steps": 3295, "loss": 0.025, "lr": 6.474378530469509e-05, "epoch": 2.3201592266135913, "percentage": 46.43, "elapsed_time": "4:39:04", "remaining_time": "5:21:56"}
184
+ {"current_steps": 1540, "total_steps": 3295, "loss": 0.0205, "lr": 6.42367439501193e-05, "epoch": 2.3353236660032226, "percentage": 46.74, "elapsed_time": "4:40:21", "remaining_time": "5:19:30"}
185
+ {"current_steps": 1550, "total_steps": 3295, "loss": 0.0189, "lr": 6.372810430046862e-05, "epoch": 2.350488105392854, "percentage": 47.04, "elapsed_time": "4:41:38", "remaining_time": "5:17:04"}
186
+ {"current_steps": 1550, "total_steps": 3295, "eval_loss": 0.03922748565673828, "epoch": 2.350488105392854, "percentage": 47.04, "elapsed_time": "4:44:18", "remaining_time": "5:20:05"}
187
+ {"current_steps": 1560, "total_steps": 3295, "loss": 0.0228, "lr": 6.321792345842402e-05, "epoch": 2.365652544782485, "percentage": 47.34, "elapsed_time": "4:45:41", "remaining_time": "5:17:43"}
188
+ {"current_steps": 1570, "total_steps": 3295, "loss": 0.0323, "lr": 6.270625869968906e-05, "epoch": 2.3808169841721165, "percentage": 47.65, "elapsed_time": "4:46:58", "remaining_time": "5:15:18"}
189
+ {"current_steps": 1580, "total_steps": 3295, "loss": 0.0284, "lr": 6.219316746656007e-05, "epoch": 2.395981423561748, "percentage": 47.95, "elapsed_time": "4:48:15", "remaining_time": "5:12:53"}
190
+ {"current_steps": 1590, "total_steps": 3295, "loss": 0.0234, "lr": 6.167870736147713e-05, "epoch": 2.411145862951379, "percentage": 48.25, "elapsed_time": "4:49:32", "remaining_time": "5:10:29"}
191
+ {"current_steps": 1600, "total_steps": 3295, "loss": 0.0195, "lr": 6.116293614055744e-05, "epoch": 2.4263103023410104, "percentage": 48.56, "elapsed_time": "4:50:49", "remaining_time": "5:08:05"}
192
+ {"current_steps": 1600, "total_steps": 3295, "eval_loss": 0.03961315006017685, "epoch": 2.4263103023410104, "percentage": 48.56, "elapsed_time": "4:53:29", "remaining_time": "5:10:54"}
193
+ {"current_steps": 1610, "total_steps": 3295, "loss": 0.0186, "lr": 6.06459117071113e-05, "epoch": 2.4414747417306417, "percentage": 48.86, "elapsed_time": "4:54:51", "remaining_time": "5:08:35"}
194
+ {"current_steps": 1620, "total_steps": 3295, "loss": 0.0213, "lr": 6.012769210514146e-05, "epoch": 2.456639181120273, "percentage": 49.17, "elapsed_time": "4:56:09", "remaining_time": "5:06:12"}
195
+ {"current_steps": 1630, "total_steps": 3295, "loss": 0.0207, "lr": 5.9608335512826915e-05, "epoch": 2.4718036205099043, "percentage": 49.47, "elapsed_time": "4:57:26", "remaining_time": "5:03:49"}
196
+ {"current_steps": 1640, "total_steps": 3295, "loss": 0.0143, "lr": 5.908790023599144e-05, "epoch": 2.4869680598995356, "percentage": 49.77, "elapsed_time": "4:58:43", "remaining_time": "5:01:27"}
197
+ {"current_steps": 1650, "total_steps": 3295, "loss": 0.0221, "lr": 5.856644470155781e-05, "epoch": 2.502132499289167, "percentage": 50.08, "elapsed_time": "5:00:00", "remaining_time": "4:59:05"}
198
+ {"current_steps": 1650, "total_steps": 3295, "eval_loss": 0.04753277450799942, "epoch": 2.502132499289167, "percentage": 50.08, "elapsed_time": "5:02:40", "remaining_time": "5:01:45"}
199
+ {"current_steps": 1660, "total_steps": 3295, "loss": 0.028, "lr": 5.8044027450988546e-05, "epoch": 2.5172969386787982, "percentage": 50.38, "elapsed_time": "5:04:02", "remaining_time": "4:59:27"}
200
+ {"current_steps": 1670, "total_steps": 3295, "loss": 0.0161, "lr": 5.752070713371371e-05, "epoch": 2.5324613780684295, "percentage": 50.68, "elapsed_time": "5:05:19", "remaining_time": "4:57:06"}
201
+ {"current_steps": 1680, "total_steps": 3295, "loss": 0.0165, "lr": 5.699654250054662e-05, "epoch": 2.547625817458061, "percentage": 50.99, "elapsed_time": "5:06:36", "remaining_time": "4:54:45"}
202
+ {"current_steps": 1690, "total_steps": 3295, "loss": 0.014, "lr": 5.647159239708809e-05, "epoch": 2.562790256847692, "percentage": 51.29, "elapsed_time": "5:07:54", "remaining_time": "4:52:24"}
203
+ {"current_steps": 1700, "total_steps": 3295, "loss": 0.0179, "lr": 5.5945915757120146e-05, "epoch": 2.5779546962373234, "percentage": 51.59, "elapsed_time": "5:09:10", "remaining_time": "4:50:05"}
204
+ {"current_steps": 1700, "total_steps": 3295, "eval_loss": 0.04084445536136627, "epoch": 2.5779546962373234, "percentage": 51.59, "elapsed_time": "5:11:50", "remaining_time": "4:52:35"}
205
+ {"current_steps": 1710, "total_steps": 3295, "loss": 0.0272, "lr": 5.5419571595989825e-05, "epoch": 2.5931191356269547, "percentage": 51.9, "elapsed_time": "5:13:13", "remaining_time": "4:50:19"}
206
+ {"current_steps": 1720, "total_steps": 3295, "loss": 0.0248, "lr": 5.4892619003983734e-05, "epoch": 2.608283575016586, "percentage": 52.2, "elapsed_time": "5:14:30", "remaining_time": "4:47:59"}
207
+ {"current_steps": 1730, "total_steps": 3295, "loss": 0.0157, "lr": 5.436511713969428e-05, "epoch": 2.6234480144062173, "percentage": 52.5, "elapsed_time": "5:15:47", "remaining_time": "4:45:40"}
208
+ {"current_steps": 1740, "total_steps": 3295, "loss": 0.024, "lr": 5.383712522337817e-05, "epoch": 2.6386124537958486, "percentage": 52.81, "elapsed_time": "5:17:04", "remaining_time": "4:43:21"}
209
+ {"current_steps": 1750, "total_steps": 3295, "loss": 0.0225, "lr": 5.3308702530308076e-05, "epoch": 2.65377689318548, "percentage": 53.11, "elapsed_time": "5:18:21", "remaining_time": "4:41:04"}
210
+ {"current_steps": 1750, "total_steps": 3295, "eval_loss": 0.038576629012823105, "epoch": 2.65377689318548, "percentage": 53.11, "elapsed_time": "5:21:01", "remaining_time": "4:43:25"}
211
+ {"current_steps": 1760, "total_steps": 3295, "loss": 0.0258, "lr": 5.2779908384118025e-05, "epoch": 2.6689413325751112, "percentage": 53.41, "elapsed_time": "5:22:23", "remaining_time": "4:41:10"}
212
+ {"current_steps": 1770, "total_steps": 3295, "loss": 0.0215, "lr": 5.22508021501434e-05, "epoch": 2.6841057719647425, "percentage": 53.72, "elapsed_time": "5:23:40", "remaining_time": "4:38:52"}
213
+ {"current_steps": 1780, "total_steps": 3295, "loss": 0.0163, "lr": 5.1721443228756284e-05, "epoch": 2.699270211354374, "percentage": 54.02, "elapsed_time": "5:24:57", "remaining_time": "4:36:34"}
214
+ {"current_steps": 1790, "total_steps": 3295, "loss": 0.0219, "lr": 5.119189104869683e-05, "epoch": 2.714434650744005, "percentage": 54.32, "elapsed_time": "5:26:14", "remaining_time": "4:34:18"}
215
+ {"current_steps": 1800, "total_steps": 3295, "loss": 0.0207, "lr": 5.066220506040148e-05, "epoch": 2.729599090133637, "percentage": 54.63, "elapsed_time": "5:27:31", "remaining_time": "4:32:02"}
216
+ {"current_steps": 1800, "total_steps": 3295, "eval_loss": 0.03975927457213402, "epoch": 2.729599090133637, "percentage": 54.63, "elapsed_time": "5:30:11", "remaining_time": "4:34:14"}
217
+ {"current_steps": 1810, "total_steps": 3295, "loss": 0.0248, "lr": 5.013244472932872e-05, "epoch": 2.7447635295232677, "percentage": 54.93, "elapsed_time": "5:31:33", "remaining_time": "4:32:01"}
218
+ {"current_steps": 1820, "total_steps": 3295, "loss": 0.0215, "lr": 4.960266952928316e-05, "epoch": 2.7599279689128995, "percentage": 55.24, "elapsed_time": "5:32:51", "remaining_time": "4:29:45"}
219
+ {"current_steps": 1830, "total_steps": 3295, "loss": 0.0225, "lr": 4.907293893573867e-05, "epoch": 2.7750924083025303, "percentage": 55.54, "elapsed_time": "5:34:07", "remaining_time": "4:27:29"}
220
+ {"current_steps": 1840, "total_steps": 3295, "loss": 0.0197, "lr": 4.8543312419161396e-05, "epoch": 2.790256847692162, "percentage": 55.84, "elapsed_time": "5:35:24", "remaining_time": "4:25:14"}
221
+ {"current_steps": 1850, "total_steps": 3295, "loss": 0.015, "lr": 4.8013849438333165e-05, "epoch": 2.805421287081793, "percentage": 56.15, "elapsed_time": "5:36:41", "remaining_time": "4:22:59"}
222
+ {"current_steps": 1850, "total_steps": 3295, "eval_loss": 0.041027262806892395, "epoch": 2.805421287081793, "percentage": 56.15, "elapsed_time": "5:39:21", "remaining_time": "4:25:04"}
223
+ {"current_steps": 1860, "total_steps": 3295, "loss": 0.0212, "lr": 4.748460943367643e-05, "epoch": 2.8205857264714247, "percentage": 56.45, "elapsed_time": "5:40:43", "remaining_time": "4:22:52"}
224
+ {"current_steps": 1870, "total_steps": 3295, "loss": 0.0312, "lr": 4.695565182058113e-05, "epoch": 2.8357501658610555, "percentage": 56.75, "elapsed_time": "5:42:00", "remaining_time": "4:20:37"}
225
+ {"current_steps": 1880, "total_steps": 3295, "loss": 0.0249, "lr": 4.642703598273431e-05, "epoch": 2.8509146052506873, "percentage": 57.06, "elapsed_time": "5:43:17", "remaining_time": "4:18:22"}
226
+ {"current_steps": 1890, "total_steps": 3295, "loss": 0.0234, "lr": 4.589882126545352e-05, "epoch": 2.8660790446403186, "percentage": 57.36, "elapsed_time": "5:44:34", "remaining_time": "4:16:08"}
227
+ {"current_steps": 1900, "total_steps": 3295, "loss": 0.0295, "lr": 4.537106696902425e-05, "epoch": 2.88124348402995, "percentage": 57.66, "elapsed_time": "5:45:51", "remaining_time": "4:13:55"}
228
+ {"current_steps": 1900, "total_steps": 3295, "eval_loss": 0.03719955310225487, "epoch": 2.88124348402995, "percentage": 57.66, "elapsed_time": "5:48:31", "remaining_time": "4:15:53"}
229
+ {"current_steps": 1910, "total_steps": 3295, "loss": 0.0224, "lr": 4.484383234204266e-05, "epoch": 2.896407923419581, "percentage": 57.97, "elapsed_time": "5:49:53", "remaining_time": "4:13:42"}
230
+ {"current_steps": 1920, "total_steps": 3295, "loss": 0.0247, "lr": 4.4317176574763935e-05, "epoch": 2.9115723628092125, "percentage": 58.27, "elapsed_time": "5:51:10", "remaining_time": "4:11:29"}
231
+ {"current_steps": 1930, "total_steps": 3295, "loss": 0.024, "lr": 4.3791158792457334e-05, "epoch": 2.926736802198844, "percentage": 58.57, "elapsed_time": "5:52:27", "remaining_time": "4:09:16"}
232
+ {"current_steps": 1940, "total_steps": 3295, "loss": 0.0216, "lr": 4.3265838048768334e-05, "epoch": 2.941901241588475, "percentage": 58.88, "elapsed_time": "5:53:44", "remaining_time": "4:07:03"}
233
+ {"current_steps": 1950, "total_steps": 3295, "loss": 0.0227, "lr": 4.274127331908915e-05, "epoch": 2.9570656809781064, "percentage": 59.18, "elapsed_time": "5:55:01", "remaining_time": "4:04:52"}
234
+ {"current_steps": 1950, "total_steps": 3295, "eval_loss": 0.03795257583260536, "epoch": 2.9570656809781064, "percentage": 59.18, "elapsed_time": "5:57:41", "remaining_time": "4:06:42"}
235
+ {"current_steps": 1960, "total_steps": 3295, "loss": 0.0173, "lr": 4.221752349393758e-05, "epoch": 2.9722301203677377, "percentage": 59.48, "elapsed_time": "5:59:03", "remaining_time": "4:04:33"}
236
+ {"current_steps": 1970, "total_steps": 3295, "loss": 0.0249, "lr": 4.1694647372345886e-05, "epoch": 2.987394559757369, "percentage": 59.79, "elapsed_time": "6:00:20", "remaining_time": "4:02:21"}
237
+ {"current_steps": 1980, "total_steps": 3295, "loss": 0.0182, "lr": 4.117270365525946e-05, "epoch": 3.0025589991470003, "percentage": 60.09, "elapsed_time": "6:01:37", "remaining_time": "4:00:10"}
238
+ {"current_steps": 1990, "total_steps": 3295, "loss": 0.0132, "lr": 4.065175093894694e-05, "epoch": 3.0177234385366316, "percentage": 60.39, "elapsed_time": "6:02:54", "remaining_time": "3:57:59"}
239
+ {"current_steps": 2000, "total_steps": 3295, "loss": 0.0128, "lr": 4.013184770842167e-05, "epoch": 3.032887877926263, "percentage": 60.7, "elapsed_time": "6:04:11", "remaining_time": "3:55:48"}
240
+ {"current_steps": 2000, "total_steps": 3295, "eval_loss": 0.03980863094329834, "epoch": 3.032887877926263, "percentage": 60.7, "elapsed_time": "6:06:51", "remaining_time": "3:57:32"}
241
+ {"current_steps": 2010, "total_steps": 3295, "loss": 0.0166, "lr": 3.9613052330876064e-05, "epoch": 3.048052317315894, "percentage": 61.0, "elapsed_time": "6:08:12", "remaining_time": "3:55:23"}
242
+ {"current_steps": 2020, "total_steps": 3295, "loss": 0.0136, "lr": 3.909542304912881e-05, "epoch": 3.0632167567055255, "percentage": 61.31, "elapsed_time": "6:09:29", "remaining_time": "3:53:13"}
243
+ {"current_steps": 2030, "total_steps": 3295, "loss": 0.0162, "lr": 3.857901797508628e-05, "epoch": 3.078381196095157, "percentage": 61.61, "elapsed_time": "6:10:46", "remaining_time": "3:51:03"}
244
+ {"current_steps": 2040, "total_steps": 3295, "loss": 0.0174, "lr": 3.80638950832186e-05, "epoch": 3.093545635484788, "percentage": 61.91, "elapsed_time": "6:12:03", "remaining_time": "3:48:53"}
245
+ {"current_steps": 2050, "total_steps": 3295, "loss": 0.0096, "lr": 3.7550112204051014e-05, "epoch": 3.1087100748744194, "percentage": 62.22, "elapsed_time": "6:13:20", "remaining_time": "3:46:44"}
246
+ {"current_steps": 2050, "total_steps": 3295, "eval_loss": 0.04321278631687164, "epoch": 3.1087100748744194, "percentage": 62.22, "elapsed_time": "6:16:00", "remaining_time": "3:48:21"}
247
+ {"current_steps": 2060, "total_steps": 3295, "loss": 0.0098, "lr": 3.703772701767167e-05, "epoch": 3.1238745142640507, "percentage": 62.52, "elapsed_time": "6:17:23", "remaining_time": "3:46:14"}
248
+ {"current_steps": 2070, "total_steps": 3295, "loss": 0.0095, "lr": 3.652679704725596e-05, "epoch": 3.139038953653682, "percentage": 62.82, "elapsed_time": "6:18:40", "remaining_time": "3:44:05"}
249
+ {"current_steps": 2080, "total_steps": 3295, "loss": 0.0111, "lr": 3.601737965260882e-05, "epoch": 3.1542033930433133, "percentage": 63.13, "elapsed_time": "6:19:57", "remaining_time": "3:41:56"}
250
+ {"current_steps": 2090, "total_steps": 3295, "loss": 0.0072, "lr": 3.550953202372503e-05, "epoch": 3.1693678324329446, "percentage": 63.43, "elapsed_time": "6:21:14", "remaining_time": "3:39:48"}
251
+ {"current_steps": 2100, "total_steps": 3295, "loss": 0.0076, "lr": 3.500331117436895e-05, "epoch": 3.184532271822576, "percentage": 63.73, "elapsed_time": "6:22:31", "remaining_time": "3:37:40"}
252
+ {"current_steps": 2100, "total_steps": 3295, "eval_loss": 0.048784155398607254, "epoch": 3.184532271822576, "percentage": 63.73, "elapsed_time": "6:25:11", "remaining_time": "3:39:11"}
253
+ {"current_steps": 2110, "total_steps": 3295, "loss": 0.0089, "lr": 3.4498773935673626e-05, "epoch": 3.1996967112122072, "percentage": 64.04, "elapsed_time": "6:26:33", "remaining_time": "3:37:05"}
254
+ {"current_steps": 2120, "total_steps": 3295, "loss": 0.0116, "lr": 3.399597694976081e-05, "epoch": 3.2148611506018385, "percentage": 64.34, "elapsed_time": "6:27:50", "remaining_time": "3:34:57"}
255
+ {"current_steps": 2130, "total_steps": 3295, "loss": 0.0152, "lr": 3.349497666338187e-05, "epoch": 3.23002558999147, "percentage": 64.64, "elapsed_time": "6:29:07", "remaining_time": "3:32:49"}
256
+ {"current_steps": 2140, "total_steps": 3295, "loss": 0.0118, "lr": 3.299582932158085e-05, "epoch": 3.245190029381101, "percentage": 64.95, "elapsed_time": "6:30:24", "remaining_time": "3:30:42"}
257
+ {"current_steps": 2150, "total_steps": 3295, "loss": 0.0122, "lr": 3.2498590961379996e-05, "epoch": 3.260354468770733, "percentage": 65.25, "elapsed_time": "6:31:41", "remaining_time": "3:28:35"}
258
+ {"current_steps": 2150, "total_steps": 3295, "eval_loss": 0.04506111145019531, "epoch": 3.260354468770733, "percentage": 65.25, "elapsed_time": "6:34:21", "remaining_time": "3:30:00"}
259
+ {"current_steps": 2160, "total_steps": 3295, "loss": 0.0105, "lr": 3.200331740548887e-05, "epoch": 3.2755189081603637, "percentage": 65.55, "elapsed_time": "6:35:42", "remaining_time": "3:27:55"}
260
+ {"current_steps": 2170, "total_steps": 3295, "loss": 0.0136, "lr": 3.1510064256037274e-05, "epoch": 3.2906833475499955, "percentage": 65.86, "elapsed_time": "6:36:59", "remaining_time": "3:25:48"}
261
+ {"current_steps": 2180, "total_steps": 3295, "loss": 0.0089, "lr": 3.1018886888333065e-05, "epoch": 3.3058477869396263, "percentage": 66.16, "elapsed_time": "6:38:16", "remaining_time": "3:23:42"}
262
+ {"current_steps": 2190, "total_steps": 3295, "loss": 0.0159, "lr": 3.052984044464548e-05, "epoch": 3.321012226329258, "percentage": 66.46, "elapsed_time": "6:39:33", "remaining_time": "3:21:36"}
263
+ {"current_steps": 2200, "total_steps": 3295, "loss": 0.0101, "lr": 3.0042979828014496e-05, "epoch": 3.3361766657188894, "percentage": 66.77, "elapsed_time": "6:40:50", "remaining_time": "3:19:30"}
264
+ {"current_steps": 2200, "total_steps": 3295, "eval_loss": 0.046676941215991974, "epoch": 3.3361766657188894, "percentage": 66.77, "elapsed_time": "6:43:30", "remaining_time": "3:20:50"}
265
+ {"current_steps": 2210, "total_steps": 3295, "loss": 0.015, "lr": 2.9558359696087152e-05, "epoch": 3.3513411051085207, "percentage": 67.07, "elapsed_time": "6:44:52", "remaining_time": "3:18:46"}
266
+ {"current_steps": 2220, "total_steps": 3295, "loss": 0.0143, "lr": 2.9076034454981332e-05, "epoch": 3.366505544498152, "percentage": 67.37, "elapsed_time": "6:46:09", "remaining_time": "3:16:40"}
267
+ {"current_steps": 2230, "total_steps": 3295, "loss": 0.0124, "lr": 2.8596058253177932e-05, "epoch": 3.3816699838877833, "percentage": 67.68, "elapsed_time": "6:47:26", "remaining_time": "3:14:35"}
268
+ {"current_steps": 2240, "total_steps": 3295, "loss": 0.013, "lr": 2.811848497544175e-05, "epoch": 3.3968344232774146, "percentage": 67.98, "elapsed_time": "6:48:43", "remaining_time": "3:12:30"}
269
+ {"current_steps": 2250, "total_steps": 3295, "loss": 0.0124, "lr": 2.764336823677216e-05, "epoch": 3.411998862667046, "percentage": 68.29, "elapsed_time": "6:50:00", "remaining_time": "3:10:25"}
270
+ {"current_steps": 2250, "total_steps": 3295, "eval_loss": 0.04635697975754738, "epoch": 3.411998862667046, "percentage": 68.29, "elapsed_time": "6:52:40", "remaining_time": "3:11:39"}
271
+ {"current_steps": 2260, "total_steps": 3295, "loss": 0.0096, "lr": 2.717076137638388e-05, "epoch": 3.427163302056677, "percentage": 68.59, "elapsed_time": "6:54:01", "remaining_time": "3:09:36"}
272
+ {"current_steps": 2270, "total_steps": 3295, "loss": 0.0153, "lr": 2.6700717451719066e-05, "epoch": 3.4423277414463085, "percentage": 68.89, "elapsed_time": "6:55:19", "remaining_time": "3:07:31"}
273
+ {"current_steps": 2280, "total_steps": 3295, "loss": 0.0156, "lr": 2.6233289232490447e-05, "epoch": 3.45749218083594, "percentage": 69.2, "elapsed_time": "6:56:36", "remaining_time": "3:05:27"}
274
+ {"current_steps": 2290, "total_steps": 3295, "loss": 0.0071, "lr": 2.5768529194757474e-05, "epoch": 3.472656620225571, "percentage": 69.5, "elapsed_time": "6:57:53", "remaining_time": "3:03:23"}
275
+ {"current_steps": 2300, "total_steps": 3295, "loss": 0.0113, "lr": 2.5306489515034713e-05, "epoch": 3.4878210596152024, "percentage": 69.8, "elapsed_time": "6:59:10", "remaining_time": "3:01:20"}
276
+ {"current_steps": 2300, "total_steps": 3295, "eval_loss": 0.047961652278900146, "epoch": 3.4878210596152024, "percentage": 69.8, "elapsed_time": "7:01:50", "remaining_time": "3:02:29"}
277
+ {"current_steps": 2310, "total_steps": 3295, "loss": 0.017, "lr": 2.484722206443455e-05, "epoch": 3.5029854990048337, "percentage": 70.11, "elapsed_time": "7:03:12", "remaining_time": "3:00:27"}
278
+ {"current_steps": 2320, "total_steps": 3295, "loss": 0.0129, "lr": 2.4390778402843605e-05, "epoch": 3.518149938394465, "percentage": 70.41, "elapsed_time": "7:04:29", "remaining_time": "2:58:23"}
279
+ {"current_steps": 2330, "total_steps": 3295, "loss": 0.0094, "lr": 2.3937209773134472e-05, "epoch": 3.5333143777840963, "percentage": 70.71, "elapsed_time": "7:05:46", "remaining_time": "2:56:20"}
280
+ {"current_steps": 2340, "total_steps": 3295, "loss": 0.0098, "lr": 2.3486567095412864e-05, "epoch": 3.5484788171737276, "percentage": 71.02, "elapsed_time": "7:07:03", "remaining_time": "2:54:17"}
281
+ {"current_steps": 2350, "total_steps": 3295, "loss": 0.0126, "lr": 2.3038900961301053e-05, "epoch": 3.563643256563359, "percentage": 71.32, "elapsed_time": "7:08:20", "remaining_time": "2:52:14"}
282
+ {"current_steps": 2350, "total_steps": 3295, "eval_loss": 0.047991689294576645, "epoch": 3.563643256563359, "percentage": 71.32, "elapsed_time": "7:11:00", "remaining_time": "2:53:19"}
283
+ {"current_steps": 2360, "total_steps": 3295, "loss": 0.0099, "lr": 2.259426162825819e-05, "epoch": 3.57880769595299, "percentage": 71.62, "elapsed_time": "7:12:23", "remaining_time": "2:51:18"}
284
+ {"current_steps": 2370, "total_steps": 3295, "loss": 0.0164, "lr": 2.215269901393805e-05, "epoch": 3.5939721353426215, "percentage": 71.93, "elapsed_time": "7:13:40", "remaining_time": "2:49:15"}
285
+ {"current_steps": 2380, "total_steps": 3295, "loss": 0.0094, "lr": 2.1714262690585192e-05, "epoch": 3.609136574732253, "percentage": 72.23, "elapsed_time": "7:14:58", "remaining_time": "2:47:13"}
286
+ {"current_steps": 2390, "total_steps": 3295, "loss": 0.0126, "lr": 2.1279001879469424e-05, "epoch": 3.624301014121884, "percentage": 72.53, "elapsed_time": "7:16:15", "remaining_time": "2:45:11"}
287
+ {"current_steps": 2400, "total_steps": 3295, "loss": 0.0114, "lr": 2.084696544536025e-05, "epoch": 3.6394654535115154, "percentage": 72.84, "elapsed_time": "7:17:32", "remaining_time": "2:43:10"}
288
+ {"current_steps": 2400, "total_steps": 3295, "eval_loss": 0.04358929395675659, "epoch": 3.6394654535115154, "percentage": 72.84, "elapsed_time": "7:20:12", "remaining_time": "2:44:09"}
289
+ {"current_steps": 2410, "total_steps": 3295, "loss": 0.0102, "lr": 2.0418201891040778e-05, "epoch": 3.6546298929011467, "percentage": 73.14, "elapsed_time": "7:21:34", "remaining_time": "2:42:09"}
290
+ {"current_steps": 2420, "total_steps": 3295, "loss": 0.0201, "lr": 1.9992759351862772e-05, "epoch": 3.669794332290778, "percentage": 73.44, "elapsed_time": "7:22:51", "remaining_time": "2:40:07"}
291
+ {"current_steps": 2430, "total_steps": 3295, "loss": 0.0098, "lr": 1.9570685590342463e-05, "epoch": 3.6849587716804093, "percentage": 73.75, "elapsed_time": "7:24:08", "remaining_time": "2:38:06"}
292
+ {"current_steps": 2440, "total_steps": 3295, "loss": 0.0109, "lr": 1.9152027990798748e-05, "epoch": 3.7001232110700406, "percentage": 74.05, "elapsed_time": "7:25:25", "remaining_time": "2:36:04"}
293
+ {"current_steps": 2450, "total_steps": 3295, "loss": 0.0071, "lr": 1.8736833554033263e-05, "epoch": 3.715287650459672, "percentage": 74.36, "elapsed_time": "7:26:43", "remaining_time": "2:34:04"}
294
+ {"current_steps": 2450, "total_steps": 3295, "eval_loss": 0.047177620232105255, "epoch": 3.715287650459672, "percentage": 74.36, "elapsed_time": "7:29:22", "remaining_time": "2:34:59"}
295
+ {"current_steps": 2460, "total_steps": 3295, "loss": 0.0125, "lr": 1.8325148892054093e-05, "epoch": 3.7304520898493037, "percentage": 74.66, "elapsed_time": "7:30:44", "remaining_time": "2:32:59"}
296
+ {"current_steps": 2470, "total_steps": 3295, "loss": 0.0089, "lr": 1.7917020222842662e-05, "epoch": 3.7456165292389345, "percentage": 74.96, "elapsed_time": "7:32:01", "remaining_time": "2:30:58"}
297
+ {"current_steps": 2480, "total_steps": 3295, "loss": 0.0106, "lr": 1.751249336516513e-05, "epoch": 3.7607809686285663, "percentage": 75.27, "elapsed_time": "7:33:19", "remaining_time": "2:28:58"}
298
+ {"current_steps": 2490, "total_steps": 3295, "loss": 0.0125, "lr": 1.7111613733428522e-05, "epoch": 3.775945408018197, "percentage": 75.57, "elapsed_time": "7:34:35", "remaining_time": "2:26:58"}
299
+ {"current_steps": 2500, "total_steps": 3295, "loss": 0.0117, "lr": 1.671442633258218e-05, "epoch": 3.791109847407829, "percentage": 75.87, "elapsed_time": "7:35:53", "remaining_time": "2:24:58"}
300
+ {"current_steps": 2500, "total_steps": 3295, "eval_loss": 0.04904229938983917, "epoch": 3.791109847407829, "percentage": 75.87, "elapsed_time": "7:38:33", "remaining_time": "2:25:49"}
301
+ {"current_steps": 2510, "total_steps": 3295, "loss": 0.0095, "lr": 1.6320975753065453e-05, "epoch": 3.8062742867974597, "percentage": 76.18, "elapsed_time": "7:39:55", "remaining_time": "2:23:50"}
302
+ {"current_steps": 2520, "total_steps": 3295, "loss": 0.01, "lr": 1.5931306165801452e-05, "epoch": 3.8214387261870915, "percentage": 76.48, "elapsed_time": "7:41:12", "remaining_time": "2:21:50"}
303
+ {"current_steps": 2530, "total_steps": 3295, "loss": 0.0112, "lr": 1.554546131723848e-05, "epoch": 3.8366031655767223, "percentage": 76.78, "elapsed_time": "7:42:30", "remaining_time": "2:19:50"}
304
+ {"current_steps": 2540, "total_steps": 3295, "loss": 0.0075, "lr": 1.5163484524438516e-05, "epoch": 3.851767604966354, "percentage": 77.09, "elapsed_time": "7:43:47", "remaining_time": "2:17:51"}
305
+ {"current_steps": 2550, "total_steps": 3295, "loss": 0.0145, "lr": 1.4785418670214496e-05, "epoch": 3.8669320443559854, "percentage": 77.39, "elapsed_time": "7:45:04", "remaining_time": "2:15:52"}
306
+ {"current_steps": 2550, "total_steps": 3295, "eval_loss": 0.047451041638851166, "epoch": 3.8669320443559854, "percentage": 77.39, "elapsed_time": "7:47:44", "remaining_time": "2:16:39"}
307
+ {"current_steps": 2560, "total_steps": 3295, "loss": 0.0123, "lr": 1.4411306198315777e-05, "epoch": 3.8820964837456167, "percentage": 77.69, "elapsed_time": "7:49:06", "remaining_time": "2:14:41"}
308
+ {"current_steps": 2570, "total_steps": 3295, "loss": 0.008, "lr": 1.4041189108663421e-05, "epoch": 3.897260923135248, "percentage": 78.0, "elapsed_time": "7:50:23", "remaining_time": "2:12:42"}
309
+ {"current_steps": 2580, "total_steps": 3295, "loss": 0.007, "lr": 1.3675108952634824e-05, "epoch": 3.9124253625248793, "percentage": 78.3, "elapsed_time": "7:51:40", "remaining_time": "2:10:43"}
310
+ {"current_steps": 2590, "total_steps": 3295, "loss": 0.0147, "lr": 1.3313106828399147e-05, "epoch": 3.9275898019145106, "percentage": 78.6, "elapsed_time": "7:52:57", "remaining_time": "2:08:44"}
311
+ {"current_steps": 2600, "total_steps": 3295, "loss": 0.008, "lr": 1.2955223376303205e-05, "epoch": 3.942754241304142, "percentage": 78.91, "elapsed_time": "7:54:14", "remaining_time": "2:06:46"}
312
+ {"current_steps": 2600, "total_steps": 3295, "eval_loss": 0.04594454541802406, "epoch": 3.942754241304142, "percentage": 78.91, "elapsed_time": "7:56:54", "remaining_time": "2:07:28"}
313
+ {"current_steps": 2610, "total_steps": 3295, "loss": 0.0104, "lr": 1.2601498774309112e-05, "epoch": 3.957918680693773, "percentage": 79.21, "elapsed_time": "7:58:16", "remaining_time": "2:05:31"}
314
+ {"current_steps": 2620, "total_steps": 3295, "loss": 0.0117, "lr": 1.2251972733483612e-05, "epoch": 3.9730831200834045, "percentage": 79.51, "elapsed_time": "7:59:34", "remaining_time": "2:03:33"}
315
+ {"current_steps": 2630, "total_steps": 3295, "loss": 0.0106, "lr": 1.19066844935399e-05, "epoch": 3.9882475594730358, "percentage": 79.82, "elapsed_time": "8:00:51", "remaining_time": "2:01:35"}
316
+ {"current_steps": 2640, "total_steps": 3295, "loss": 0.0095, "lr": 1.156567281843241e-05, "epoch": 4.003411998862667, "percentage": 80.12, "elapsed_time": "8:02:08", "remaining_time": "1:59:37"}
317
+ {"current_steps": 2650, "total_steps": 3295, "loss": 0.0044, "lr": 1.1228975992004842e-05, "epoch": 4.018576438252298, "percentage": 80.42, "elapsed_time": "8:03:25", "remaining_time": "1:57:39"}
318
+ {"current_steps": 2650, "total_steps": 3295, "eval_loss": 0.048001233488321304, "epoch": 4.018576438252298, "percentage": 80.42, "elapsed_time": "8:06:04", "remaining_time": "1:58:18"}
319
+ {"current_steps": 2660, "total_steps": 3295, "loss": 0.0076, "lr": 1.0896631813692377e-05, "epoch": 4.03374087764193, "percentage": 80.73, "elapsed_time": "8:07:26", "remaining_time": "1:56:21"}
320
+ {"current_steps": 2670, "total_steps": 3295, "loss": 0.0043, "lr": 1.0568677594277899e-05, "epoch": 4.048905317031561, "percentage": 81.03, "elapsed_time": "8:08:44", "remaining_time": "1:54:24"}
321
+ {"current_steps": 2680, "total_steps": 3295, "loss": 0.003, "lr": 1.0245150151703509e-05, "epoch": 4.064069756421192, "percentage": 81.34, "elapsed_time": "8:10:01", "remaining_time": "1:52:27"}
322
+ {"current_steps": 2690, "total_steps": 3295, "loss": 0.0057, "lr": 9.926085806936918e-06, "epoch": 4.079234195810824, "percentage": 81.64, "elapsed_time": "8:11:18", "remaining_time": "1:50:29"}
323
+ {"current_steps": 2700, "total_steps": 3295, "loss": 0.0061, "lr": 9.611520379894068e-06, "epoch": 4.094398635200455, "percentage": 81.94, "elapsed_time": "8:12:35", "remaining_time": "1:48:33"}
324
+ {"current_steps": 2700, "total_steps": 3295, "eval_loss": 0.05424731224775314, "epoch": 4.094398635200455, "percentage": 81.94, "elapsed_time": "8:15:15", "remaining_time": "1:49:08"}
325
+ {"current_steps": 2710, "total_steps": 3295, "loss": 0.0043, "lr": 9.301489185417578e-06, "epoch": 4.109563074590087, "percentage": 82.25, "elapsed_time": "8:16:37", "remaining_time": "1:47:12"}
326
+ {"current_steps": 2720, "total_steps": 3295, "loss": 0.0038, "lr": 8.996027029312314e-06, "epoch": 4.1247275139797175, "percentage": 82.55, "elapsed_time": "8:17:54", "remaining_time": "1:45:15"}
327
+ {"current_steps": 2730, "total_steps": 3295, "loss": 0.0102, "lr": 8.695168204437721e-06, "epoch": 4.139891953369349, "percentage": 82.85, "elapsed_time": "8:19:12", "remaining_time": "1:43:18"}
328
+ {"current_steps": 2740, "total_steps": 3295, "loss": 0.0066, "lr": 8.398946486858029e-06, "epoch": 4.15505639275898, "percentage": 83.16, "elapsed_time": "8:20:28", "remaining_time": "1:41:22"}
329
+ {"current_steps": 2750, "total_steps": 3295, "loss": 0.0048, "lr": 8.107395132050333e-06, "epoch": 4.170220832148612, "percentage": 83.46, "elapsed_time": "8:21:45", "remaining_time": "1:39:26"}
330
+ {"current_steps": 2750, "total_steps": 3295, "eval_loss": 0.05559329688549042, "epoch": 4.170220832148612, "percentage": 83.46, "elapsed_time": "8:24:25", "remaining_time": "1:39:58"}
331
+ {"current_steps": 2760, "total_steps": 3295, "loss": 0.0067, "lr": 7.820546871171142e-06, "epoch": 4.185385271538243, "percentage": 83.76, "elapsed_time": "8:25:47", "remaining_time": "1:38:02"}
332
+ {"current_steps": 2770, "total_steps": 3295, "loss": 0.0052, "lr": 7.5384339073818145e-06, "epoch": 4.200549710927874, "percentage": 84.07, "elapsed_time": "8:27:04", "remaining_time": "1:36:06"}
333
+ {"current_steps": 2780, "total_steps": 3295, "loss": 0.0057, "lr": 7.261087912233228e-06, "epoch": 4.215714150317505, "percentage": 84.37, "elapsed_time": "8:28:21", "remaining_time": "1:34:10"}
334
+ {"current_steps": 2790, "total_steps": 3295, "loss": 0.0062, "lr": 6.988540022110235e-06, "epoch": 4.230878589707137, "percentage": 84.67, "elapsed_time": "8:29:38", "remaining_time": "1:32:14"}
335
+ {"current_steps": 2800, "total_steps": 3295, "loss": 0.0043, "lr": 6.720820834735969e-06, "epoch": 4.246043029096768, "percentage": 84.98, "elapsed_time": "8:30:55", "remaining_time": "1:30:19"}
336
+ {"current_steps": 2800, "total_steps": 3295, "eval_loss": 0.05572189763188362, "epoch": 4.246043029096768, "percentage": 84.98, "elapsed_time": "8:33:35", "remaining_time": "1:30:47"}
337
+ {"current_steps": 2810, "total_steps": 3295, "loss": 0.0077, "lr": 6.457960405736968e-06, "epoch": 4.2612074684864, "percentage": 85.28, "elapsed_time": "8:34:56", "remaining_time": "1:28:52"}
338
+ {"current_steps": 2820, "total_steps": 3295, "loss": 0.0043, "lr": 6.199988245268778e-06, "epoch": 4.2763719078760305, "percentage": 85.58, "elapsed_time": "8:36:13", "remaining_time": "1:26:57"}
339
+ {"current_steps": 2830, "total_steps": 3295, "loss": 0.003, "lr": 5.946933314703157e-06, "epoch": 4.291536347265662, "percentage": 85.89, "elapsed_time": "8:37:30", "remaining_time": "1:25:02"}
340
+ {"current_steps": 2840, "total_steps": 3295, "loss": 0.0051, "lr": 5.698824023376531e-06, "epoch": 4.306700786655293, "percentage": 86.19, "elapsed_time": "8:38:48", "remaining_time": "1:23:07"}
341
+ {"current_steps": 2850, "total_steps": 3295, "loss": 0.0049, "lr": 5.455688225400802e-06, "epoch": 4.321865226044925, "percentage": 86.49, "elapsed_time": "8:40:05", "remaining_time": "1:21:12"}
342
+ {"current_steps": 2850, "total_steps": 3295, "eval_loss": 0.05698266625404358, "epoch": 4.321865226044925, "percentage": 86.49, "elapsed_time": "8:42:45", "remaining_time": "1:21:37"}
343
+ {"current_steps": 2860, "total_steps": 3295, "loss": 0.0069, "lr": 5.217553216536098e-06, "epoch": 4.337029665434556, "percentage": 86.8, "elapsed_time": "8:44:07", "remaining_time": "1:19:43"}
344
+ {"current_steps": 2870, "total_steps": 3295, "loss": 0.0059, "lr": 4.984445731126542e-06, "epoch": 4.3521941048241874, "percentage": 87.1, "elapsed_time": "8:45:24", "remaining_time": "1:17:48"}
345
+ {"current_steps": 2880, "total_steps": 3295, "loss": 0.0036, "lr": 4.756391939098853e-06, "epoch": 4.367358544213818, "percentage": 87.41, "elapsed_time": "8:46:41", "remaining_time": "1:15:53"}
346
+ {"current_steps": 2890, "total_steps": 3295, "loss": 0.0077, "lr": 4.533417443024374e-06, "epoch": 4.38252298360345, "percentage": 87.71, "elapsed_time": "8:47:58", "remaining_time": "1:13:59"}
347
+ {"current_steps": 2900, "total_steps": 3295, "loss": 0.0019, "lr": 4.315547275244769e-06, "epoch": 4.397687422993081, "percentage": 88.01, "elapsed_time": "8:49:15", "remaining_time": "1:12:05"}
348
+ {"current_steps": 2900, "total_steps": 3295, "eval_loss": 0.05874261260032654, "epoch": 4.397687422993081, "percentage": 88.01, "elapsed_time": "8:51:55", "remaining_time": "1:12:27"}
349
+ {"current_steps": 2910, "total_steps": 3295, "loss": 0.0069, "lr": 4.10280589506179e-06, "epoch": 4.412851862382713, "percentage": 88.32, "elapsed_time": "8:53:18", "remaining_time": "1:10:33"}
350
+ {"current_steps": 2920, "total_steps": 3295, "loss": 0.0039, "lr": 3.895217185991312e-06, "epoch": 4.4280163017723435, "percentage": 88.62, "elapsed_time": "8:54:35", "remaining_time": "1:08:39"}
351
+ {"current_steps": 2930, "total_steps": 3295, "loss": 0.0046, "lr": 3.692804453082038e-06, "epoch": 4.443180741161975, "percentage": 88.92, "elapsed_time": "8:55:52", "remaining_time": "1:06:45"}
352
+ {"current_steps": 2940, "total_steps": 3295, "loss": 0.0051, "lr": 3.495590420299194e-06, "epoch": 4.458345180551606, "percentage": 89.23, "elapsed_time": "8:57:09", "remaining_time": "1:04:51"}
353
+ {"current_steps": 2950, "total_steps": 3295, "loss": 0.0053, "lr": 3.3035972279733207e-06, "epoch": 4.473509619941238, "percentage": 89.53, "elapsed_time": "8:58:27", "remaining_time": "1:02:58"}
354
+ {"current_steps": 2950, "total_steps": 3295, "eval_loss": 0.05949469655752182, "epoch": 4.473509619941238, "percentage": 89.53, "elapsed_time": "9:01:06", "remaining_time": "1:03:16"}
355
+ {"current_steps": 2960, "total_steps": 3295, "loss": 0.0053, "lr": 3.116846430314796e-06, "epoch": 4.488674059330869, "percentage": 89.83, "elapsed_time": "9:02:27", "remaining_time": "1:01:23"}
356
+ {"current_steps": 2970, "total_steps": 3295, "loss": 0.0025, "lr": 2.9353589929939087e-06, "epoch": 4.5038384987205005, "percentage": 90.14, "elapsed_time": "9:03:45", "remaining_time": "0:59:30"}
357
+ {"current_steps": 2980, "total_steps": 3295, "loss": 0.0043, "lr": 2.7591552907872574e-06, "epoch": 4.519002938110132, "percentage": 90.44, "elapsed_time": "9:05:02", "remaining_time": "0:57:36"}
358
+ {"current_steps": 2990, "total_steps": 3295, "loss": 0.0049, "lr": 2.5882551052902883e-06, "epoch": 4.534167377499763, "percentage": 90.74, "elapsed_time": "9:06:19", "remaining_time": "0:55:43"}
359
+ {"current_steps": 3000, "total_steps": 3295, "loss": 0.0072, "lr": 2.4226776226965453e-06, "epoch": 4.549331816889394, "percentage": 91.05, "elapsed_time": "9:07:36", "remaining_time": "0:53:50"}
360
+ {"current_steps": 3000, "total_steps": 3295, "eval_loss": 0.05965949594974518, "epoch": 4.549331816889394, "percentage": 91.05, "elapsed_time": "9:10:15", "remaining_time": "0:54:06"}
361
+ {"current_steps": 3010, "total_steps": 3295, "loss": 0.0062, "lr": 2.262441431643697e-06, "epoch": 4.564496256279026, "percentage": 91.35, "elapsed_time": "9:11:38", "remaining_time": "0:52:13"}
362
+ {"current_steps": 3020, "total_steps": 3295, "loss": 0.0017, "lr": 2.1075645211266927e-06, "epoch": 4.579660695668657, "percentage": 91.65, "elapsed_time": "9:12:55", "remaining_time": "0:50:20"}
363
+ {"current_steps": 3030, "total_steps": 3295, "loss": 0.0046, "lr": 1.9580642784782053e-06, "epoch": 4.594825135058288, "percentage": 91.96, "elapsed_time": "9:14:12", "remaining_time": "0:48:28"}
364
+ {"current_steps": 3040, "total_steps": 3295, "loss": 0.0023, "lr": 1.813957487416651e-06, "epoch": 4.60998957444792, "percentage": 92.26, "elapsed_time": "9:15:28", "remaining_time": "0:46:35"}
365
+ {"current_steps": 3050, "total_steps": 3295, "loss": 0.0047, "lr": 1.6752603261619315e-06, "epoch": 4.625154013837551, "percentage": 92.56, "elapsed_time": "9:16:45", "remaining_time": "0:44:43"}
366
+ {"current_steps": 3050, "total_steps": 3295, "eval_loss": 0.05990082770586014, "epoch": 4.625154013837551, "percentage": 92.56, "elapsed_time": "9:19:25", "remaining_time": "0:44:56"}
367
+ {"current_steps": 3060, "total_steps": 3295, "loss": 0.0044, "lr": 1.541988365619207e-06, "epoch": 4.640318453227183, "percentage": 92.87, "elapsed_time": "9:20:47", "remaining_time": "0:43:04"}
368
+ {"current_steps": 3070, "total_steps": 3295, "loss": 0.0052, "lr": 1.4141565676307865e-06, "epoch": 4.6554828926168135, "percentage": 93.17, "elapsed_time": "9:22:04", "remaining_time": "0:41:11"}
369
+ {"current_steps": 3080, "total_steps": 3295, "loss": 0.0029, "lr": 1.291779283296468e-06, "epoch": 4.670647332006445, "percentage": 93.47, "elapsed_time": "9:23:21", "remaining_time": "0:39:19"}
370
+ {"current_steps": 3090, "total_steps": 3295, "loss": 0.0064, "lr": 1.1748702513623922e-06, "epoch": 4.685811771396076, "percentage": 93.78, "elapsed_time": "9:24:38", "remaining_time": "0:37:27"}
371
+ {"current_steps": 3100, "total_steps": 3295, "loss": 0.003, "lr": 1.0634425966786155e-06, "epoch": 4.700976210785708, "percentage": 94.08, "elapsed_time": "9:25:55", "remaining_time": "0:35:35"}
372
+ {"current_steps": 3100, "total_steps": 3295, "eval_loss": 0.06024787947535515, "epoch": 4.700976210785708, "percentage": 94.08, "elapsed_time": "9:28:34", "remaining_time": "0:35:45"}
373
+ {"current_steps": 3110, "total_steps": 3295, "loss": 0.005, "lr": 9.575088287257118e-07, "epoch": 4.716140650175339, "percentage": 94.39, "elapsed_time": "9:29:56", "remaining_time": "0:33:54"}
374
+ {"current_steps": 3120, "total_steps": 3295, "loss": 0.0059, "lr": 8.570808402103392e-07, "epoch": 4.73130508956497, "percentage": 94.69, "elapsed_time": "9:31:13", "remaining_time": "0:32:02"}
375
+ {"current_steps": 3130, "total_steps": 3295, "loss": 0.0048, "lr": 7.62169905730109e-07, "epoch": 4.746469528954601, "percentage": 94.99, "elapsed_time": "9:32:29", "remaining_time": "0:30:10"}
376
+ {"current_steps": 3140, "total_steps": 3295, "loss": 0.0029, "lr": 6.727866805078531e-07, "epoch": 4.761633968344233, "percentage": 95.3, "elapsed_time": "9:33:46", "remaining_time": "0:28:19"}
377
+ {"current_steps": 3150, "total_steps": 3295, "loss": 0.0025, "lr": 5.889411991953975e-07, "epoch": 4.776798407733864, "percentage": 95.6, "elapsed_time": "9:35:03", "remaining_time": "0:26:28"}
378
+ {"current_steps": 3150, "total_steps": 3295, "eval_loss": 0.06030402332544327, "epoch": 4.776798407733864, "percentage": 95.6, "elapsed_time": "9:37:43", "remaining_time": "0:26:35"}
379
+ {"current_steps": 3160, "total_steps": 3295, "loss": 0.0033, "lr": 5.106428747470137e-07, "epoch": 4.791962847123496, "percentage": 95.9, "elapsed_time": "9:39:05", "remaining_time": "0:24:44"}
380
+ {"current_steps": 3170, "total_steps": 3295, "loss": 0.0061, "lr": 4.37900497362681e-07, "epoch": 4.8071272865131265, "percentage": 96.21, "elapsed_time": "9:40:22", "remaining_time": "0:22:53"}
381
+ {"current_steps": 3180, "total_steps": 3295, "loss": 0.0028, "lr": 3.7072223350124167e-07, "epoch": 4.822291725902758, "percentage": 96.51, "elapsed_time": "9:41:39", "remaining_time": "0:21:02"}
382
+ {"current_steps": 3190, "total_steps": 3295, "loss": 0.0062, "lr": 3.0911562496358517e-07, "epoch": 4.837456165292389, "percentage": 96.81, "elapsed_time": "9:42:56", "remaining_time": "0:19:11"}
383
+ {"current_steps": 3200, "total_steps": 3295, "loss": 0.0027, "lr": 2.53087588045986e-07, "epoch": 4.852620604682021, "percentage": 97.12, "elapsed_time": "9:44:13", "remaining_time": "0:17:20"}
384
+ {"current_steps": 3200, "total_steps": 3295, "eval_loss": 0.06035413593053818, "epoch": 4.852620604682021, "percentage": 97.12, "elapsed_time": "9:46:53", "remaining_time": "0:17:25"}
385
+ {"current_steps": 3210, "total_steps": 3295, "loss": 0.0034, "lr": 2.026444127636029e-07, "epoch": 4.867785044071652, "percentage": 97.42, "elapsed_time": "9:48:14", "remaining_time": "0:15:34"}
386
+ {"current_steps": 3220, "total_steps": 3295, "loss": 0.0051, "lr": 1.577917621443825e-07, "epoch": 4.882949483461283, "percentage": 97.72, "elapsed_time": "9:49:31", "remaining_time": "0:13:43"}
387
+ {"current_steps": 3230, "total_steps": 3295, "loss": 0.0083, "lr": 1.185346715932345e-07, "epoch": 4.898113922850914, "percentage": 98.03, "elapsed_time": "9:50:48", "remaining_time": "0:11:53"}
388
+ {"current_steps": 3240, "total_steps": 3295, "loss": 0.0055, "lr": 8.48775483267783e-08, "epoch": 4.913278362240546, "percentage": 98.33, "elapsed_time": "9:52:06", "remaining_time": "0:10:03"}
389
+ {"current_steps": 3250, "total_steps": 3295, "loss": 0.0022, "lr": 5.6824170878544414e-08, "epoch": 4.928442801630177, "percentage": 98.63, "elapsed_time": "9:53:23", "remaining_time": "0:08:12"}
390
+ {"current_steps": 3250, "total_steps": 3295, "eval_loss": 0.060390591621398926, "epoch": 4.928442801630177, "percentage": 98.63, "elapsed_time": "9:56:02", "remaining_time": "0:08:15"}
391
+ {"current_steps": 3260, "total_steps": 3295, "loss": 0.0053, "lr": 3.4377688674774866e-08, "epoch": 4.943607241019809, "percentage": 98.94, "elapsed_time": "9:57:25", "remaining_time": "0:06:24"}
392
+ {"current_steps": 3270, "total_steps": 3295, "loss": 0.0029, "lr": 1.7540621680850466e-08, "epoch": 4.9587716804094395, "percentage": 99.24, "elapsed_time": "9:58:42", "remaining_time": "0:04:34"}
393
+ {"current_steps": 3280, "total_steps": 3295, "loss": 0.0064, "lr": 6.314860118400434e-09, "epoch": 4.973936119799071, "percentage": 99.54, "elapsed_time": "9:59:59", "remaining_time": "0:02:44"}
394
+ {"current_steps": 3290, "total_steps": 3295, "loss": 0.0032, "lr": 7.016642530777162e-10, "epoch": 4.989100559188703, "percentage": 99.85, "elapsed_time": "10:01:16", "remaining_time": "0:00:54"}
395
+ {"current_steps": 3295, "total_steps": 3295, "epoch": 4.996682778883518, "percentage": 100.0, "elapsed_time": "10:01:59", "remaining_time": "0:00:00"}
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold8/trainer_state.json ADDED
@@ -0,0 +1,2865 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.03543492406606674,
3
+ "best_model_checkpoint": "saves/psy-course/Llama-3.1-8B-Instruct/train/fold8/checkpoint-1200",
4
+ "epoch": 4.996682778883518,
5
+ "eval_steps": 50,
6
+ "global_step": 3295,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.015164439389631315,
13
+ "grad_norm": 4.908313751220703,
14
+ "learning_rate": 3.0303030303030305e-06,
15
+ "loss": 1.59,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.03032887877926263,
20
+ "grad_norm": 4.702552318572998,
21
+ "learning_rate": 6.060606060606061e-06,
22
+ "loss": 1.5951,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.045493318168893945,
27
+ "grad_norm": 7.187352657318115,
28
+ "learning_rate": 9.090909090909091e-06,
29
+ "loss": 1.2503,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.06065775755852526,
34
+ "grad_norm": 2.202908515930176,
35
+ "learning_rate": 1.2121212121212122e-05,
36
+ "loss": 0.9145,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.07582219694815658,
41
+ "grad_norm": 1.6536071300506592,
42
+ "learning_rate": 1.5151515151515153e-05,
43
+ "loss": 0.6782,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.07582219694815658,
48
+ "eval_loss": 0.43230628967285156,
49
+ "eval_runtime": 159.6252,
50
+ "eval_samples_per_second": 7.348,
51
+ "eval_steps_per_second": 7.348,
52
+ "step": 50
53
+ },
54
+ {
55
+ "epoch": 0.09098663633778789,
56
+ "grad_norm": 1.2327362298965454,
57
+ "learning_rate": 1.8181818181818182e-05,
58
+ "loss": 0.3929,
59
+ "step": 60
60
+ },
61
+ {
62
+ "epoch": 0.1061510757274192,
63
+ "grad_norm": 0.9732389450073242,
64
+ "learning_rate": 2.1212121212121215e-05,
65
+ "loss": 0.2232,
66
+ "step": 70
67
+ },
68
+ {
69
+ "epoch": 0.12131551511705052,
70
+ "grad_norm": 0.822551429271698,
71
+ "learning_rate": 2.4242424242424244e-05,
72
+ "loss": 0.2301,
73
+ "step": 80
74
+ },
75
+ {
76
+ "epoch": 0.13647995450668182,
77
+ "grad_norm": 0.8734151124954224,
78
+ "learning_rate": 2.7272727272727273e-05,
79
+ "loss": 0.127,
80
+ "step": 90
81
+ },
82
+ {
83
+ "epoch": 0.15164439389631315,
84
+ "grad_norm": 0.9926938414573669,
85
+ "learning_rate": 3.0303030303030306e-05,
86
+ "loss": 0.1528,
87
+ "step": 100
88
+ },
89
+ {
90
+ "epoch": 0.15164439389631315,
91
+ "eval_loss": 0.0901423990726471,
92
+ "eval_runtime": 159.655,
93
+ "eval_samples_per_second": 7.347,
94
+ "eval_steps_per_second": 7.347,
95
+ "step": 100
96
+ },
97
+ {
98
+ "epoch": 0.16680883328594445,
99
+ "grad_norm": 0.5548447966575623,
100
+ "learning_rate": 3.3333333333333335e-05,
101
+ "loss": 0.0945,
102
+ "step": 110
103
+ },
104
+ {
105
+ "epoch": 0.18197327267557578,
106
+ "grad_norm": 1.0051425695419312,
107
+ "learning_rate": 3.6363636363636364e-05,
108
+ "loss": 0.0798,
109
+ "step": 120
110
+ },
111
+ {
112
+ "epoch": 0.19713771206520708,
113
+ "grad_norm": 1.2151364088058472,
114
+ "learning_rate": 3.939393939393939e-05,
115
+ "loss": 0.0769,
116
+ "step": 130
117
+ },
118
+ {
119
+ "epoch": 0.2123021514548384,
120
+ "grad_norm": 0.7133122086524963,
121
+ "learning_rate": 4.242424242424243e-05,
122
+ "loss": 0.0684,
123
+ "step": 140
124
+ },
125
+ {
126
+ "epoch": 0.2274665908444697,
127
+ "grad_norm": 1.0978891849517822,
128
+ "learning_rate": 4.545454545454546e-05,
129
+ "loss": 0.0741,
130
+ "step": 150
131
+ },
132
+ {
133
+ "epoch": 0.2274665908444697,
134
+ "eval_loss": 0.06654910743236542,
135
+ "eval_runtime": 159.7218,
136
+ "eval_samples_per_second": 7.344,
137
+ "eval_steps_per_second": 7.344,
138
+ "step": 150
139
+ },
140
+ {
141
+ "epoch": 0.24263103023410104,
142
+ "grad_norm": 0.9477673768997192,
143
+ "learning_rate": 4.848484848484849e-05,
144
+ "loss": 0.0795,
145
+ "step": 160
146
+ },
147
+ {
148
+ "epoch": 0.25779546962373234,
149
+ "grad_norm": 1.3763097524642944,
150
+ "learning_rate": 5.151515151515152e-05,
151
+ "loss": 0.0702,
152
+ "step": 170
153
+ },
154
+ {
155
+ "epoch": 0.27295990901336364,
156
+ "grad_norm": 0.5879313945770264,
157
+ "learning_rate": 5.4545454545454546e-05,
158
+ "loss": 0.0818,
159
+ "step": 180
160
+ },
161
+ {
162
+ "epoch": 0.288124348402995,
163
+ "grad_norm": 0.590936541557312,
164
+ "learning_rate": 5.757575757575758e-05,
165
+ "loss": 0.0682,
166
+ "step": 190
167
+ },
168
+ {
169
+ "epoch": 0.3032887877926263,
170
+ "grad_norm": 1.0090534687042236,
171
+ "learning_rate": 6.060606060606061e-05,
172
+ "loss": 0.0544,
173
+ "step": 200
174
+ },
175
+ {
176
+ "epoch": 0.3032887877926263,
177
+ "eval_loss": 0.05628184229135513,
178
+ "eval_runtime": 159.7671,
179
+ "eval_samples_per_second": 7.342,
180
+ "eval_steps_per_second": 7.342,
181
+ "step": 200
182
+ },
183
+ {
184
+ "epoch": 0.3184532271822576,
185
+ "grad_norm": 0.6095383167266846,
186
+ "learning_rate": 6.363636363636364e-05,
187
+ "loss": 0.0538,
188
+ "step": 210
189
+ },
190
+ {
191
+ "epoch": 0.3336176665718889,
192
+ "grad_norm": 0.9077891707420349,
193
+ "learning_rate": 6.666666666666667e-05,
194
+ "loss": 0.0571,
195
+ "step": 220
196
+ },
197
+ {
198
+ "epoch": 0.34878210596152026,
199
+ "grad_norm": 0.4802258014678955,
200
+ "learning_rate": 6.96969696969697e-05,
201
+ "loss": 0.0628,
202
+ "step": 230
203
+ },
204
+ {
205
+ "epoch": 0.36394654535115156,
206
+ "grad_norm": 0.7471550107002258,
207
+ "learning_rate": 7.272727272727273e-05,
208
+ "loss": 0.0476,
209
+ "step": 240
210
+ },
211
+ {
212
+ "epoch": 0.37911098474078286,
213
+ "grad_norm": 0.8440163731575012,
214
+ "learning_rate": 7.575757575757576e-05,
215
+ "loss": 0.053,
216
+ "step": 250
217
+ },
218
+ {
219
+ "epoch": 0.37911098474078286,
220
+ "eval_loss": 0.0572020523250103,
221
+ "eval_runtime": 159.824,
222
+ "eval_samples_per_second": 7.339,
223
+ "eval_steps_per_second": 7.339,
224
+ "step": 250
225
+ },
226
+ {
227
+ "epoch": 0.39427542413041416,
228
+ "grad_norm": 0.8062713146209717,
229
+ "learning_rate": 7.878787878787879e-05,
230
+ "loss": 0.0516,
231
+ "step": 260
232
+ },
233
+ {
234
+ "epoch": 0.40943986352004547,
235
+ "grad_norm": 0.33338773250579834,
236
+ "learning_rate": 8.181818181818183e-05,
237
+ "loss": 0.0712,
238
+ "step": 270
239
+ },
240
+ {
241
+ "epoch": 0.4246043029096768,
242
+ "grad_norm": 0.550988495349884,
243
+ "learning_rate": 8.484848484848486e-05,
244
+ "loss": 0.0531,
245
+ "step": 280
246
+ },
247
+ {
248
+ "epoch": 0.4397687422993081,
249
+ "grad_norm": 0.37053975462913513,
250
+ "learning_rate": 8.787878787878789e-05,
251
+ "loss": 0.0466,
252
+ "step": 290
253
+ },
254
+ {
255
+ "epoch": 0.4549331816889394,
256
+ "grad_norm": 0.7273926734924316,
257
+ "learning_rate": 9.090909090909092e-05,
258
+ "loss": 0.0626,
259
+ "step": 300
260
+ },
261
+ {
262
+ "epoch": 0.4549331816889394,
263
+ "eval_loss": 0.05890120193362236,
264
+ "eval_runtime": 159.7681,
265
+ "eval_samples_per_second": 7.342,
266
+ "eval_steps_per_second": 7.342,
267
+ "step": 300
268
+ },
269
+ {
270
+ "epoch": 0.4700976210785707,
271
+ "grad_norm": 0.6740069389343262,
272
+ "learning_rate": 9.393939393939395e-05,
273
+ "loss": 0.0501,
274
+ "step": 310
275
+ },
276
+ {
277
+ "epoch": 0.4852620604682021,
278
+ "grad_norm": 0.5992850065231323,
279
+ "learning_rate": 9.696969696969698e-05,
280
+ "loss": 0.0443,
281
+ "step": 320
282
+ },
283
+ {
284
+ "epoch": 0.5004264998578334,
285
+ "grad_norm": 0.6561434268951416,
286
+ "learning_rate": 0.0001,
287
+ "loss": 0.0479,
288
+ "step": 330
289
+ },
290
+ {
291
+ "epoch": 0.5155909392474647,
292
+ "grad_norm": 0.614966630935669,
293
+ "learning_rate": 9.999719336268101e-05,
294
+ "loss": 0.0507,
295
+ "step": 340
296
+ },
297
+ {
298
+ "epoch": 0.530755378637096,
299
+ "grad_norm": 0.4214603304862976,
300
+ "learning_rate": 9.998877376581251e-05,
301
+ "loss": 0.0646,
302
+ "step": 350
303
+ },
304
+ {
305
+ "epoch": 0.530755378637096,
306
+ "eval_loss": 0.04616093635559082,
307
+ "eval_runtime": 159.8294,
308
+ "eval_samples_per_second": 7.339,
309
+ "eval_steps_per_second": 7.339,
310
+ "step": 350
311
+ },
312
+ {
313
+ "epoch": 0.5459198180267273,
314
+ "grad_norm": 0.5347225069999695,
315
+ "learning_rate": 9.997474215462472e-05,
316
+ "loss": 0.0549,
317
+ "step": 360
318
+ },
319
+ {
320
+ "epoch": 0.5610842574163586,
321
+ "grad_norm": 0.6282948851585388,
322
+ "learning_rate": 9.995510010438337e-05,
323
+ "loss": 0.0442,
324
+ "step": 370
325
+ },
326
+ {
327
+ "epoch": 0.57624869680599,
328
+ "grad_norm": 0.8127485513687134,
329
+ "learning_rate": 9.992984982021295e-05,
330
+ "loss": 0.0607,
331
+ "step": 380
332
+ },
333
+ {
334
+ "epoch": 0.5914131361956213,
335
+ "grad_norm": 0.7069970965385437,
336
+ "learning_rate": 9.9898994136849e-05,
337
+ "loss": 0.0526,
338
+ "step": 390
339
+ },
340
+ {
341
+ "epoch": 0.6065775755852526,
342
+ "grad_norm": 0.3750600516796112,
343
+ "learning_rate": 9.986253651832005e-05,
344
+ "loss": 0.0336,
345
+ "step": 400
346
+ },
347
+ {
348
+ "epoch": 0.6065775755852526,
349
+ "eval_loss": 0.04486996307969093,
350
+ "eval_runtime": 159.7479,
351
+ "eval_samples_per_second": 7.343,
352
+ "eval_steps_per_second": 7.343,
353
+ "step": 400
354
+ },
355
+ {
356
+ "epoch": 0.6217420149748839,
357
+ "grad_norm": 0.2943829298019409,
358
+ "learning_rate": 9.982048105755859e-05,
359
+ "loss": 0.0409,
360
+ "step": 410
361
+ },
362
+ {
363
+ "epoch": 0.6369064543645152,
364
+ "grad_norm": 0.3517925441265106,
365
+ "learning_rate": 9.977283247594166e-05,
366
+ "loss": 0.052,
367
+ "step": 420
368
+ },
369
+ {
370
+ "epoch": 0.6520708937541465,
371
+ "grad_norm": 0.47345930337905884,
372
+ "learning_rate": 9.971959612276076e-05,
373
+ "loss": 0.047,
374
+ "step": 430
375
+ },
376
+ {
377
+ "epoch": 0.6672353331437778,
378
+ "grad_norm": 0.5188047289848328,
379
+ "learning_rate": 9.966077797462129e-05,
380
+ "loss": 0.0456,
381
+ "step": 440
382
+ },
383
+ {
384
+ "epoch": 0.6823997725334091,
385
+ "grad_norm": 0.3099527060985565,
386
+ "learning_rate": 9.959638463477165e-05,
387
+ "loss": 0.0426,
388
+ "step": 450
389
+ },
390
+ {
391
+ "epoch": 0.6823997725334091,
392
+ "eval_loss": 0.043455954641103745,
393
+ "eval_runtime": 159.7181,
394
+ "eval_samples_per_second": 7.344,
395
+ "eval_steps_per_second": 7.344,
396
+ "step": 450
397
+ },
398
+ {
399
+ "epoch": 0.6975642119230405,
400
+ "grad_norm": 0.4291819632053375,
401
+ "learning_rate": 9.952642333236186e-05,
402
+ "loss": 0.0471,
403
+ "step": 460
404
+ },
405
+ {
406
+ "epoch": 0.7127286513126718,
407
+ "grad_norm": 0.47742322087287903,
408
+ "learning_rate": 9.945090192163202e-05,
409
+ "loss": 0.0514,
410
+ "step": 470
411
+ },
412
+ {
413
+ "epoch": 0.7278930907023031,
414
+ "grad_norm": 0.5357955098152161,
415
+ "learning_rate": 9.936982888103051e-05,
416
+ "loss": 0.0372,
417
+ "step": 480
418
+ },
419
+ {
420
+ "epoch": 0.7430575300919344,
421
+ "grad_norm": 0.3578835725784302,
422
+ "learning_rate": 9.928321331226219e-05,
423
+ "loss": 0.036,
424
+ "step": 490
425
+ },
426
+ {
427
+ "epoch": 0.7582219694815657,
428
+ "grad_norm": 1.1390984058380127,
429
+ "learning_rate": 9.919106493926655e-05,
430
+ "loss": 0.0354,
431
+ "step": 500
432
+ },
433
+ {
434
+ "epoch": 0.7582219694815657,
435
+ "eval_loss": 0.04678919166326523,
436
+ "eval_runtime": 159.8624,
437
+ "eval_samples_per_second": 7.338,
438
+ "eval_steps_per_second": 7.338,
439
+ "step": 500
440
+ },
441
+ {
442
+ "epoch": 0.773386408871197,
443
+ "grad_norm": 0.2849079966545105,
444
+ "learning_rate": 9.909339410712612e-05,
445
+ "loss": 0.0463,
446
+ "step": 510
447
+ },
448
+ {
449
+ "epoch": 0.7885508482608283,
450
+ "grad_norm": 0.43958020210266113,
451
+ "learning_rate": 9.8990211780905e-05,
452
+ "loss": 0.0388,
453
+ "step": 520
454
+ },
455
+ {
456
+ "epoch": 0.8037152876504596,
457
+ "grad_norm": 0.4281414747238159,
458
+ "learning_rate": 9.888152954441785e-05,
459
+ "loss": 0.0368,
460
+ "step": 530
461
+ },
462
+ {
463
+ "epoch": 0.8188797270400909,
464
+ "grad_norm": 0.20032383501529694,
465
+ "learning_rate": 9.876735959892953e-05,
466
+ "loss": 0.039,
467
+ "step": 540
468
+ },
469
+ {
470
+ "epoch": 0.8340441664297223,
471
+ "grad_norm": 0.697373628616333,
472
+ "learning_rate": 9.864771476178522e-05,
473
+ "loss": 0.0506,
474
+ "step": 550
475
+ },
476
+ {
477
+ "epoch": 0.8340441664297223,
478
+ "eval_loss": 0.04438818246126175,
479
+ "eval_runtime": 159.8887,
480
+ "eval_samples_per_second": 7.336,
481
+ "eval_steps_per_second": 7.336,
482
+ "step": 550
483
+ },
484
+ {
485
+ "epoch": 0.8492086058193536,
486
+ "grad_norm": 0.4126269817352295,
487
+ "learning_rate": 9.852260846497153e-05,
488
+ "loss": 0.0515,
489
+ "step": 560
490
+ },
491
+ {
492
+ "epoch": 0.864373045208985,
493
+ "grad_norm": 0.31782063841819763,
494
+ "learning_rate": 9.839205475360851e-05,
495
+ "loss": 0.0537,
496
+ "step": 570
497
+ },
498
+ {
499
+ "epoch": 0.8795374845986162,
500
+ "grad_norm": 0.28636643290519714,
501
+ "learning_rate": 9.825606828437291e-05,
502
+ "loss": 0.0497,
503
+ "step": 580
504
+ },
505
+ {
506
+ "epoch": 0.8947019239882475,
507
+ "grad_norm": 0.3322339951992035,
508
+ "learning_rate": 9.811466432385267e-05,
509
+ "loss": 0.0392,
510
+ "step": 590
511
+ },
512
+ {
513
+ "epoch": 0.9098663633778789,
514
+ "grad_norm": 0.40966206789016724,
515
+ "learning_rate": 9.796785874683314e-05,
516
+ "loss": 0.0346,
517
+ "step": 600
518
+ },
519
+ {
520
+ "epoch": 0.9098663633778789,
521
+ "eval_loss": 0.04112881049513817,
522
+ "eval_runtime": 159.8597,
523
+ "eval_samples_per_second": 7.338,
524
+ "eval_steps_per_second": 7.338,
525
+ "step": 600
526
+ },
527
+ {
528
+ "epoch": 0.9250308027675102,
529
+ "grad_norm": 0.34210318326950073,
530
+ "learning_rate": 9.781566803451475e-05,
531
+ "loss": 0.05,
532
+ "step": 610
533
+ },
534
+ {
535
+ "epoch": 0.9401952421571415,
536
+ "grad_norm": 0.45713552832603455,
537
+ "learning_rate": 9.765810927266281e-05,
538
+ "loss": 0.0414,
539
+ "step": 620
540
+ },
541
+ {
542
+ "epoch": 0.9553596815467729,
543
+ "grad_norm": 0.320637047290802,
544
+ "learning_rate": 9.749520014968934e-05,
545
+ "loss": 0.0389,
546
+ "step": 630
547
+ },
548
+ {
549
+ "epoch": 0.9705241209364042,
550
+ "grad_norm": 0.3496937155723572,
551
+ "learning_rate": 9.732695895466735e-05,
552
+ "loss": 0.0449,
553
+ "step": 640
554
+ },
555
+ {
556
+ "epoch": 0.9856885603260355,
557
+ "grad_norm": 0.3174608647823334,
558
+ "learning_rate": 9.715340457527746e-05,
559
+ "loss": 0.0514,
560
+ "step": 650
561
+ },
562
+ {
563
+ "epoch": 0.9856885603260355,
564
+ "eval_loss": 0.04426902160048485,
565
+ "eval_runtime": 159.8605,
566
+ "eval_samples_per_second": 7.338,
567
+ "eval_steps_per_second": 7.338,
568
+ "step": 650
569
+ },
570
+ {
571
+ "epoch": 1.0008529997156668,
572
+ "grad_norm": 0.26187363266944885,
573
+ "learning_rate": 9.697455649568761e-05,
574
+ "loss": 0.04,
575
+ "step": 660
576
+ },
577
+ {
578
+ "epoch": 1.016017439105298,
579
+ "grad_norm": 0.6161110997200012,
580
+ "learning_rate": 9.679043479436556e-05,
581
+ "loss": 0.0294,
582
+ "step": 670
583
+ },
584
+ {
585
+ "epoch": 1.0311818784949294,
586
+ "grad_norm": 0.18970751762390137,
587
+ "learning_rate": 9.660106014182489e-05,
588
+ "loss": 0.0277,
589
+ "step": 680
590
+ },
591
+ {
592
+ "epoch": 1.0463463178845607,
593
+ "grad_norm": 0.5361956357955933,
594
+ "learning_rate": 9.640645379830424e-05,
595
+ "loss": 0.0444,
596
+ "step": 690
597
+ },
598
+ {
599
+ "epoch": 1.061510757274192,
600
+ "grad_norm": 0.288272500038147,
601
+ "learning_rate": 9.620663761138067e-05,
602
+ "loss": 0.0323,
603
+ "step": 700
604
+ },
605
+ {
606
+ "epoch": 1.061510757274192,
607
+ "eval_loss": 0.041203178465366364,
608
+ "eval_runtime": 159.9229,
609
+ "eval_samples_per_second": 7.335,
610
+ "eval_steps_per_second": 7.335,
611
+ "step": 700
612
+ },
613
+ {
614
+ "epoch": 1.0766751966638233,
615
+ "grad_norm": 0.11579044908285141,
616
+ "learning_rate": 9.600163401351688e-05,
617
+ "loss": 0.0261,
618
+ "step": 710
619
+ },
620
+ {
621
+ "epoch": 1.0918396360534546,
622
+ "grad_norm": 0.3901958167552948,
623
+ "learning_rate": 9.579146601954276e-05,
624
+ "loss": 0.0453,
625
+ "step": 720
626
+ },
627
+ {
628
+ "epoch": 1.1070040754430859,
629
+ "grad_norm": 0.15443949401378632,
630
+ "learning_rate": 9.557615722407177e-05,
631
+ "loss": 0.0364,
632
+ "step": 730
633
+ },
634
+ {
635
+ "epoch": 1.1221685148327172,
636
+ "grad_norm": 0.1345423012971878,
637
+ "learning_rate": 9.535573179885191e-05,
638
+ "loss": 0.0279,
639
+ "step": 740
640
+ },
641
+ {
642
+ "epoch": 1.1373329542223485,
643
+ "grad_norm": 0.17373351752758026,
644
+ "learning_rate": 9.513021449005214e-05,
645
+ "loss": 0.0261,
646
+ "step": 750
647
+ },
648
+ {
649
+ "epoch": 1.1373329542223485,
650
+ "eval_loss": 0.04307902976870537,
651
+ "eval_runtime": 159.8102,
652
+ "eval_samples_per_second": 7.34,
653
+ "eval_steps_per_second": 7.34,
654
+ "step": 750
655
+ },
656
+ {
657
+ "epoch": 1.15249739361198,
658
+ "grad_norm": 0.1945541799068451,
659
+ "learning_rate": 9.489963061548428e-05,
660
+ "loss": 0.0326,
661
+ "step": 760
662
+ },
663
+ {
664
+ "epoch": 1.1676618330016113,
665
+ "grad_norm": 0.14704962074756622,
666
+ "learning_rate": 9.466400606176062e-05,
667
+ "loss": 0.0232,
668
+ "step": 770
669
+ },
670
+ {
671
+ "epoch": 1.1828262723912426,
672
+ "grad_norm": 0.2738613486289978,
673
+ "learning_rate": 9.442336728138779e-05,
674
+ "loss": 0.0235,
675
+ "step": 780
676
+ },
677
+ {
678
+ "epoch": 1.197990711780874,
679
+ "grad_norm": 0.14102770388126373,
680
+ "learning_rate": 9.417774128979706e-05,
681
+ "loss": 0.0364,
682
+ "step": 790
683
+ },
684
+ {
685
+ "epoch": 1.2131551511705052,
686
+ "grad_norm": 0.3271743953227997,
687
+ "learning_rate": 9.39271556623114e-05,
688
+ "loss": 0.0307,
689
+ "step": 800
690
+ },
691
+ {
692
+ "epoch": 1.2131551511705052,
693
+ "eval_loss": 0.03978438675403595,
694
+ "eval_runtime": 159.8781,
695
+ "eval_samples_per_second": 7.337,
696
+ "eval_steps_per_second": 7.337,
697
+ "step": 800
698
+ },
699
+ {
700
+ "epoch": 1.2283195905601365,
701
+ "grad_norm": 0.4989463686943054,
702
+ "learning_rate": 9.367163853104975e-05,
703
+ "loss": 0.039,
704
+ "step": 810
705
+ },
706
+ {
707
+ "epoch": 1.2434840299497678,
708
+ "grad_norm": 0.19276122748851776,
709
+ "learning_rate": 9.341121858176876e-05,
710
+ "loss": 0.0413,
711
+ "step": 820
712
+ },
713
+ {
714
+ "epoch": 1.2586484693393991,
715
+ "grad_norm": 0.29775118827819824,
716
+ "learning_rate": 9.314592505064239e-05,
717
+ "loss": 0.036,
718
+ "step": 830
719
+ },
720
+ {
721
+ "epoch": 1.2738129087290304,
722
+ "grad_norm": 0.23416060209274292,
723
+ "learning_rate": 9.28757877209796e-05,
724
+ "loss": 0.0258,
725
+ "step": 840
726
+ },
727
+ {
728
+ "epoch": 1.2889773481186617,
729
+ "grad_norm": 0.14653538167476654,
730
+ "learning_rate": 9.260083691988084e-05,
731
+ "loss": 0.0284,
732
+ "step": 850
733
+ },
734
+ {
735
+ "epoch": 1.2889773481186617,
736
+ "eval_loss": 0.04156646877527237,
737
+ "eval_runtime": 159.8802,
738
+ "eval_samples_per_second": 7.337,
739
+ "eval_steps_per_second": 7.337,
740
+ "step": 850
741
+ },
742
+ {
743
+ "epoch": 1.304141787508293,
744
+ "grad_norm": 0.4026676416397095,
745
+ "learning_rate": 9.232110351483327e-05,
746
+ "loss": 0.0368,
747
+ "step": 860
748
+ },
749
+ {
750
+ "epoch": 1.3193062268979243,
751
+ "grad_norm": 0.4935552179813385,
752
+ "learning_rate": 9.203661891024547e-05,
753
+ "loss": 0.0369,
754
+ "step": 870
755
+ },
756
+ {
757
+ "epoch": 1.3344706662875556,
758
+ "grad_norm": 0.3299759328365326,
759
+ "learning_rate": 9.174741504392173e-05,
760
+ "loss": 0.0345,
761
+ "step": 880
762
+ },
763
+ {
764
+ "epoch": 1.349635105677187,
765
+ "grad_norm": 0.24818608164787292,
766
+ "learning_rate": 9.145352438347662e-05,
767
+ "loss": 0.0413,
768
+ "step": 890
769
+ },
770
+ {
771
+ "epoch": 1.3647995450668184,
772
+ "grad_norm": 0.2329672873020172,
773
+ "learning_rate": 9.115497992268995e-05,
774
+ "loss": 0.0316,
775
+ "step": 900
776
+ },
777
+ {
778
+ "epoch": 1.3647995450668184,
779
+ "eval_loss": 0.03982315585017204,
780
+ "eval_runtime": 159.8004,
781
+ "eval_samples_per_second": 7.34,
782
+ "eval_steps_per_second": 7.34,
783
+ "step": 900
784
+ },
785
+ {
786
+ "epoch": 1.3799639844564497,
787
+ "grad_norm": 0.07506946474313736,
788
+ "learning_rate": 9.085181517780273e-05,
789
+ "loss": 0.0309,
790
+ "step": 910
791
+ },
792
+ {
793
+ "epoch": 1.395128423846081,
794
+ "grad_norm": 0.19676469266414642,
795
+ "learning_rate": 9.054406418375443e-05,
796
+ "loss": 0.0355,
797
+ "step": 920
798
+ },
799
+ {
800
+ "epoch": 1.4102928632357123,
801
+ "grad_norm": 0.2670162320137024,
802
+ "learning_rate": 9.023176149036203e-05,
803
+ "loss": 0.0299,
804
+ "step": 930
805
+ },
806
+ {
807
+ "epoch": 1.4254573026253436,
808
+ "grad_norm": 0.24655964970588684,
809
+ "learning_rate": 8.991494215844132e-05,
810
+ "loss": 0.0416,
811
+ "step": 940
812
+ },
813
+ {
814
+ "epoch": 1.440621742014975,
815
+ "grad_norm": 0.42746463418006897,
816
+ "learning_rate": 8.959364175587069e-05,
817
+ "loss": 0.0288,
818
+ "step": 950
819
+ },
820
+ {
821
+ "epoch": 1.440621742014975,
822
+ "eval_loss": 0.039692338556051254,
823
+ "eval_runtime": 159.8479,
824
+ "eval_samples_per_second": 7.338,
825
+ "eval_steps_per_second": 7.338,
826
+ "step": 950
827
+ },
828
+ {
829
+ "epoch": 1.4557861814046062,
830
+ "grad_norm": 0.20224446058273315,
831
+ "learning_rate": 8.926789635359817e-05,
832
+ "loss": 0.0448,
833
+ "step": 960
834
+ },
835
+ {
836
+ "epoch": 1.4709506207942376,
837
+ "grad_norm": 0.16787214577198029,
838
+ "learning_rate": 8.893774252159187e-05,
839
+ "loss": 0.0294,
840
+ "step": 970
841
+ },
842
+ {
843
+ "epoch": 1.4861150601838689,
844
+ "grad_norm": 0.20546148717403412,
845
+ "learning_rate": 8.860321732473439e-05,
846
+ "loss": 0.0396,
847
+ "step": 980
848
+ },
849
+ {
850
+ "epoch": 1.5012794995735002,
851
+ "grad_norm": 0.4057621657848358,
852
+ "learning_rate": 8.826435831866184e-05,
853
+ "loss": 0.0389,
854
+ "step": 990
855
+ },
856
+ {
857
+ "epoch": 1.5164439389631315,
858
+ "grad_norm": 0.09442304074764252,
859
+ "learning_rate": 8.79212035455475e-05,
860
+ "loss": 0.0306,
861
+ "step": 1000
862
+ },
863
+ {
864
+ "epoch": 1.5164439389631315,
865
+ "eval_loss": 0.041055887937545776,
866
+ "eval_runtime": 159.778,
867
+ "eval_samples_per_second": 7.341,
868
+ "eval_steps_per_second": 7.341,
869
+ "step": 1000
870
+ },
871
+ {
872
+ "epoch": 1.5316083783527628,
873
+ "grad_norm": 0.2399837076663971,
874
+ "learning_rate": 8.757379152983103e-05,
875
+ "loss": 0.03,
876
+ "step": 1010
877
+ },
878
+ {
879
+ "epoch": 1.546772817742394,
880
+ "grad_norm": 0.38911059498786926,
881
+ "learning_rate": 8.722216127389363e-05,
882
+ "loss": 0.0335,
883
+ "step": 1020
884
+ },
885
+ {
886
+ "epoch": 1.5619372571320254,
887
+ "grad_norm": 0.6509933471679688,
888
+ "learning_rate": 8.686635225367919e-05,
889
+ "loss": 0.0361,
890
+ "step": 1030
891
+ },
892
+ {
893
+ "epoch": 1.5771016965216567,
894
+ "grad_norm": 0.20148853957653046,
895
+ "learning_rate": 8.650640441426274e-05,
896
+ "loss": 0.038,
897
+ "step": 1040
898
+ },
899
+ {
900
+ "epoch": 1.592266135911288,
901
+ "grad_norm": 0.3823687434196472,
902
+ "learning_rate": 8.614235816536582e-05,
903
+ "loss": 0.0449,
904
+ "step": 1050
905
+ },
906
+ {
907
+ "epoch": 1.592266135911288,
908
+ "eval_loss": 0.03836758807301521,
909
+ "eval_runtime": 159.8354,
910
+ "eval_samples_per_second": 7.339,
911
+ "eval_steps_per_second": 7.339,
912
+ "step": 1050
913
+ },
914
+ {
915
+ "epoch": 1.6074305753009193,
916
+ "grad_norm": 0.3107754588127136,
917
+ "learning_rate": 8.577425437681994e-05,
918
+ "loss": 0.0377,
919
+ "step": 1060
920
+ },
921
+ {
922
+ "epoch": 1.6225950146905506,
923
+ "grad_norm": 0.17179957032203674,
924
+ "learning_rate": 8.540213437397833e-05,
925
+ "loss": 0.0322,
926
+ "step": 1070
927
+ },
928
+ {
929
+ "epoch": 1.6377594540801819,
930
+ "grad_norm": 0.10634970664978027,
931
+ "learning_rate": 8.502603993307647e-05,
932
+ "loss": 0.0273,
933
+ "step": 1080
934
+ },
935
+ {
936
+ "epoch": 1.6529238934698132,
937
+ "grad_norm": 0.32147282361984253,
938
+ "learning_rate": 8.464601327654207e-05,
939
+ "loss": 0.0251,
940
+ "step": 1090
941
+ },
942
+ {
943
+ "epoch": 1.6680883328594445,
944
+ "grad_norm": 0.29508742690086365,
945
+ "learning_rate": 8.4262097068255e-05,
946
+ "loss": 0.0281,
947
+ "step": 1100
948
+ },
949
+ {
950
+ "epoch": 1.6680883328594445,
951
+ "eval_loss": 0.038478951901197433,
952
+ "eval_runtime": 159.8811,
953
+ "eval_samples_per_second": 7.337,
954
+ "eval_steps_per_second": 7.337,
955
+ "step": 1100
956
+ },
957
+ {
958
+ "epoch": 1.6832527722490758,
959
+ "grad_norm": 0.5426458716392517,
960
+ "learning_rate": 8.387433440875758e-05,
961
+ "loss": 0.0331,
962
+ "step": 1110
963
+ },
964
+ {
965
+ "epoch": 1.698417211638707,
966
+ "grad_norm": 0.2759105861186981,
967
+ "learning_rate": 8.348276883041583e-05,
968
+ "loss": 0.0336,
969
+ "step": 1120
970
+ },
971
+ {
972
+ "epoch": 1.7135816510283386,
973
+ "grad_norm": 0.4834611415863037,
974
+ "learning_rate": 8.308744429253238e-05,
975
+ "loss": 0.0464,
976
+ "step": 1130
977
+ },
978
+ {
979
+ "epoch": 1.72874609041797,
980
+ "grad_norm": 0.3538722097873688,
981
+ "learning_rate": 8.268840517641123e-05,
982
+ "loss": 0.0345,
983
+ "step": 1140
984
+ },
985
+ {
986
+ "epoch": 1.7439105298076012,
987
+ "grad_norm": 0.41168689727783203,
988
+ "learning_rate": 8.228569628037543e-05,
989
+ "loss": 0.038,
990
+ "step": 1150
991
+ },
992
+ {
993
+ "epoch": 1.7439105298076012,
994
+ "eval_loss": 0.03758051246404648,
995
+ "eval_runtime": 159.8738,
996
+ "eval_samples_per_second": 7.337,
997
+ "eval_steps_per_second": 7.337,
998
+ "step": 1150
999
+ },
1000
+ {
1001
+ "epoch": 1.7590749691972325,
1002
+ "grad_norm": 0.3065544068813324,
1003
+ "learning_rate": 8.187936281473758e-05,
1004
+ "loss": 0.0325,
1005
+ "step": 1160
1006
+ },
1007
+ {
1008
+ "epoch": 1.7742394085868638,
1009
+ "grad_norm": 0.24398308992385864,
1010
+ "learning_rate": 8.146945039672446e-05,
1011
+ "loss": 0.0276,
1012
+ "step": 1170
1013
+ },
1014
+ {
1015
+ "epoch": 1.789403847976495,
1016
+ "grad_norm": 0.29391804337501526,
1017
+ "learning_rate": 8.105600504535567e-05,
1018
+ "loss": 0.0306,
1019
+ "step": 1180
1020
+ },
1021
+ {
1022
+ "epoch": 1.8045682873661264,
1023
+ "grad_norm": 0.33613964915275574,
1024
+ "learning_rate": 8.06390731762773e-05,
1025
+ "loss": 0.0416,
1026
+ "step": 1190
1027
+ },
1028
+ {
1029
+ "epoch": 1.8197327267557577,
1030
+ "grad_norm": 0.6730492115020752,
1031
+ "learning_rate": 8.021870159655109e-05,
1032
+ "loss": 0.0277,
1033
+ "step": 1200
1034
+ },
1035
+ {
1036
+ "epoch": 1.8197327267557577,
1037
+ "eval_loss": 0.03543492406606674,
1038
+ "eval_runtime": 159.8678,
1039
+ "eval_samples_per_second": 7.337,
1040
+ "eval_steps_per_second": 7.337,
1041
+ "step": 1200
1042
+ },
1043
+ {
1044
+ "epoch": 1.8348971661453892,
1045
+ "grad_norm": 0.31159326434135437,
1046
+ "learning_rate": 7.979493749939955e-05,
1047
+ "loss": 0.0335,
1048
+ "step": 1210
1049
+ },
1050
+ {
1051
+ "epoch": 1.8500616055350205,
1052
+ "grad_norm": 0.2657136917114258,
1053
+ "learning_rate": 7.93678284589079e-05,
1054
+ "loss": 0.0421,
1055
+ "step": 1220
1056
+ },
1057
+ {
1058
+ "epoch": 1.8652260449246518,
1059
+ "grad_norm": 0.1698162853717804,
1060
+ "learning_rate": 7.893742242468301e-05,
1061
+ "loss": 0.0282,
1062
+ "step": 1230
1063
+ },
1064
+ {
1065
+ "epoch": 1.8803904843142831,
1066
+ "grad_norm": 0.5252974629402161,
1067
+ "learning_rate": 7.850376771647038e-05,
1068
+ "loss": 0.0386,
1069
+ "step": 1240
1070
+ },
1071
+ {
1072
+ "epoch": 1.8955549237039144,
1073
+ "grad_norm": 0.31378066539764404,
1074
+ "learning_rate": 7.806691301872958e-05,
1075
+ "loss": 0.0381,
1076
+ "step": 1250
1077
+ },
1078
+ {
1079
+ "epoch": 1.8955549237039144,
1080
+ "eval_loss": 0.037748388946056366,
1081
+ "eval_runtime": 159.8804,
1082
+ "eval_samples_per_second": 7.337,
1083
+ "eval_steps_per_second": 7.337,
1084
+ "step": 1250
1085
+ },
1086
+ {
1087
+ "epoch": 1.9107193630935457,
1088
+ "grad_norm": 0.16329045593738556,
1089
+ "learning_rate": 7.762690737516846e-05,
1090
+ "loss": 0.0359,
1091
+ "step": 1260
1092
+ },
1093
+ {
1094
+ "epoch": 1.925883802483177,
1095
+ "grad_norm": 0.23127301037311554,
1096
+ "learning_rate": 7.718380018323742e-05,
1097
+ "loss": 0.0326,
1098
+ "step": 1270
1099
+ },
1100
+ {
1101
+ "epoch": 1.9410482418728083,
1102
+ "grad_norm": 0.29971396923065186,
1103
+ "learning_rate": 7.673764118858371e-05,
1104
+ "loss": 0.0279,
1105
+ "step": 1280
1106
+ },
1107
+ {
1108
+ "epoch": 1.9562126812624396,
1109
+ "grad_norm": 0.14393766224384308,
1110
+ "learning_rate": 7.628848047946675e-05,
1111
+ "loss": 0.0408,
1112
+ "step": 1290
1113
+ },
1114
+ {
1115
+ "epoch": 1.971377120652071,
1116
+ "grad_norm": 0.24297180771827698,
1117
+ "learning_rate": 7.583636848113483e-05,
1118
+ "loss": 0.0278,
1119
+ "step": 1300
1120
+ },
1121
+ {
1122
+ "epoch": 1.971377120652071,
1123
+ "eval_loss": 0.03594334051012993,
1124
+ "eval_runtime": 159.9049,
1125
+ "eval_samples_per_second": 7.336,
1126
+ "eval_steps_per_second": 7.336,
1127
+ "step": 1300
1128
+ },
1129
+ {
1130
+ "epoch": 1.9865415600417022,
1131
+ "grad_norm": 0.33698412775993347,
1132
+ "learning_rate": 7.538135595016423e-05,
1133
+ "loss": 0.0322,
1134
+ "step": 1310
1135
+ },
1136
+ {
1137
+ "epoch": 2.0017059994313335,
1138
+ "grad_norm": 0.28321677446365356,
1139
+ "learning_rate": 7.492349396876096e-05,
1140
+ "loss": 0.0292,
1141
+ "step": 1320
1142
+ },
1143
+ {
1144
+ "epoch": 2.016870438820965,
1145
+ "grad_norm": 0.11086804419755936,
1146
+ "learning_rate": 7.4462833939026e-05,
1147
+ "loss": 0.0237,
1148
+ "step": 1330
1149
+ },
1150
+ {
1151
+ "epoch": 2.032034878210596,
1152
+ "grad_norm": 0.3019621670246124,
1153
+ "learning_rate": 7.399942757718455e-05,
1154
+ "loss": 0.0219,
1155
+ "step": 1340
1156
+ },
1157
+ {
1158
+ "epoch": 2.0471993176002274,
1159
+ "grad_norm": 0.26927098631858826,
1160
+ "learning_rate": 7.35333269077802e-05,
1161
+ "loss": 0.0194,
1162
+ "step": 1350
1163
+ },
1164
+ {
1165
+ "epoch": 2.0471993176002274,
1166
+ "eval_loss": 0.03932846337556839,
1167
+ "eval_runtime": 159.9101,
1168
+ "eval_samples_per_second": 7.335,
1169
+ "eval_steps_per_second": 7.335,
1170
+ "step": 1350
1171
+ },
1172
+ {
1173
+ "epoch": 2.0623637569898587,
1174
+ "grad_norm": 0.1983146220445633,
1175
+ "learning_rate": 7.306458425783426e-05,
1176
+ "loss": 0.0287,
1177
+ "step": 1360
1178
+ },
1179
+ {
1180
+ "epoch": 2.07752819637949,
1181
+ "grad_norm": 0.2132590264081955,
1182
+ "learning_rate": 7.25932522509713e-05,
1183
+ "loss": 0.02,
1184
+ "step": 1370
1185
+ },
1186
+ {
1187
+ "epoch": 2.0926926357691213,
1188
+ "grad_norm": 0.4830004572868347,
1189
+ "learning_rate": 7.211938380151133e-05,
1190
+ "loss": 0.0244,
1191
+ "step": 1380
1192
+ },
1193
+ {
1194
+ "epoch": 2.1078570751587526,
1195
+ "grad_norm": 0.3054353594779968,
1196
+ "learning_rate": 7.164303210852934e-05,
1197
+ "loss": 0.0309,
1198
+ "step": 1390
1199
+ },
1200
+ {
1201
+ "epoch": 2.123021514548384,
1202
+ "grad_norm": 0.22349397838115692,
1203
+ "learning_rate": 7.116425064988286e-05,
1204
+ "loss": 0.0149,
1205
+ "step": 1400
1206
+ },
1207
+ {
1208
+ "epoch": 2.123021514548384,
1209
+ "eval_loss": 0.03746328130364418,
1210
+ "eval_runtime": 159.9069,
1211
+ "eval_samples_per_second": 7.336,
1212
+ "eval_steps_per_second": 7.336,
1213
+ "step": 1400
1214
+ },
1215
+ {
1216
+ "epoch": 2.1381859539380152,
1217
+ "grad_norm": 0.23747169971466064,
1218
+ "learning_rate": 7.068309317620827e-05,
1219
+ "loss": 0.0244,
1220
+ "step": 1410
1221
+ },
1222
+ {
1223
+ "epoch": 2.1533503933276466,
1224
+ "grad_norm": 0.2875257730484009,
1225
+ "learning_rate": 7.019961370488645e-05,
1226
+ "loss": 0.0211,
1227
+ "step": 1420
1228
+ },
1229
+ {
1230
+ "epoch": 2.168514832717278,
1231
+ "grad_norm": 0.24418668448925018,
1232
+ "learning_rate": 6.971386651397849e-05,
1233
+ "loss": 0.02,
1234
+ "step": 1430
1235
+ },
1236
+ {
1237
+ "epoch": 2.183679272106909,
1238
+ "grad_norm": 0.5265827178955078,
1239
+ "learning_rate": 6.922590613613211e-05,
1240
+ "loss": 0.0169,
1241
+ "step": 1440
1242
+ },
1243
+ {
1244
+ "epoch": 2.1988437114965405,
1245
+ "grad_norm": 0.2406657487154007,
1246
+ "learning_rate": 6.873578735245961e-05,
1247
+ "loss": 0.0243,
1248
+ "step": 1450
1249
+ },
1250
+ {
1251
+ "epoch": 2.1988437114965405,
1252
+ "eval_loss": 0.04021035507321358,
1253
+ "eval_runtime": 159.985,
1254
+ "eval_samples_per_second": 7.332,
1255
+ "eval_steps_per_second": 7.332,
1256
+ "step": 1450
1257
+ },
1258
+ {
1259
+ "epoch": 2.2140081508861718,
1260
+ "grad_norm": 0.14891931414604187,
1261
+ "learning_rate": 6.824356518638775e-05,
1262
+ "loss": 0.021,
1263
+ "step": 1460
1264
+ },
1265
+ {
1266
+ "epoch": 2.229172590275803,
1267
+ "grad_norm": 0.32252541184425354,
1268
+ "learning_rate": 6.774929489748052e-05,
1269
+ "loss": 0.0198,
1270
+ "step": 1470
1271
+ },
1272
+ {
1273
+ "epoch": 2.2443370296654344,
1274
+ "grad_norm": 1.1908115148544312,
1275
+ "learning_rate": 6.725303197523548e-05,
1276
+ "loss": 0.0302,
1277
+ "step": 1480
1278
+ },
1279
+ {
1280
+ "epoch": 2.259501469055066,
1281
+ "grad_norm": 0.19598431885242462,
1282
+ "learning_rate": 6.675483213285412e-05,
1283
+ "loss": 0.0225,
1284
+ "step": 1490
1285
+ },
1286
+ {
1287
+ "epoch": 2.274665908444697,
1288
+ "grad_norm": 0.37645435333251953,
1289
+ "learning_rate": 6.625475130098728e-05,
1290
+ "loss": 0.0234,
1291
+ "step": 1500
1292
+ },
1293
+ {
1294
+ "epoch": 2.274665908444697,
1295
+ "eval_loss": 0.039622507989406586,
1296
+ "eval_runtime": 160.0131,
1297
+ "eval_samples_per_second": 7.331,
1298
+ "eval_steps_per_second": 7.331,
1299
+ "step": 1500
1300
+ },
1301
+ {
1302
+ "epoch": 2.2898303478343287,
1303
+ "grad_norm": 0.2178558111190796,
1304
+ "learning_rate": 6.575284562145593e-05,
1305
+ "loss": 0.0213,
1306
+ "step": 1510
1307
+ },
1308
+ {
1309
+ "epoch": 2.30499478722396,
1310
+ "grad_norm": 0.4462236762046814,
1311
+ "learning_rate": 6.524917144094851e-05,
1312
+ "loss": 0.0258,
1313
+ "step": 1520
1314
+ },
1315
+ {
1316
+ "epoch": 2.3201592266135913,
1317
+ "grad_norm": 0.0876719132065773,
1318
+ "learning_rate": 6.474378530469509e-05,
1319
+ "loss": 0.025,
1320
+ "step": 1530
1321
+ },
1322
+ {
1323
+ "epoch": 2.3353236660032226,
1324
+ "grad_norm": 0.16359026730060577,
1325
+ "learning_rate": 6.42367439501193e-05,
1326
+ "loss": 0.0205,
1327
+ "step": 1540
1328
+ },
1329
+ {
1330
+ "epoch": 2.350488105392854,
1331
+ "grad_norm": 0.25489160418510437,
1332
+ "learning_rate": 6.372810430046862e-05,
1333
+ "loss": 0.0189,
1334
+ "step": 1550
1335
+ },
1336
+ {
1337
+ "epoch": 2.350488105392854,
1338
+ "eval_loss": 0.03922748565673828,
1339
+ "eval_runtime": 159.9514,
1340
+ "eval_samples_per_second": 7.333,
1341
+ "eval_steps_per_second": 7.333,
1342
+ "step": 1550
1343
+ },
1344
+ {
1345
+ "epoch": 2.365652544782485,
1346
+ "grad_norm": 0.11957678943872452,
1347
+ "learning_rate": 6.321792345842402e-05,
1348
+ "loss": 0.0228,
1349
+ "step": 1560
1350
+ },
1351
+ {
1352
+ "epoch": 2.3808169841721165,
1353
+ "grad_norm": 0.23994044959545135,
1354
+ "learning_rate": 6.270625869968906e-05,
1355
+ "loss": 0.0323,
1356
+ "step": 1570
1357
+ },
1358
+ {
1359
+ "epoch": 2.395981423561748,
1360
+ "grad_norm": 0.1954767256975174,
1361
+ "learning_rate": 6.219316746656007e-05,
1362
+ "loss": 0.0284,
1363
+ "step": 1580
1364
+ },
1365
+ {
1366
+ "epoch": 2.411145862951379,
1367
+ "grad_norm": 0.25645068287849426,
1368
+ "learning_rate": 6.167870736147713e-05,
1369
+ "loss": 0.0234,
1370
+ "step": 1590
1371
+ },
1372
+ {
1373
+ "epoch": 2.4263103023410104,
1374
+ "grad_norm": 0.7860223054885864,
1375
+ "learning_rate": 6.116293614055744e-05,
1376
+ "loss": 0.0195,
1377
+ "step": 1600
1378
+ },
1379
+ {
1380
+ "epoch": 2.4263103023410104,
1381
+ "eval_loss": 0.03961315006017685,
1382
+ "eval_runtime": 159.8725,
1383
+ "eval_samples_per_second": 7.337,
1384
+ "eval_steps_per_second": 7.337,
1385
+ "step": 1600
1386
+ },
1387
+ {
1388
+ "epoch": 2.4414747417306417,
1389
+ "grad_norm": 0.2385544329881668,
1390
+ "learning_rate": 6.06459117071113e-05,
1391
+ "loss": 0.0186,
1392
+ "step": 1610
1393
+ },
1394
+ {
1395
+ "epoch": 2.456639181120273,
1396
+ "grad_norm": 0.5610677599906921,
1397
+ "learning_rate": 6.012769210514146e-05,
1398
+ "loss": 0.0213,
1399
+ "step": 1620
1400
+ },
1401
+ {
1402
+ "epoch": 2.4718036205099043,
1403
+ "grad_norm": 0.1168915182352066,
1404
+ "learning_rate": 5.9608335512826915e-05,
1405
+ "loss": 0.0207,
1406
+ "step": 1630
1407
+ },
1408
+ {
1409
+ "epoch": 2.4869680598995356,
1410
+ "grad_norm": 0.08927187323570251,
1411
+ "learning_rate": 5.908790023599144e-05,
1412
+ "loss": 0.0143,
1413
+ "step": 1640
1414
+ },
1415
+ {
1416
+ "epoch": 2.502132499289167,
1417
+ "grad_norm": 0.2827674448490143,
1418
+ "learning_rate": 5.856644470155781e-05,
1419
+ "loss": 0.0221,
1420
+ "step": 1650
1421
+ },
1422
+ {
1423
+ "epoch": 2.502132499289167,
1424
+ "eval_loss": 0.04753277450799942,
1425
+ "eval_runtime": 159.8134,
1426
+ "eval_samples_per_second": 7.34,
1427
+ "eval_steps_per_second": 7.34,
1428
+ "step": 1650
1429
+ },
1430
+ {
1431
+ "epoch": 2.5172969386787982,
1432
+ "grad_norm": 0.2750401496887207,
1433
+ "learning_rate": 5.8044027450988546e-05,
1434
+ "loss": 0.028,
1435
+ "step": 1660
1436
+ },
1437
+ {
1438
+ "epoch": 2.5324613780684295,
1439
+ "grad_norm": 0.19203156232833862,
1440
+ "learning_rate": 5.752070713371371e-05,
1441
+ "loss": 0.0161,
1442
+ "step": 1670
1443
+ },
1444
+ {
1445
+ "epoch": 2.547625817458061,
1446
+ "grad_norm": 0.1918914020061493,
1447
+ "learning_rate": 5.699654250054662e-05,
1448
+ "loss": 0.0165,
1449
+ "step": 1680
1450
+ },
1451
+ {
1452
+ "epoch": 2.562790256847692,
1453
+ "grad_norm": 0.1869034469127655,
1454
+ "learning_rate": 5.647159239708809e-05,
1455
+ "loss": 0.014,
1456
+ "step": 1690
1457
+ },
1458
+ {
1459
+ "epoch": 2.5779546962373234,
1460
+ "grad_norm": 0.18233343958854675,
1461
+ "learning_rate": 5.5945915757120146e-05,
1462
+ "loss": 0.0179,
1463
+ "step": 1700
1464
+ },
1465
+ {
1466
+ "epoch": 2.5779546962373234,
1467
+ "eval_loss": 0.04084445536136627,
1468
+ "eval_runtime": 159.9315,
1469
+ "eval_samples_per_second": 7.334,
1470
+ "eval_steps_per_second": 7.334,
1471
+ "step": 1700
1472
+ },
1473
+ {
1474
+ "epoch": 2.5931191356269547,
1475
+ "grad_norm": 0.4812876284122467,
1476
+ "learning_rate": 5.5419571595989825e-05,
1477
+ "loss": 0.0272,
1478
+ "step": 1710
1479
+ },
1480
+ {
1481
+ "epoch": 2.608283575016586,
1482
+ "grad_norm": 0.3959842920303345,
1483
+ "learning_rate": 5.4892619003983734e-05,
1484
+ "loss": 0.0248,
1485
+ "step": 1720
1486
+ },
1487
+ {
1488
+ "epoch": 2.6234480144062173,
1489
+ "grad_norm": 0.14155489206314087,
1490
+ "learning_rate": 5.436511713969428e-05,
1491
+ "loss": 0.0157,
1492
+ "step": 1730
1493
+ },
1494
+ {
1495
+ "epoch": 2.6386124537958486,
1496
+ "grad_norm": 0.07145866006612778,
1497
+ "learning_rate": 5.383712522337817e-05,
1498
+ "loss": 0.024,
1499
+ "step": 1740
1500
+ },
1501
+ {
1502
+ "epoch": 2.65377689318548,
1503
+ "grad_norm": 0.26969072222709656,
1504
+ "learning_rate": 5.3308702530308076e-05,
1505
+ "loss": 0.0225,
1506
+ "step": 1750
1507
+ },
1508
+ {
1509
+ "epoch": 2.65377689318548,
1510
+ "eval_loss": 0.038576629012823105,
1511
+ "eval_runtime": 159.8548,
1512
+ "eval_samples_per_second": 7.338,
1513
+ "eval_steps_per_second": 7.338,
1514
+ "step": 1750
1515
+ },
1516
+ {
1517
+ "epoch": 2.6689413325751112,
1518
+ "grad_norm": 0.3706766366958618,
1519
+ "learning_rate": 5.2779908384118025e-05,
1520
+ "loss": 0.0258,
1521
+ "step": 1760
1522
+ },
1523
+ {
1524
+ "epoch": 2.6841057719647425,
1525
+ "grad_norm": 0.36738407611846924,
1526
+ "learning_rate": 5.22508021501434e-05,
1527
+ "loss": 0.0215,
1528
+ "step": 1770
1529
+ },
1530
+ {
1531
+ "epoch": 2.699270211354374,
1532
+ "grad_norm": 0.34079742431640625,
1533
+ "learning_rate": 5.1721443228756284e-05,
1534
+ "loss": 0.0163,
1535
+ "step": 1780
1536
+ },
1537
+ {
1538
+ "epoch": 2.714434650744005,
1539
+ "grad_norm": 0.33863401412963867,
1540
+ "learning_rate": 5.119189104869683e-05,
1541
+ "loss": 0.0219,
1542
+ "step": 1790
1543
+ },
1544
+ {
1545
+ "epoch": 2.729599090133637,
1546
+ "grad_norm": 0.2650861442089081,
1547
+ "learning_rate": 5.066220506040148e-05,
1548
+ "loss": 0.0207,
1549
+ "step": 1800
1550
+ },
1551
+ {
1552
+ "epoch": 2.729599090133637,
1553
+ "eval_loss": 0.03975927457213402,
1554
+ "eval_runtime": 159.781,
1555
+ "eval_samples_per_second": 7.341,
1556
+ "eval_steps_per_second": 7.341,
1557
+ "step": 1800
1558
+ },
1559
+ {
1560
+ "epoch": 2.7447635295232677,
1561
+ "grad_norm": 0.20335064828395844,
1562
+ "learning_rate": 5.013244472932872e-05,
1563
+ "loss": 0.0248,
1564
+ "step": 1810
1565
+ },
1566
+ {
1567
+ "epoch": 2.7599279689128995,
1568
+ "grad_norm": 0.29428455233573914,
1569
+ "learning_rate": 4.960266952928316e-05,
1570
+ "loss": 0.0215,
1571
+ "step": 1820
1572
+ },
1573
+ {
1574
+ "epoch": 2.7750924083025303,
1575
+ "grad_norm": 0.3635200262069702,
1576
+ "learning_rate": 4.907293893573867e-05,
1577
+ "loss": 0.0225,
1578
+ "step": 1830
1579
+ },
1580
+ {
1581
+ "epoch": 2.790256847692162,
1582
+ "grad_norm": 0.32583731412887573,
1583
+ "learning_rate": 4.8543312419161396e-05,
1584
+ "loss": 0.0197,
1585
+ "step": 1840
1586
+ },
1587
+ {
1588
+ "epoch": 2.805421287081793,
1589
+ "grad_norm": 0.20632241666316986,
1590
+ "learning_rate": 4.8013849438333165e-05,
1591
+ "loss": 0.015,
1592
+ "step": 1850
1593
+ },
1594
+ {
1595
+ "epoch": 2.805421287081793,
1596
+ "eval_loss": 0.041027262806892395,
1597
+ "eval_runtime": 159.7438,
1598
+ "eval_samples_per_second": 7.343,
1599
+ "eval_steps_per_second": 7.343,
1600
+ "step": 1850
1601
+ },
1602
+ {
1603
+ "epoch": 2.8205857264714247,
1604
+ "grad_norm": 0.8117703795433044,
1605
+ "learning_rate": 4.748460943367643e-05,
1606
+ "loss": 0.0212,
1607
+ "step": 1860
1608
+ },
1609
+ {
1610
+ "epoch": 2.8357501658610555,
1611
+ "grad_norm": 0.374080628156662,
1612
+ "learning_rate": 4.695565182058113e-05,
1613
+ "loss": 0.0312,
1614
+ "step": 1870
1615
+ },
1616
+ {
1617
+ "epoch": 2.8509146052506873,
1618
+ "grad_norm": 0.36783552169799805,
1619
+ "learning_rate": 4.642703598273431e-05,
1620
+ "loss": 0.0249,
1621
+ "step": 1880
1622
+ },
1623
+ {
1624
+ "epoch": 2.8660790446403186,
1625
+ "grad_norm": 0.2705755829811096,
1626
+ "learning_rate": 4.589882126545352e-05,
1627
+ "loss": 0.0234,
1628
+ "step": 1890
1629
+ },
1630
+ {
1631
+ "epoch": 2.88124348402995,
1632
+ "grad_norm": 0.25217315554618835,
1633
+ "learning_rate": 4.537106696902425e-05,
1634
+ "loss": 0.0295,
1635
+ "step": 1900
1636
+ },
1637
+ {
1638
+ "epoch": 2.88124348402995,
1639
+ "eval_loss": 0.03719955310225487,
1640
+ "eval_runtime": 159.7214,
1641
+ "eval_samples_per_second": 7.344,
1642
+ "eval_steps_per_second": 7.344,
1643
+ "step": 1900
1644
+ },
1645
+ {
1646
+ "epoch": 2.896407923419581,
1647
+ "grad_norm": 0.40652021765708923,
1648
+ "learning_rate": 4.484383234204266e-05,
1649
+ "loss": 0.0224,
1650
+ "step": 1910
1651
+ },
1652
+ {
1653
+ "epoch": 2.9115723628092125,
1654
+ "grad_norm": 0.3361893892288208,
1655
+ "learning_rate": 4.4317176574763935e-05,
1656
+ "loss": 0.0247,
1657
+ "step": 1920
1658
+ },
1659
+ {
1660
+ "epoch": 2.926736802198844,
1661
+ "grad_norm": 0.35932040214538574,
1662
+ "learning_rate": 4.3791158792457334e-05,
1663
+ "loss": 0.024,
1664
+ "step": 1930
1665
+ },
1666
+ {
1667
+ "epoch": 2.941901241588475,
1668
+ "grad_norm": 0.15191532671451569,
1669
+ "learning_rate": 4.3265838048768334e-05,
1670
+ "loss": 0.0216,
1671
+ "step": 1940
1672
+ },
1673
+ {
1674
+ "epoch": 2.9570656809781064,
1675
+ "grad_norm": 0.5233368873596191,
1676
+ "learning_rate": 4.274127331908915e-05,
1677
+ "loss": 0.0227,
1678
+ "step": 1950
1679
+ },
1680
+ {
1681
+ "epoch": 2.9570656809781064,
1682
+ "eval_loss": 0.03795257583260536,
1683
+ "eval_runtime": 159.8645,
1684
+ "eval_samples_per_second": 7.337,
1685
+ "eval_steps_per_second": 7.337,
1686
+ "step": 1950
1687
+ },
1688
+ {
1689
+ "epoch": 2.9722301203677377,
1690
+ "grad_norm": 0.05902265012264252,
1691
+ "learning_rate": 4.221752349393758e-05,
1692
+ "loss": 0.0173,
1693
+ "step": 1960
1694
+ },
1695
+ {
1696
+ "epoch": 2.987394559757369,
1697
+ "grad_norm": 0.1508518010377884,
1698
+ "learning_rate": 4.1694647372345886e-05,
1699
+ "loss": 0.0249,
1700
+ "step": 1970
1701
+ },
1702
+ {
1703
+ "epoch": 3.0025589991470003,
1704
+ "grad_norm": 0.13050998747348785,
1705
+ "learning_rate": 4.117270365525946e-05,
1706
+ "loss": 0.0182,
1707
+ "step": 1980
1708
+ },
1709
+ {
1710
+ "epoch": 3.0177234385366316,
1711
+ "grad_norm": 0.06321557611227036,
1712
+ "learning_rate": 4.065175093894694e-05,
1713
+ "loss": 0.0132,
1714
+ "step": 1990
1715
+ },
1716
+ {
1717
+ "epoch": 3.032887877926263,
1718
+ "grad_norm": 0.155404731631279,
1719
+ "learning_rate": 4.013184770842167e-05,
1720
+ "loss": 0.0128,
1721
+ "step": 2000
1722
+ },
1723
+ {
1724
+ "epoch": 3.032887877926263,
1725
+ "eval_loss": 0.03980863094329834,
1726
+ "eval_runtime": 159.767,
1727
+ "eval_samples_per_second": 7.342,
1728
+ "eval_steps_per_second": 7.342,
1729
+ "step": 2000
1730
+ },
1731
+ {
1732
+ "epoch": 3.048052317315894,
1733
+ "grad_norm": 0.18662160634994507,
1734
+ "learning_rate": 3.9613052330876064e-05,
1735
+ "loss": 0.0166,
1736
+ "step": 2010
1737
+ },
1738
+ {
1739
+ "epoch": 3.0632167567055255,
1740
+ "grad_norm": 0.5268431901931763,
1741
+ "learning_rate": 3.909542304912881e-05,
1742
+ "loss": 0.0136,
1743
+ "step": 2020
1744
+ },
1745
+ {
1746
+ "epoch": 3.078381196095157,
1747
+ "grad_norm": 0.18333646655082703,
1748
+ "learning_rate": 3.857901797508628e-05,
1749
+ "loss": 0.0162,
1750
+ "step": 2030
1751
+ },
1752
+ {
1753
+ "epoch": 3.093545635484788,
1754
+ "grad_norm": 0.2035679817199707,
1755
+ "learning_rate": 3.80638950832186e-05,
1756
+ "loss": 0.0174,
1757
+ "step": 2040
1758
+ },
1759
+ {
1760
+ "epoch": 3.1087100748744194,
1761
+ "grad_norm": 0.200400710105896,
1762
+ "learning_rate": 3.7550112204051014e-05,
1763
+ "loss": 0.0096,
1764
+ "step": 2050
1765
+ },
1766
+ {
1767
+ "epoch": 3.1087100748744194,
1768
+ "eval_loss": 0.04321278631687164,
1769
+ "eval_runtime": 159.8384,
1770
+ "eval_samples_per_second": 7.339,
1771
+ "eval_steps_per_second": 7.339,
1772
+ "step": 2050
1773
+ },
1774
+ {
1775
+ "epoch": 3.1238745142640507,
1776
+ "grad_norm": 0.10098811984062195,
1777
+ "learning_rate": 3.703772701767167e-05,
1778
+ "loss": 0.0098,
1779
+ "step": 2060
1780
+ },
1781
+ {
1782
+ "epoch": 3.139038953653682,
1783
+ "grad_norm": 0.3599345088005066,
1784
+ "learning_rate": 3.652679704725596e-05,
1785
+ "loss": 0.0095,
1786
+ "step": 2070
1787
+ },
1788
+ {
1789
+ "epoch": 3.1542033930433133,
1790
+ "grad_norm": 0.17654354870319366,
1791
+ "learning_rate": 3.601737965260882e-05,
1792
+ "loss": 0.0111,
1793
+ "step": 2080
1794
+ },
1795
+ {
1796
+ "epoch": 3.1693678324329446,
1797
+ "grad_norm": 0.3085581660270691,
1798
+ "learning_rate": 3.550953202372503e-05,
1799
+ "loss": 0.0072,
1800
+ "step": 2090
1801
+ },
1802
+ {
1803
+ "epoch": 3.184532271822576,
1804
+ "grad_norm": 0.5332884192466736,
1805
+ "learning_rate": 3.500331117436895e-05,
1806
+ "loss": 0.0076,
1807
+ "step": 2100
1808
+ },
1809
+ {
1810
+ "epoch": 3.184532271822576,
1811
+ "eval_loss": 0.048784155398607254,
1812
+ "eval_runtime": 159.7604,
1813
+ "eval_samples_per_second": 7.342,
1814
+ "eval_steps_per_second": 7.342,
1815
+ "step": 2100
1816
+ },
1817
+ {
1818
+ "epoch": 3.1996967112122072,
1819
+ "grad_norm": 0.20715317130088806,
1820
+ "learning_rate": 3.4498773935673626e-05,
1821
+ "loss": 0.0089,
1822
+ "step": 2110
1823
+ },
1824
+ {
1825
+ "epoch": 3.2148611506018385,
1826
+ "grad_norm": 0.1660224199295044,
1827
+ "learning_rate": 3.399597694976081e-05,
1828
+ "loss": 0.0116,
1829
+ "step": 2120
1830
+ },
1831
+ {
1832
+ "epoch": 3.23002558999147,
1833
+ "grad_norm": 0.19592803716659546,
1834
+ "learning_rate": 3.349497666338187e-05,
1835
+ "loss": 0.0152,
1836
+ "step": 2130
1837
+ },
1838
+ {
1839
+ "epoch": 3.245190029381101,
1840
+ "grad_norm": 0.19497735798358917,
1841
+ "learning_rate": 3.299582932158085e-05,
1842
+ "loss": 0.0118,
1843
+ "step": 2140
1844
+ },
1845
+ {
1846
+ "epoch": 3.260354468770733,
1847
+ "grad_norm": 0.23641538619995117,
1848
+ "learning_rate": 3.2498590961379996e-05,
1849
+ "loss": 0.0122,
1850
+ "step": 2150
1851
+ },
1852
+ {
1853
+ "epoch": 3.260354468770733,
1854
+ "eval_loss": 0.04506111145019531,
1855
+ "eval_runtime": 159.8166,
1856
+ "eval_samples_per_second": 7.34,
1857
+ "eval_steps_per_second": 7.34,
1858
+ "step": 2150
1859
+ },
1860
+ {
1861
+ "epoch": 3.2755189081603637,
1862
+ "grad_norm": 0.037290170788764954,
1863
+ "learning_rate": 3.200331740548887e-05,
1864
+ "loss": 0.0105,
1865
+ "step": 2160
1866
+ },
1867
+ {
1868
+ "epoch": 3.2906833475499955,
1869
+ "grad_norm": 0.43852153420448303,
1870
+ "learning_rate": 3.1510064256037274e-05,
1871
+ "loss": 0.0136,
1872
+ "step": 2170
1873
+ },
1874
+ {
1875
+ "epoch": 3.3058477869396263,
1876
+ "grad_norm": 0.11988549679517746,
1877
+ "learning_rate": 3.1018886888333065e-05,
1878
+ "loss": 0.0089,
1879
+ "step": 2180
1880
+ },
1881
+ {
1882
+ "epoch": 3.321012226329258,
1883
+ "grad_norm": 0.32281386852264404,
1884
+ "learning_rate": 3.052984044464548e-05,
1885
+ "loss": 0.0159,
1886
+ "step": 2190
1887
+ },
1888
+ {
1889
+ "epoch": 3.3361766657188894,
1890
+ "grad_norm": 0.1835431307554245,
1891
+ "learning_rate": 3.0042979828014496e-05,
1892
+ "loss": 0.0101,
1893
+ "step": 2200
1894
+ },
1895
+ {
1896
+ "epoch": 3.3361766657188894,
1897
+ "eval_loss": 0.046676941215991974,
1898
+ "eval_runtime": 159.7855,
1899
+ "eval_samples_per_second": 7.341,
1900
+ "eval_steps_per_second": 7.341,
1901
+ "step": 2200
1902
+ },
1903
+ {
1904
+ "epoch": 3.3513411051085207,
1905
+ "grad_norm": 0.20971719920635223,
1906
+ "learning_rate": 2.9558359696087152e-05,
1907
+ "loss": 0.015,
1908
+ "step": 2210
1909
+ },
1910
+ {
1911
+ "epoch": 3.366505544498152,
1912
+ "grad_norm": 0.30802661180496216,
1913
+ "learning_rate": 2.9076034454981332e-05,
1914
+ "loss": 0.0143,
1915
+ "step": 2220
1916
+ },
1917
+ {
1918
+ "epoch": 3.3816699838877833,
1919
+ "grad_norm": 0.24673651158809662,
1920
+ "learning_rate": 2.8596058253177932e-05,
1921
+ "loss": 0.0124,
1922
+ "step": 2230
1923
+ },
1924
+ {
1925
+ "epoch": 3.3968344232774146,
1926
+ "grad_norm": 0.09349372982978821,
1927
+ "learning_rate": 2.811848497544175e-05,
1928
+ "loss": 0.013,
1929
+ "step": 2240
1930
+ },
1931
+ {
1932
+ "epoch": 3.411998862667046,
1933
+ "grad_norm": 0.14247673749923706,
1934
+ "learning_rate": 2.764336823677216e-05,
1935
+ "loss": 0.0124,
1936
+ "step": 2250
1937
+ },
1938
+ {
1939
+ "epoch": 3.411998862667046,
1940
+ "eval_loss": 0.04635697975754738,
1941
+ "eval_runtime": 159.7764,
1942
+ "eval_samples_per_second": 7.342,
1943
+ "eval_steps_per_second": 7.342,
1944
+ "step": 2250
1945
+ },
1946
+ {
1947
+ "epoch": 3.427163302056677,
1948
+ "grad_norm": 0.2467641681432724,
1949
+ "learning_rate": 2.717076137638388e-05,
1950
+ "loss": 0.0096,
1951
+ "step": 2260
1952
+ },
1953
+ {
1954
+ "epoch": 3.4423277414463085,
1955
+ "grad_norm": 0.32236963510513306,
1956
+ "learning_rate": 2.6700717451719066e-05,
1957
+ "loss": 0.0153,
1958
+ "step": 2270
1959
+ },
1960
+ {
1961
+ "epoch": 3.45749218083594,
1962
+ "grad_norm": 0.33867254853248596,
1963
+ "learning_rate": 2.6233289232490447e-05,
1964
+ "loss": 0.0156,
1965
+ "step": 2280
1966
+ },
1967
+ {
1968
+ "epoch": 3.472656620225571,
1969
+ "grad_norm": 0.17547796666622162,
1970
+ "learning_rate": 2.5768529194757474e-05,
1971
+ "loss": 0.0071,
1972
+ "step": 2290
1973
+ },
1974
+ {
1975
+ "epoch": 3.4878210596152024,
1976
+ "grad_norm": 0.22590090334415436,
1977
+ "learning_rate": 2.5306489515034713e-05,
1978
+ "loss": 0.0113,
1979
+ "step": 2300
1980
+ },
1981
+ {
1982
+ "epoch": 3.4878210596152024,
1983
+ "eval_loss": 0.047961652278900146,
1984
+ "eval_runtime": 159.815,
1985
+ "eval_samples_per_second": 7.34,
1986
+ "eval_steps_per_second": 7.34,
1987
+ "step": 2300
1988
+ },
1989
+ {
1990
+ "epoch": 3.5029854990048337,
1991
+ "grad_norm": 0.1563863903284073,
1992
+ "learning_rate": 2.484722206443455e-05,
1993
+ "loss": 0.017,
1994
+ "step": 2310
1995
+ },
1996
+ {
1997
+ "epoch": 3.518149938394465,
1998
+ "grad_norm": 0.09933234751224518,
1999
+ "learning_rate": 2.4390778402843605e-05,
2000
+ "loss": 0.0129,
2001
+ "step": 2320
2002
+ },
2003
+ {
2004
+ "epoch": 3.5333143777840963,
2005
+ "grad_norm": 0.2538220286369324,
2006
+ "learning_rate": 2.3937209773134472e-05,
2007
+ "loss": 0.0094,
2008
+ "step": 2330
2009
+ },
2010
+ {
2011
+ "epoch": 3.5484788171737276,
2012
+ "grad_norm": 0.32708045840263367,
2013
+ "learning_rate": 2.3486567095412864e-05,
2014
+ "loss": 0.0098,
2015
+ "step": 2340
2016
+ },
2017
+ {
2018
+ "epoch": 3.563643256563359,
2019
+ "grad_norm": 0.3891366720199585,
2020
+ "learning_rate": 2.3038900961301053e-05,
2021
+ "loss": 0.0126,
2022
+ "step": 2350
2023
+ },
2024
+ {
2025
+ "epoch": 3.563643256563359,
2026
+ "eval_loss": 0.047991689294576645,
2027
+ "eval_runtime": 159.8161,
2028
+ "eval_samples_per_second": 7.34,
2029
+ "eval_steps_per_second": 7.34,
2030
+ "step": 2350
2031
+ },
2032
+ {
2033
+ "epoch": 3.57880769595299,
2034
+ "grad_norm": 0.06344733387231827,
2035
+ "learning_rate": 2.259426162825819e-05,
2036
+ "loss": 0.0099,
2037
+ "step": 2360
2038
+ },
2039
+ {
2040
+ "epoch": 3.5939721353426215,
2041
+ "grad_norm": 0.5568035244941711,
2042
+ "learning_rate": 2.215269901393805e-05,
2043
+ "loss": 0.0164,
2044
+ "step": 2370
2045
+ },
2046
+ {
2047
+ "epoch": 3.609136574732253,
2048
+ "grad_norm": 0.06175050139427185,
2049
+ "learning_rate": 2.1714262690585192e-05,
2050
+ "loss": 0.0094,
2051
+ "step": 2380
2052
+ },
2053
+ {
2054
+ "epoch": 3.624301014121884,
2055
+ "grad_norm": 0.6271355152130127,
2056
+ "learning_rate": 2.1279001879469424e-05,
2057
+ "loss": 0.0126,
2058
+ "step": 2390
2059
+ },
2060
+ {
2061
+ "epoch": 3.6394654535115154,
2062
+ "grad_norm": 0.14509186148643494,
2063
+ "learning_rate": 2.084696544536025e-05,
2064
+ "loss": 0.0114,
2065
+ "step": 2400
2066
+ },
2067
+ {
2068
+ "epoch": 3.6394654535115154,
2069
+ "eval_loss": 0.04358929395675659,
2070
+ "eval_runtime": 159.7768,
2071
+ "eval_samples_per_second": 7.341,
2072
+ "eval_steps_per_second": 7.341,
2073
+ "step": 2400
2074
+ },
2075
+ {
2076
+ "epoch": 3.6546298929011467,
2077
+ "grad_norm": 0.04602226987481117,
2078
+ "learning_rate": 2.0418201891040778e-05,
2079
+ "loss": 0.0102,
2080
+ "step": 2410
2081
+ },
2082
+ {
2083
+ "epoch": 3.669794332290778,
2084
+ "grad_norm": 0.4110815227031708,
2085
+ "learning_rate": 1.9992759351862772e-05,
2086
+ "loss": 0.0201,
2087
+ "step": 2420
2088
+ },
2089
+ {
2090
+ "epoch": 3.6849587716804093,
2091
+ "grad_norm": 0.3334294557571411,
2092
+ "learning_rate": 1.9570685590342463e-05,
2093
+ "loss": 0.0098,
2094
+ "step": 2430
2095
+ },
2096
+ {
2097
+ "epoch": 3.7001232110700406,
2098
+ "grad_norm": 0.19647225737571716,
2099
+ "learning_rate": 1.9152027990798748e-05,
2100
+ "loss": 0.0109,
2101
+ "step": 2440
2102
+ },
2103
+ {
2104
+ "epoch": 3.715287650459672,
2105
+ "grad_norm": 0.06987540423870087,
2106
+ "learning_rate": 1.8736833554033263e-05,
2107
+ "loss": 0.0071,
2108
+ "step": 2450
2109
+ },
2110
+ {
2111
+ "epoch": 3.715287650459672,
2112
+ "eval_loss": 0.047177620232105255,
2113
+ "eval_runtime": 159.8168,
2114
+ "eval_samples_per_second": 7.34,
2115
+ "eval_steps_per_second": 7.34,
2116
+ "step": 2450
2117
+ },
2118
+ {
2119
+ "epoch": 3.7304520898493037,
2120
+ "grad_norm": 0.3399925231933594,
2121
+ "learning_rate": 1.8325148892054093e-05,
2122
+ "loss": 0.0125,
2123
+ "step": 2460
2124
+ },
2125
+ {
2126
+ "epoch": 3.7456165292389345,
2127
+ "grad_norm": 0.1921069622039795,
2128
+ "learning_rate": 1.7917020222842662e-05,
2129
+ "loss": 0.0089,
2130
+ "step": 2470
2131
+ },
2132
+ {
2133
+ "epoch": 3.7607809686285663,
2134
+ "grad_norm": 0.10305212438106537,
2135
+ "learning_rate": 1.751249336516513e-05,
2136
+ "loss": 0.0106,
2137
+ "step": 2480
2138
+ },
2139
+ {
2140
+ "epoch": 3.775945408018197,
2141
+ "grad_norm": 0.07067303359508514,
2142
+ "learning_rate": 1.7111613733428522e-05,
2143
+ "loss": 0.0125,
2144
+ "step": 2490
2145
+ },
2146
+ {
2147
+ "epoch": 3.791109847407829,
2148
+ "grad_norm": 0.1127607673406601,
2149
+ "learning_rate": 1.671442633258218e-05,
2150
+ "loss": 0.0117,
2151
+ "step": 2500
2152
+ },
2153
+ {
2154
+ "epoch": 3.791109847407829,
2155
+ "eval_loss": 0.04904229938983917,
2156
+ "eval_runtime": 159.7619,
2157
+ "eval_samples_per_second": 7.342,
2158
+ "eval_steps_per_second": 7.342,
2159
+ "step": 2500
2160
+ },
2161
+ {
2162
+ "epoch": 3.8062742867974597,
2163
+ "grad_norm": 0.47790926694869995,
2164
+ "learning_rate": 1.6320975753065453e-05,
2165
+ "loss": 0.0095,
2166
+ "step": 2510
2167
+ },
2168
+ {
2169
+ "epoch": 3.8214387261870915,
2170
+ "grad_norm": 0.6272779703140259,
2171
+ "learning_rate": 1.5931306165801452e-05,
2172
+ "loss": 0.01,
2173
+ "step": 2520
2174
+ },
2175
+ {
2176
+ "epoch": 3.8366031655767223,
2177
+ "grad_norm": 0.11979278177022934,
2178
+ "learning_rate": 1.554546131723848e-05,
2179
+ "loss": 0.0112,
2180
+ "step": 2530
2181
+ },
2182
+ {
2183
+ "epoch": 3.851767604966354,
2184
+ "grad_norm": 0.4187261760234833,
2185
+ "learning_rate": 1.5163484524438516e-05,
2186
+ "loss": 0.0075,
2187
+ "step": 2540
2188
+ },
2189
+ {
2190
+ "epoch": 3.8669320443559854,
2191
+ "grad_norm": 0.5277063846588135,
2192
+ "learning_rate": 1.4785418670214496e-05,
2193
+ "loss": 0.0145,
2194
+ "step": 2550
2195
+ },
2196
+ {
2197
+ "epoch": 3.8669320443559854,
2198
+ "eval_loss": 0.047451041638851166,
2199
+ "eval_runtime": 159.8306,
2200
+ "eval_samples_per_second": 7.339,
2201
+ "eval_steps_per_second": 7.339,
2202
+ "step": 2550
2203
+ },
2204
+ {
2205
+ "epoch": 3.8820964837456167,
2206
+ "grad_norm": 0.4268508553504944,
2207
+ "learning_rate": 1.4411306198315777e-05,
2208
+ "loss": 0.0123,
2209
+ "step": 2560
2210
+ },
2211
+ {
2212
+ "epoch": 3.897260923135248,
2213
+ "grad_norm": 0.10897725075483322,
2214
+ "learning_rate": 1.4041189108663421e-05,
2215
+ "loss": 0.008,
2216
+ "step": 2570
2217
+ },
2218
+ {
2219
+ "epoch": 3.9124253625248793,
2220
+ "grad_norm": 0.24288566410541534,
2221
+ "learning_rate": 1.3675108952634824e-05,
2222
+ "loss": 0.007,
2223
+ "step": 2580
2224
+ },
2225
+ {
2226
+ "epoch": 3.9275898019145106,
2227
+ "grad_norm": 0.3925674259662628,
2228
+ "learning_rate": 1.3313106828399147e-05,
2229
+ "loss": 0.0147,
2230
+ "step": 2590
2231
+ },
2232
+ {
2233
+ "epoch": 3.942754241304142,
2234
+ "grad_norm": 0.07586287707090378,
2235
+ "learning_rate": 1.2955223376303205e-05,
2236
+ "loss": 0.008,
2237
+ "step": 2600
2238
+ },
2239
+ {
2240
+ "epoch": 3.942754241304142,
2241
+ "eval_loss": 0.04594454541802406,
2242
+ "eval_runtime": 159.8774,
2243
+ "eval_samples_per_second": 7.337,
2244
+ "eval_steps_per_second": 7.337,
2245
+ "step": 2600
2246
+ },
2247
+ {
2248
+ "epoch": 3.957918680693773,
2249
+ "grad_norm": 0.19912473857402802,
2250
+ "learning_rate": 1.2601498774309112e-05,
2251
+ "loss": 0.0104,
2252
+ "step": 2610
2253
+ },
2254
+ {
2255
+ "epoch": 3.9730831200834045,
2256
+ "grad_norm": 0.40546008944511414,
2257
+ "learning_rate": 1.2251972733483612e-05,
2258
+ "loss": 0.0117,
2259
+ "step": 2620
2260
+ },
2261
+ {
2262
+ "epoch": 3.9882475594730358,
2263
+ "grad_norm": 0.6201793551445007,
2264
+ "learning_rate": 1.19066844935399e-05,
2265
+ "loss": 0.0106,
2266
+ "step": 2630
2267
+ },
2268
+ {
2269
+ "epoch": 4.003411998862667,
2270
+ "grad_norm": 0.12441912293434143,
2271
+ "learning_rate": 1.156567281843241e-05,
2272
+ "loss": 0.0095,
2273
+ "step": 2640
2274
+ },
2275
+ {
2276
+ "epoch": 4.018576438252298,
2277
+ "grad_norm": 0.24595439434051514,
2278
+ "learning_rate": 1.1228975992004842e-05,
2279
+ "loss": 0.0044,
2280
+ "step": 2650
2281
+ },
2282
+ {
2283
+ "epoch": 4.018576438252298,
2284
+ "eval_loss": 0.048001233488321304,
2285
+ "eval_runtime": 159.8103,
2286
+ "eval_samples_per_second": 7.34,
2287
+ "eval_steps_per_second": 7.34,
2288
+ "step": 2650
2289
+ },
2290
+ {
2291
+ "epoch": 4.03374087764193,
2292
+ "grad_norm": 0.33981209993362427,
2293
+ "learning_rate": 1.0896631813692377e-05,
2294
+ "loss": 0.0076,
2295
+ "step": 2660
2296
+ },
2297
+ {
2298
+ "epoch": 4.048905317031561,
2299
+ "grad_norm": 0.2191678285598755,
2300
+ "learning_rate": 1.0568677594277899e-05,
2301
+ "loss": 0.0043,
2302
+ "step": 2670
2303
+ },
2304
+ {
2305
+ "epoch": 4.064069756421192,
2306
+ "grad_norm": 0.06934363394975662,
2307
+ "learning_rate": 1.0245150151703509e-05,
2308
+ "loss": 0.003,
2309
+ "step": 2680
2310
+ },
2311
+ {
2312
+ "epoch": 4.079234195810824,
2313
+ "grad_norm": 0.19347621500492096,
2314
+ "learning_rate": 9.926085806936918e-06,
2315
+ "loss": 0.0057,
2316
+ "step": 2690
2317
+ },
2318
+ {
2319
+ "epoch": 4.094398635200455,
2320
+ "grad_norm": 0.28373149037361145,
2321
+ "learning_rate": 9.611520379894068e-06,
2322
+ "loss": 0.0061,
2323
+ "step": 2700
2324
+ },
2325
+ {
2326
+ "epoch": 4.094398635200455,
2327
+ "eval_loss": 0.05424731224775314,
2328
+ "eval_runtime": 159.7665,
2329
+ "eval_samples_per_second": 7.342,
2330
+ "eval_steps_per_second": 7.342,
2331
+ "step": 2700
2332
+ },
2333
+ {
2334
+ "epoch": 4.109563074590087,
2335
+ "grad_norm": 0.10718700289726257,
2336
+ "learning_rate": 9.301489185417578e-06,
2337
+ "loss": 0.0043,
2338
+ "step": 2710
2339
+ },
2340
+ {
2341
+ "epoch": 4.1247275139797175,
2342
+ "grad_norm": 0.06889745593070984,
2343
+ "learning_rate": 8.996027029312314e-06,
2344
+ "loss": 0.0038,
2345
+ "step": 2720
2346
+ },
2347
+ {
2348
+ "epoch": 4.139891953369349,
2349
+ "grad_norm": 0.4347403645515442,
2350
+ "learning_rate": 8.695168204437721e-06,
2351
+ "loss": 0.0102,
2352
+ "step": 2730
2353
+ },
2354
+ {
2355
+ "epoch": 4.15505639275898,
2356
+ "grad_norm": 1.3129316568374634,
2357
+ "learning_rate": 8.398946486858029e-06,
2358
+ "loss": 0.0066,
2359
+ "step": 2740
2360
+ },
2361
+ {
2362
+ "epoch": 4.170220832148612,
2363
+ "grad_norm": 0.044139549136161804,
2364
+ "learning_rate": 8.107395132050333e-06,
2365
+ "loss": 0.0048,
2366
+ "step": 2750
2367
+ },
2368
+ {
2369
+ "epoch": 4.170220832148612,
2370
+ "eval_loss": 0.05559329688549042,
2371
+ "eval_runtime": 159.8213,
2372
+ "eval_samples_per_second": 7.339,
2373
+ "eval_steps_per_second": 7.339,
2374
+ "step": 2750
2375
+ },
2376
+ {
2377
+ "epoch": 4.185385271538243,
2378
+ "grad_norm": 0.0535513274371624,
2379
+ "learning_rate": 7.820546871171142e-06,
2380
+ "loss": 0.0067,
2381
+ "step": 2760
2382
+ },
2383
+ {
2384
+ "epoch": 4.200549710927874,
2385
+ "grad_norm": 0.37897995114326477,
2386
+ "learning_rate": 7.5384339073818145e-06,
2387
+ "loss": 0.0052,
2388
+ "step": 2770
2389
+ },
2390
+ {
2391
+ "epoch": 4.215714150317505,
2392
+ "grad_norm": 0.18212661147117615,
2393
+ "learning_rate": 7.261087912233228e-06,
2394
+ "loss": 0.0057,
2395
+ "step": 2780
2396
+ },
2397
+ {
2398
+ "epoch": 4.230878589707137,
2399
+ "grad_norm": 0.09377432614564896,
2400
+ "learning_rate": 6.988540022110235e-06,
2401
+ "loss": 0.0062,
2402
+ "step": 2790
2403
+ },
2404
+ {
2405
+ "epoch": 4.246043029096768,
2406
+ "grad_norm": 0.1912451833486557,
2407
+ "learning_rate": 6.720820834735969e-06,
2408
+ "loss": 0.0043,
2409
+ "step": 2800
2410
+ },
2411
+ {
2412
+ "epoch": 4.246043029096768,
2413
+ "eval_loss": 0.05572189763188362,
2414
+ "eval_runtime": 159.8918,
2415
+ "eval_samples_per_second": 7.336,
2416
+ "eval_steps_per_second": 7.336,
2417
+ "step": 2800
2418
+ },
2419
+ {
2420
+ "epoch": 4.2612074684864,
2421
+ "grad_norm": 0.32161590456962585,
2422
+ "learning_rate": 6.457960405736968e-06,
2423
+ "loss": 0.0077,
2424
+ "step": 2810
2425
+ },
2426
+ {
2427
+ "epoch": 4.2763719078760305,
2428
+ "grad_norm": 0.07208878546953201,
2429
+ "learning_rate": 6.199988245268778e-06,
2430
+ "loss": 0.0043,
2431
+ "step": 2820
2432
+ },
2433
+ {
2434
+ "epoch": 4.291536347265662,
2435
+ "grad_norm": 0.09758219122886658,
2436
+ "learning_rate": 5.946933314703157e-06,
2437
+ "loss": 0.003,
2438
+ "step": 2830
2439
+ },
2440
+ {
2441
+ "epoch": 4.306700786655293,
2442
+ "grad_norm": 0.22281204164028168,
2443
+ "learning_rate": 5.698824023376531e-06,
2444
+ "loss": 0.0051,
2445
+ "step": 2840
2446
+ },
2447
+ {
2448
+ "epoch": 4.321865226044925,
2449
+ "grad_norm": 0.4457966983318329,
2450
+ "learning_rate": 5.455688225400802e-06,
2451
+ "loss": 0.0049,
2452
+ "step": 2850
2453
+ },
2454
+ {
2455
+ "epoch": 4.321865226044925,
2456
+ "eval_loss": 0.05698266625404358,
2457
+ "eval_runtime": 159.8196,
2458
+ "eval_samples_per_second": 7.34,
2459
+ "eval_steps_per_second": 7.34,
2460
+ "step": 2850
2461
+ },
2462
+ {
2463
+ "epoch": 4.337029665434556,
2464
+ "grad_norm": 0.22873935103416443,
2465
+ "learning_rate": 5.217553216536098e-06,
2466
+ "loss": 0.0069,
2467
+ "step": 2860
2468
+ },
2469
+ {
2470
+ "epoch": 4.3521941048241874,
2471
+ "grad_norm": 0.13292750716209412,
2472
+ "learning_rate": 4.984445731126542e-06,
2473
+ "loss": 0.0059,
2474
+ "step": 2870
2475
+ },
2476
+ {
2477
+ "epoch": 4.367358544213818,
2478
+ "grad_norm": 0.021369215101003647,
2479
+ "learning_rate": 4.756391939098853e-06,
2480
+ "loss": 0.0036,
2481
+ "step": 2880
2482
+ },
2483
+ {
2484
+ "epoch": 4.38252298360345,
2485
+ "grad_norm": 0.06876254081726074,
2486
+ "learning_rate": 4.533417443024374e-06,
2487
+ "loss": 0.0077,
2488
+ "step": 2890
2489
+ },
2490
+ {
2491
+ "epoch": 4.397687422993081,
2492
+ "grad_norm": 0.1053222119808197,
2493
+ "learning_rate": 4.315547275244769e-06,
2494
+ "loss": 0.0019,
2495
+ "step": 2900
2496
+ },
2497
+ {
2498
+ "epoch": 4.397687422993081,
2499
+ "eval_loss": 0.05874261260032654,
2500
+ "eval_runtime": 159.7069,
2501
+ "eval_samples_per_second": 7.345,
2502
+ "eval_steps_per_second": 7.345,
2503
+ "step": 2900
2504
+ },
2505
+ {
2506
+ "epoch": 4.412851862382713,
2507
+ "grad_norm": 2.4315688610076904,
2508
+ "learning_rate": 4.10280589506179e-06,
2509
+ "loss": 0.0069,
2510
+ "step": 2910
2511
+ },
2512
+ {
2513
+ "epoch": 4.4280163017723435,
2514
+ "grad_norm": 0.21709750592708588,
2515
+ "learning_rate": 3.895217185991312e-06,
2516
+ "loss": 0.0039,
2517
+ "step": 2920
2518
+ },
2519
+ {
2520
+ "epoch": 4.443180741161975,
2521
+ "grad_norm": 0.3738054037094116,
2522
+ "learning_rate": 3.692804453082038e-06,
2523
+ "loss": 0.0046,
2524
+ "step": 2930
2525
+ },
2526
+ {
2527
+ "epoch": 4.458345180551606,
2528
+ "grad_norm": 0.07227662950754166,
2529
+ "learning_rate": 3.495590420299194e-06,
2530
+ "loss": 0.0051,
2531
+ "step": 2940
2532
+ },
2533
+ {
2534
+ "epoch": 4.473509619941238,
2535
+ "grad_norm": 0.25434616208076477,
2536
+ "learning_rate": 3.3035972279733207e-06,
2537
+ "loss": 0.0053,
2538
+ "step": 2950
2539
+ },
2540
+ {
2541
+ "epoch": 4.473509619941238,
2542
+ "eval_loss": 0.05949469655752182,
2543
+ "eval_runtime": 159.7116,
2544
+ "eval_samples_per_second": 7.344,
2545
+ "eval_steps_per_second": 7.344,
2546
+ "step": 2950
2547
+ },
2548
+ {
2549
+ "epoch": 4.488674059330869,
2550
+ "grad_norm": 0.5970948934555054,
2551
+ "learning_rate": 3.116846430314796e-06,
2552
+ "loss": 0.0053,
2553
+ "step": 2960
2554
+ },
2555
+ {
2556
+ "epoch": 4.5038384987205005,
2557
+ "grad_norm": 0.07033645361661911,
2558
+ "learning_rate": 2.9353589929939087e-06,
2559
+ "loss": 0.0025,
2560
+ "step": 2970
2561
+ },
2562
+ {
2563
+ "epoch": 4.519002938110132,
2564
+ "grad_norm": 0.0930805653333664,
2565
+ "learning_rate": 2.7591552907872574e-06,
2566
+ "loss": 0.0043,
2567
+ "step": 2980
2568
+ },
2569
+ {
2570
+ "epoch": 4.534167377499763,
2571
+ "grad_norm": 0.10770905762910843,
2572
+ "learning_rate": 2.5882551052902883e-06,
2573
+ "loss": 0.0049,
2574
+ "step": 2990
2575
+ },
2576
+ {
2577
+ "epoch": 4.549331816889394,
2578
+ "grad_norm": 0.7434157133102417,
2579
+ "learning_rate": 2.4226776226965453e-06,
2580
+ "loss": 0.0072,
2581
+ "step": 3000
2582
+ },
2583
+ {
2584
+ "epoch": 4.549331816889394,
2585
+ "eval_loss": 0.05965949594974518,
2586
+ "eval_runtime": 159.644,
2587
+ "eval_samples_per_second": 7.348,
2588
+ "eval_steps_per_second": 7.348,
2589
+ "step": 3000
2590
+ },
2591
+ {
2592
+ "epoch": 4.564496256279026,
2593
+ "grad_norm": 0.01642761193215847,
2594
+ "learning_rate": 2.262441431643697e-06,
2595
+ "loss": 0.0062,
2596
+ "step": 3010
2597
+ },
2598
+ {
2599
+ "epoch": 4.579660695668657,
2600
+ "grad_norm": 0.06564271450042725,
2601
+ "learning_rate": 2.1075645211266927e-06,
2602
+ "loss": 0.0017,
2603
+ "step": 3020
2604
+ },
2605
+ {
2606
+ "epoch": 4.594825135058288,
2607
+ "grad_norm": 0.38251250982284546,
2608
+ "learning_rate": 1.9580642784782053e-06,
2609
+ "loss": 0.0046,
2610
+ "step": 3030
2611
+ },
2612
+ {
2613
+ "epoch": 4.60998957444792,
2614
+ "grad_norm": 0.10563746094703674,
2615
+ "learning_rate": 1.813957487416651e-06,
2616
+ "loss": 0.0023,
2617
+ "step": 3040
2618
+ },
2619
+ {
2620
+ "epoch": 4.625154013837551,
2621
+ "grad_norm": 0.1952509880065918,
2622
+ "learning_rate": 1.6752603261619315e-06,
2623
+ "loss": 0.0047,
2624
+ "step": 3050
2625
+ },
2626
+ {
2627
+ "epoch": 4.625154013837551,
2628
+ "eval_loss": 0.05990082770586014,
2629
+ "eval_runtime": 159.6308,
2630
+ "eval_samples_per_second": 7.348,
2631
+ "eval_steps_per_second": 7.348,
2632
+ "step": 3050
2633
+ },
2634
+ {
2635
+ "epoch": 4.640318453227183,
2636
+ "grad_norm": 0.2965155243873596,
2637
+ "learning_rate": 1.541988365619207e-06,
2638
+ "loss": 0.0044,
2639
+ "step": 3060
2640
+ },
2641
+ {
2642
+ "epoch": 4.6554828926168135,
2643
+ "grad_norm": 0.28507962822914124,
2644
+ "learning_rate": 1.4141565676307865e-06,
2645
+ "loss": 0.0052,
2646
+ "step": 3070
2647
+ },
2648
+ {
2649
+ "epoch": 4.670647332006445,
2650
+ "grad_norm": 0.09388308972120285,
2651
+ "learning_rate": 1.291779283296468e-06,
2652
+ "loss": 0.0029,
2653
+ "step": 3080
2654
+ },
2655
+ {
2656
+ "epoch": 4.685811771396076,
2657
+ "grad_norm": 0.3553768992424011,
2658
+ "learning_rate": 1.1748702513623922e-06,
2659
+ "loss": 0.0064,
2660
+ "step": 3090
2661
+ },
2662
+ {
2663
+ "epoch": 4.700976210785708,
2664
+ "grad_norm": 0.01811501383781433,
2665
+ "learning_rate": 1.0634425966786155e-06,
2666
+ "loss": 0.003,
2667
+ "step": 3100
2668
+ },
2669
+ {
2670
+ "epoch": 4.700976210785708,
2671
+ "eval_loss": 0.06024787947535515,
2672
+ "eval_runtime": 159.5976,
2673
+ "eval_samples_per_second": 7.35,
2674
+ "eval_steps_per_second": 7.35,
2675
+ "step": 3100
2676
+ },
2677
+ {
2678
+ "epoch": 4.716140650175339,
2679
+ "grad_norm": 0.17447508871555328,
2680
+ "learning_rate": 9.575088287257118e-07,
2681
+ "loss": 0.005,
2682
+ "step": 3110
2683
+ },
2684
+ {
2685
+ "epoch": 4.73130508956497,
2686
+ "grad_norm": 2.3331735134124756,
2687
+ "learning_rate": 8.570808402103392e-07,
2688
+ "loss": 0.0059,
2689
+ "step": 3120
2690
+ },
2691
+ {
2692
+ "epoch": 4.746469528954601,
2693
+ "grad_norm": 0.20535585284233093,
2694
+ "learning_rate": 7.62169905730109e-07,
2695
+ "loss": 0.0048,
2696
+ "step": 3130
2697
+ },
2698
+ {
2699
+ "epoch": 4.761633968344233,
2700
+ "grad_norm": 0.5628078579902649,
2701
+ "learning_rate": 6.727866805078531e-07,
2702
+ "loss": 0.0029,
2703
+ "step": 3140
2704
+ },
2705
+ {
2706
+ "epoch": 4.776798407733864,
2707
+ "grad_norm": 0.09494868665933609,
2708
+ "learning_rate": 5.889411991953975e-07,
2709
+ "loss": 0.0025,
2710
+ "step": 3150
2711
+ },
2712
+ {
2713
+ "epoch": 4.776798407733864,
2714
+ "eval_loss": 0.06030402332544327,
2715
+ "eval_runtime": 159.5412,
2716
+ "eval_samples_per_second": 7.352,
2717
+ "eval_steps_per_second": 7.352,
2718
+ "step": 3150
2719
+ },
2720
+ {
2721
+ "epoch": 4.791962847123496,
2722
+ "grad_norm": 0.21833842992782593,
2723
+ "learning_rate": 5.106428747470137e-07,
2724
+ "loss": 0.0033,
2725
+ "step": 3160
2726
+ },
2727
+ {
2728
+ "epoch": 4.8071272865131265,
2729
+ "grad_norm": 0.24270612001419067,
2730
+ "learning_rate": 4.37900497362681e-07,
2731
+ "loss": 0.0061,
2732
+ "step": 3170
2733
+ },
2734
+ {
2735
+ "epoch": 4.822291725902758,
2736
+ "grad_norm": 0.10475039482116699,
2737
+ "learning_rate": 3.7072223350124167e-07,
2738
+ "loss": 0.0028,
2739
+ "step": 3180
2740
+ },
2741
+ {
2742
+ "epoch": 4.837456165292389,
2743
+ "grad_norm": 0.19077710807323456,
2744
+ "learning_rate": 3.0911562496358517e-07,
2745
+ "loss": 0.0062,
2746
+ "step": 3190
2747
+ },
2748
+ {
2749
+ "epoch": 4.852620604682021,
2750
+ "grad_norm": 0.36398255825042725,
2751
+ "learning_rate": 2.53087588045986e-07,
2752
+ "loss": 0.0027,
2753
+ "step": 3200
2754
+ },
2755
+ {
2756
+ "epoch": 4.852620604682021,
2757
+ "eval_loss": 0.06035413593053818,
2758
+ "eval_runtime": 159.4969,
2759
+ "eval_samples_per_second": 7.354,
2760
+ "eval_steps_per_second": 7.354,
2761
+ "step": 3200
2762
+ },
2763
+ {
2764
+ "epoch": 4.867785044071652,
2765
+ "grad_norm": 0.1687215268611908,
2766
+ "learning_rate": 2.026444127636029e-07,
2767
+ "loss": 0.0034,
2768
+ "step": 3210
2769
+ },
2770
+ {
2771
+ "epoch": 4.882949483461283,
2772
+ "grad_norm": 0.03258746862411499,
2773
+ "learning_rate": 1.577917621443825e-07,
2774
+ "loss": 0.0051,
2775
+ "step": 3220
2776
+ },
2777
+ {
2778
+ "epoch": 4.898113922850914,
2779
+ "grad_norm": 0.1656346619129181,
2780
+ "learning_rate": 1.185346715932345e-07,
2781
+ "loss": 0.0083,
2782
+ "step": 3230
2783
+ },
2784
+ {
2785
+ "epoch": 4.913278362240546,
2786
+ "grad_norm": 0.45706111192703247,
2787
+ "learning_rate": 8.48775483267783e-08,
2788
+ "loss": 0.0055,
2789
+ "step": 3240
2790
+ },
2791
+ {
2792
+ "epoch": 4.928442801630177,
2793
+ "grad_norm": 0.07887681573629379,
2794
+ "learning_rate": 5.6824170878544414e-08,
2795
+ "loss": 0.0022,
2796
+ "step": 3250
2797
+ },
2798
+ {
2799
+ "epoch": 4.928442801630177,
2800
+ "eval_loss": 0.060390591621398926,
2801
+ "eval_runtime": 159.4858,
2802
+ "eval_samples_per_second": 7.355,
2803
+ "eval_steps_per_second": 7.355,
2804
+ "step": 3250
2805
+ },
2806
+ {
2807
+ "epoch": 4.943607241019809,
2808
+ "grad_norm": 0.4127300977706909,
2809
+ "learning_rate": 3.4377688674774866e-08,
2810
+ "loss": 0.0053,
2811
+ "step": 3260
2812
+ },
2813
+ {
2814
+ "epoch": 4.9587716804094395,
2815
+ "grad_norm": 0.03591546416282654,
2816
+ "learning_rate": 1.7540621680850466e-08,
2817
+ "loss": 0.0029,
2818
+ "step": 3270
2819
+ },
2820
+ {
2821
+ "epoch": 4.973936119799071,
2822
+ "grad_norm": 0.06558314710855484,
2823
+ "learning_rate": 6.314860118400434e-09,
2824
+ "loss": 0.0064,
2825
+ "step": 3280
2826
+ },
2827
+ {
2828
+ "epoch": 4.989100559188703,
2829
+ "grad_norm": 0.06449679285287857,
2830
+ "learning_rate": 7.016642530777162e-10,
2831
+ "loss": 0.0032,
2832
+ "step": 3290
2833
+ },
2834
+ {
2835
+ "epoch": 4.996682778883518,
2836
+ "step": 3295,
2837
+ "total_flos": 8.269502901505229e+17,
2838
+ "train_loss": 0.04518177697310657,
2839
+ "train_runtime": 36119.4942,
2840
+ "train_samples_per_second": 1.461,
2841
+ "train_steps_per_second": 0.091
2842
+ }
2843
+ ],
2844
+ "logging_steps": 10,
2845
+ "max_steps": 3295,
2846
+ "num_input_tokens_seen": 0,
2847
+ "num_train_epochs": 5,
2848
+ "save_steps": 50,
2849
+ "stateful_callbacks": {
2850
+ "TrainerControl": {
2851
+ "args": {
2852
+ "should_epoch_stop": false,
2853
+ "should_evaluate": false,
2854
+ "should_log": false,
2855
+ "should_save": true,
2856
+ "should_training_stop": true
2857
+ },
2858
+ "attributes": {}
2859
+ }
2860
+ },
2861
+ "total_flos": 8.269502901505229e+17,
2862
+ "train_batch_size": 1,
2863
+ "trial_name": null,
2864
+ "trial_params": null
2865
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold8/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d30032dcce2ecb3fb1beac38c4eab9fd77919717b940d3de1b61bf5c192772d
3
+ size 5624
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold8/training_eval_loss.png ADDED
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold8/training_loss.png ADDED