jjee2 commited on
Commit
3d059f6
·
verified ·
1 Parent(s): d2bd543

Add chchen__Llama-3.1-8B-Instruct-PsyCourse-fold1

Browse files
.gitattributes CHANGED
@@ -109,3 +109,4 @@ chchen__Llama-3.1-8B-Instruct-PsyCourse-doc-fold7/tokenizer.json filter=lfs diff
109
  thalllsssss__afd78bcf-de36-409a-b378-aa3f9a29400b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
110
  myhaaaaaaa__35fcd68c-7b33-4397-ba35-6942de06b574/tokenizer.json filter=lfs diff=lfs merge=lfs -text
111
  datlaaaaaaa__cf707148-8a14-4b17-af50-c0c419a06bb2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
109
  thalllsssss__afd78bcf-de36-409a-b378-aa3f9a29400b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
110
  myhaaaaaaa__35fcd68c-7b33-4397-ba35-6942de06b574/tokenizer.json filter=lfs diff=lfs merge=lfs -text
111
  datlaaaaaaa__cf707148-8a14-4b17-af50-c0c419a06bb2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
112
+ chchen__Llama-3.1-8B-Instruct-PsyCourse-fold1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold1/.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-fold1/README.md ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-fold1
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-fold1
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-fold1 dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.0338
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
+ | 0.5562 | 0.0770 | 50 | 0.4070 |
56
+ | 0.1226 | 0.1539 | 100 | 0.0915 |
57
+ | 0.0859 | 0.2309 | 150 | 0.0644 |
58
+ | 0.0714 | 0.3078 | 200 | 0.0530 |
59
+ | 0.054 | 0.3848 | 250 | 0.0493 |
60
+ | 0.0553 | 0.4617 | 300 | 0.0478 |
61
+ | 0.053 | 0.5387 | 350 | 0.0479 |
62
+ | 0.0645 | 0.6156 | 400 | 0.0487 |
63
+ | 0.0391 | 0.6926 | 450 | 0.0451 |
64
+ | 0.0339 | 0.7695 | 500 | 0.0405 |
65
+ | 0.0513 | 0.8465 | 550 | 0.0405 |
66
+ | 0.0374 | 0.9234 | 600 | 0.0385 |
67
+ | 0.0334 | 1.0004 | 650 | 0.0381 |
68
+ | 0.0405 | 1.0773 | 700 | 0.0403 |
69
+ | 0.0337 | 1.1543 | 750 | 0.0361 |
70
+ | 0.0344 | 1.2312 | 800 | 0.0359 |
71
+ | 0.0344 | 1.3082 | 850 | 0.0373 |
72
+ | 0.0221 | 1.3851 | 900 | 0.0357 |
73
+ | 0.0457 | 1.4621 | 950 | 0.0375 |
74
+ | 0.0357 | 1.5391 | 1000 | 0.0365 |
75
+ | 0.034 | 1.6160 | 1050 | 0.0356 |
76
+ | 0.0394 | 1.6930 | 1100 | 0.0364 |
77
+ | 0.0244 | 1.7699 | 1150 | 0.0360 |
78
+ | 0.023 | 1.8469 | 1200 | 0.0371 |
79
+ | 0.0339 | 1.9238 | 1250 | 0.0358 |
80
+ | 0.0252 | 2.0008 | 1300 | 0.0344 |
81
+ | 0.019 | 2.0777 | 1350 | 0.0338 |
82
+ | 0.0297 | 2.1547 | 1400 | 0.0361 |
83
+ | 0.0142 | 2.2316 | 1450 | 0.0371 |
84
+ | 0.0227 | 2.3086 | 1500 | 0.0354 |
85
+ | 0.0179 | 2.3855 | 1550 | 0.0411 |
86
+ | 0.0189 | 2.4625 | 1600 | 0.0363 |
87
+ | 0.0246 | 2.5394 | 1650 | 0.0360 |
88
+ | 0.0244 | 2.6164 | 1700 | 0.0354 |
89
+ | 0.0295 | 2.6933 | 1750 | 0.0355 |
90
+ | 0.0257 | 2.7703 | 1800 | 0.0354 |
91
+ | 0.0313 | 2.8472 | 1850 | 0.0339 |
92
+ | 0.0208 | 2.9242 | 1900 | 0.0348 |
93
+ | 0.0314 | 3.0012 | 1950 | 0.0349 |
94
+ | 0.0119 | 3.0781 | 2000 | 0.0392 |
95
+ | 0.0147 | 3.1551 | 2050 | 0.0425 |
96
+ | 0.011 | 3.2320 | 2100 | 0.0402 |
97
+ | 0.012 | 3.3090 | 2150 | 0.0416 |
98
+ | 0.0205 | 3.3859 | 2200 | 0.0398 |
99
+ | 0.0127 | 3.4629 | 2250 | 0.0399 |
100
+ | 0.0141 | 3.5398 | 2300 | 0.0419 |
101
+ | 0.0081 | 3.6168 | 2350 | 0.0435 |
102
+ | 0.0132 | 3.6937 | 2400 | 0.0412 |
103
+ | 0.0111 | 3.7707 | 2450 | 0.0433 |
104
+ | 0.0069 | 3.8476 | 2500 | 0.0446 |
105
+ | 0.0135 | 3.9246 | 2550 | 0.0454 |
106
+ | 0.0093 | 4.0015 | 2600 | 0.0452 |
107
+ | 0.0024 | 4.0785 | 2650 | 0.0488 |
108
+ | 0.0082 | 4.1554 | 2700 | 0.0550 |
109
+ | 0.004 | 4.2324 | 2750 | 0.0540 |
110
+ | 0.0044 | 4.3093 | 2800 | 0.0571 |
111
+ | 0.0027 | 4.3863 | 2850 | 0.0591 |
112
+ | 0.0044 | 4.4633 | 2900 | 0.0599 |
113
+ | 0.0017 | 4.5402 | 2950 | 0.0583 |
114
+ | 0.0034 | 4.6172 | 3000 | 0.0581 |
115
+ | 0.0048 | 4.6941 | 3050 | 0.0578 |
116
+ | 0.0051 | 4.7711 | 3100 | 0.0577 |
117
+ | 0.0053 | 4.8480 | 3150 | 0.0578 |
118
+ | 0.0033 | 4.9250 | 3200 | 0.0577 |
119
+
120
+
121
+ ### Framework versions
122
+
123
+ - PEFT 0.12.0
124
+ - Transformers 4.46.1
125
+ - Pytorch 2.5.1+cu124
126
+ - Datasets 3.1.0
127
+ - Tokenizers 0.20.3
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold1/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
+ "down_proj",
24
+ "k_proj",
25
+ "v_proj",
26
+ "gate_proj",
27
+ "q_proj",
28
+ "up_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold1/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9a05b7e2705b952fa223a9a819f33a8059c0efc57d59c8366c3cf68ee3e5537
3
+ size 83945296
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold1/all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.994228549442093,
3
+ "eval_loss": 0.03381282836198807,
4
+ "eval_runtime": 171.9456,
5
+ "eval_samples_per_second": 6.723,
6
+ "eval_steps_per_second": 6.723,
7
+ "total_flos": 8.1511813636463e+17,
8
+ "train_loss": 0.04558033469306715,
9
+ "train_runtime": 40942.202,
10
+ "train_samples_per_second": 1.27,
11
+ "train_steps_per_second": 0.079
12
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold1/eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.994228549442093,
3
+ "eval_loss": 0.03381282836198807,
4
+ "eval_runtime": 171.9456,
5
+ "eval_samples_per_second": 6.723,
6
+ "eval_steps_per_second": 6.723
7
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold1/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-fold1
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/fold1
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-fold1
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-fold1/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-fold1/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-fold1/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-fold1/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.994228549442093,
3
+ "total_flos": 8.1511813636463e+17,
4
+ "train_loss": 0.04558033469306715,
5
+ "train_runtime": 40942.202,
6
+ "train_samples_per_second": 1.27,
7
+ "train_steps_per_second": 0.079
8
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold1/trainer_log.jsonl ADDED
@@ -0,0 +1,389 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 3245, "loss": 1.6199, "lr": 3.0769230769230774e-06, "epoch": 0.015390534821085032, "percentage": 0.31, "elapsed_time": "0:01:19", "remaining_time": "7:06:06"}
2
+ {"current_steps": 20, "total_steps": 3245, "loss": 1.5918, "lr": 6.153846153846155e-06, "epoch": 0.030781069642170065, "percentage": 0.62, "elapsed_time": "0:02:42", "remaining_time": "7:15:35"}
3
+ {"current_steps": 30, "total_steps": 3245, "loss": 1.3184, "lr": 9.230769230769232e-06, "epoch": 0.0461716044632551, "percentage": 0.92, "elapsed_time": "0:04:07", "remaining_time": "7:22:54"}
4
+ {"current_steps": 40, "total_steps": 3245, "loss": 0.8797, "lr": 1.230769230769231e-05, "epoch": 0.06156213928434013, "percentage": 1.23, "elapsed_time": "0:05:35", "remaining_time": "7:27:47"}
5
+ {"current_steps": 50, "total_steps": 3245, "loss": 0.5562, "lr": 1.5384615384615387e-05, "epoch": 0.07695267410542517, "percentage": 1.54, "elapsed_time": "0:07:03", "remaining_time": "7:31:15"}
6
+ {"current_steps": 50, "total_steps": 3245, "eval_loss": 0.40699678659439087, "epoch": 0.07695267410542517, "percentage": 1.54, "elapsed_time": "0:10:09", "remaining_time": "10:48:49"}
7
+ {"current_steps": 60, "total_steps": 3245, "loss": 0.3409, "lr": 1.8461538461538465e-05, "epoch": 0.0923432089265102, "percentage": 1.85, "elapsed_time": "0:11:41", "remaining_time": "10:20:47"}
8
+ {"current_steps": 70, "total_steps": 3245, "loss": 0.2488, "lr": 2.1538461538461542e-05, "epoch": 0.10773374374759523, "percentage": 2.16, "elapsed_time": "0:13:11", "remaining_time": "9:58:22"}
9
+ {"current_steps": 80, "total_steps": 3245, "loss": 0.1659, "lr": 2.461538461538462e-05, "epoch": 0.12312427856868026, "percentage": 2.47, "elapsed_time": "0:14:41", "remaining_time": "9:40:58"}
10
+ {"current_steps": 90, "total_steps": 3245, "loss": 0.167, "lr": 2.7692307692307694e-05, "epoch": 0.1385148133897653, "percentage": 2.77, "elapsed_time": "0:16:11", "remaining_time": "9:27:23"}
11
+ {"current_steps": 100, "total_steps": 3245, "loss": 0.1226, "lr": 3.0769230769230774e-05, "epoch": 0.15390534821085033, "percentage": 3.08, "elapsed_time": "0:17:42", "remaining_time": "9:16:46"}
12
+ {"current_steps": 100, "total_steps": 3245, "eval_loss": 0.09147929400205612, "epoch": 0.15390534821085033, "percentage": 3.08, "elapsed_time": "0:20:50", "remaining_time": "10:55:19"}
13
+ {"current_steps": 110, "total_steps": 3245, "loss": 0.0863, "lr": 3.384615384615385e-05, "epoch": 0.16929588303193535, "percentage": 3.39, "elapsed_time": "0:22:24", "remaining_time": "10:38:50"}
14
+ {"current_steps": 120, "total_steps": 3245, "loss": 0.0894, "lr": 3.692307692307693e-05, "epoch": 0.1846864178530204, "percentage": 3.7, "elapsed_time": "0:23:55", "remaining_time": "10:22:58"}
15
+ {"current_steps": 130, "total_steps": 3245, "loss": 0.0754, "lr": 4e-05, "epoch": 0.2000769526741054, "percentage": 4.01, "elapsed_time": "0:25:25", "remaining_time": "10:09:18"}
16
+ {"current_steps": 140, "total_steps": 3245, "loss": 0.0912, "lr": 4.3076923076923084e-05, "epoch": 0.21546748749519046, "percentage": 4.31, "elapsed_time": "0:26:56", "remaining_time": "9:57:21"}
17
+ {"current_steps": 150, "total_steps": 3245, "loss": 0.0859, "lr": 4.615384615384616e-05, "epoch": 0.2308580223162755, "percentage": 4.62, "elapsed_time": "0:28:26", "remaining_time": "9:46:47"}
18
+ {"current_steps": 150, "total_steps": 3245, "eval_loss": 0.0644315704703331, "epoch": 0.2308580223162755, "percentage": 4.62, "elapsed_time": "0:31:34", "remaining_time": "10:51:29"}
19
+ {"current_steps": 160, "total_steps": 3245, "loss": 0.0727, "lr": 4.923076923076924e-05, "epoch": 0.24624855713736052, "percentage": 4.93, "elapsed_time": "0:33:08", "remaining_time": "10:38:55"}
20
+ {"current_steps": 170, "total_steps": 3245, "loss": 0.0806, "lr": 5.230769230769231e-05, "epoch": 0.26163909195844554, "percentage": 5.24, "elapsed_time": "0:34:38", "remaining_time": "10:26:41"}
21
+ {"current_steps": 180, "total_steps": 3245, "loss": 0.0615, "lr": 5.538461538461539e-05, "epoch": 0.2770296267795306, "percentage": 5.55, "elapsed_time": "0:36:09", "remaining_time": "10:15:39"}
22
+ {"current_steps": 190, "total_steps": 3245, "loss": 0.0521, "lr": 5.846153846153847e-05, "epoch": 0.2924201616006156, "percentage": 5.86, "elapsed_time": "0:37:39", "remaining_time": "10:05:29"}
23
+ {"current_steps": 200, "total_steps": 3245, "loss": 0.0714, "lr": 6.153846153846155e-05, "epoch": 0.30781069642170067, "percentage": 6.16, "elapsed_time": "0:39:10", "remaining_time": "9:56:24"}
24
+ {"current_steps": 200, "total_steps": 3245, "eval_loss": 0.052990105003118515, "epoch": 0.30781069642170067, "percentage": 6.16, "elapsed_time": "0:42:18", "remaining_time": "10:44:15"}
25
+ {"current_steps": 210, "total_steps": 3245, "loss": 0.0609, "lr": 6.461538461538462e-05, "epoch": 0.3232012312427857, "percentage": 6.47, "elapsed_time": "0:43:52", "remaining_time": "10:34:11"}
26
+ {"current_steps": 220, "total_steps": 3245, "loss": 0.0594, "lr": 6.76923076923077e-05, "epoch": 0.3385917660638707, "percentage": 6.78, "elapsed_time": "0:45:23", "remaining_time": "10:24:03"}
27
+ {"current_steps": 230, "total_steps": 3245, "loss": 0.0502, "lr": 7.076923076923078e-05, "epoch": 0.35398230088495575, "percentage": 7.09, "elapsed_time": "0:46:53", "remaining_time": "10:14:41"}
28
+ {"current_steps": 240, "total_steps": 3245, "loss": 0.0525, "lr": 7.384615384615386e-05, "epoch": 0.3693728357060408, "percentage": 7.4, "elapsed_time": "0:48:23", "remaining_time": "10:06:00"}
29
+ {"current_steps": 250, "total_steps": 3245, "loss": 0.054, "lr": 7.692307692307693e-05, "epoch": 0.38476337052712584, "percentage": 7.7, "elapsed_time": "0:49:54", "remaining_time": "9:57:57"}
30
+ {"current_steps": 250, "total_steps": 3245, "eval_loss": 0.049264274537563324, "epoch": 0.38476337052712584, "percentage": 7.7, "elapsed_time": "0:53:02", "remaining_time": "10:35:30"}
31
+ {"current_steps": 260, "total_steps": 3245, "loss": 0.0509, "lr": 8e-05, "epoch": 0.4001539053482108, "percentage": 8.01, "elapsed_time": "0:54:36", "remaining_time": "10:26:58"}
32
+ {"current_steps": 270, "total_steps": 3245, "loss": 0.0538, "lr": 8.307692307692309e-05, "epoch": 0.41554444016929587, "percentage": 8.32, "elapsed_time": "0:56:06", "remaining_time": "10:18:17"}
33
+ {"current_steps": 280, "total_steps": 3245, "loss": 0.0605, "lr": 8.615384615384617e-05, "epoch": 0.4309349749903809, "percentage": 8.63, "elapsed_time": "0:57:37", "remaining_time": "10:10:08"}
34
+ {"current_steps": 290, "total_steps": 3245, "loss": 0.0605, "lr": 8.923076923076924e-05, "epoch": 0.44632550981146596, "percentage": 8.94, "elapsed_time": "0:59:07", "remaining_time": "10:02:23"}
35
+ {"current_steps": 300, "total_steps": 3245, "loss": 0.0553, "lr": 9.230769230769232e-05, "epoch": 0.461716044632551, "percentage": 9.24, "elapsed_time": "1:00:37", "remaining_time": "9:55:06"}
36
+ {"current_steps": 300, "total_steps": 3245, "eval_loss": 0.04779207333922386, "epoch": 0.461716044632551, "percentage": 9.24, "elapsed_time": "1:03:45", "remaining_time": "10:25:49"}
37
+ {"current_steps": 310, "total_steps": 3245, "loss": 0.0552, "lr": 9.53846153846154e-05, "epoch": 0.477106579453636, "percentage": 9.55, "elapsed_time": "1:05:19", "remaining_time": "10:18:25"}
38
+ {"current_steps": 320, "total_steps": 3245, "loss": 0.0587, "lr": 9.846153846153848e-05, "epoch": 0.49249711427472104, "percentage": 9.86, "elapsed_time": "1:06:49", "remaining_time": "10:10:45"}
39
+ {"current_steps": 330, "total_steps": 3245, "loss": 0.0608, "lr": 9.999927654251793e-05, "epoch": 0.5078876490958061, "percentage": 10.17, "elapsed_time": "1:08:19", "remaining_time": "10:03:33"}
40
+ {"current_steps": 340, "total_steps": 3245, "loss": 0.0566, "lr": 9.99934890082745e-05, "epoch": 0.5232781839168911, "percentage": 10.48, "elapsed_time": "1:09:50", "remaining_time": "9:56:43"}
41
+ {"current_steps": 350, "total_steps": 3245, "loss": 0.053, "lr": 9.99819146097084e-05, "epoch": 0.5386687187379762, "percentage": 10.79, "elapsed_time": "1:11:20", "remaining_time": "9:50:05"}
42
+ {"current_steps": 350, "total_steps": 3245, "eval_loss": 0.0478888563811779, "epoch": 0.5386687187379762, "percentage": 10.79, "elapsed_time": "1:14:27", "remaining_time": "10:15:55"}
43
+ {"current_steps": 360, "total_steps": 3245, "loss": 0.0679, "lr": 9.996455468658355e-05, "epoch": 0.5540592535590612, "percentage": 11.09, "elapsed_time": "1:16:01", "remaining_time": "10:09:11"}
44
+ {"current_steps": 370, "total_steps": 3245, "loss": 0.0511, "lr": 9.994141124835203e-05, "epoch": 0.5694497883801463, "percentage": 11.4, "elapsed_time": "1:17:32", "remaining_time": "10:02:27"}
45
+ {"current_steps": 380, "total_steps": 3245, "loss": 0.0499, "lr": 9.991248697392142e-05, "epoch": 0.5848403232012312, "percentage": 11.71, "elapsed_time": "1:19:01", "remaining_time": "9:55:51"}
46
+ {"current_steps": 390, "total_steps": 3245, "loss": 0.0364, "lr": 9.987778521134476e-05, "epoch": 0.6002308580223162, "percentage": 12.02, "elapsed_time": "1:20:32", "remaining_time": "9:49:33"}
47
+ {"current_steps": 400, "total_steps": 3245, "loss": 0.0645, "lr": 9.983730997743294e-05, "epoch": 0.6156213928434013, "percentage": 12.33, "elapsed_time": "1:22:02", "remaining_time": "9:43:32"}
48
+ {"current_steps": 400, "total_steps": 3245, "eval_loss": 0.048657890409231186, "epoch": 0.6156213928434013, "percentage": 12.33, "elapsed_time": "1:25:09", "remaining_time": "10:05:43"}
49
+ {"current_steps": 410, "total_steps": 3245, "loss": 0.0462, "lr": 9.979106595728978e-05, "epoch": 0.6310119276644863, "percentage": 12.63, "elapsed_time": "1:26:43", "remaining_time": "9:59:43"}
50
+ {"current_steps": 420, "total_steps": 3245, "loss": 0.0509, "lr": 9.973905850376977e-05, "epoch": 0.6464024624855714, "percentage": 12.94, "elapsed_time": "1:28:14", "remaining_time": "9:53:34"}
51
+ {"current_steps": 430, "total_steps": 3245, "loss": 0.0529, "lr": 9.968129363685833e-05, "epoch": 0.6617929973066564, "percentage": 13.25, "elapsed_time": "1:29:45", "remaining_time": "9:47:34"}
52
+ {"current_steps": 440, "total_steps": 3245, "loss": 0.0658, "lr": 9.961777804297514e-05, "epoch": 0.6771835321277414, "percentage": 13.56, "elapsed_time": "1:31:15", "remaining_time": "9:41:49"}
53
+ {"current_steps": 450, "total_steps": 3245, "loss": 0.0391, "lr": 9.954851907420009e-05, "epoch": 0.6925740669488265, "percentage": 13.87, "elapsed_time": "1:32:46", "remaining_time": "9:36:11"}
54
+ {"current_steps": 450, "total_steps": 3245, "eval_loss": 0.04509444162249565, "epoch": 0.6925740669488265, "percentage": 13.87, "elapsed_time": "1:35:53", "remaining_time": "9:55:37"}
55
+ {"current_steps": 460, "total_steps": 3245, "loss": 0.0422, "lr": 9.947352474742222e-05, "epoch": 0.7079646017699115, "percentage": 14.18, "elapsed_time": "1:37:28", "remaining_time": "9:50:06"}
56
+ {"current_steps": 470, "total_steps": 3245, "loss": 0.0336, "lr": 9.93928037434118e-05, "epoch": 0.7233551365909965, "percentage": 14.48, "elapsed_time": "1:38:58", "remaining_time": "9:44:23"}
57
+ {"current_steps": 480, "total_steps": 3245, "loss": 0.0403, "lr": 9.930636540581556e-05, "epoch": 0.7387456714120816, "percentage": 14.79, "elapsed_time": "1:40:29", "remaining_time": "9:38:50"}
58
+ {"current_steps": 490, "total_steps": 3245, "loss": 0.0452, "lr": 9.921421974007506e-05, "epoch": 0.7541362062331666, "percentage": 15.1, "elapsed_time": "1:42:00", "remaining_time": "9:33:30"}
59
+ {"current_steps": 500, "total_steps": 3245, "loss": 0.0339, "lr": 9.911637741226849e-05, "epoch": 0.7695267410542517, "percentage": 15.41, "elapsed_time": "1:43:30", "remaining_time": "9:28:15"}
60
+ {"current_steps": 500, "total_steps": 3245, "eval_loss": 0.04046137258410454, "epoch": 0.7695267410542517, "percentage": 15.41, "elapsed_time": "1:46:38", "remaining_time": "9:45:27"}
61
+ {"current_steps": 510, "total_steps": 3245, "loss": 0.0328, "lr": 9.90128497478762e-05, "epoch": 0.7849172758753367, "percentage": 15.72, "elapsed_time": "1:48:11", "remaining_time": "9:40:13"}
62
+ {"current_steps": 520, "total_steps": 3245, "loss": 0.0519, "lr": 9.890364873046965e-05, "epoch": 0.8003078106964217, "percentage": 16.02, "elapsed_time": "1:49:41", "remaining_time": "9:34:51"}
63
+ {"current_steps": 530, "total_steps": 3245, "loss": 0.0656, "lr": 9.878878700032427e-05, "epoch": 0.8156983455175068, "percentage": 16.33, "elapsed_time": "1:51:12", "remaining_time": "9:29:40"}
64
+ {"current_steps": 540, "total_steps": 3245, "loss": 0.0456, "lr": 9.866827785295638e-05, "epoch": 0.8310888803385917, "percentage": 16.64, "elapsed_time": "1:52:43", "remaining_time": "9:24:37"}
65
+ {"current_steps": 550, "total_steps": 3245, "loss": 0.0513, "lr": 9.854213523758413e-05, "epoch": 0.8464794151596768, "percentage": 16.95, "elapsed_time": "1:54:13", "remaining_time": "9:19:41"}
66
+ {"current_steps": 550, "total_steps": 3245, "eval_loss": 0.04050951078534126, "epoch": 0.8464794151596768, "percentage": 16.95, "elapsed_time": "1:57:21", "remaining_time": "9:35:03"}
67
+ {"current_steps": 560, "total_steps": 3245, "loss": 0.0417, "lr": 9.841037375551294e-05, "epoch": 0.8618699499807618, "percentage": 17.26, "elapsed_time": "1:58:55", "remaining_time": "9:30:12"}
68
+ {"current_steps": 570, "total_steps": 3245, "loss": 0.0333, "lr": 9.827300865844527e-05, "epoch": 0.8772604848018468, "percentage": 17.57, "elapsed_time": "2:00:26", "remaining_time": "9:25:12"}
69
+ {"current_steps": 580, "total_steps": 3245, "loss": 0.0362, "lr": 9.813005584671522e-05, "epoch": 0.8926510196229319, "percentage": 17.87, "elapsed_time": "2:01:56", "remaining_time": "9:20:19"}
70
+ {"current_steps": 590, "total_steps": 3245, "loss": 0.0579, "lr": 9.79815318674481e-05, "epoch": 0.9080415544440169, "percentage": 18.18, "elapsed_time": "2:03:27", "remaining_time": "9:15:34"}
71
+ {"current_steps": 600, "total_steps": 3245, "loss": 0.0374, "lr": 9.782745391264498e-05, "epoch": 0.923432089265102, "percentage": 18.49, "elapsed_time": "2:04:58", "remaining_time": "9:10:54"}
72
+ {"current_steps": 600, "total_steps": 3245, "eval_loss": 0.03845710679888725, "epoch": 0.923432089265102, "percentage": 18.49, "elapsed_time": "2:08:05", "remaining_time": "9:24:41"}
73
+ {"current_steps": 610, "total_steps": 3245, "loss": 0.0377, "lr": 9.76678398171927e-05, "epoch": 0.938822624086187, "percentage": 18.8, "elapsed_time": "2:09:40", "remaining_time": "9:20:08"}
74
+ {"current_steps": 620, "total_steps": 3245, "loss": 0.053, "lr": 9.750270805679945e-05, "epoch": 0.954213158907272, "percentage": 19.11, "elapsed_time": "2:11:10", "remaining_time": "9:15:23"}
75
+ {"current_steps": 630, "total_steps": 3245, "loss": 0.0484, "lr": 9.733207774585618e-05, "epoch": 0.9696036937283571, "percentage": 19.41, "elapsed_time": "2:12:40", "remaining_time": "9:10:43"}
76
+ {"current_steps": 640, "total_steps": 3245, "loss": 0.0355, "lr": 9.715596863522398e-05, "epoch": 0.9849942285494421, "percentage": 19.72, "elapsed_time": "2:14:11", "remaining_time": "9:06:11"}
77
+ {"current_steps": 650, "total_steps": 3245, "loss": 0.0334, "lr": 9.697440110994801e-05, "epoch": 1.0003847633705272, "percentage": 20.03, "elapsed_time": "2:15:41", "remaining_time": "9:01:44"}
78
+ {"current_steps": 650, "total_steps": 3245, "eval_loss": 0.03811522200703621, "epoch": 1.0003847633705272, "percentage": 20.03, "elapsed_time": "2:18:49", "remaining_time": "9:14:13"}
79
+ {"current_steps": 660, "total_steps": 3245, "loss": 0.0398, "lr": 9.678739618689775e-05, "epoch": 1.0157752981916122, "percentage": 20.34, "elapsed_time": "2:20:24", "remaining_time": "9:09:54"}
80
+ {"current_steps": 670, "total_steps": 3245, "loss": 0.038, "lr": 9.659497551233431e-05, "epoch": 1.0311658330126972, "percentage": 20.65, "elapsed_time": "2:21:55", "remaining_time": "9:05:26"}
81
+ {"current_steps": 680, "total_steps": 3245, "loss": 0.0351, "lr": 9.639716135940485e-05, "epoch": 1.0465563678337821, "percentage": 20.96, "elapsed_time": "2:23:25", "remaining_time": "9:01:00"}
82
+ {"current_steps": 690, "total_steps": 3245, "loss": 0.0486, "lr": 9.619397662556435e-05, "epoch": 1.0619469026548674, "percentage": 21.26, "elapsed_time": "2:24:56", "remaining_time": "8:56:41"}
83
+ {"current_steps": 700, "total_steps": 3245, "loss": 0.0405, "lr": 9.598544482992517e-05, "epoch": 1.0773374374759523, "percentage": 21.57, "elapsed_time": "2:26:27", "remaining_time": "8:52:27"}
84
+ {"current_steps": 700, "total_steps": 3245, "eval_loss": 0.04033925011754036, "epoch": 1.0773374374759523, "percentage": 21.57, "elapsed_time": "2:29:35", "remaining_time": "9:03:50"}
85
+ {"current_steps": 710, "total_steps": 3245, "loss": 0.033, "lr": 9.57715901105348e-05, "epoch": 1.0927279722970373, "percentage": 21.88, "elapsed_time": "2:31:09", "remaining_time": "8:59:40"}
86
+ {"current_steps": 720, "total_steps": 3245, "loss": 0.0338, "lr": 9.555243722158158e-05, "epoch": 1.1081185071181223, "percentage": 22.19, "elapsed_time": "2:32:39", "remaining_time": "8:55:22"}
87
+ {"current_steps": 730, "total_steps": 3245, "loss": 0.0323, "lr": 9.532801153052958e-05, "epoch": 1.1235090419392073, "percentage": 22.5, "elapsed_time": "2:34:10", "remaining_time": "8:51:08"}
88
+ {"current_steps": 740, "total_steps": 3245, "loss": 0.05, "lr": 9.509833901518209e-05, "epoch": 1.1388995767602923, "percentage": 22.8, "elapsed_time": "2:35:40", "remaining_time": "8:46:58"}
89
+ {"current_steps": 750, "total_steps": 3245, "loss": 0.0337, "lr": 9.486344626067475e-05, "epoch": 1.1542901115813775, "percentage": 23.11, "elapsed_time": "2:37:11", "remaining_time": "8:42:54"}
90
+ {"current_steps": 750, "total_steps": 3245, "eval_loss": 0.0360797680914402, "epoch": 1.1542901115813775, "percentage": 23.11, "elapsed_time": "2:40:19", "remaining_time": "8:53:20"}
91
+ {"current_steps": 760, "total_steps": 3245, "loss": 0.0407, "lr": 9.462336045639815e-05, "epoch": 1.1696806464024625, "percentage": 23.42, "elapsed_time": "2:41:52", "remaining_time": "8:49:17"}
92
+ {"current_steps": 770, "total_steps": 3245, "loss": 0.0407, "lr": 9.437810939285068e-05, "epoch": 1.1850711812235475, "percentage": 23.73, "elapsed_time": "2:43:22", "remaining_time": "8:45:08"}
93
+ {"current_steps": 780, "total_steps": 3245, "loss": 0.038, "lr": 9.412772145842165e-05, "epoch": 1.2004617160446325, "percentage": 24.04, "elapsed_time": "2:44:52", "remaining_time": "8:41:04"}
94
+ {"current_steps": 790, "total_steps": 3245, "loss": 0.0358, "lr": 9.387222563610535e-05, "epoch": 1.2158522508657175, "percentage": 24.35, "elapsed_time": "2:46:22", "remaining_time": "8:37:02"}
95
+ {"current_steps": 800, "total_steps": 3245, "loss": 0.0344, "lr": 9.361165150014606e-05, "epoch": 1.2312427856868027, "percentage": 24.65, "elapsed_time": "2:47:53", "remaining_time": "8:33:06"}
96
+ {"current_steps": 800, "total_steps": 3245, "eval_loss": 0.03588108345866203, "epoch": 1.2312427856868027, "percentage": 24.65, "elapsed_time": "2:51:00", "remaining_time": "8:42:40"}
97
+ {"current_steps": 810, "total_steps": 3245, "loss": 0.033, "lr": 9.334602921261492e-05, "epoch": 1.2466333205078877, "percentage": 24.96, "elapsed_time": "2:52:34", "remaining_time": "8:38:46"}
98
+ {"current_steps": 820, "total_steps": 3245, "loss": 0.0315, "lr": 9.307538951991852e-05, "epoch": 1.2620238553289727, "percentage": 25.27, "elapsed_time": "2:54:04", "remaining_time": "8:34:46"}
99
+ {"current_steps": 830, "total_steps": 3245, "loss": 0.038, "lr": 9.279976374923988e-05, "epoch": 1.2774143901500576, "percentage": 25.58, "elapsed_time": "2:55:34", "remaining_time": "8:30:50"}
100
+ {"current_steps": 840, "total_steps": 3245, "loss": 0.0279, "lr": 9.251918380491238e-05, "epoch": 1.2928049249711426, "percentage": 25.89, "elapsed_time": "2:57:04", "remaining_time": "8:26:59"}
101
+ {"current_steps": 850, "total_steps": 3245, "loss": 0.0344, "lr": 9.223368216472668e-05, "epoch": 1.3081954597922278, "percentage": 26.19, "elapsed_time": "2:58:35", "remaining_time": "8:23:11"}
102
+ {"current_steps": 850, "total_steps": 3245, "eval_loss": 0.037309836596250534, "epoch": 1.3081954597922278, "percentage": 26.19, "elapsed_time": "3:01:42", "remaining_time": "8:31:59"}
103
+ {"current_steps": 860, "total_steps": 3245, "loss": 0.0331, "lr": 9.194329187617127e-05, "epoch": 1.3235859946133128, "percentage": 26.5, "elapsed_time": "3:03:15", "remaining_time": "8:28:12"}
104
+ {"current_steps": 870, "total_steps": 3245, "loss": 0.033, "lr": 9.164804655260735e-05, "epoch": 1.3389765294343978, "percentage": 26.81, "elapsed_time": "3:04:44", "remaining_time": "8:24:20"}
105
+ {"current_steps": 880, "total_steps": 3245, "loss": 0.0266, "lr": 9.134798036937778e-05, "epoch": 1.3543670642554828, "percentage": 27.12, "elapsed_time": "3:06:14", "remaining_time": "8:20:31"}
106
+ {"current_steps": 890, "total_steps": 3245, "loss": 0.0434, "lr": 9.104312805985134e-05, "epoch": 1.3697575990765678, "percentage": 27.43, "elapsed_time": "3:07:45", "remaining_time": "8:16:48"}
107
+ {"current_steps": 900, "total_steps": 3245, "loss": 0.0221, "lr": 9.073352491140221e-05, "epoch": 1.385148133897653, "percentage": 27.73, "elapsed_time": "3:09:15", "remaining_time": "8:13:07"}
108
+ {"current_steps": 900, "total_steps": 3245, "eval_loss": 0.03570735454559326, "epoch": 1.385148133897653, "percentage": 27.73, "elapsed_time": "3:12:22", "remaining_time": "8:21:14"}
109
+ {"current_steps": 910, "total_steps": 3245, "loss": 0.0304, "lr": 9.041920676132543e-05, "epoch": 1.400538668718738, "percentage": 28.04, "elapsed_time": "3:13:56", "remaining_time": "8:17:39"}
110
+ {"current_steps": 920, "total_steps": 3245, "loss": 0.0366, "lr": 9.010020999268854e-05, "epoch": 1.415929203539823, "percentage": 28.35, "elapsed_time": "3:15:27", "remaining_time": "8:13:57"}
111
+ {"current_steps": 930, "total_steps": 3245, "loss": 0.0328, "lr": 8.977657153012027e-05, "epoch": 1.431319738360908, "percentage": 28.66, "elapsed_time": "3:16:57", "remaining_time": "8:10:17"}
112
+ {"current_steps": 940, "total_steps": 3245, "loss": 0.0377, "lr": 8.944832883553633e-05, "epoch": 1.446710273181993, "percentage": 28.97, "elapsed_time": "3:18:27", "remaining_time": "8:06:39"}
113
+ {"current_steps": 950, "total_steps": 3245, "loss": 0.0457, "lr": 8.91155199038032e-05, "epoch": 1.4621008080030782, "percentage": 29.28, "elapsed_time": "3:19:58", "remaining_time": "8:03:04"}
114
+ {"current_steps": 950, "total_steps": 3245, "eval_loss": 0.03746819868683815, "epoch": 1.4621008080030782, "percentage": 29.28, "elapsed_time": "3:23:05", "remaining_time": "8:10:37"}
115
+ {"current_steps": 960, "total_steps": 3245, "loss": 0.0286, "lr": 8.877818325834006e-05, "epoch": 1.4774913428241632, "percentage": 29.58, "elapsed_time": "3:24:39", "remaining_time": "8:07:06"}
116
+ {"current_steps": 970, "total_steps": 3245, "loss": 0.027, "lr": 8.843635794665961e-05, "epoch": 1.4928818776452482, "percentage": 29.89, "elapsed_time": "3:26:09", "remaining_time": "8:03:31"}
117
+ {"current_steps": 980, "total_steps": 3245, "loss": 0.0345, "lr": 8.809008353584829e-05, "epoch": 1.5082724124663334, "percentage": 30.2, "elapsed_time": "3:27:39", "remaining_time": "7:59:57"}
118
+ {"current_steps": 990, "total_steps": 3245, "loss": 0.0398, "lr": 8.773940010798627e-05, "epoch": 1.5236629472874181, "percentage": 30.51, "elapsed_time": "3:29:10", "remaining_time": "7:56:27"}
119
+ {"current_steps": 1000, "total_steps": 3245, "loss": 0.0357, "lr": 8.738434825550785e-05, "epoch": 1.5390534821085033, "percentage": 30.82, "elapsed_time": "3:30:41", "remaining_time": "7:52:59"}
120
+ {"current_steps": 1000, "total_steps": 3245, "eval_loss": 0.03651273250579834, "epoch": 1.5390534821085033, "percentage": 30.82, "elapsed_time": "3:33:48", "remaining_time": "8:00:01"}
121
+ {"current_steps": 1010, "total_steps": 3245, "loss": 0.0398, "lr": 8.702496907650274e-05, "epoch": 1.5544440169295883, "percentage": 31.12, "elapsed_time": "3:35:22", "remaining_time": "7:56:35"}
122
+ {"current_steps": 1020, "total_steps": 3245, "loss": 0.0374, "lr": 8.666130416995897e-05, "epoch": 1.5698345517506733, "percentage": 31.43, "elapsed_time": "3:36:52", "remaining_time": "7:53:06"}
123
+ {"current_steps": 1030, "total_steps": 3245, "loss": 0.0357, "lr": 8.629339563094758e-05, "epoch": 1.5852250865717585, "percentage": 31.74, "elapsed_time": "3:38:23", "remaining_time": "7:49:39"}
124
+ {"current_steps": 1040, "total_steps": 3245, "loss": 0.033, "lr": 8.592128604575014e-05, "epoch": 1.6006156213928433, "percentage": 32.05, "elapsed_time": "3:39:54", "remaining_time": "7:46:14"}
125
+ {"current_steps": 1050, "total_steps": 3245, "loss": 0.034, "lr": 8.554501848692921e-05, "epoch": 1.6160061562139285, "percentage": 32.36, "elapsed_time": "3:41:25", "remaining_time": "7:42:52"}
126
+ {"current_steps": 1050, "total_steps": 3245, "eval_loss": 0.03555304929614067, "epoch": 1.6160061562139285, "percentage": 32.36, "elapsed_time": "3:44:33", "remaining_time": "7:49:25"}
127
+ {"current_steps": 1060, "total_steps": 3245, "loss": 0.0285, "lr": 8.51646365083426e-05, "epoch": 1.6313966910350135, "percentage": 32.67, "elapsed_time": "3:46:07", "remaining_time": "7:46:07"}
128
+ {"current_steps": 1070, "total_steps": 3245, "loss": 0.0318, "lr": 8.478018414010191e-05, "epoch": 1.6467872258560985, "percentage": 32.97, "elapsed_time": "3:47:37", "remaining_time": "7:42:41"}
129
+ {"current_steps": 1080, "total_steps": 3245, "loss": 0.0271, "lr": 8.439170588347598e-05, "epoch": 1.6621777606771835, "percentage": 33.28, "elapsed_time": "3:49:07", "remaining_time": "7:39:17"}
130
+ {"current_steps": 1090, "total_steps": 3245, "loss": 0.0262, "lr": 8.399924670573969e-05, "epoch": 1.6775682954982685, "percentage": 33.59, "elapsed_time": "3:50:37", "remaining_time": "7:35:57"}
131
+ {"current_steps": 1100, "total_steps": 3245, "loss": 0.0394, "lr": 8.360285203496894e-05, "epoch": 1.6929588303193537, "percentage": 33.9, "elapsed_time": "3:52:08", "remaining_time": "7:32:40"}
132
+ {"current_steps": 1100, "total_steps": 3245, "eval_loss": 0.03640196472406387, "epoch": 1.6929588303193537, "percentage": 33.9, "elapsed_time": "3:55:16", "remaining_time": "7:38:47"}
133
+ {"current_steps": 1110, "total_steps": 3245, "loss": 0.041, "lr": 8.320256775478228e-05, "epoch": 1.7083493651404387, "percentage": 34.21, "elapsed_time": "3:56:50", "remaining_time": "7:35:32"}
134
+ {"current_steps": 1120, "total_steps": 3245, "loss": 0.0315, "lr": 8.279844019902968e-05, "epoch": 1.7237398999615237, "percentage": 34.51, "elapsed_time": "3:58:21", "remaining_time": "7:32:13"}
135
+ {"current_steps": 1130, "total_steps": 3245, "loss": 0.0396, "lr": 8.239051614642934e-05, "epoch": 1.7391304347826086, "percentage": 34.82, "elapsed_time": "3:59:51", "remaining_time": "7:28:55"}
136
+ {"current_steps": 1140, "total_steps": 3245, "loss": 0.049, "lr": 8.197884281515292e-05, "epoch": 1.7545209696036936, "percentage": 35.13, "elapsed_time": "4:01:21", "remaining_time": "7:25:40"}
137
+ {"current_steps": 1150, "total_steps": 3245, "loss": 0.0244, "lr": 8.156346785735997e-05, "epoch": 1.7699115044247788, "percentage": 35.44, "elapsed_time": "4:02:52", "remaining_time": "7:22:26"}
138
+ {"current_steps": 1150, "total_steps": 3245, "eval_loss": 0.0359814316034317, "epoch": 1.7699115044247788, "percentage": 35.44, "elapsed_time": "4:05:59", "remaining_time": "7:28:08"}
139
+ {"current_steps": 1160, "total_steps": 3245, "loss": 0.0349, "lr": 8.114443935368198e-05, "epoch": 1.7853020392458638, "percentage": 35.75, "elapsed_time": "4:07:36", "remaining_time": "7:25:03"}
140
+ {"current_steps": 1170, "total_steps": 3245, "loss": 0.0263, "lr": 8.072180580765709e-05, "epoch": 1.8006925740669488, "percentage": 36.06, "elapsed_time": "4:09:07", "remaining_time": "7:21:48"}
141
+ {"current_steps": 1180, "total_steps": 3245, "loss": 0.0283, "lr": 8.02956161401155e-05, "epoch": 1.8160831088880338, "percentage": 36.36, "elapsed_time": "4:10:37", "remaining_time": "7:18:36"}
142
+ {"current_steps": 1190, "total_steps": 3245, "loss": 0.0356, "lr": 7.98659196835169e-05, "epoch": 1.8314736437091188, "percentage": 36.67, "elapsed_time": "4:12:08", "remaining_time": "7:15:24"}
143
+ {"current_steps": 1200, "total_steps": 3245, "loss": 0.023, "lr": 7.943276617624014e-05, "epoch": 1.846864178530204, "percentage": 36.98, "elapsed_time": "4:13:38", "remaining_time": "7:12:14"}
144
+ {"current_steps": 1200, "total_steps": 3245, "eval_loss": 0.03705717623233795, "epoch": 1.846864178530204, "percentage": 36.98, "elapsed_time": "4:16:45", "remaining_time": "7:17:33"}
145
+ {"current_steps": 1210, "total_steps": 3245, "loss": 0.0346, "lr": 7.899620575682578e-05, "epoch": 1.862254713351289, "percentage": 37.29, "elapsed_time": "4:18:18", "remaining_time": "7:14:26"}
146
+ {"current_steps": 1220, "total_steps": 3245, "loss": 0.026, "lr": 7.85562889581725e-05, "epoch": 1.877645248172374, "percentage": 37.6, "elapsed_time": "4:19:49", "remaining_time": "7:11:15"}
147
+ {"current_steps": 1230, "total_steps": 3245, "loss": 0.0338, "lr": 7.811306670168788e-05, "epoch": 1.893035782993459, "percentage": 37.9, "elapsed_time": "4:21:19", "remaining_time": "7:08:06"}
148
+ {"current_steps": 1240, "total_steps": 3245, "loss": 0.0417, "lr": 7.766659029139393e-05, "epoch": 1.908426317814544, "percentage": 38.21, "elapsed_time": "4:22:49", "remaining_time": "7:04:58"}
149
+ {"current_steps": 1250, "total_steps": 3245, "loss": 0.0339, "lr": 7.72169114079887e-05, "epoch": 1.9238168526356292, "percentage": 38.52, "elapsed_time": "4:24:20", "remaining_time": "7:01:52"}
150
+ {"current_steps": 1250, "total_steps": 3245, "eval_loss": 0.035844240337610245, "epoch": 1.9238168526356292, "percentage": 38.52, "elapsed_time": "4:27:27", "remaining_time": "7:06:52"}
151
+ {"current_steps": 1260, "total_steps": 3245, "loss": 0.0342, "lr": 7.676408210286407e-05, "epoch": 1.9392073874567142, "percentage": 38.83, "elapsed_time": "4:29:02", "remaining_time": "7:03:50"}
152
+ {"current_steps": 1270, "total_steps": 3245, "loss": 0.0364, "lr": 7.630815479208066e-05, "epoch": 1.9545979222777992, "percentage": 39.14, "elapsed_time": "4:30:32", "remaining_time": "7:00:43"}
153
+ {"current_steps": 1280, "total_steps": 3245, "loss": 0.025, "lr": 7.584918225030053e-05, "epoch": 1.9699884570988841, "percentage": 39.45, "elapsed_time": "4:32:03", "remaining_time": "6:57:38"}
154
+ {"current_steps": 1290, "total_steps": 3245, "loss": 0.0372, "lr": 7.538721760467845e-05, "epoch": 1.9853789919199691, "percentage": 39.75, "elapsed_time": "4:33:33", "remaining_time": "6:54:34"}
155
+ {"current_steps": 1300, "total_steps": 3245, "loss": 0.0252, "lr": 7.49223143287122e-05, "epoch": 2.0007695267410543, "percentage": 40.06, "elapsed_time": "4:35:03", "remaining_time": "6:51:32"}
156
+ {"current_steps": 1300, "total_steps": 3245, "eval_loss": 0.0344332717359066, "epoch": 2.0007695267410543, "percentage": 40.06, "elapsed_time": "4:38:11", "remaining_time": "6:56:13"}
157
+ {"current_steps": 1310, "total_steps": 3245, "loss": 0.0227, "lr": 7.445452623605307e-05, "epoch": 2.016160061562139, "percentage": 40.37, "elapsed_time": "4:39:46", "remaining_time": "6:53:15"}
158
+ {"current_steps": 1320, "total_steps": 3245, "loss": 0.0237, "lr": 7.398390747427662e-05, "epoch": 2.0315505963832243, "percentage": 40.68, "elapsed_time": "4:41:16", "remaining_time": "6:50:12"}
159
+ {"current_steps": 1330, "total_steps": 3245, "loss": 0.0255, "lr": 7.351051251861501e-05, "epoch": 2.0469411312043095, "percentage": 40.99, "elapsed_time": "4:42:47", "remaining_time": "6:47:10"}
160
+ {"current_steps": 1340, "total_steps": 3245, "loss": 0.0248, "lr": 7.303439616565146e-05, "epoch": 2.0623316660253943, "percentage": 41.29, "elapsed_time": "4:44:18", "remaining_time": "6:44:10"}
161
+ {"current_steps": 1350, "total_steps": 3245, "loss": 0.019, "lr": 7.255561352697732e-05, "epoch": 2.0777222008464795, "percentage": 41.6, "elapsed_time": "4:45:48", "remaining_time": "6:41:10"}
162
+ {"current_steps": 1350, "total_steps": 3245, "eval_loss": 0.03381282836198807, "epoch": 2.0777222008464795, "percentage": 41.6, "elapsed_time": "4:48:55", "remaining_time": "6:45:34"}
163
+ {"current_steps": 1360, "total_steps": 3245, "loss": 0.0227, "lr": 7.207422002281281e-05, "epoch": 2.0931127356675643, "percentage": 41.91, "elapsed_time": "4:50:30", "remaining_time": "6:42:38"}
164
+ {"current_steps": 1370, "total_steps": 3245, "loss": 0.0218, "lr": 7.159027137559197e-05, "epoch": 2.1085032704886495, "percentage": 42.22, "elapsed_time": "4:52:00", "remaining_time": "6:39:38"}
165
+ {"current_steps": 1380, "total_steps": 3245, "loss": 0.0153, "lr": 7.110382360351267e-05, "epoch": 2.1238938053097347, "percentage": 42.53, "elapsed_time": "4:53:30", "remaining_time": "6:36:39"}
166
+ {"current_steps": 1390, "total_steps": 3245, "loss": 0.0208, "lr": 7.061493301405244e-05, "epoch": 2.1392843401308195, "percentage": 42.84, "elapsed_time": "4:55:00", "remaining_time": "6:33:42"}
167
+ {"current_steps": 1400, "total_steps": 3245, "loss": 0.0297, "lr": 7.012365619745064e-05, "epoch": 2.1546748749519047, "percentage": 43.14, "elapsed_time": "4:56:31", "remaining_time": "6:30:46"}
168
+ {"current_steps": 1400, "total_steps": 3245, "eval_loss": 0.03612199053168297, "epoch": 2.1546748749519047, "percentage": 43.14, "elapsed_time": "4:59:38", "remaining_time": "6:34:52"}
169
+ {"current_steps": 1410, "total_steps": 3245, "loss": 0.024, "lr": 6.963005002015808e-05, "epoch": 2.1700654097729895, "percentage": 43.45, "elapsed_time": "5:01:11", "remaining_time": "6:31:58"}
170
+ {"current_steps": 1420, "total_steps": 3245, "loss": 0.03, "lr": 6.91341716182545e-05, "epoch": 2.1854559445940747, "percentage": 43.76, "elapsed_time": "5:02:41", "remaining_time": "6:29:01"}
171
+ {"current_steps": 1430, "total_steps": 3245, "loss": 0.0178, "lr": 6.863607839083507e-05, "epoch": 2.20084647941516, "percentage": 44.07, "elapsed_time": "5:04:11", "remaining_time": "6:26:04"}
172
+ {"current_steps": 1440, "total_steps": 3245, "loss": 0.0261, "lr": 6.813582799336624e-05, "epoch": 2.2162370142362446, "percentage": 44.38, "elapsed_time": "5:05:41", "remaining_time": "6:23:10"}
173
+ {"current_steps": 1450, "total_steps": 3245, "loss": 0.0142, "lr": 6.763347833101192e-05, "epoch": 2.23162754905733, "percentage": 44.68, "elapsed_time": "5:07:11", "remaining_time": "6:20:17"}
174
+ {"current_steps": 1450, "total_steps": 3245, "eval_loss": 0.03711491823196411, "epoch": 2.23162754905733, "percentage": 44.68, "elapsed_time": "5:10:18", "remaining_time": "6:24:08"}
175
+ {"current_steps": 1460, "total_steps": 3245, "loss": 0.0233, "lr": 6.712908755193094e-05, "epoch": 2.2470180838784146, "percentage": 44.99, "elapsed_time": "5:11:51", "remaining_time": "6:21:16"}
176
+ {"current_steps": 1470, "total_steps": 3245, "loss": 0.0268, "lr": 6.662271404054621e-05, "epoch": 2.2624086186995, "percentage": 45.3, "elapsed_time": "5:13:21", "remaining_time": "6:18:22"}
177
+ {"current_steps": 1480, "total_steps": 3245, "loss": 0.0233, "lr": 6.611441641078657e-05, "epoch": 2.2777991535205846, "percentage": 45.61, "elapsed_time": "5:14:51", "remaining_time": "6:15:29"}
178
+ {"current_steps": 1490, "total_steps": 3245, "loss": 0.0253, "lr": 6.560425349930208e-05, "epoch": 2.29318968834167, "percentage": 45.92, "elapsed_time": "5:16:21", "remaining_time": "6:12:37"}
179
+ {"current_steps": 1500, "total_steps": 3245, "loss": 0.0227, "lr": 6.509228435865357e-05, "epoch": 2.308580223162755, "percentage": 46.22, "elapsed_time": "5:17:51", "remaining_time": "6:09:46"}
180
+ {"current_steps": 1500, "total_steps": 3245, "eval_loss": 0.0353684276342392, "epoch": 2.308580223162755, "percentage": 46.22, "elapsed_time": "5:20:57", "remaining_time": "6:13:22"}
181
+ {"current_steps": 1510, "total_steps": 3245, "loss": 0.0244, "lr": 6.45785682504772e-05, "epoch": 2.32397075798384, "percentage": 46.53, "elapsed_time": "5:22:31", "remaining_time": "6:10:34"}
182
+ {"current_steps": 1520, "total_steps": 3245, "loss": 0.0214, "lr": 6.406316463862467e-05, "epoch": 2.339361292804925, "percentage": 46.84, "elapsed_time": "5:24:01", "remaining_time": "6:07:43"}
183
+ {"current_steps": 1530, "total_steps": 3245, "loss": 0.0201, "lr": 6.35461331822803e-05, "epoch": 2.3547518276260098, "percentage": 47.15, "elapsed_time": "5:25:31", "remaining_time": "6:04:53"}
184
+ {"current_steps": 1540, "total_steps": 3245, "loss": 0.0199, "lr": 6.302753372905515e-05, "epoch": 2.370142362447095, "percentage": 47.46, "elapsed_time": "5:27:01", "remaining_time": "6:02:03"}
185
+ {"current_steps": 1550, "total_steps": 3245, "loss": 0.0179, "lr": 6.250742630805971e-05, "epoch": 2.38553289726818, "percentage": 47.77, "elapsed_time": "5:28:31", "remaining_time": "5:59:15"}
186
+ {"current_steps": 1550, "total_steps": 3245, "eval_loss": 0.04112153872847557, "epoch": 2.38553289726818, "percentage": 47.77, "elapsed_time": "5:31:37", "remaining_time": "6:02:39"}
187
+ {"current_steps": 1560, "total_steps": 3245, "loss": 0.0155, "lr": 6.198587112295526e-05, "epoch": 2.400923432089265, "percentage": 48.07, "elapsed_time": "5:33:11", "remaining_time": "5:59:53"}
188
+ {"current_steps": 1570, "total_steps": 3245, "loss": 0.0246, "lr": 6.14629285449852e-05, "epoch": 2.41631396691035, "percentage": 48.38, "elapsed_time": "5:34:41", "remaining_time": "5:57:04"}
189
+ {"current_steps": 1580, "total_steps": 3245, "loss": 0.0217, "lr": 6.093865910598688e-05, "epoch": 2.431704501731435, "percentage": 48.69, "elapsed_time": "5:36:11", "remaining_time": "5:54:16"}
190
+ {"current_steps": 1590, "total_steps": 3245, "loss": 0.0262, "lr": 6.0413123491385025e-05, "epoch": 2.44709503655252, "percentage": 49.0, "elapsed_time": "5:37:40", "remaining_time": "5:51:29"}
191
+ {"current_steps": 1600, "total_steps": 3245, "loss": 0.0189, "lr": 5.988638253316713e-05, "epoch": 2.4624855713736054, "percentage": 49.31, "elapsed_time": "5:39:10", "remaining_time": "5:48:42"}
192
+ {"current_steps": 1600, "total_steps": 3245, "eval_loss": 0.036341600120067596, "epoch": 2.4624855713736054, "percentage": 49.31, "elapsed_time": "5:42:17", "remaining_time": "5:51:54"}
193
+ {"current_steps": 1610, "total_steps": 3245, "loss": 0.0182, "lr": 5.935849720284206e-05, "epoch": 2.47787610619469, "percentage": 49.61, "elapsed_time": "5:43:50", "remaining_time": "5:49:10"}
194
+ {"current_steps": 1620, "total_steps": 3245, "loss": 0.0236, "lr": 5.8829528604382436e-05, "epoch": 2.4932666410157753, "percentage": 49.92, "elapsed_time": "5:45:19", "remaining_time": "5:46:23"}
195
+ {"current_steps": 1630, "total_steps": 3245, "loss": 0.0208, "lr": 5.829953796715176e-05, "epoch": 2.50865717583686, "percentage": 50.23, "elapsed_time": "5:46:49", "remaining_time": "5:43:37"}
196
+ {"current_steps": 1640, "total_steps": 3245, "loss": 0.0236, "lr": 5.7768586638816924e-05, "epoch": 2.5240477106579453, "percentage": 50.54, "elapsed_time": "5:48:18", "remaining_time": "5:40:52"}
197
+ {"current_steps": 1650, "total_steps": 3245, "loss": 0.0246, "lr": 5.723673607824705e-05, "epoch": 2.5394382454790305, "percentage": 50.85, "elapsed_time": "5:49:48", "remaining_time": "5:38:08"}
198
+ {"current_steps": 1650, "total_steps": 3245, "eval_loss": 0.0360361784696579, "epoch": 2.5394382454790305, "percentage": 50.85, "elapsed_time": "5:52:55", "remaining_time": "5:41:09"}
199
+ {"current_steps": 1660, "total_steps": 3245, "loss": 0.0202, "lr": 5.670404784839953e-05, "epoch": 2.5548287803001153, "percentage": 51.16, "elapsed_time": "5:54:29", "remaining_time": "5:38:28"}
200
+ {"current_steps": 1670, "total_steps": 3245, "loss": 0.0231, "lr": 5.6170583609193984e-05, "epoch": 2.5702193151212005, "percentage": 51.46, "elapsed_time": "5:55:58", "remaining_time": "5:35:43"}
201
+ {"current_steps": 1680, "total_steps": 3245, "loss": 0.0261, "lr": 5.56364051103749e-05, "epoch": 2.5856098499422853, "percentage": 51.77, "elapsed_time": "5:57:28", "remaining_time": "5:33:00"}
202
+ {"current_steps": 1690, "total_steps": 3245, "loss": 0.025, "lr": 5.5101574184364056e-05, "epoch": 2.6010003847633705, "percentage": 52.08, "elapsed_time": "5:58:58", "remaining_time": "5:30:17"}
203
+ {"current_steps": 1700, "total_steps": 3245, "loss": 0.0244, "lr": 5.4566152739103116e-05, "epoch": 2.6163909195844557, "percentage": 52.39, "elapsed_time": "6:00:27", "remaining_time": "5:27:35"}
204
+ {"current_steps": 1700, "total_steps": 3245, "eval_loss": 0.03538386896252632, "epoch": 2.6163909195844557, "percentage": 52.39, "elapsed_time": "6:03:34", "remaining_time": "5:30:25"}
205
+ {"current_steps": 1710, "total_steps": 3245, "loss": 0.0197, "lr": 5.403020275088786e-05, "epoch": 2.6317814544055405, "percentage": 52.7, "elapsed_time": "6:05:07", "remaining_time": "5:27:45"}
206
+ {"current_steps": 1720, "total_steps": 3245, "loss": 0.0327, "lr": 5.349378625719408e-05, "epoch": 2.6471719892266257, "percentage": 53.0, "elapsed_time": "6:06:37", "remaining_time": "5:25:03"}
207
+ {"current_steps": 1730, "total_steps": 3245, "loss": 0.0252, "lr": 5.2956965349496743e-05, "epoch": 2.6625625240477104, "percentage": 53.31, "elapsed_time": "6:08:07", "remaining_time": "5:22:22"}
208
+ {"current_steps": 1740, "total_steps": 3245, "loss": 0.018, "lr": 5.241980216608261e-05, "epoch": 2.6779530588687956, "percentage": 53.62, "elapsed_time": "6:09:36", "remaining_time": "5:19:41"}
209
+ {"current_steps": 1750, "total_steps": 3245, "loss": 0.0295, "lr": 5.188235888485773e-05, "epoch": 2.693343593689881, "percentage": 53.93, "elapsed_time": "6:11:06", "remaining_time": "5:17:02"}
210
+ {"current_steps": 1750, "total_steps": 3245, "eval_loss": 0.03553741052746773, "epoch": 2.693343593689881, "percentage": 53.93, "elapsed_time": "6:14:13", "remaining_time": "5:19:41"}
211
+ {"current_steps": 1760, "total_steps": 3245, "loss": 0.0174, "lr": 5.13446977161501e-05, "epoch": 2.7087341285109656, "percentage": 54.24, "elapsed_time": "6:15:46", "remaining_time": "5:17:03"}
212
+ {"current_steps": 1770, "total_steps": 3245, "loss": 0.0274, "lr": 5.0806880895508766e-05, "epoch": 2.724124663332051, "percentage": 54.55, "elapsed_time": "6:17:16", "remaining_time": "5:14:23"}
213
+ {"current_steps": 1780, "total_steps": 3245, "loss": 0.0286, "lr": 5.026897067649976e-05, "epoch": 2.7395151981531356, "percentage": 54.85, "elapsed_time": "6:18:46", "remaining_time": "5:11:44"}
214
+ {"current_steps": 1790, "total_steps": 3245, "loss": 0.0228, "lr": 4.973102932350026e-05, "epoch": 2.754905732974221, "percentage": 55.16, "elapsed_time": "6:20:16", "remaining_time": "5:09:06"}
215
+ {"current_steps": 1800, "total_steps": 3245, "loss": 0.0257, "lr": 4.9193119104491245e-05, "epoch": 2.770296267795306, "percentage": 55.47, "elapsed_time": "6:21:46", "remaining_time": "5:06:28"}
216
+ {"current_steps": 1800, "total_steps": 3245, "eval_loss": 0.03536887839436531, "epoch": 2.770296267795306, "percentage": 55.47, "elapsed_time": "6:24:52", "remaining_time": "5:08:58"}
217
+ {"current_steps": 1810, "total_steps": 3245, "loss": 0.0223, "lr": 4.86553022838499e-05, "epoch": 2.785686802616391, "percentage": 55.78, "elapsed_time": "6:26:25", "remaining_time": "5:06:22"}
218
+ {"current_steps": 1820, "total_steps": 3245, "loss": 0.0244, "lr": 4.8117641115142285e-05, "epoch": 2.801077337437476, "percentage": 56.09, "elapsed_time": "6:27:56", "remaining_time": "5:03:44"}
219
+ {"current_steps": 1830, "total_steps": 3245, "loss": 0.0207, "lr": 4.758019783391741e-05, "epoch": 2.8164678722585608, "percentage": 56.39, "elapsed_time": "6:29:25", "remaining_time": "5:01:07"}
220
+ {"current_steps": 1840, "total_steps": 3245, "loss": 0.0256, "lr": 4.704303465050327e-05, "epoch": 2.831858407079646, "percentage": 56.7, "elapsed_time": "6:30:55", "remaining_time": "4:58:30"}
221
+ {"current_steps": 1850, "total_steps": 3245, "loss": 0.0313, "lr": 4.6506213742805924e-05, "epoch": 2.847248941900731, "percentage": 57.01, "elapsed_time": "6:32:25", "remaining_time": "4:55:54"}
222
+ {"current_steps": 1850, "total_steps": 3245, "eval_loss": 0.03393126651644707, "epoch": 2.847248941900731, "percentage": 57.01, "elapsed_time": "6:35:31", "remaining_time": "4:58:14"}
223
+ {"current_steps": 1860, "total_steps": 3245, "loss": 0.0183, "lr": 4.5969797249112146e-05, "epoch": 2.862639476721816, "percentage": 57.32, "elapsed_time": "6:37:04", "remaining_time": "4:55:40"}
224
+ {"current_steps": 1870, "total_steps": 3245, "loss": 0.0286, "lr": 4.54338472608969e-05, "epoch": 2.878030011542901, "percentage": 57.63, "elapsed_time": "6:38:34", "remaining_time": "4:53:03"}
225
+ {"current_steps": 1880, "total_steps": 3245, "loss": 0.0176, "lr": 4.489842581563597e-05, "epoch": 2.893420546363986, "percentage": 57.94, "elapsed_time": "6:40:04", "remaining_time": "4:50:28"}
226
+ {"current_steps": 1890, "total_steps": 3245, "loss": 0.0193, "lr": 4.436359488962511e-05, "epoch": 2.908811081185071, "percentage": 58.24, "elapsed_time": "6:41:33", "remaining_time": "4:47:53"}
227
+ {"current_steps": 1900, "total_steps": 3245, "loss": 0.0208, "lr": 4.382941639080602e-05, "epoch": 2.9242016160061564, "percentage": 58.55, "elapsed_time": "6:43:03", "remaining_time": "4:45:19"}
228
+ {"current_steps": 1900, "total_steps": 3245, "eval_loss": 0.034816108644008636, "epoch": 2.9242016160061564, "percentage": 58.55, "elapsed_time": "6:46:10", "remaining_time": "4:47:31"}
229
+ {"current_steps": 1910, "total_steps": 3245, "loss": 0.0228, "lr": 4.3295952151600475e-05, "epoch": 2.939592150827241, "percentage": 58.86, "elapsed_time": "6:47:43", "remaining_time": "4:44:59"}
230
+ {"current_steps": 1920, "total_steps": 3245, "loss": 0.0201, "lr": 4.276326392175296e-05, "epoch": 2.9549826856483263, "percentage": 59.17, "elapsed_time": "6:49:13", "remaining_time": "4:42:24"}
231
+ {"current_steps": 1930, "total_steps": 3245, "loss": 0.017, "lr": 4.2231413361183095e-05, "epoch": 2.970373220469411, "percentage": 59.48, "elapsed_time": "6:50:42", "remaining_time": "4:39:50"}
232
+ {"current_steps": 1940, "total_steps": 3245, "loss": 0.0187, "lr": 4.1700462032848244e-05, "epoch": 2.9857637552904963, "percentage": 59.78, "elapsed_time": "6:52:12", "remaining_time": "4:37:16"}
233
+ {"current_steps": 1950, "total_steps": 3245, "loss": 0.0314, "lr": 4.117047139561758e-05, "epoch": 3.0011542901115815, "percentage": 60.09, "elapsed_time": "6:53:42", "remaining_time": "4:34:44"}
234
+ {"current_steps": 1950, "total_steps": 3245, "eval_loss": 0.034862760454416275, "epoch": 3.0011542901115815, "percentage": 60.09, "elapsed_time": "6:56:49", "remaining_time": "4:36:48"}
235
+ {"current_steps": 1960, "total_steps": 3245, "loss": 0.01, "lr": 4.0641502797157966e-05, "epoch": 3.0165448249326663, "percentage": 60.4, "elapsed_time": "6:58:22", "remaining_time": "4:34:17"}
236
+ {"current_steps": 1970, "total_steps": 3245, "loss": 0.012, "lr": 4.011361746683288e-05, "epoch": 3.0319353597537515, "percentage": 60.71, "elapsed_time": "6:59:51", "remaining_time": "4:31:43"}
237
+ {"current_steps": 1980, "total_steps": 3245, "loss": 0.0127, "lr": 3.958687650861499e-05, "epoch": 3.0473258945748363, "percentage": 61.02, "elapsed_time": "7:01:20", "remaining_time": "4:29:11"}
238
+ {"current_steps": 1990, "total_steps": 3245, "loss": 0.0078, "lr": 3.906134089401313e-05, "epoch": 3.0627164293959215, "percentage": 61.33, "elapsed_time": "7:02:50", "remaining_time": "4:26:39"}
239
+ {"current_steps": 2000, "total_steps": 3245, "loss": 0.0119, "lr": 3.853707145501482e-05, "epoch": 3.0781069642170067, "percentage": 61.63, "elapsed_time": "7:04:20", "remaining_time": "4:24:09"}
240
+ {"current_steps": 2000, "total_steps": 3245, "eval_loss": 0.0392003133893013, "epoch": 3.0781069642170067, "percentage": 61.63, "elapsed_time": "7:07:26", "remaining_time": "4:26:04"}
241
+ {"current_steps": 2010, "total_steps": 3245, "loss": 0.0087, "lr": 3.801412887704475e-05, "epoch": 3.0934974990380915, "percentage": 61.94, "elapsed_time": "7:09:02", "remaining_time": "4:23:36"}
242
+ {"current_steps": 2020, "total_steps": 3245, "loss": 0.0102, "lr": 3.749257369194029e-05, "epoch": 3.1088880338591767, "percentage": 62.25, "elapsed_time": "7:10:31", "remaining_time": "4:21:05"}
243
+ {"current_steps": 2030, "total_steps": 3245, "loss": 0.0162, "lr": 3.697246627094487e-05, "epoch": 3.1242785686802614, "percentage": 62.56, "elapsed_time": "7:12:01", "remaining_time": "4:18:34"}
244
+ {"current_steps": 2040, "total_steps": 3245, "loss": 0.0094, "lr": 3.6453866817719726e-05, "epoch": 3.1396691035013466, "percentage": 62.87, "elapsed_time": "7:13:31", "remaining_time": "4:16:04"}
245
+ {"current_steps": 2050, "total_steps": 3245, "loss": 0.0147, "lr": 3.593683536137533e-05, "epoch": 3.155059638322432, "percentage": 63.17, "elapsed_time": "7:15:01", "remaining_time": "4:13:35"}
246
+ {"current_steps": 2050, "total_steps": 3245, "eval_loss": 0.04251823201775551, "epoch": 3.155059638322432, "percentage": 63.17, "elapsed_time": "7:18:07", "remaining_time": "4:15:23"}
247
+ {"current_steps": 2060, "total_steps": 3245, "loss": 0.0085, "lr": 3.542143174952282e-05, "epoch": 3.1704501731435166, "percentage": 63.48, "elapsed_time": "7:19:40", "remaining_time": "4:12:55"}
248
+ {"current_steps": 2070, "total_steps": 3245, "loss": 0.0112, "lr": 3.490771564134643e-05, "epoch": 3.185840707964602, "percentage": 63.79, "elapsed_time": "7:21:09", "remaining_time": "4:10:25"}
249
+ {"current_steps": 2080, "total_steps": 3245, "loss": 0.0177, "lr": 3.4395746500697925e-05, "epoch": 3.2012312427856866, "percentage": 64.1, "elapsed_time": "7:22:39", "remaining_time": "4:07:56"}
250
+ {"current_steps": 2090, "total_steps": 3245, "loss": 0.0112, "lr": 3.388558358921343e-05, "epoch": 3.216621777606772, "percentage": 64.41, "elapsed_time": "7:24:09", "remaining_time": "4:05:27"}
251
+ {"current_steps": 2100, "total_steps": 3245, "loss": 0.011, "lr": 3.337728595945378e-05, "epoch": 3.232012312427857, "percentage": 64.71, "elapsed_time": "7:25:39", "remaining_time": "4:02:59"}
252
+ {"current_steps": 2100, "total_steps": 3245, "eval_loss": 0.040228795260190964, "epoch": 3.232012312427857, "percentage": 64.71, "elapsed_time": "7:28:46", "remaining_time": "4:04:41"}
253
+ {"current_steps": 2110, "total_steps": 3245, "loss": 0.0104, "lr": 3.287091244806907e-05, "epoch": 3.247402847248942, "percentage": 65.02, "elapsed_time": "7:30:18", "remaining_time": "4:02:13"}
254
+ {"current_steps": 2120, "total_steps": 3245, "loss": 0.0107, "lr": 3.2366521668988106e-05, "epoch": 3.262793382070027, "percentage": 65.33, "elapsed_time": "7:31:49", "remaining_time": "3:59:45"}
255
+ {"current_steps": 2130, "total_steps": 3245, "loss": 0.0168, "lr": 3.186417200663379e-05, "epoch": 3.2781839168911118, "percentage": 65.64, "elapsed_time": "7:33:18", "remaining_time": "3:57:17"}
256
+ {"current_steps": 2140, "total_steps": 3245, "loss": 0.0079, "lr": 3.136392160916495e-05, "epoch": 3.293574451712197, "percentage": 65.95, "elapsed_time": "7:34:48", "remaining_time": "3:54:50"}
257
+ {"current_steps": 2150, "total_steps": 3245, "loss": 0.012, "lr": 3.086582838174551e-05, "epoch": 3.308964986533282, "percentage": 66.26, "elapsed_time": "7:36:18", "remaining_time": "3:52:23"}
258
+ {"current_steps": 2150, "total_steps": 3245, "eval_loss": 0.04161189869046211, "epoch": 3.308964986533282, "percentage": 66.26, "elapsed_time": "7:39:24", "remaining_time": "3:53:58"}
259
+ {"current_steps": 2160, "total_steps": 3245, "loss": 0.0131, "lr": 3.036994997984194e-05, "epoch": 3.324355521354367, "percentage": 66.56, "elapsed_time": "7:40:58", "remaining_time": "3:51:33"}
260
+ {"current_steps": 2170, "total_steps": 3245, "loss": 0.0135, "lr": 2.9876343802549357e-05, "epoch": 3.339746056175452, "percentage": 66.87, "elapsed_time": "7:42:28", "remaining_time": "3:49:06"}
261
+ {"current_steps": 2180, "total_steps": 3245, "loss": 0.01, "lr": 2.938506698594755e-05, "epoch": 3.355136590996537, "percentage": 67.18, "elapsed_time": "7:43:58", "remaining_time": "3:46:39"}
262
+ {"current_steps": 2190, "total_steps": 3245, "loss": 0.0108, "lr": 2.8896176396487334e-05, "epoch": 3.370527125817622, "percentage": 67.49, "elapsed_time": "7:45:28", "remaining_time": "3:44:13"}
263
+ {"current_steps": 2200, "total_steps": 3245, "loss": 0.0205, "lr": 2.8409728624408067e-05, "epoch": 3.3859176606387074, "percentage": 67.8, "elapsed_time": "7:46:57", "remaining_time": "3:41:48"}
264
+ {"current_steps": 2200, "total_steps": 3245, "eval_loss": 0.03981276601552963, "epoch": 3.3859176606387074, "percentage": 67.8, "elapsed_time": "7:50:04", "remaining_time": "3:43:16"}
265
+ {"current_steps": 2210, "total_steps": 3245, "loss": 0.0139, "lr": 2.7925779977187215e-05, "epoch": 3.401308195459792, "percentage": 68.1, "elapsed_time": "7:51:37", "remaining_time": "3:40:52"}
266
+ {"current_steps": 2220, "total_steps": 3245, "loss": 0.0108, "lr": 2.7444386473022686e-05, "epoch": 3.4166987302808773, "percentage": 68.41, "elapsed_time": "7:53:06", "remaining_time": "3:38:26"}
267
+ {"current_steps": 2230, "total_steps": 3245, "loss": 0.0166, "lr": 2.696560383434854e-05, "epoch": 3.432089265101962, "percentage": 68.72, "elapsed_time": "7:54:35", "remaining_time": "3:36:00"}
268
+ {"current_steps": 2240, "total_steps": 3245, "loss": 0.0135, "lr": 2.6489487481384988e-05, "epoch": 3.4474797999230473, "percentage": 69.03, "elapsed_time": "7:56:05", "remaining_time": "3:33:36"}
269
+ {"current_steps": 2250, "total_steps": 3245, "loss": 0.0127, "lr": 2.601609252572339e-05, "epoch": 3.4628703347441325, "percentage": 69.34, "elapsed_time": "7:57:35", "remaining_time": "3:31:11"}
270
+ {"current_steps": 2250, "total_steps": 3245, "eval_loss": 0.039891570806503296, "epoch": 3.4628703347441325, "percentage": 69.34, "elapsed_time": "8:00:41", "remaining_time": "3:32:34"}
271
+ {"current_steps": 2260, "total_steps": 3245, "loss": 0.0073, "lr": 2.554547376394692e-05, "epoch": 3.4782608695652173, "percentage": 69.65, "elapsed_time": "8:02:15", "remaining_time": "3:30:11"}
272
+ {"current_steps": 2270, "total_steps": 3245, "loss": 0.0108, "lr": 2.5077685671287808e-05, "epoch": 3.4936514043863025, "percentage": 69.95, "elapsed_time": "8:03:44", "remaining_time": "3:27:46"}
273
+ {"current_steps": 2280, "total_steps": 3245, "loss": 0.0148, "lr": 2.4612782395321593e-05, "epoch": 3.5090419392073873, "percentage": 70.26, "elapsed_time": "8:05:13", "remaining_time": "3:25:22"}
274
+ {"current_steps": 2290, "total_steps": 3245, "loss": 0.0086, "lr": 2.4150817749699496e-05, "epoch": 3.5244324740284725, "percentage": 70.57, "elapsed_time": "8:06:43", "remaining_time": "3:22:58"}
275
+ {"current_steps": 2300, "total_steps": 3245, "loss": 0.0141, "lr": 2.3691845207919357e-05, "epoch": 3.5398230088495577, "percentage": 70.88, "elapsed_time": "8:08:13", "remaining_time": "3:20:35"}
276
+ {"current_steps": 2300, "total_steps": 3245, "eval_loss": 0.0418756864964962, "epoch": 3.5398230088495577, "percentage": 70.88, "elapsed_time": "8:11:19", "remaining_time": "3:21:52"}
277
+ {"current_steps": 2310, "total_steps": 3245, "loss": 0.0127, "lr": 2.3235917897135934e-05, "epoch": 3.5552135436706425, "percentage": 71.19, "elapsed_time": "8:12:53", "remaining_time": "3:19:30"}
278
+ {"current_steps": 2320, "total_steps": 3245, "loss": 0.0145, "lr": 2.2783088592011303e-05, "epoch": 3.5706040784917277, "percentage": 71.49, "elapsed_time": "8:14:23", "remaining_time": "3:17:06"}
279
+ {"current_steps": 2330, "total_steps": 3245, "loss": 0.0085, "lr": 2.233340970860608e-05, "epoch": 3.5859946133128124, "percentage": 71.8, "elapsed_time": "8:15:53", "remaining_time": "3:14:44"}
280
+ {"current_steps": 2340, "total_steps": 3245, "loss": 0.0151, "lr": 2.1886933298312125e-05, "epoch": 3.6013851481338977, "percentage": 72.11, "elapsed_time": "8:17:23", "remaining_time": "3:12:21"}
281
+ {"current_steps": 2350, "total_steps": 3245, "loss": 0.0081, "lr": 2.1443711041827503e-05, "epoch": 3.616775682954983, "percentage": 72.42, "elapsed_time": "8:18:52", "remaining_time": "3:09:59"}
282
+ {"current_steps": 2350, "total_steps": 3245, "eval_loss": 0.043476805090904236, "epoch": 3.616775682954983, "percentage": 72.42, "elapsed_time": "8:21:58", "remaining_time": "3:11:10"}
283
+ {"current_steps": 2360, "total_steps": 3245, "loss": 0.0159, "lr": 2.1003794243174252e-05, "epoch": 3.6321662177760676, "percentage": 72.73, "elapsed_time": "8:23:32", "remaining_time": "3:08:49"}
284
+ {"current_steps": 2370, "total_steps": 3245, "loss": 0.0094, "lr": 2.0567233823759886e-05, "epoch": 3.647556752597153, "percentage": 73.04, "elapsed_time": "8:25:01", "remaining_time": "3:06:27"}
285
+ {"current_steps": 2380, "total_steps": 3245, "loss": 0.013, "lr": 2.0134080316483113e-05, "epoch": 3.6629472874182376, "percentage": 73.34, "elapsed_time": "8:26:31", "remaining_time": "3:04:05"}
286
+ {"current_steps": 2390, "total_steps": 3245, "loss": 0.0153, "lr": 1.970438385988452e-05, "epoch": 3.678337822239323, "percentage": 73.65, "elapsed_time": "8:28:01", "remaining_time": "3:01:44"}
287
+ {"current_steps": 2400, "total_steps": 3245, "loss": 0.0132, "lr": 1.927819419234292e-05, "epoch": 3.693728357060408, "percentage": 73.96, "elapsed_time": "8:29:31", "remaining_time": "2:59:23"}
288
+ {"current_steps": 2400, "total_steps": 3245, "eval_loss": 0.04118052124977112, "epoch": 3.693728357060408, "percentage": 73.96, "elapsed_time": "8:32:37", "remaining_time": "3:00:29"}
289
+ {"current_steps": 2410, "total_steps": 3245, "loss": 0.011, "lr": 1.885556064631801e-05, "epoch": 3.709118891881493, "percentage": 74.27, "elapsed_time": "8:34:10", "remaining_time": "2:58:08"}
290
+ {"current_steps": 2420, "total_steps": 3245, "loss": 0.0091, "lr": 1.843653214264003e-05, "epoch": 3.724509426702578, "percentage": 74.58, "elapsed_time": "8:35:40", "remaining_time": "2:55:47"}
291
+ {"current_steps": 2430, "total_steps": 3245, "loss": 0.0147, "lr": 1.8021157184847087e-05, "epoch": 3.7398999615236628, "percentage": 74.88, "elapsed_time": "8:37:09", "remaining_time": "2:53:27"}
292
+ {"current_steps": 2440, "total_steps": 3245, "loss": 0.0086, "lr": 1.7609483853570668e-05, "epoch": 3.755290496344748, "percentage": 75.19, "elapsed_time": "8:38:39", "remaining_time": "2:51:06"}
293
+ {"current_steps": 2450, "total_steps": 3245, "loss": 0.0111, "lr": 1.720155980097034e-05, "epoch": 3.770681031165833, "percentage": 75.5, "elapsed_time": "8:40:08", "remaining_time": "2:48:46"}
294
+ {"current_steps": 2450, "total_steps": 3245, "eval_loss": 0.04333437979221344, "epoch": 3.770681031165833, "percentage": 75.5, "elapsed_time": "8:43:14", "remaining_time": "2:49:47"}
295
+ {"current_steps": 2460, "total_steps": 3245, "loss": 0.0113, "lr": 1.6797432245217736e-05, "epoch": 3.786071565986918, "percentage": 75.81, "elapsed_time": "8:44:46", "remaining_time": "2:47:27"}
296
+ {"current_steps": 2470, "total_steps": 3245, "loss": 0.0076, "lr": 1.6397147965031072e-05, "epoch": 3.801462100808003, "percentage": 76.12, "elapsed_time": "8:46:15", "remaining_time": "2:45:07"}
297
+ {"current_steps": 2480, "total_steps": 3245, "loss": 0.012, "lr": 1.600075329426033e-05, "epoch": 3.816852635629088, "percentage": 76.43, "elapsed_time": "8:47:44", "remaining_time": "2:42:47"}
298
+ {"current_steps": 2490, "total_steps": 3245, "loss": 0.0137, "lr": 1.560829411652403e-05, "epoch": 3.832243170450173, "percentage": 76.73, "elapsed_time": "8:49:13", "remaining_time": "2:40:28"}
299
+ {"current_steps": 2500, "total_steps": 3245, "loss": 0.0069, "lr": 1.521981585989809e-05, "epoch": 3.8476337052712584, "percentage": 77.04, "elapsed_time": "8:50:42", "remaining_time": "2:38:09"}
300
+ {"current_steps": 2500, "total_steps": 3245, "eval_loss": 0.044614341109991074, "epoch": 3.8476337052712584, "percentage": 77.04, "elapsed_time": "8:53:47", "remaining_time": "2:39:04"}
301
+ {"current_steps": 2510, "total_steps": 3245, "loss": 0.0141, "lr": 1.4835363491657412e-05, "epoch": 3.863024240092343, "percentage": 77.35, "elapsed_time": "8:55:19", "remaining_time": "2:36:45"}
302
+ {"current_steps": 2520, "total_steps": 3245, "loss": 0.0062, "lr": 1.4454981513070791e-05, "epoch": 3.8784147749134283, "percentage": 77.66, "elapsed_time": "8:56:47", "remaining_time": "2:34:26"}
303
+ {"current_steps": 2530, "total_steps": 3245, "loss": 0.0093, "lr": 1.4078713954249873e-05, "epoch": 3.893805309734513, "percentage": 77.97, "elapsed_time": "8:58:16", "remaining_time": "2:32:07"}
304
+ {"current_steps": 2540, "total_steps": 3245, "loss": 0.0059, "lr": 1.3706604369052434e-05, "epoch": 3.9091958445555983, "percentage": 78.27, "elapsed_time": "8:59:45", "remaining_time": "2:29:48"}
305
+ {"current_steps": 2550, "total_steps": 3245, "loss": 0.0135, "lr": 1.3338695830041047e-05, "epoch": 3.9245863793766835, "percentage": 78.58, "elapsed_time": "9:01:14", "remaining_time": "2:27:30"}
306
+ {"current_steps": 2550, "total_steps": 3245, "eval_loss": 0.04540552943944931, "epoch": 3.9245863793766835, "percentage": 78.58, "elapsed_time": "9:04:17", "remaining_time": "2:28:20"}
307
+ {"current_steps": 2560, "total_steps": 3245, "loss": 0.0127, "lr": 1.2975030923497262e-05, "epoch": 3.9399769141977683, "percentage": 78.89, "elapsed_time": "9:05:50", "remaining_time": "2:26:03"}
308
+ {"current_steps": 2570, "total_steps": 3245, "loss": 0.008, "lr": 1.2615651744492151e-05, "epoch": 3.9553674490188535, "percentage": 79.2, "elapsed_time": "9:07:18", "remaining_time": "2:23:44"}
309
+ {"current_steps": 2580, "total_steps": 3245, "loss": 0.014, "lr": 1.2260599892013719e-05, "epoch": 3.9707579838399383, "percentage": 79.51, "elapsed_time": "9:08:46", "remaining_time": "2:21:26"}
310
+ {"current_steps": 2590, "total_steps": 3245, "loss": 0.009, "lr": 1.1909916464151715e-05, "epoch": 3.9861485186610235, "percentage": 79.82, "elapsed_time": "9:10:15", "remaining_time": "2:19:09"}
311
+ {"current_steps": 2600, "total_steps": 3245, "loss": 0.0093, "lr": 1.1563642053340406e-05, "epoch": 4.001539053482109, "percentage": 80.12, "elapsed_time": "9:11:43", "remaining_time": "2:16:52"}
312
+ {"current_steps": 2600, "total_steps": 3245, "eval_loss": 0.04523477330803871, "epoch": 4.001539053482109, "percentage": 80.12, "elapsed_time": "9:14:46", "remaining_time": "2:17:37"}
313
+ {"current_steps": 2610, "total_steps": 3245, "loss": 0.0061, "lr": 1.1221816741659964e-05, "epoch": 4.016929588303194, "percentage": 80.43, "elapsed_time": "9:16:17", "remaining_time": "2:15:20"}
314
+ {"current_steps": 2620, "total_steps": 3245, "loss": 0.0027, "lr": 1.0884480096196803e-05, "epoch": 4.032320123124278, "percentage": 80.74, "elapsed_time": "9:17:45", "remaining_time": "2:13:03"}
315
+ {"current_steps": 2630, "total_steps": 3245, "loss": 0.0032, "lr": 1.0551671164463666e-05, "epoch": 4.047710657945363, "percentage": 81.05, "elapsed_time": "9:19:12", "remaining_time": "2:10:45"}
316
+ {"current_steps": 2640, "total_steps": 3245, "loss": 0.0058, "lr": 1.0223428469879736e-05, "epoch": 4.063101192766449, "percentage": 81.36, "elapsed_time": "9:20:40", "remaining_time": "2:08:29"}
317
+ {"current_steps": 2650, "total_steps": 3245, "loss": 0.0024, "lr": 9.899790007311455e-06, "epoch": 4.078491727587534, "percentage": 81.66, "elapsed_time": "9:22:07", "remaining_time": "2:06:12"}
318
+ {"current_steps": 2650, "total_steps": 3245, "eval_loss": 0.04883251711726189, "epoch": 4.078491727587534, "percentage": 81.66, "elapsed_time": "9:25:07", "remaining_time": "2:06:53"}
319
+ {"current_steps": 2660, "total_steps": 3245, "loss": 0.0065, "lr": 9.580793238674573e-06, "epoch": 4.093882262408619, "percentage": 81.97, "elapsed_time": "9:26:38", "remaining_time": "2:04:37"}
320
+ {"current_steps": 2670, "total_steps": 3245, "loss": 0.0035, "lr": 9.266475088597781e-06, "epoch": 4.109272797229703, "percentage": 82.28, "elapsed_time": "9:28:05", "remaining_time": "2:02:20"}
321
+ {"current_steps": 2680, "total_steps": 3245, "loss": 0.0035, "lr": 8.956871940148681e-06, "epoch": 4.124663332050789, "percentage": 82.59, "elapsed_time": "9:29:31", "remaining_time": "2:00:04"}
322
+ {"current_steps": 2690, "total_steps": 3245, "loss": 0.0042, "lr": 8.65201963062225e-06, "epoch": 4.140053866871874, "percentage": 82.9, "elapsed_time": "9:30:57", "remaining_time": "1:57:48"}
323
+ {"current_steps": 2700, "total_steps": 3245, "loss": 0.0082, "lr": 8.351953447392674e-06, "epoch": 4.155444401692959, "percentage": 83.2, "elapsed_time": "9:32:24", "remaining_time": "1:55:32"}
324
+ {"current_steps": 2700, "total_steps": 3245, "eval_loss": 0.05498456954956055, "epoch": 4.155444401692959, "percentage": 83.2, "elapsed_time": "9:35:22", "remaining_time": "1:56:08"}
325
+ {"current_steps": 2710, "total_steps": 3245, "loss": 0.0058, "lr": 8.056708123828738e-06, "epoch": 4.170834936514044, "percentage": 83.51, "elapsed_time": "9:36:52", "remaining_time": "1:53:53"}
326
+ {"current_steps": 2720, "total_steps": 3245, "loss": 0.0107, "lr": 7.76631783527334e-06, "epoch": 4.186225471335129, "percentage": 83.82, "elapsed_time": "9:38:18", "remaining_time": "1:51:37"}
327
+ {"current_steps": 2730, "total_steps": 3245, "loss": 0.0059, "lr": 7.4808161950876145e-06, "epoch": 4.201616006156214, "percentage": 84.13, "elapsed_time": "9:39:44", "remaining_time": "1:49:21"}
328
+ {"current_steps": 2740, "total_steps": 3245, "loss": 0.0066, "lr": 7.200236250760111e-06, "epoch": 4.217006540977299, "percentage": 84.44, "elapsed_time": "9:41:10", "remaining_time": "1:47:06"}
329
+ {"current_steps": 2750, "total_steps": 3245, "loss": 0.004, "lr": 6.924610480081478e-06, "epoch": 4.232397075798384, "percentage": 84.75, "elapsed_time": "9:42:36", "remaining_time": "1:44:52"}
330
+ {"current_steps": 2750, "total_steps": 3245, "eval_loss": 0.05399877950549126, "epoch": 4.232397075798384, "percentage": 84.75, "elapsed_time": "9:45:32", "remaining_time": "1:45:23"}
331
+ {"current_steps": 2760, "total_steps": 3245, "loss": 0.002, "lr": 6.6539707873850774e-06, "epoch": 4.247787610619469, "percentage": 85.05, "elapsed_time": "9:47:02", "remaining_time": "1:43:09"}
332
+ {"current_steps": 2770, "total_steps": 3245, "loss": 0.0034, "lr": 6.3883484998539525e-06, "epoch": 4.263178145440554, "percentage": 85.36, "elapsed_time": "9:48:27", "remaining_time": "1:40:54"}
333
+ {"current_steps": 2780, "total_steps": 3245, "loss": 0.0029, "lr": 6.127774363894667e-06, "epoch": 4.278568680261639, "percentage": 85.67, "elapsed_time": "9:49:52", "remaining_time": "1:38:39"}
334
+ {"current_steps": 2790, "total_steps": 3245, "loss": 0.0036, "lr": 5.872278541578352e-06, "epoch": 4.293959215082724, "percentage": 85.98, "elapsed_time": "9:51:17", "remaining_time": "1:36:25"}
335
+ {"current_steps": 2800, "total_steps": 3245, "loss": 0.0044, "lr": 5.6218906071493275e-06, "epoch": 4.309349749903809, "percentage": 86.29, "elapsed_time": "9:52:42", "remaining_time": "1:34:11"}
336
+ {"current_steps": 2800, "total_steps": 3245, "eval_loss": 0.0570867583155632, "epoch": 4.309349749903809, "percentage": 86.29, "elapsed_time": "9:55:39", "remaining_time": "1:34:39"}
337
+ {"current_steps": 2810, "total_steps": 3245, "loss": 0.0045, "lr": 5.376639543601858e-06, "epoch": 4.324740284724895, "percentage": 86.59, "elapsed_time": "9:57:07", "remaining_time": "1:32:26"}
338
+ {"current_steps": 2820, "total_steps": 3245, "loss": 0.0031, "lr": 5.136553739325256e-06, "epoch": 4.340130819545979, "percentage": 86.9, "elapsed_time": "9:58:31", "remaining_time": "1:30:12"}
339
+ {"current_steps": 2830, "total_steps": 3245, "loss": 0.0026, "lr": 4.901660984817908e-06, "epoch": 4.355521354367064, "percentage": 87.21, "elapsed_time": "9:59:55", "remaining_time": "1:27:58"}
340
+ {"current_steps": 2840, "total_steps": 3245, "loss": 0.0035, "lr": 4.671988469470434e-06, "epoch": 4.370911889188149, "percentage": 87.52, "elapsed_time": "10:01:18", "remaining_time": "1:25:44"}
341
+ {"current_steps": 2850, "total_steps": 3245, "loss": 0.0027, "lr": 4.447562778418435e-06, "epoch": 4.3863024240092345, "percentage": 87.83, "elapsed_time": "10:02:42", "remaining_time": "1:23:32"}
342
+ {"current_steps": 2850, "total_steps": 3245, "eval_loss": 0.059105079621076584, "epoch": 4.3863024240092345, "percentage": 87.83, "elapsed_time": "10:05:37", "remaining_time": "1:23:56"}
343
+ {"current_steps": 2860, "total_steps": 3245, "loss": 0.0024, "lr": 4.228409889465218e-06, "epoch": 4.40169295883032, "percentage": 88.14, "elapsed_time": "10:07:05", "remaining_time": "1:21:43"}
344
+ {"current_steps": 2870, "total_steps": 3245, "loss": 0.0018, "lr": 4.014555170074824e-06, "epoch": 4.417083493651404, "percentage": 88.44, "elapsed_time": "10:08:30", "remaining_time": "1:19:30"}
345
+ {"current_steps": 2880, "total_steps": 3245, "loss": 0.0095, "lr": 3.8060233744356633e-06, "epoch": 4.432474028472489, "percentage": 88.75, "elapsed_time": "10:09:54", "remaining_time": "1:17:17"}
346
+ {"current_steps": 2890, "total_steps": 3245, "loss": 0.0033, "lr": 3.602838640595152e-06, "epoch": 4.4478645632935745, "percentage": 89.06, "elapsed_time": "10:11:19", "remaining_time": "1:15:05"}
347
+ {"current_steps": 2900, "total_steps": 3245, "loss": 0.0044, "lr": 3.4050244876656866e-06, "epoch": 4.46325509811466, "percentage": 89.37, "elapsed_time": "10:12:44", "remaining_time": "1:12:53"}
348
+ {"current_steps": 2900, "total_steps": 3245, "eval_loss": 0.059850871562957764, "epoch": 4.46325509811466, "percentage": 89.37, "elapsed_time": "10:15:39", "remaining_time": "1:13:14"}
349
+ {"current_steps": 2910, "total_steps": 3245, "loss": 0.0113, "lr": 3.2126038131022552e-06, "epoch": 4.478645632935745, "percentage": 89.68, "elapsed_time": "10:17:07", "remaining_time": "1:11:02"}
350
+ {"current_steps": 2920, "total_steps": 3245, "loss": 0.0043, "lr": 3.025598890051995e-06, "epoch": 4.494036167756829, "percentage": 89.98, "elapsed_time": "10:18:32", "remaining_time": "1:08:50"}
351
+ {"current_steps": 2930, "total_steps": 3245, "loss": 0.0029, "lr": 2.8440313647760288e-06, "epoch": 4.5094267025779144, "percentage": 90.29, "elapsed_time": "10:19:57", "remaining_time": "1:06:39"}
352
+ {"current_steps": 2940, "total_steps": 3245, "loss": 0.0065, "lr": 2.6679222541438397e-06, "epoch": 4.524817237399, "percentage": 90.6, "elapsed_time": "10:21:22", "remaining_time": "1:04:27"}
353
+ {"current_steps": 2950, "total_steps": 3245, "loss": 0.0017, "lr": 2.4972919432005582e-06, "epoch": 4.540207772220085, "percentage": 90.91, "elapsed_time": "10:22:46", "remaining_time": "1:02:16"}
354
+ {"current_steps": 2950, "total_steps": 3245, "eval_loss": 0.05833715572953224, "epoch": 4.540207772220085, "percentage": 90.91, "elapsed_time": "10:25:41", "remaining_time": "1:02:34"}
355
+ {"current_steps": 2960, "total_steps": 3245, "loss": 0.0027, "lr": 2.3321601828073135e-06, "epoch": 4.555598307041169, "percentage": 91.22, "elapsed_time": "10:27:09", "remaining_time": "1:00:23"}
356
+ {"current_steps": 2970, "total_steps": 3245, "loss": 0.0074, "lr": 2.1725460873550317e-06, "epoch": 4.570988841862254, "percentage": 91.53, "elapsed_time": "10:28:34", "remaining_time": "0:58:12"}
357
+ {"current_steps": 2980, "total_steps": 3245, "loss": 0.0054, "lr": 2.0184681325519096e-06, "epoch": 4.58637937668334, "percentage": 91.83, "elapsed_time": "10:29:58", "remaining_time": "0:56:01"}
358
+ {"current_steps": 2990, "total_steps": 3245, "loss": 0.0055, "lr": 1.869944153284786e-06, "epoch": 4.601769911504425, "percentage": 92.14, "elapsed_time": "10:31:23", "remaining_time": "0:53:50"}
359
+ {"current_steps": 3000, "total_steps": 3245, "loss": 0.0034, "lr": 1.7269913415547456e-06, "epoch": 4.61716044632551, "percentage": 92.45, "elapsed_time": "10:32:48", "remaining_time": "0:51:40"}
360
+ {"current_steps": 3000, "total_steps": 3245, "eval_loss": 0.05813543125987053, "epoch": 4.61716044632551, "percentage": 92.45, "elapsed_time": "10:35:42", "remaining_time": "0:51:55"}
361
+ {"current_steps": 3010, "total_steps": 3245, "loss": 0.0026, "lr": 1.589626244487069e-06, "epoch": 4.632550981146595, "percentage": 92.76, "elapsed_time": "10:37:11", "remaining_time": "0:49:44"}
362
+ {"current_steps": 3020, "total_steps": 3245, "loss": 0.0069, "lr": 1.4578647624158726e-06, "epoch": 4.64794151596768, "percentage": 93.07, "elapsed_time": "10:38:35", "remaining_time": "0:47:34"}
363
+ {"current_steps": 3030, "total_steps": 3245, "loss": 0.0059, "lr": 1.3317221470436293e-06, "epoch": 4.663332050788765, "percentage": 93.37, "elapsed_time": "10:40:00", "remaining_time": "0:45:24"}
364
+ {"current_steps": 3040, "total_steps": 3245, "loss": 0.0091, "lr": 1.2112129996757315e-06, "epoch": 4.67872258560985, "percentage": 93.68, "elapsed_time": "10:41:25", "remaining_time": "0:43:15"}
365
+ {"current_steps": 3050, "total_steps": 3245, "loss": 0.0048, "lr": 1.0963512695303546e-06, "epoch": 4.694113120430935, "percentage": 93.99, "elapsed_time": "10:42:49", "remaining_time": "0:41:05"}
366
+ {"current_steps": 3050, "total_steps": 3245, "eval_loss": 0.05782487243413925, "epoch": 4.694113120430935, "percentage": 93.99, "elapsed_time": "10:45:44", "remaining_time": "0:41:17"}
367
+ {"current_steps": 3060, "total_steps": 3245, "loss": 0.0032, "lr": 9.871502521237975e-07, "epoch": 4.7095036552520195, "percentage": 94.3, "elapsed_time": "10:47:21", "remaining_time": "0:39:08"}
368
+ {"current_steps": 3070, "total_steps": 3245, "loss": 0.0033, "lr": 8.83622587731514e-07, "epoch": 4.724894190073105, "percentage": 94.61, "elapsed_time": "10:48:46", "remaining_time": "0:36:58"}
369
+ {"current_steps": 3080, "total_steps": 3245, "loss": 0.0107, "lr": 7.857802599249564e-07, "epoch": 4.74028472489419, "percentage": 94.92, "elapsed_time": "10:50:10", "remaining_time": "0:34:49"}
370
+ {"current_steps": 3090, "total_steps": 3245, "loss": 0.0038, "lr": 6.936345941844335e-07, "epoch": 4.755675259715275, "percentage": 95.22, "elapsed_time": "10:51:34", "remaining_time": "0:32:41"}
371
+ {"current_steps": 3100, "total_steps": 3245, "loss": 0.0051, "lr": 6.071962565881939e-07, "epoch": 4.77106579453636, "percentage": 95.53, "elapsed_time": "10:52:59", "remaining_time": "0:30:32"}
372
+ {"current_steps": 3100, "total_steps": 3245, "eval_loss": 0.0577433742582798, "epoch": 4.77106579453636, "percentage": 95.53, "elapsed_time": "10:55:53", "remaining_time": "0:30:40"}
373
+ {"current_steps": 3110, "total_steps": 3245, "loss": 0.0095, "lr": 5.264752525777961e-07, "epoch": 4.786456329357446, "percentage": 95.84, "elapsed_time": "10:57:22", "remaining_time": "0:28:32"}
374
+ {"current_steps": 3120, "total_steps": 3245, "loss": 0.002, "lr": 4.5148092579991863e-07, "epoch": 4.80184686417853, "percentage": 96.15, "elapsed_time": "10:58:46", "remaining_time": "0:26:23"}
375
+ {"current_steps": 3130, "total_steps": 3245, "loss": 0.006, "lr": 3.822219570248531e-07, "epoch": 4.817237398999615, "percentage": 96.46, "elapsed_time": "11:00:10", "remaining_time": "0:24:15"}
376
+ {"current_steps": 3140, "total_steps": 3245, "loss": 0.0026, "lr": 3.187063631416742e-07, "epoch": 4.8326279338207, "percentage": 96.76, "elapsed_time": "11:01:35", "remaining_time": "0:22:07"}
377
+ {"current_steps": 3150, "total_steps": 3245, "loss": 0.0053, "lr": 2.6094149623024365e-07, "epoch": 4.8480184686417855, "percentage": 97.07, "elapsed_time": "11:02:59", "remaining_time": "0:19:59"}
378
+ {"current_steps": 3150, "total_steps": 3245, "eval_loss": 0.057770997285842896, "epoch": 4.8480184686417855, "percentage": 97.07, "elapsed_time": "11:05:53", "remaining_time": "0:20:04"}
379
+ {"current_steps": 3160, "total_steps": 3245, "loss": 0.0058, "lr": 2.0893404271022376e-07, "epoch": 4.86340900346287, "percentage": 97.38, "elapsed_time": "11:07:21", "remaining_time": "0:17:57"}
380
+ {"current_steps": 3170, "total_steps": 3245, "loss": 0.0041, "lr": 1.626900225670691e-07, "epoch": 4.878799538283955, "percentage": 97.69, "elapsed_time": "11:08:46", "remaining_time": "0:15:49"}
381
+ {"current_steps": 3180, "total_steps": 3245, "loss": 0.0024, "lr": 1.2221478865524493e-07, "epoch": 4.89419007310504, "percentage": 98.0, "elapsed_time": "11:10:10", "remaining_time": "0:13:41"}
382
+ {"current_steps": 3190, "total_steps": 3245, "loss": 0.0053, "lr": 8.751302607857836e-08, "epoch": 4.9095806079261255, "percentage": 98.31, "elapsed_time": "11:11:35", "remaining_time": "0:11:34"}
383
+ {"current_steps": 3200, "total_steps": 3245, "loss": 0.0033, "lr": 5.8588751647975506e-08, "epoch": 4.924971142747211, "percentage": 98.61, "elapsed_time": "11:13:00", "remaining_time": "0:09:27"}
384
+ {"current_steps": 3200, "total_steps": 3245, "eval_loss": 0.057740841060876846, "epoch": 4.924971142747211, "percentage": 98.61, "elapsed_time": "11:15:54", "remaining_time": "0:09:30"}
385
+ {"current_steps": 3210, "total_steps": 3245, "loss": 0.0061, "lr": 3.544531341646007e-08, "epoch": 4.940361677568296, "percentage": 98.92, "elapsed_time": "11:17:22", "remaining_time": "0:07:23"}
386
+ {"current_steps": 3220, "total_steps": 3245, "loss": 0.0039, "lr": 1.808539029161116e-08, "epoch": 4.95575221238938, "percentage": 99.23, "elapsed_time": "11:18:46", "remaining_time": "0:05:16"}
387
+ {"current_steps": 3230, "total_steps": 3245, "loss": 0.0058, "lr": 6.510991725500182e-09, "epoch": 4.9711427472104655, "percentage": 99.54, "elapsed_time": "11:20:10", "remaining_time": "0:03:09"}
388
+ {"current_steps": 3240, "total_steps": 3245, "loss": 0.0044, "lr": 7.234574820769169e-10, "epoch": 4.986533282031551, "percentage": 99.85, "elapsed_time": "11:21:34", "remaining_time": "0:01:03"}
389
+ {"current_steps": 3245, "total_steps": 3245, "epoch": 4.994228549442093, "percentage": 100.0, "elapsed_time": "11:22:22", "remaining_time": "0:00:00"}
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold1/trainer_state.json ADDED
@@ -0,0 +1,2822 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.03381282836198807,
3
+ "best_model_checkpoint": "saves/psy-course/Llama-3.1-8B-Instruct/train/fold1/checkpoint-1350",
4
+ "epoch": 4.994228549442093,
5
+ "eval_steps": 50,
6
+ "global_step": 3245,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.015390534821085032,
13
+ "grad_norm": 5.0106048583984375,
14
+ "learning_rate": 3.0769230769230774e-06,
15
+ "loss": 1.6199,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.030781069642170065,
20
+ "grad_norm": 5.837756633758545,
21
+ "learning_rate": 6.153846153846155e-06,
22
+ "loss": 1.5918,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.0461716044632551,
27
+ "grad_norm": 7.694819927215576,
28
+ "learning_rate": 9.230769230769232e-06,
29
+ "loss": 1.3184,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.06156213928434013,
34
+ "grad_norm": 2.596924066543579,
35
+ "learning_rate": 1.230769230769231e-05,
36
+ "loss": 0.8797,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.07695267410542517,
41
+ "grad_norm": 1.5033406019210815,
42
+ "learning_rate": 1.5384615384615387e-05,
43
+ "loss": 0.5562,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.07695267410542517,
48
+ "eval_loss": 0.40699678659439087,
49
+ "eval_runtime": 185.4981,
50
+ "eval_samples_per_second": 6.232,
51
+ "eval_steps_per_second": 6.232,
52
+ "step": 50
53
+ },
54
+ {
55
+ "epoch": 0.0923432089265102,
56
+ "grad_norm": 0.904315173625946,
57
+ "learning_rate": 1.8461538461538465e-05,
58
+ "loss": 0.3409,
59
+ "step": 60
60
+ },
61
+ {
62
+ "epoch": 0.10773374374759523,
63
+ "grad_norm": 1.0325497388839722,
64
+ "learning_rate": 2.1538461538461542e-05,
65
+ "loss": 0.2488,
66
+ "step": 70
67
+ },
68
+ {
69
+ "epoch": 0.12312427856868026,
70
+ "grad_norm": 0.5230876803398132,
71
+ "learning_rate": 2.461538461538462e-05,
72
+ "loss": 0.1659,
73
+ "step": 80
74
+ },
75
+ {
76
+ "epoch": 0.1385148133897653,
77
+ "grad_norm": 0.9011468887329102,
78
+ "learning_rate": 2.7692307692307694e-05,
79
+ "loss": 0.167,
80
+ "step": 90
81
+ },
82
+ {
83
+ "epoch": 0.15390534821085033,
84
+ "grad_norm": 0.6379432678222656,
85
+ "learning_rate": 3.0769230769230774e-05,
86
+ "loss": 0.1226,
87
+ "step": 100
88
+ },
89
+ {
90
+ "epoch": 0.15390534821085033,
91
+ "eval_loss": 0.09147929400205612,
92
+ "eval_runtime": 188.019,
93
+ "eval_samples_per_second": 6.148,
94
+ "eval_steps_per_second": 6.148,
95
+ "step": 100
96
+ },
97
+ {
98
+ "epoch": 0.16929588303193535,
99
+ "grad_norm": 0.8800907731056213,
100
+ "learning_rate": 3.384615384615385e-05,
101
+ "loss": 0.0863,
102
+ "step": 110
103
+ },
104
+ {
105
+ "epoch": 0.1846864178530204,
106
+ "grad_norm": 0.41934528946876526,
107
+ "learning_rate": 3.692307692307693e-05,
108
+ "loss": 0.0894,
109
+ "step": 120
110
+ },
111
+ {
112
+ "epoch": 0.2000769526741054,
113
+ "grad_norm": 0.8273314237594604,
114
+ "learning_rate": 4e-05,
115
+ "loss": 0.0754,
116
+ "step": 130
117
+ },
118
+ {
119
+ "epoch": 0.21546748749519046,
120
+ "grad_norm": 0.9328588247299194,
121
+ "learning_rate": 4.3076923076923084e-05,
122
+ "loss": 0.0912,
123
+ "step": 140
124
+ },
125
+ {
126
+ "epoch": 0.2308580223162755,
127
+ "grad_norm": 0.8604061007499695,
128
+ "learning_rate": 4.615384615384616e-05,
129
+ "loss": 0.0859,
130
+ "step": 150
131
+ },
132
+ {
133
+ "epoch": 0.2308580223162755,
134
+ "eval_loss": 0.0644315704703331,
135
+ "eval_runtime": 188.1359,
136
+ "eval_samples_per_second": 6.144,
137
+ "eval_steps_per_second": 6.144,
138
+ "step": 150
139
+ },
140
+ {
141
+ "epoch": 0.24624855713736052,
142
+ "grad_norm": 1.4581396579742432,
143
+ "learning_rate": 4.923076923076924e-05,
144
+ "loss": 0.0727,
145
+ "step": 160
146
+ },
147
+ {
148
+ "epoch": 0.26163909195844554,
149
+ "grad_norm": 0.7286003232002258,
150
+ "learning_rate": 5.230769230769231e-05,
151
+ "loss": 0.0806,
152
+ "step": 170
153
+ },
154
+ {
155
+ "epoch": 0.2770296267795306,
156
+ "grad_norm": 0.9489079713821411,
157
+ "learning_rate": 5.538461538461539e-05,
158
+ "loss": 0.0615,
159
+ "step": 180
160
+ },
161
+ {
162
+ "epoch": 0.2924201616006156,
163
+ "grad_norm": 0.828267514705658,
164
+ "learning_rate": 5.846153846153847e-05,
165
+ "loss": 0.0521,
166
+ "step": 190
167
+ },
168
+ {
169
+ "epoch": 0.30781069642170067,
170
+ "grad_norm": 0.6866675615310669,
171
+ "learning_rate": 6.153846153846155e-05,
172
+ "loss": 0.0714,
173
+ "step": 200
174
+ },
175
+ {
176
+ "epoch": 0.30781069642170067,
177
+ "eval_loss": 0.052990105003118515,
178
+ "eval_runtime": 188.5543,
179
+ "eval_samples_per_second": 6.131,
180
+ "eval_steps_per_second": 6.131,
181
+ "step": 200
182
+ },
183
+ {
184
+ "epoch": 0.3232012312427857,
185
+ "grad_norm": 0.725680410861969,
186
+ "learning_rate": 6.461538461538462e-05,
187
+ "loss": 0.0609,
188
+ "step": 210
189
+ },
190
+ {
191
+ "epoch": 0.3385917660638707,
192
+ "grad_norm": 0.8611897826194763,
193
+ "learning_rate": 6.76923076923077e-05,
194
+ "loss": 0.0594,
195
+ "step": 220
196
+ },
197
+ {
198
+ "epoch": 0.35398230088495575,
199
+ "grad_norm": 0.34665313363075256,
200
+ "learning_rate": 7.076923076923078e-05,
201
+ "loss": 0.0502,
202
+ "step": 230
203
+ },
204
+ {
205
+ "epoch": 0.3693728357060408,
206
+ "grad_norm": 0.6683058738708496,
207
+ "learning_rate": 7.384615384615386e-05,
208
+ "loss": 0.0525,
209
+ "step": 240
210
+ },
211
+ {
212
+ "epoch": 0.38476337052712584,
213
+ "grad_norm": 0.4202400743961334,
214
+ "learning_rate": 7.692307692307693e-05,
215
+ "loss": 0.054,
216
+ "step": 250
217
+ },
218
+ {
219
+ "epoch": 0.38476337052712584,
220
+ "eval_loss": 0.049264274537563324,
221
+ "eval_runtime": 188.1154,
222
+ "eval_samples_per_second": 6.145,
223
+ "eval_steps_per_second": 6.145,
224
+ "step": 250
225
+ },
226
+ {
227
+ "epoch": 0.4001539053482108,
228
+ "grad_norm": 0.3903276324272156,
229
+ "learning_rate": 8e-05,
230
+ "loss": 0.0509,
231
+ "step": 260
232
+ },
233
+ {
234
+ "epoch": 0.41554444016929587,
235
+ "grad_norm": 0.7589438557624817,
236
+ "learning_rate": 8.307692307692309e-05,
237
+ "loss": 0.0538,
238
+ "step": 270
239
+ },
240
+ {
241
+ "epoch": 0.4309349749903809,
242
+ "grad_norm": 0.5696157217025757,
243
+ "learning_rate": 8.615384615384617e-05,
244
+ "loss": 0.0605,
245
+ "step": 280
246
+ },
247
+ {
248
+ "epoch": 0.44632550981146596,
249
+ "grad_norm": 0.3944014608860016,
250
+ "learning_rate": 8.923076923076924e-05,
251
+ "loss": 0.0605,
252
+ "step": 290
253
+ },
254
+ {
255
+ "epoch": 0.461716044632551,
256
+ "grad_norm": 0.588414192199707,
257
+ "learning_rate": 9.230769230769232e-05,
258
+ "loss": 0.0553,
259
+ "step": 300
260
+ },
261
+ {
262
+ "epoch": 0.461716044632551,
263
+ "eval_loss": 0.04779207333922386,
264
+ "eval_runtime": 187.659,
265
+ "eval_samples_per_second": 6.16,
266
+ "eval_steps_per_second": 6.16,
267
+ "step": 300
268
+ },
269
+ {
270
+ "epoch": 0.477106579453636,
271
+ "grad_norm": 0.46967023611068726,
272
+ "learning_rate": 9.53846153846154e-05,
273
+ "loss": 0.0552,
274
+ "step": 310
275
+ },
276
+ {
277
+ "epoch": 0.49249711427472104,
278
+ "grad_norm": 0.4400937259197235,
279
+ "learning_rate": 9.846153846153848e-05,
280
+ "loss": 0.0587,
281
+ "step": 320
282
+ },
283
+ {
284
+ "epoch": 0.5078876490958061,
285
+ "grad_norm": 0.7571660876274109,
286
+ "learning_rate": 9.999927654251793e-05,
287
+ "loss": 0.0608,
288
+ "step": 330
289
+ },
290
+ {
291
+ "epoch": 0.5232781839168911,
292
+ "grad_norm": 0.356673002243042,
293
+ "learning_rate": 9.99934890082745e-05,
294
+ "loss": 0.0566,
295
+ "step": 340
296
+ },
297
+ {
298
+ "epoch": 0.5386687187379762,
299
+ "grad_norm": 0.4959634244441986,
300
+ "learning_rate": 9.99819146097084e-05,
301
+ "loss": 0.053,
302
+ "step": 350
303
+ },
304
+ {
305
+ "epoch": 0.5386687187379762,
306
+ "eval_loss": 0.0478888563811779,
307
+ "eval_runtime": 187.3914,
308
+ "eval_samples_per_second": 6.169,
309
+ "eval_steps_per_second": 6.169,
310
+ "step": 350
311
+ },
312
+ {
313
+ "epoch": 0.5540592535590612,
314
+ "grad_norm": 0.3542782664299011,
315
+ "learning_rate": 9.996455468658355e-05,
316
+ "loss": 0.0679,
317
+ "step": 360
318
+ },
319
+ {
320
+ "epoch": 0.5694497883801463,
321
+ "grad_norm": 0.49819979071617126,
322
+ "learning_rate": 9.994141124835203e-05,
323
+ "loss": 0.0511,
324
+ "step": 370
325
+ },
326
+ {
327
+ "epoch": 0.5848403232012312,
328
+ "grad_norm": 0.37595507502555847,
329
+ "learning_rate": 9.991248697392142e-05,
330
+ "loss": 0.0499,
331
+ "step": 380
332
+ },
333
+ {
334
+ "epoch": 0.6002308580223162,
335
+ "grad_norm": 0.8225634694099426,
336
+ "learning_rate": 9.987778521134476e-05,
337
+ "loss": 0.0364,
338
+ "step": 390
339
+ },
340
+ {
341
+ "epoch": 0.6156213928434013,
342
+ "grad_norm": 0.4043976962566376,
343
+ "learning_rate": 9.983730997743294e-05,
344
+ "loss": 0.0645,
345
+ "step": 400
346
+ },
347
+ {
348
+ "epoch": 0.6156213928434013,
349
+ "eval_loss": 0.048657890409231186,
350
+ "eval_runtime": 187.2004,
351
+ "eval_samples_per_second": 6.175,
352
+ "eval_steps_per_second": 6.175,
353
+ "step": 400
354
+ },
355
+ {
356
+ "epoch": 0.6310119276644863,
357
+ "grad_norm": 0.29372572898864746,
358
+ "learning_rate": 9.979106595728978e-05,
359
+ "loss": 0.0462,
360
+ "step": 410
361
+ },
362
+ {
363
+ "epoch": 0.6464024624855714,
364
+ "grad_norm": 0.5222019553184509,
365
+ "learning_rate": 9.973905850376977e-05,
366
+ "loss": 0.0509,
367
+ "step": 420
368
+ },
369
+ {
370
+ "epoch": 0.6617929973066564,
371
+ "grad_norm": 0.8109437227249146,
372
+ "learning_rate": 9.968129363685833e-05,
373
+ "loss": 0.0529,
374
+ "step": 430
375
+ },
376
+ {
377
+ "epoch": 0.6771835321277414,
378
+ "grad_norm": 0.4393615424633026,
379
+ "learning_rate": 9.961777804297514e-05,
380
+ "loss": 0.0658,
381
+ "step": 440
382
+ },
383
+ {
384
+ "epoch": 0.6925740669488265,
385
+ "grad_norm": 0.3185001015663147,
386
+ "learning_rate": 9.954851907420009e-05,
387
+ "loss": 0.0391,
388
+ "step": 450
389
+ },
390
+ {
391
+ "epoch": 0.6925740669488265,
392
+ "eval_loss": 0.04509444162249565,
393
+ "eval_runtime": 187.6444,
394
+ "eval_samples_per_second": 6.161,
395
+ "eval_steps_per_second": 6.161,
396
+ "step": 450
397
+ },
398
+ {
399
+ "epoch": 0.7079646017699115,
400
+ "grad_norm": 0.4155886173248291,
401
+ "learning_rate": 9.947352474742222e-05,
402
+ "loss": 0.0422,
403
+ "step": 460
404
+ },
405
+ {
406
+ "epoch": 0.7233551365909965,
407
+ "grad_norm": 0.31224191188812256,
408
+ "learning_rate": 9.93928037434118e-05,
409
+ "loss": 0.0336,
410
+ "step": 470
411
+ },
412
+ {
413
+ "epoch": 0.7387456714120816,
414
+ "grad_norm": 0.4808642566204071,
415
+ "learning_rate": 9.930636540581556e-05,
416
+ "loss": 0.0403,
417
+ "step": 480
418
+ },
419
+ {
420
+ "epoch": 0.7541362062331666,
421
+ "grad_norm": 0.18449532985687256,
422
+ "learning_rate": 9.921421974007506e-05,
423
+ "loss": 0.0452,
424
+ "step": 490
425
+ },
426
+ {
427
+ "epoch": 0.7695267410542517,
428
+ "grad_norm": 0.48674625158309937,
429
+ "learning_rate": 9.911637741226849e-05,
430
+ "loss": 0.0339,
431
+ "step": 500
432
+ },
433
+ {
434
+ "epoch": 0.7695267410542517,
435
+ "eval_loss": 0.04046137258410454,
436
+ "eval_runtime": 187.9753,
437
+ "eval_samples_per_second": 6.15,
438
+ "eval_steps_per_second": 6.15,
439
+ "step": 500
440
+ },
441
+ {
442
+ "epoch": 0.7849172758753367,
443
+ "grad_norm": 0.5263739228248596,
444
+ "learning_rate": 9.90128497478762e-05,
445
+ "loss": 0.0328,
446
+ "step": 510
447
+ },
448
+ {
449
+ "epoch": 0.8003078106964217,
450
+ "grad_norm": 0.24675846099853516,
451
+ "learning_rate": 9.890364873046965e-05,
452
+ "loss": 0.0519,
453
+ "step": 520
454
+ },
455
+ {
456
+ "epoch": 0.8156983455175068,
457
+ "grad_norm": 0.3642294704914093,
458
+ "learning_rate": 9.878878700032427e-05,
459
+ "loss": 0.0656,
460
+ "step": 530
461
+ },
462
+ {
463
+ "epoch": 0.8310888803385917,
464
+ "grad_norm": 0.487305223941803,
465
+ "learning_rate": 9.866827785295638e-05,
466
+ "loss": 0.0456,
467
+ "step": 540
468
+ },
469
+ {
470
+ "epoch": 0.8464794151596768,
471
+ "grad_norm": 0.2354636788368225,
472
+ "learning_rate": 9.854213523758413e-05,
473
+ "loss": 0.0513,
474
+ "step": 550
475
+ },
476
+ {
477
+ "epoch": 0.8464794151596768,
478
+ "eval_loss": 0.04050951078534126,
479
+ "eval_runtime": 188.1628,
480
+ "eval_samples_per_second": 6.144,
481
+ "eval_steps_per_second": 6.144,
482
+ "step": 550
483
+ },
484
+ {
485
+ "epoch": 0.8618699499807618,
486
+ "grad_norm": 0.18946993350982666,
487
+ "learning_rate": 9.841037375551294e-05,
488
+ "loss": 0.0417,
489
+ "step": 560
490
+ },
491
+ {
492
+ "epoch": 0.8772604848018468,
493
+ "grad_norm": 0.40360134840011597,
494
+ "learning_rate": 9.827300865844527e-05,
495
+ "loss": 0.0333,
496
+ "step": 570
497
+ },
498
+ {
499
+ "epoch": 0.8926510196229319,
500
+ "grad_norm": 0.316399484872818,
501
+ "learning_rate": 9.813005584671522e-05,
502
+ "loss": 0.0362,
503
+ "step": 580
504
+ },
505
+ {
506
+ "epoch": 0.9080415544440169,
507
+ "grad_norm": 0.4593469798564911,
508
+ "learning_rate": 9.79815318674481e-05,
509
+ "loss": 0.0579,
510
+ "step": 590
511
+ },
512
+ {
513
+ "epoch": 0.923432089265102,
514
+ "grad_norm": 0.28380537033081055,
515
+ "learning_rate": 9.782745391264498e-05,
516
+ "loss": 0.0374,
517
+ "step": 600
518
+ },
519
+ {
520
+ "epoch": 0.923432089265102,
521
+ "eval_loss": 0.03845710679888725,
522
+ "eval_runtime": 187.7867,
523
+ "eval_samples_per_second": 6.156,
524
+ "eval_steps_per_second": 6.156,
525
+ "step": 600
526
+ },
527
+ {
528
+ "epoch": 0.938822624086187,
529
+ "grad_norm": 0.2812202274799347,
530
+ "learning_rate": 9.76678398171927e-05,
531
+ "loss": 0.0377,
532
+ "step": 610
533
+ },
534
+ {
535
+ "epoch": 0.954213158907272,
536
+ "grad_norm": 0.2947665750980377,
537
+ "learning_rate": 9.750270805679945e-05,
538
+ "loss": 0.053,
539
+ "step": 620
540
+ },
541
+ {
542
+ "epoch": 0.9696036937283571,
543
+ "grad_norm": 0.33196261525154114,
544
+ "learning_rate": 9.733207774585618e-05,
545
+ "loss": 0.0484,
546
+ "step": 630
547
+ },
548
+ {
549
+ "epoch": 0.9849942285494421,
550
+ "grad_norm": 0.27342891693115234,
551
+ "learning_rate": 9.715596863522398e-05,
552
+ "loss": 0.0355,
553
+ "step": 640
554
+ },
555
+ {
556
+ "epoch": 1.0003847633705272,
557
+ "grad_norm": 0.8010798692703247,
558
+ "learning_rate": 9.697440110994801e-05,
559
+ "loss": 0.0334,
560
+ "step": 650
561
+ },
562
+ {
563
+ "epoch": 1.0003847633705272,
564
+ "eval_loss": 0.03811522200703621,
565
+ "eval_runtime": 187.6177,
566
+ "eval_samples_per_second": 6.161,
567
+ "eval_steps_per_second": 6.161,
568
+ "step": 650
569
+ },
570
+ {
571
+ "epoch": 1.0157752981916122,
572
+ "grad_norm": 0.4056728780269623,
573
+ "learning_rate": 9.678739618689775e-05,
574
+ "loss": 0.0398,
575
+ "step": 660
576
+ },
577
+ {
578
+ "epoch": 1.0311658330126972,
579
+ "grad_norm": 0.2418406456708908,
580
+ "learning_rate": 9.659497551233431e-05,
581
+ "loss": 0.038,
582
+ "step": 670
583
+ },
584
+ {
585
+ "epoch": 1.0465563678337821,
586
+ "grad_norm": 0.28666359186172485,
587
+ "learning_rate": 9.639716135940485e-05,
588
+ "loss": 0.0351,
589
+ "step": 680
590
+ },
591
+ {
592
+ "epoch": 1.0619469026548674,
593
+ "grad_norm": 0.41955092549324036,
594
+ "learning_rate": 9.619397662556435e-05,
595
+ "loss": 0.0486,
596
+ "step": 690
597
+ },
598
+ {
599
+ "epoch": 1.0773374374759523,
600
+ "grad_norm": 0.4770854413509369,
601
+ "learning_rate": 9.598544482992517e-05,
602
+ "loss": 0.0405,
603
+ "step": 700
604
+ },
605
+ {
606
+ "epoch": 1.0773374374759523,
607
+ "eval_loss": 0.04033925011754036,
608
+ "eval_runtime": 187.98,
609
+ "eval_samples_per_second": 6.15,
610
+ "eval_steps_per_second": 6.15,
611
+ "step": 700
612
+ },
613
+ {
614
+ "epoch": 1.0927279722970373,
615
+ "grad_norm": 0.4085399806499481,
616
+ "learning_rate": 9.57715901105348e-05,
617
+ "loss": 0.033,
618
+ "step": 710
619
+ },
620
+ {
621
+ "epoch": 1.1081185071181223,
622
+ "grad_norm": 0.24918586015701294,
623
+ "learning_rate": 9.555243722158158e-05,
624
+ "loss": 0.0338,
625
+ "step": 720
626
+ },
627
+ {
628
+ "epoch": 1.1235090419392073,
629
+ "grad_norm": 0.21423755586147308,
630
+ "learning_rate": 9.532801153052958e-05,
631
+ "loss": 0.0323,
632
+ "step": 730
633
+ },
634
+ {
635
+ "epoch": 1.1388995767602923,
636
+ "grad_norm": 0.7340275049209595,
637
+ "learning_rate": 9.509833901518209e-05,
638
+ "loss": 0.05,
639
+ "step": 740
640
+ },
641
+ {
642
+ "epoch": 1.1542901115813775,
643
+ "grad_norm": 0.25578582286834717,
644
+ "learning_rate": 9.486344626067475e-05,
645
+ "loss": 0.0337,
646
+ "step": 750
647
+ },
648
+ {
649
+ "epoch": 1.1542901115813775,
650
+ "eval_loss": 0.0360797680914402,
651
+ "eval_runtime": 188.046,
652
+ "eval_samples_per_second": 6.147,
653
+ "eval_steps_per_second": 6.147,
654
+ "step": 750
655
+ },
656
+ {
657
+ "epoch": 1.1696806464024625,
658
+ "grad_norm": 0.23202097415924072,
659
+ "learning_rate": 9.462336045639815e-05,
660
+ "loss": 0.0407,
661
+ "step": 760
662
+ },
663
+ {
664
+ "epoch": 1.1850711812235475,
665
+ "grad_norm": 0.2221558541059494,
666
+ "learning_rate": 9.437810939285068e-05,
667
+ "loss": 0.0407,
668
+ "step": 770
669
+ },
670
+ {
671
+ "epoch": 1.2004617160446325,
672
+ "grad_norm": 0.29214197397232056,
673
+ "learning_rate": 9.412772145842165e-05,
674
+ "loss": 0.038,
675
+ "step": 780
676
+ },
677
+ {
678
+ "epoch": 1.2158522508657175,
679
+ "grad_norm": 0.4598447382450104,
680
+ "learning_rate": 9.387222563610535e-05,
681
+ "loss": 0.0358,
682
+ "step": 790
683
+ },
684
+ {
685
+ "epoch": 1.2312427856868027,
686
+ "grad_norm": 0.24903126060962677,
687
+ "learning_rate": 9.361165150014606e-05,
688
+ "loss": 0.0344,
689
+ "step": 800
690
+ },
691
+ {
692
+ "epoch": 1.2312427856868027,
693
+ "eval_loss": 0.03588108345866203,
694
+ "eval_runtime": 187.57,
695
+ "eval_samples_per_second": 6.163,
696
+ "eval_steps_per_second": 6.163,
697
+ "step": 800
698
+ },
699
+ {
700
+ "epoch": 1.2466333205078877,
701
+ "grad_norm": 0.15016677975654602,
702
+ "learning_rate": 9.334602921261492e-05,
703
+ "loss": 0.033,
704
+ "step": 810
705
+ },
706
+ {
707
+ "epoch": 1.2620238553289727,
708
+ "grad_norm": 0.3766383230686188,
709
+ "learning_rate": 9.307538951991852e-05,
710
+ "loss": 0.0315,
711
+ "step": 820
712
+ },
713
+ {
714
+ "epoch": 1.2774143901500576,
715
+ "grad_norm": 0.3017776310443878,
716
+ "learning_rate": 9.279976374923988e-05,
717
+ "loss": 0.038,
718
+ "step": 830
719
+ },
720
+ {
721
+ "epoch": 1.2928049249711426,
722
+ "grad_norm": 0.37091585993766785,
723
+ "learning_rate": 9.251918380491238e-05,
724
+ "loss": 0.0279,
725
+ "step": 840
726
+ },
727
+ {
728
+ "epoch": 1.3081954597922278,
729
+ "grad_norm": 0.32512232661247253,
730
+ "learning_rate": 9.223368216472668e-05,
731
+ "loss": 0.0344,
732
+ "step": 850
733
+ },
734
+ {
735
+ "epoch": 1.3081954597922278,
736
+ "eval_loss": 0.037309836596250534,
737
+ "eval_runtime": 187.42,
738
+ "eval_samples_per_second": 6.168,
739
+ "eval_steps_per_second": 6.168,
740
+ "step": 850
741
+ },
742
+ {
743
+ "epoch": 1.3235859946133128,
744
+ "grad_norm": 0.19161005318164825,
745
+ "learning_rate": 9.194329187617127e-05,
746
+ "loss": 0.0331,
747
+ "step": 860
748
+ },
749
+ {
750
+ "epoch": 1.3389765294343978,
751
+ "grad_norm": 0.41218462586402893,
752
+ "learning_rate": 9.164804655260735e-05,
753
+ "loss": 0.033,
754
+ "step": 870
755
+ },
756
+ {
757
+ "epoch": 1.3543670642554828,
758
+ "grad_norm": 0.151007279753685,
759
+ "learning_rate": 9.134798036937778e-05,
760
+ "loss": 0.0266,
761
+ "step": 880
762
+ },
763
+ {
764
+ "epoch": 1.3697575990765678,
765
+ "grad_norm": 0.19659636914730072,
766
+ "learning_rate": 9.104312805985134e-05,
767
+ "loss": 0.0434,
768
+ "step": 890
769
+ },
770
+ {
771
+ "epoch": 1.385148133897653,
772
+ "grad_norm": 0.1985592097043991,
773
+ "learning_rate": 9.073352491140221e-05,
774
+ "loss": 0.0221,
775
+ "step": 900
776
+ },
777
+ {
778
+ "epoch": 1.385148133897653,
779
+ "eval_loss": 0.03570735454559326,
780
+ "eval_runtime": 187.0359,
781
+ "eval_samples_per_second": 6.181,
782
+ "eval_steps_per_second": 6.181,
783
+ "step": 900
784
+ },
785
+ {
786
+ "epoch": 1.400538668718738,
787
+ "grad_norm": 0.30656376481056213,
788
+ "learning_rate": 9.041920676132543e-05,
789
+ "loss": 0.0304,
790
+ "step": 910
791
+ },
792
+ {
793
+ "epoch": 1.415929203539823,
794
+ "grad_norm": 0.5850927233695984,
795
+ "learning_rate": 9.010020999268854e-05,
796
+ "loss": 0.0366,
797
+ "step": 920
798
+ },
799
+ {
800
+ "epoch": 1.431319738360908,
801
+ "grad_norm": 0.21166619658470154,
802
+ "learning_rate": 8.977657153012027e-05,
803
+ "loss": 0.0328,
804
+ "step": 930
805
+ },
806
+ {
807
+ "epoch": 1.446710273181993,
808
+ "grad_norm": 0.4661455452442169,
809
+ "learning_rate": 8.944832883553633e-05,
810
+ "loss": 0.0377,
811
+ "step": 940
812
+ },
813
+ {
814
+ "epoch": 1.4621008080030782,
815
+ "grad_norm": 0.11176864802837372,
816
+ "learning_rate": 8.91155199038032e-05,
817
+ "loss": 0.0457,
818
+ "step": 950
819
+ },
820
+ {
821
+ "epoch": 1.4621008080030782,
822
+ "eval_loss": 0.03746819868683815,
823
+ "eval_runtime": 187.3821,
824
+ "eval_samples_per_second": 6.169,
825
+ "eval_steps_per_second": 6.169,
826
+ "step": 950
827
+ },
828
+ {
829
+ "epoch": 1.4774913428241632,
830
+ "grad_norm": 0.2294084131717682,
831
+ "learning_rate": 8.877818325834006e-05,
832
+ "loss": 0.0286,
833
+ "step": 960
834
+ },
835
+ {
836
+ "epoch": 1.4928818776452482,
837
+ "grad_norm": 0.09593243896961212,
838
+ "learning_rate": 8.843635794665961e-05,
839
+ "loss": 0.027,
840
+ "step": 970
841
+ },
842
+ {
843
+ "epoch": 1.5082724124663334,
844
+ "grad_norm": 0.3172210454940796,
845
+ "learning_rate": 8.809008353584829e-05,
846
+ "loss": 0.0345,
847
+ "step": 980
848
+ },
849
+ {
850
+ "epoch": 1.5236629472874181,
851
+ "grad_norm": 0.21809054911136627,
852
+ "learning_rate": 8.773940010798627e-05,
853
+ "loss": 0.0398,
854
+ "step": 990
855
+ },
856
+ {
857
+ "epoch": 1.5390534821085033,
858
+ "grad_norm": 0.36311158537864685,
859
+ "learning_rate": 8.738434825550785e-05,
860
+ "loss": 0.0357,
861
+ "step": 1000
862
+ },
863
+ {
864
+ "epoch": 1.5390534821085033,
865
+ "eval_loss": 0.03651273250579834,
866
+ "eval_runtime": 187.9276,
867
+ "eval_samples_per_second": 6.151,
868
+ "eval_steps_per_second": 6.151,
869
+ "step": 1000
870
+ },
871
+ {
872
+ "epoch": 1.5544440169295883,
873
+ "grad_norm": 0.2572426199913025,
874
+ "learning_rate": 8.702496907650274e-05,
875
+ "loss": 0.0398,
876
+ "step": 1010
877
+ },
878
+ {
879
+ "epoch": 1.5698345517506733,
880
+ "grad_norm": 0.2838153541088104,
881
+ "learning_rate": 8.666130416995897e-05,
882
+ "loss": 0.0374,
883
+ "step": 1020
884
+ },
885
+ {
886
+ "epoch": 1.5852250865717585,
887
+ "grad_norm": 0.22808720171451569,
888
+ "learning_rate": 8.629339563094758e-05,
889
+ "loss": 0.0357,
890
+ "step": 1030
891
+ },
892
+ {
893
+ "epoch": 1.6006156213928433,
894
+ "grad_norm": 0.25805601477622986,
895
+ "learning_rate": 8.592128604575014e-05,
896
+ "loss": 0.033,
897
+ "step": 1040
898
+ },
899
+ {
900
+ "epoch": 1.6160061562139285,
901
+ "grad_norm": 0.2337527722120285,
902
+ "learning_rate": 8.554501848692921e-05,
903
+ "loss": 0.034,
904
+ "step": 1050
905
+ },
906
+ {
907
+ "epoch": 1.6160061562139285,
908
+ "eval_loss": 0.03555304929614067,
909
+ "eval_runtime": 188.0492,
910
+ "eval_samples_per_second": 6.147,
911
+ "eval_steps_per_second": 6.147,
912
+ "step": 1050
913
+ },
914
+ {
915
+ "epoch": 1.6313966910350135,
916
+ "grad_norm": 0.25864410400390625,
917
+ "learning_rate": 8.51646365083426e-05,
918
+ "loss": 0.0285,
919
+ "step": 1060
920
+ },
921
+ {
922
+ "epoch": 1.6467872258560985,
923
+ "grad_norm": 0.20299604535102844,
924
+ "learning_rate": 8.478018414010191e-05,
925
+ "loss": 0.0318,
926
+ "step": 1070
927
+ },
928
+ {
929
+ "epoch": 1.6621777606771835,
930
+ "grad_norm": 0.2811971604824066,
931
+ "learning_rate": 8.439170588347598e-05,
932
+ "loss": 0.0271,
933
+ "step": 1080
934
+ },
935
+ {
936
+ "epoch": 1.6775682954982685,
937
+ "grad_norm": 0.32877394556999207,
938
+ "learning_rate": 8.399924670573969e-05,
939
+ "loss": 0.0262,
940
+ "step": 1090
941
+ },
942
+ {
943
+ "epoch": 1.6929588303193537,
944
+ "grad_norm": 0.15650756657123566,
945
+ "learning_rate": 8.360285203496894e-05,
946
+ "loss": 0.0394,
947
+ "step": 1100
948
+ },
949
+ {
950
+ "epoch": 1.6929588303193537,
951
+ "eval_loss": 0.03640196472406387,
952
+ "eval_runtime": 187.9016,
953
+ "eval_samples_per_second": 6.152,
954
+ "eval_steps_per_second": 6.152,
955
+ "step": 1100
956
+ },
957
+ {
958
+ "epoch": 1.7083493651404387,
959
+ "grad_norm": 0.41813358664512634,
960
+ "learning_rate": 8.320256775478228e-05,
961
+ "loss": 0.041,
962
+ "step": 1110
963
+ },
964
+ {
965
+ "epoch": 1.7237398999615237,
966
+ "grad_norm": 0.18765102326869965,
967
+ "learning_rate": 8.279844019902968e-05,
968
+ "loss": 0.0315,
969
+ "step": 1120
970
+ },
971
+ {
972
+ "epoch": 1.7391304347826086,
973
+ "grad_norm": 0.2128918319940567,
974
+ "learning_rate": 8.239051614642934e-05,
975
+ "loss": 0.0396,
976
+ "step": 1130
977
+ },
978
+ {
979
+ "epoch": 1.7545209696036936,
980
+ "grad_norm": 0.12499304115772247,
981
+ "learning_rate": 8.197884281515292e-05,
982
+ "loss": 0.049,
983
+ "step": 1140
984
+ },
985
+ {
986
+ "epoch": 1.7699115044247788,
987
+ "grad_norm": 0.19719086587429047,
988
+ "learning_rate": 8.156346785735997e-05,
989
+ "loss": 0.0244,
990
+ "step": 1150
991
+ },
992
+ {
993
+ "epoch": 1.7699115044247788,
994
+ "eval_loss": 0.0359814316034317,
995
+ "eval_runtime": 187.8554,
996
+ "eval_samples_per_second": 6.154,
997
+ "eval_steps_per_second": 6.154,
998
+ "step": 1150
999
+ },
1000
+ {
1001
+ "epoch": 1.7853020392458638,
1002
+ "grad_norm": 0.1700337678194046,
1003
+ "learning_rate": 8.114443935368198e-05,
1004
+ "loss": 0.0349,
1005
+ "step": 1160
1006
+ },
1007
+ {
1008
+ "epoch": 1.8006925740669488,
1009
+ "grad_norm": 0.2521379292011261,
1010
+ "learning_rate": 8.072180580765709e-05,
1011
+ "loss": 0.0263,
1012
+ "step": 1170
1013
+ },
1014
+ {
1015
+ "epoch": 1.8160831088880338,
1016
+ "grad_norm": 0.26141706109046936,
1017
+ "learning_rate": 8.02956161401155e-05,
1018
+ "loss": 0.0283,
1019
+ "step": 1180
1020
+ },
1021
+ {
1022
+ "epoch": 1.8314736437091188,
1023
+ "grad_norm": 0.4066651165485382,
1024
+ "learning_rate": 7.98659196835169e-05,
1025
+ "loss": 0.0356,
1026
+ "step": 1190
1027
+ },
1028
+ {
1029
+ "epoch": 1.846864178530204,
1030
+ "grad_norm": 0.1369960904121399,
1031
+ "learning_rate": 7.943276617624014e-05,
1032
+ "loss": 0.023,
1033
+ "step": 1200
1034
+ },
1035
+ {
1036
+ "epoch": 1.846864178530204,
1037
+ "eval_loss": 0.03705717623233795,
1038
+ "eval_runtime": 187.2707,
1039
+ "eval_samples_per_second": 6.173,
1040
+ "eval_steps_per_second": 6.173,
1041
+ "step": 1200
1042
+ },
1043
+ {
1044
+ "epoch": 1.862254713351289,
1045
+ "grad_norm": 0.243990957736969,
1046
+ "learning_rate": 7.899620575682578e-05,
1047
+ "loss": 0.0346,
1048
+ "step": 1210
1049
+ },
1050
+ {
1051
+ "epoch": 1.877645248172374,
1052
+ "grad_norm": 0.14930765330791473,
1053
+ "learning_rate": 7.85562889581725e-05,
1054
+ "loss": 0.026,
1055
+ "step": 1220
1056
+ },
1057
+ {
1058
+ "epoch": 1.893035782993459,
1059
+ "grad_norm": 0.10069471597671509,
1060
+ "learning_rate": 7.811306670168788e-05,
1061
+ "loss": 0.0338,
1062
+ "step": 1230
1063
+ },
1064
+ {
1065
+ "epoch": 1.908426317814544,
1066
+ "grad_norm": 0.24041235446929932,
1067
+ "learning_rate": 7.766659029139393e-05,
1068
+ "loss": 0.0417,
1069
+ "step": 1240
1070
+ },
1071
+ {
1072
+ "epoch": 1.9238168526356292,
1073
+ "grad_norm": 0.28064167499542236,
1074
+ "learning_rate": 7.72169114079887e-05,
1075
+ "loss": 0.0339,
1076
+ "step": 1250
1077
+ },
1078
+ {
1079
+ "epoch": 1.9238168526356292,
1080
+ "eval_loss": 0.035844240337610245,
1081
+ "eval_runtime": 187.6727,
1082
+ "eval_samples_per_second": 6.16,
1083
+ "eval_steps_per_second": 6.16,
1084
+ "step": 1250
1085
+ },
1086
+ {
1087
+ "epoch": 1.9392073874567142,
1088
+ "grad_norm": 0.3073214292526245,
1089
+ "learning_rate": 7.676408210286407e-05,
1090
+ "loss": 0.0342,
1091
+ "step": 1260
1092
+ },
1093
+ {
1094
+ "epoch": 1.9545979222777992,
1095
+ "grad_norm": 0.26703837513923645,
1096
+ "learning_rate": 7.630815479208066e-05,
1097
+ "loss": 0.0364,
1098
+ "step": 1270
1099
+ },
1100
+ {
1101
+ "epoch": 1.9699884570988841,
1102
+ "grad_norm": 0.21204885840415955,
1103
+ "learning_rate": 7.584918225030053e-05,
1104
+ "loss": 0.025,
1105
+ "step": 1280
1106
+ },
1107
+ {
1108
+ "epoch": 1.9853789919199691,
1109
+ "grad_norm": 0.3635454475879669,
1110
+ "learning_rate": 7.538721760467845e-05,
1111
+ "loss": 0.0372,
1112
+ "step": 1290
1113
+ },
1114
+ {
1115
+ "epoch": 2.0007695267410543,
1116
+ "grad_norm": 0.11565925180912018,
1117
+ "learning_rate": 7.49223143287122e-05,
1118
+ "loss": 0.0252,
1119
+ "step": 1300
1120
+ },
1121
+ {
1122
+ "epoch": 2.0007695267410543,
1123
+ "eval_loss": 0.0344332717359066,
1124
+ "eval_runtime": 187.9094,
1125
+ "eval_samples_per_second": 6.152,
1126
+ "eval_steps_per_second": 6.152,
1127
+ "step": 1300
1128
+ },
1129
+ {
1130
+ "epoch": 2.016160061562139,
1131
+ "grad_norm": 0.19626887142658234,
1132
+ "learning_rate": 7.445452623605307e-05,
1133
+ "loss": 0.0227,
1134
+ "step": 1310
1135
+ },
1136
+ {
1137
+ "epoch": 2.0315505963832243,
1138
+ "grad_norm": 0.34589436650276184,
1139
+ "learning_rate": 7.398390747427662e-05,
1140
+ "loss": 0.0237,
1141
+ "step": 1320
1142
+ },
1143
+ {
1144
+ "epoch": 2.0469411312043095,
1145
+ "grad_norm": 0.21786868572235107,
1146
+ "learning_rate": 7.351051251861501e-05,
1147
+ "loss": 0.0255,
1148
+ "step": 1330
1149
+ },
1150
+ {
1151
+ "epoch": 2.0623316660253943,
1152
+ "grad_norm": 0.15011264383792877,
1153
+ "learning_rate": 7.303439616565146e-05,
1154
+ "loss": 0.0248,
1155
+ "step": 1340
1156
+ },
1157
+ {
1158
+ "epoch": 2.0777222008464795,
1159
+ "grad_norm": 0.18167394399642944,
1160
+ "learning_rate": 7.255561352697732e-05,
1161
+ "loss": 0.019,
1162
+ "step": 1350
1163
+ },
1164
+ {
1165
+ "epoch": 2.0777222008464795,
1166
+ "eval_loss": 0.03381282836198807,
1167
+ "eval_runtime": 187.8437,
1168
+ "eval_samples_per_second": 6.154,
1169
+ "eval_steps_per_second": 6.154,
1170
+ "step": 1350
1171
+ },
1172
+ {
1173
+ "epoch": 2.0931127356675643,
1174
+ "grad_norm": 0.10537901520729065,
1175
+ "learning_rate": 7.207422002281281e-05,
1176
+ "loss": 0.0227,
1177
+ "step": 1360
1178
+ },
1179
+ {
1180
+ "epoch": 2.1085032704886495,
1181
+ "grad_norm": 0.5727980136871338,
1182
+ "learning_rate": 7.159027137559197e-05,
1183
+ "loss": 0.0218,
1184
+ "step": 1370
1185
+ },
1186
+ {
1187
+ "epoch": 2.1238938053097347,
1188
+ "grad_norm": 0.24711571633815765,
1189
+ "learning_rate": 7.110382360351267e-05,
1190
+ "loss": 0.0153,
1191
+ "step": 1380
1192
+ },
1193
+ {
1194
+ "epoch": 2.1392843401308195,
1195
+ "grad_norm": 0.18777436017990112,
1196
+ "learning_rate": 7.061493301405244e-05,
1197
+ "loss": 0.0208,
1198
+ "step": 1390
1199
+ },
1200
+ {
1201
+ "epoch": 2.1546748749519047,
1202
+ "grad_norm": 0.3703112304210663,
1203
+ "learning_rate": 7.012365619745064e-05,
1204
+ "loss": 0.0297,
1205
+ "step": 1400
1206
+ },
1207
+ {
1208
+ "epoch": 2.1546748749519047,
1209
+ "eval_loss": 0.03612199053168297,
1210
+ "eval_runtime": 187.1523,
1211
+ "eval_samples_per_second": 6.177,
1212
+ "eval_steps_per_second": 6.177,
1213
+ "step": 1400
1214
+ },
1215
+ {
1216
+ "epoch": 2.1700654097729895,
1217
+ "grad_norm": 0.11688963323831558,
1218
+ "learning_rate": 6.963005002015808e-05,
1219
+ "loss": 0.024,
1220
+ "step": 1410
1221
+ },
1222
+ {
1223
+ "epoch": 2.1854559445940747,
1224
+ "grad_norm": 0.27680692076683044,
1225
+ "learning_rate": 6.91341716182545e-05,
1226
+ "loss": 0.03,
1227
+ "step": 1420
1228
+ },
1229
+ {
1230
+ "epoch": 2.20084647941516,
1231
+ "grad_norm": 0.1767677664756775,
1232
+ "learning_rate": 6.863607839083507e-05,
1233
+ "loss": 0.0178,
1234
+ "step": 1430
1235
+ },
1236
+ {
1237
+ "epoch": 2.2162370142362446,
1238
+ "grad_norm": 0.21000392735004425,
1239
+ "learning_rate": 6.813582799336624e-05,
1240
+ "loss": 0.0261,
1241
+ "step": 1440
1242
+ },
1243
+ {
1244
+ "epoch": 2.23162754905733,
1245
+ "grad_norm": 0.10033946484327316,
1246
+ "learning_rate": 6.763347833101192e-05,
1247
+ "loss": 0.0142,
1248
+ "step": 1450
1249
+ },
1250
+ {
1251
+ "epoch": 2.23162754905733,
1252
+ "eval_loss": 0.03711491823196411,
1253
+ "eval_runtime": 186.5296,
1254
+ "eval_samples_per_second": 6.197,
1255
+ "eval_steps_per_second": 6.197,
1256
+ "step": 1450
1257
+ },
1258
+ {
1259
+ "epoch": 2.2470180838784146,
1260
+ "grad_norm": 0.18027913570404053,
1261
+ "learning_rate": 6.712908755193094e-05,
1262
+ "loss": 0.0233,
1263
+ "step": 1460
1264
+ },
1265
+ {
1266
+ "epoch": 2.2624086186995,
1267
+ "grad_norm": 0.16498275101184845,
1268
+ "learning_rate": 6.662271404054621e-05,
1269
+ "loss": 0.0268,
1270
+ "step": 1470
1271
+ },
1272
+ {
1273
+ "epoch": 2.2777991535205846,
1274
+ "grad_norm": 0.16076700389385223,
1275
+ "learning_rate": 6.611441641078657e-05,
1276
+ "loss": 0.0233,
1277
+ "step": 1480
1278
+ },
1279
+ {
1280
+ "epoch": 2.29318968834167,
1281
+ "grad_norm": 0.12392139434814453,
1282
+ "learning_rate": 6.560425349930208e-05,
1283
+ "loss": 0.0253,
1284
+ "step": 1490
1285
+ },
1286
+ {
1287
+ "epoch": 2.308580223162755,
1288
+ "grad_norm": 0.30897045135498047,
1289
+ "learning_rate": 6.509228435865357e-05,
1290
+ "loss": 0.0227,
1291
+ "step": 1500
1292
+ },
1293
+ {
1294
+ "epoch": 2.308580223162755,
1295
+ "eval_loss": 0.0353684276342392,
1296
+ "eval_runtime": 186.308,
1297
+ "eval_samples_per_second": 6.205,
1298
+ "eval_steps_per_second": 6.205,
1299
+ "step": 1500
1300
+ },
1301
+ {
1302
+ "epoch": 2.32397075798384,
1303
+ "grad_norm": 0.1789022982120514,
1304
+ "learning_rate": 6.45785682504772e-05,
1305
+ "loss": 0.0244,
1306
+ "step": 1510
1307
+ },
1308
+ {
1309
+ "epoch": 2.339361292804925,
1310
+ "grad_norm": 0.15649132430553436,
1311
+ "learning_rate": 6.406316463862467e-05,
1312
+ "loss": 0.0214,
1313
+ "step": 1520
1314
+ },
1315
+ {
1316
+ "epoch": 2.3547518276260098,
1317
+ "grad_norm": 0.1704787164926529,
1318
+ "learning_rate": 6.35461331822803e-05,
1319
+ "loss": 0.0201,
1320
+ "step": 1530
1321
+ },
1322
+ {
1323
+ "epoch": 2.370142362447095,
1324
+ "grad_norm": 0.22701707482337952,
1325
+ "learning_rate": 6.302753372905515e-05,
1326
+ "loss": 0.0199,
1327
+ "step": 1540
1328
+ },
1329
+ {
1330
+ "epoch": 2.38553289726818,
1331
+ "grad_norm": 0.21540381014347076,
1332
+ "learning_rate": 6.250742630805971e-05,
1333
+ "loss": 0.0179,
1334
+ "step": 1550
1335
+ },
1336
+ {
1337
+ "epoch": 2.38553289726818,
1338
+ "eval_loss": 0.04112153872847557,
1339
+ "eval_runtime": 186.6486,
1340
+ "eval_samples_per_second": 6.193,
1341
+ "eval_steps_per_second": 6.193,
1342
+ "step": 1550
1343
+ },
1344
+ {
1345
+ "epoch": 2.400923432089265,
1346
+ "grad_norm": 0.5612645745277405,
1347
+ "learning_rate": 6.198587112295526e-05,
1348
+ "loss": 0.0155,
1349
+ "step": 1560
1350
+ },
1351
+ {
1352
+ "epoch": 2.41631396691035,
1353
+ "grad_norm": 0.20288218557834625,
1354
+ "learning_rate": 6.14629285449852e-05,
1355
+ "loss": 0.0246,
1356
+ "step": 1570
1357
+ },
1358
+ {
1359
+ "epoch": 2.431704501731435,
1360
+ "grad_norm": 0.2309695929288864,
1361
+ "learning_rate": 6.093865910598688e-05,
1362
+ "loss": 0.0217,
1363
+ "step": 1580
1364
+ },
1365
+ {
1366
+ "epoch": 2.44709503655252,
1367
+ "grad_norm": 0.23696504533290863,
1368
+ "learning_rate": 6.0413123491385025e-05,
1369
+ "loss": 0.0262,
1370
+ "step": 1590
1371
+ },
1372
+ {
1373
+ "epoch": 2.4624855713736054,
1374
+ "grad_norm": 0.38717809319496155,
1375
+ "learning_rate": 5.988638253316713e-05,
1376
+ "loss": 0.0189,
1377
+ "step": 1600
1378
+ },
1379
+ {
1380
+ "epoch": 2.4624855713736054,
1381
+ "eval_loss": 0.036341600120067596,
1382
+ "eval_runtime": 186.7956,
1383
+ "eval_samples_per_second": 6.189,
1384
+ "eval_steps_per_second": 6.189,
1385
+ "step": 1600
1386
+ },
1387
+ {
1388
+ "epoch": 2.47787610619469,
1389
+ "grad_norm": 0.22446145117282867,
1390
+ "learning_rate": 5.935849720284206e-05,
1391
+ "loss": 0.0182,
1392
+ "step": 1610
1393
+ },
1394
+ {
1395
+ "epoch": 2.4932666410157753,
1396
+ "grad_norm": 0.2164313942193985,
1397
+ "learning_rate": 5.8829528604382436e-05,
1398
+ "loss": 0.0236,
1399
+ "step": 1620
1400
+ },
1401
+ {
1402
+ "epoch": 2.50865717583686,
1403
+ "grad_norm": 0.14063049852848053,
1404
+ "learning_rate": 5.829953796715176e-05,
1405
+ "loss": 0.0208,
1406
+ "step": 1630
1407
+ },
1408
+ {
1409
+ "epoch": 2.5240477106579453,
1410
+ "grad_norm": 0.3135584890842438,
1411
+ "learning_rate": 5.7768586638816924e-05,
1412
+ "loss": 0.0236,
1413
+ "step": 1640
1414
+ },
1415
+ {
1416
+ "epoch": 2.5394382454790305,
1417
+ "grad_norm": 0.16733896732330322,
1418
+ "learning_rate": 5.723673607824705e-05,
1419
+ "loss": 0.0246,
1420
+ "step": 1650
1421
+ },
1422
+ {
1423
+ "epoch": 2.5394382454790305,
1424
+ "eval_loss": 0.0360361784696579,
1425
+ "eval_runtime": 186.9536,
1426
+ "eval_samples_per_second": 6.183,
1427
+ "eval_steps_per_second": 6.183,
1428
+ "step": 1650
1429
+ },
1430
+ {
1431
+ "epoch": 2.5548287803001153,
1432
+ "grad_norm": 0.3761216402053833,
1433
+ "learning_rate": 5.670404784839953e-05,
1434
+ "loss": 0.0202,
1435
+ "step": 1660
1436
+ },
1437
+ {
1438
+ "epoch": 2.5702193151212005,
1439
+ "grad_norm": 0.37585002183914185,
1440
+ "learning_rate": 5.6170583609193984e-05,
1441
+ "loss": 0.0231,
1442
+ "step": 1670
1443
+ },
1444
+ {
1445
+ "epoch": 2.5856098499422853,
1446
+ "grad_norm": 0.5329094529151917,
1447
+ "learning_rate": 5.56364051103749e-05,
1448
+ "loss": 0.0261,
1449
+ "step": 1680
1450
+ },
1451
+ {
1452
+ "epoch": 2.6010003847633705,
1453
+ "grad_norm": 0.28828349709510803,
1454
+ "learning_rate": 5.5101574184364056e-05,
1455
+ "loss": 0.025,
1456
+ "step": 1690
1457
+ },
1458
+ {
1459
+ "epoch": 2.6163909195844557,
1460
+ "grad_norm": 0.5588506460189819,
1461
+ "learning_rate": 5.4566152739103116e-05,
1462
+ "loss": 0.0244,
1463
+ "step": 1700
1464
+ },
1465
+ {
1466
+ "epoch": 2.6163909195844557,
1467
+ "eval_loss": 0.03538386896252632,
1468
+ "eval_runtime": 186.8111,
1469
+ "eval_samples_per_second": 6.188,
1470
+ "eval_steps_per_second": 6.188,
1471
+ "step": 1700
1472
+ },
1473
+ {
1474
+ "epoch": 2.6317814544055405,
1475
+ "grad_norm": 0.22283612191677094,
1476
+ "learning_rate": 5.403020275088786e-05,
1477
+ "loss": 0.0197,
1478
+ "step": 1710
1479
+ },
1480
+ {
1481
+ "epoch": 2.6471719892266257,
1482
+ "grad_norm": 0.27689316868782043,
1483
+ "learning_rate": 5.349378625719408e-05,
1484
+ "loss": 0.0327,
1485
+ "step": 1720
1486
+ },
1487
+ {
1488
+ "epoch": 2.6625625240477104,
1489
+ "grad_norm": 0.3931240141391754,
1490
+ "learning_rate": 5.2956965349496743e-05,
1491
+ "loss": 0.0252,
1492
+ "step": 1730
1493
+ },
1494
+ {
1495
+ "epoch": 2.6779530588687956,
1496
+ "grad_norm": 0.19020158052444458,
1497
+ "learning_rate": 5.241980216608261e-05,
1498
+ "loss": 0.018,
1499
+ "step": 1740
1500
+ },
1501
+ {
1502
+ "epoch": 2.693343593689881,
1503
+ "grad_norm": 0.11216674000024796,
1504
+ "learning_rate": 5.188235888485773e-05,
1505
+ "loss": 0.0295,
1506
+ "step": 1750
1507
+ },
1508
+ {
1509
+ "epoch": 2.693343593689881,
1510
+ "eval_loss": 0.03553741052746773,
1511
+ "eval_runtime": 186.4672,
1512
+ "eval_samples_per_second": 6.199,
1513
+ "eval_steps_per_second": 6.199,
1514
+ "step": 1750
1515
+ },
1516
+ {
1517
+ "epoch": 2.7087341285109656,
1518
+ "grad_norm": 0.19189698994159698,
1519
+ "learning_rate": 5.13446977161501e-05,
1520
+ "loss": 0.0174,
1521
+ "step": 1760
1522
+ },
1523
+ {
1524
+ "epoch": 2.724124663332051,
1525
+ "grad_norm": 0.37652498483657837,
1526
+ "learning_rate": 5.0806880895508766e-05,
1527
+ "loss": 0.0274,
1528
+ "step": 1770
1529
+ },
1530
+ {
1531
+ "epoch": 2.7395151981531356,
1532
+ "grad_norm": 0.4836426377296448,
1533
+ "learning_rate": 5.026897067649976e-05,
1534
+ "loss": 0.0286,
1535
+ "step": 1780
1536
+ },
1537
+ {
1538
+ "epoch": 2.754905732974221,
1539
+ "grad_norm": 0.20131860673427582,
1540
+ "learning_rate": 4.973102932350026e-05,
1541
+ "loss": 0.0228,
1542
+ "step": 1790
1543
+ },
1544
+ {
1545
+ "epoch": 2.770296267795306,
1546
+ "grad_norm": 0.3384079337120056,
1547
+ "learning_rate": 4.9193119104491245e-05,
1548
+ "loss": 0.0257,
1549
+ "step": 1800
1550
+ },
1551
+ {
1552
+ "epoch": 2.770296267795306,
1553
+ "eval_loss": 0.03536887839436531,
1554
+ "eval_runtime": 186.2101,
1555
+ "eval_samples_per_second": 6.208,
1556
+ "eval_steps_per_second": 6.208,
1557
+ "step": 1800
1558
+ },
1559
+ {
1560
+ "epoch": 2.785686802616391,
1561
+ "grad_norm": 0.2767975330352783,
1562
+ "learning_rate": 4.86553022838499e-05,
1563
+ "loss": 0.0223,
1564
+ "step": 1810
1565
+ },
1566
+ {
1567
+ "epoch": 2.801077337437476,
1568
+ "grad_norm": 0.2422277182340622,
1569
+ "learning_rate": 4.8117641115142285e-05,
1570
+ "loss": 0.0244,
1571
+ "step": 1820
1572
+ },
1573
+ {
1574
+ "epoch": 2.8164678722585608,
1575
+ "grad_norm": 0.5190377831459045,
1576
+ "learning_rate": 4.758019783391741e-05,
1577
+ "loss": 0.0207,
1578
+ "step": 1830
1579
+ },
1580
+ {
1581
+ "epoch": 2.831858407079646,
1582
+ "grad_norm": 0.2180313616991043,
1583
+ "learning_rate": 4.704303465050327e-05,
1584
+ "loss": 0.0256,
1585
+ "step": 1840
1586
+ },
1587
+ {
1588
+ "epoch": 2.847248941900731,
1589
+ "grad_norm": 0.2425866425037384,
1590
+ "learning_rate": 4.6506213742805924e-05,
1591
+ "loss": 0.0313,
1592
+ "step": 1850
1593
+ },
1594
+ {
1595
+ "epoch": 2.847248941900731,
1596
+ "eval_loss": 0.03393126651644707,
1597
+ "eval_runtime": 186.1971,
1598
+ "eval_samples_per_second": 6.208,
1599
+ "eval_steps_per_second": 6.208,
1600
+ "step": 1850
1601
+ },
1602
+ {
1603
+ "epoch": 2.862639476721816,
1604
+ "grad_norm": 0.2784096598625183,
1605
+ "learning_rate": 4.5969797249112146e-05,
1606
+ "loss": 0.0183,
1607
+ "step": 1860
1608
+ },
1609
+ {
1610
+ "epoch": 2.878030011542901,
1611
+ "grad_norm": 0.3296208381652832,
1612
+ "learning_rate": 4.54338472608969e-05,
1613
+ "loss": 0.0286,
1614
+ "step": 1870
1615
+ },
1616
+ {
1617
+ "epoch": 2.893420546363986,
1618
+ "grad_norm": 0.5275260806083679,
1619
+ "learning_rate": 4.489842581563597e-05,
1620
+ "loss": 0.0176,
1621
+ "step": 1880
1622
+ },
1623
+ {
1624
+ "epoch": 2.908811081185071,
1625
+ "grad_norm": 0.15682271122932434,
1626
+ "learning_rate": 4.436359488962511e-05,
1627
+ "loss": 0.0193,
1628
+ "step": 1890
1629
+ },
1630
+ {
1631
+ "epoch": 2.9242016160061564,
1632
+ "grad_norm": 0.2102474868297577,
1633
+ "learning_rate": 4.382941639080602e-05,
1634
+ "loss": 0.0208,
1635
+ "step": 1900
1636
+ },
1637
+ {
1638
+ "epoch": 2.9242016160061564,
1639
+ "eval_loss": 0.034816108644008636,
1640
+ "eval_runtime": 186.8118,
1641
+ "eval_samples_per_second": 6.188,
1642
+ "eval_steps_per_second": 6.188,
1643
+ "step": 1900
1644
+ },
1645
+ {
1646
+ "epoch": 2.939592150827241,
1647
+ "grad_norm": 0.21557755768299103,
1648
+ "learning_rate": 4.3295952151600475e-05,
1649
+ "loss": 0.0228,
1650
+ "step": 1910
1651
+ },
1652
+ {
1653
+ "epoch": 2.9549826856483263,
1654
+ "grad_norm": 0.4167330861091614,
1655
+ "learning_rate": 4.276326392175296e-05,
1656
+ "loss": 0.0201,
1657
+ "step": 1920
1658
+ },
1659
+ {
1660
+ "epoch": 2.970373220469411,
1661
+ "grad_norm": 0.14496108889579773,
1662
+ "learning_rate": 4.2231413361183095e-05,
1663
+ "loss": 0.017,
1664
+ "step": 1930
1665
+ },
1666
+ {
1667
+ "epoch": 2.9857637552904963,
1668
+ "grad_norm": 0.327414870262146,
1669
+ "learning_rate": 4.1700462032848244e-05,
1670
+ "loss": 0.0187,
1671
+ "step": 1940
1672
+ },
1673
+ {
1674
+ "epoch": 3.0011542901115815,
1675
+ "grad_norm": 0.1764715611934662,
1676
+ "learning_rate": 4.117047139561758e-05,
1677
+ "loss": 0.0314,
1678
+ "step": 1950
1679
+ },
1680
+ {
1681
+ "epoch": 3.0011542901115815,
1682
+ "eval_loss": 0.034862760454416275,
1683
+ "eval_runtime": 186.7003,
1684
+ "eval_samples_per_second": 6.192,
1685
+ "eval_steps_per_second": 6.192,
1686
+ "step": 1950
1687
+ },
1688
+ {
1689
+ "epoch": 3.0165448249326663,
1690
+ "grad_norm": 0.10091342031955719,
1691
+ "learning_rate": 4.0641502797157966e-05,
1692
+ "loss": 0.01,
1693
+ "step": 1960
1694
+ },
1695
+ {
1696
+ "epoch": 3.0319353597537515,
1697
+ "grad_norm": 0.11954168230295181,
1698
+ "learning_rate": 4.011361746683288e-05,
1699
+ "loss": 0.012,
1700
+ "step": 1970
1701
+ },
1702
+ {
1703
+ "epoch": 3.0473258945748363,
1704
+ "grad_norm": 0.4728318750858307,
1705
+ "learning_rate": 3.958687650861499e-05,
1706
+ "loss": 0.0127,
1707
+ "step": 1980
1708
+ },
1709
+ {
1710
+ "epoch": 3.0627164293959215,
1711
+ "grad_norm": 0.22921116650104523,
1712
+ "learning_rate": 3.906134089401313e-05,
1713
+ "loss": 0.0078,
1714
+ "step": 1990
1715
+ },
1716
+ {
1717
+ "epoch": 3.0781069642170067,
1718
+ "grad_norm": 0.17478808760643005,
1719
+ "learning_rate": 3.853707145501482e-05,
1720
+ "loss": 0.0119,
1721
+ "step": 2000
1722
+ },
1723
+ {
1724
+ "epoch": 3.0781069642170067,
1725
+ "eval_loss": 0.0392003133893013,
1726
+ "eval_runtime": 186.2797,
1727
+ "eval_samples_per_second": 6.206,
1728
+ "eval_steps_per_second": 6.206,
1729
+ "step": 2000
1730
+ },
1731
+ {
1732
+ "epoch": 3.0934974990380915,
1733
+ "grad_norm": 0.536690890789032,
1734
+ "learning_rate": 3.801412887704475e-05,
1735
+ "loss": 0.0087,
1736
+ "step": 2010
1737
+ },
1738
+ {
1739
+ "epoch": 3.1088880338591767,
1740
+ "grad_norm": 0.08325193077325821,
1741
+ "learning_rate": 3.749257369194029e-05,
1742
+ "loss": 0.0102,
1743
+ "step": 2020
1744
+ },
1745
+ {
1746
+ "epoch": 3.1242785686802614,
1747
+ "grad_norm": 0.3025301694869995,
1748
+ "learning_rate": 3.697246627094487e-05,
1749
+ "loss": 0.0162,
1750
+ "step": 2030
1751
+ },
1752
+ {
1753
+ "epoch": 3.1396691035013466,
1754
+ "grad_norm": 0.0437934547662735,
1755
+ "learning_rate": 3.6453866817719726e-05,
1756
+ "loss": 0.0094,
1757
+ "step": 2040
1758
+ },
1759
+ {
1760
+ "epoch": 3.155059638322432,
1761
+ "grad_norm": 0.6723917126655579,
1762
+ "learning_rate": 3.593683536137533e-05,
1763
+ "loss": 0.0147,
1764
+ "step": 2050
1765
+ },
1766
+ {
1767
+ "epoch": 3.155059638322432,
1768
+ "eval_loss": 0.04251823201775551,
1769
+ "eval_runtime": 186.0299,
1770
+ "eval_samples_per_second": 6.214,
1771
+ "eval_steps_per_second": 6.214,
1772
+ "step": 2050
1773
+ },
1774
+ {
1775
+ "epoch": 3.1704501731435166,
1776
+ "grad_norm": 0.06159785017371178,
1777
+ "learning_rate": 3.542143174952282e-05,
1778
+ "loss": 0.0085,
1779
+ "step": 2060
1780
+ },
1781
+ {
1782
+ "epoch": 3.185840707964602,
1783
+ "grad_norm": 0.3324078321456909,
1784
+ "learning_rate": 3.490771564134643e-05,
1785
+ "loss": 0.0112,
1786
+ "step": 2070
1787
+ },
1788
+ {
1789
+ "epoch": 3.2012312427856866,
1790
+ "grad_norm": 0.4389561414718628,
1791
+ "learning_rate": 3.4395746500697925e-05,
1792
+ "loss": 0.0177,
1793
+ "step": 2080
1794
+ },
1795
+ {
1796
+ "epoch": 3.216621777606772,
1797
+ "grad_norm": 0.30180397629737854,
1798
+ "learning_rate": 3.388558358921343e-05,
1799
+ "loss": 0.0112,
1800
+ "step": 2090
1801
+ },
1802
+ {
1803
+ "epoch": 3.232012312427857,
1804
+ "grad_norm": 0.18360494077205658,
1805
+ "learning_rate": 3.337728595945378e-05,
1806
+ "loss": 0.011,
1807
+ "step": 2100
1808
+ },
1809
+ {
1810
+ "epoch": 3.232012312427857,
1811
+ "eval_loss": 0.040228795260190964,
1812
+ "eval_runtime": 186.1617,
1813
+ "eval_samples_per_second": 6.21,
1814
+ "eval_steps_per_second": 6.21,
1815
+ "step": 2100
1816
+ },
1817
+ {
1818
+ "epoch": 3.247402847248942,
1819
+ "grad_norm": 0.1583905965089798,
1820
+ "learning_rate": 3.287091244806907e-05,
1821
+ "loss": 0.0104,
1822
+ "step": 2110
1823
+ },
1824
+ {
1825
+ "epoch": 3.262793382070027,
1826
+ "grad_norm": 0.18586666882038116,
1827
+ "learning_rate": 3.2366521668988106e-05,
1828
+ "loss": 0.0107,
1829
+ "step": 2120
1830
+ },
1831
+ {
1832
+ "epoch": 3.2781839168911118,
1833
+ "grad_norm": 0.389637291431427,
1834
+ "learning_rate": 3.186417200663379e-05,
1835
+ "loss": 0.0168,
1836
+ "step": 2130
1837
+ },
1838
+ {
1839
+ "epoch": 3.293574451712197,
1840
+ "grad_norm": 0.093821682035923,
1841
+ "learning_rate": 3.136392160916495e-05,
1842
+ "loss": 0.0079,
1843
+ "step": 2140
1844
+ },
1845
+ {
1846
+ "epoch": 3.308964986533282,
1847
+ "grad_norm": 0.5508767366409302,
1848
+ "learning_rate": 3.086582838174551e-05,
1849
+ "loss": 0.012,
1850
+ "step": 2150
1851
+ },
1852
+ {
1853
+ "epoch": 3.308964986533282,
1854
+ "eval_loss": 0.04161189869046211,
1855
+ "eval_runtime": 186.4024,
1856
+ "eval_samples_per_second": 6.202,
1857
+ "eval_steps_per_second": 6.202,
1858
+ "step": 2150
1859
+ },
1860
+ {
1861
+ "epoch": 3.324355521354367,
1862
+ "grad_norm": 0.08765236288309097,
1863
+ "learning_rate": 3.036994997984194e-05,
1864
+ "loss": 0.0131,
1865
+ "step": 2160
1866
+ },
1867
+ {
1868
+ "epoch": 3.339746056175452,
1869
+ "grad_norm": 0.38336998224258423,
1870
+ "learning_rate": 2.9876343802549357e-05,
1871
+ "loss": 0.0135,
1872
+ "step": 2170
1873
+ },
1874
+ {
1875
+ "epoch": 3.355136590996537,
1876
+ "grad_norm": 0.2137378603219986,
1877
+ "learning_rate": 2.938506698594755e-05,
1878
+ "loss": 0.01,
1879
+ "step": 2180
1880
+ },
1881
+ {
1882
+ "epoch": 3.370527125817622,
1883
+ "grad_norm": 0.6786463856697083,
1884
+ "learning_rate": 2.8896176396487334e-05,
1885
+ "loss": 0.0108,
1886
+ "step": 2190
1887
+ },
1888
+ {
1889
+ "epoch": 3.3859176606387074,
1890
+ "grad_norm": 0.2550009489059448,
1891
+ "learning_rate": 2.8409728624408067e-05,
1892
+ "loss": 0.0205,
1893
+ "step": 2200
1894
+ },
1895
+ {
1896
+ "epoch": 3.3859176606387074,
1897
+ "eval_loss": 0.03981276601552963,
1898
+ "eval_runtime": 186.4982,
1899
+ "eval_samples_per_second": 6.198,
1900
+ "eval_steps_per_second": 6.198,
1901
+ "step": 2200
1902
+ },
1903
+ {
1904
+ "epoch": 3.401308195459792,
1905
+ "grad_norm": 0.531782865524292,
1906
+ "learning_rate": 2.7925779977187215e-05,
1907
+ "loss": 0.0139,
1908
+ "step": 2210
1909
+ },
1910
+ {
1911
+ "epoch": 3.4166987302808773,
1912
+ "grad_norm": 0.30775323510169983,
1913
+ "learning_rate": 2.7444386473022686e-05,
1914
+ "loss": 0.0108,
1915
+ "step": 2220
1916
+ },
1917
+ {
1918
+ "epoch": 3.432089265101962,
1919
+ "grad_norm": 0.45309802889823914,
1920
+ "learning_rate": 2.696560383434854e-05,
1921
+ "loss": 0.0166,
1922
+ "step": 2230
1923
+ },
1924
+ {
1925
+ "epoch": 3.4474797999230473,
1926
+ "grad_norm": 0.1881212443113327,
1927
+ "learning_rate": 2.6489487481384988e-05,
1928
+ "loss": 0.0135,
1929
+ "step": 2240
1930
+ },
1931
+ {
1932
+ "epoch": 3.4628703347441325,
1933
+ "grad_norm": 0.1511940211057663,
1934
+ "learning_rate": 2.601609252572339e-05,
1935
+ "loss": 0.0127,
1936
+ "step": 2250
1937
+ },
1938
+ {
1939
+ "epoch": 3.4628703347441325,
1940
+ "eval_loss": 0.039891570806503296,
1941
+ "eval_runtime": 186.7336,
1942
+ "eval_samples_per_second": 6.191,
1943
+ "eval_steps_per_second": 6.191,
1944
+ "step": 2250
1945
+ },
1946
+ {
1947
+ "epoch": 3.4782608695652173,
1948
+ "grad_norm": 0.049151744693517685,
1949
+ "learning_rate": 2.554547376394692e-05,
1950
+ "loss": 0.0073,
1951
+ "step": 2260
1952
+ },
1953
+ {
1954
+ "epoch": 3.4936514043863025,
1955
+ "grad_norm": 0.42421895265579224,
1956
+ "learning_rate": 2.5077685671287808e-05,
1957
+ "loss": 0.0108,
1958
+ "step": 2270
1959
+ },
1960
+ {
1961
+ "epoch": 3.5090419392073873,
1962
+ "grad_norm": 0.3423459529876709,
1963
+ "learning_rate": 2.4612782395321593e-05,
1964
+ "loss": 0.0148,
1965
+ "step": 2280
1966
+ },
1967
+ {
1968
+ "epoch": 3.5244324740284725,
1969
+ "grad_norm": 0.324720561504364,
1970
+ "learning_rate": 2.4150817749699496e-05,
1971
+ "loss": 0.0086,
1972
+ "step": 2290
1973
+ },
1974
+ {
1975
+ "epoch": 3.5398230088495577,
1976
+ "grad_norm": 0.1445930153131485,
1977
+ "learning_rate": 2.3691845207919357e-05,
1978
+ "loss": 0.0141,
1979
+ "step": 2300
1980
+ },
1981
+ {
1982
+ "epoch": 3.5398230088495577,
1983
+ "eval_loss": 0.0418756864964962,
1984
+ "eval_runtime": 186.4389,
1985
+ "eval_samples_per_second": 6.2,
1986
+ "eval_steps_per_second": 6.2,
1987
+ "step": 2300
1988
+ },
1989
+ {
1990
+ "epoch": 3.5552135436706425,
1991
+ "grad_norm": 0.27503931522369385,
1992
+ "learning_rate": 2.3235917897135934e-05,
1993
+ "loss": 0.0127,
1994
+ "step": 2310
1995
+ },
1996
+ {
1997
+ "epoch": 3.5706040784917277,
1998
+ "grad_norm": 0.46346715092658997,
1999
+ "learning_rate": 2.2783088592011303e-05,
2000
+ "loss": 0.0145,
2001
+ "step": 2320
2002
+ },
2003
+ {
2004
+ "epoch": 3.5859946133128124,
2005
+ "grad_norm": 0.11502953618764877,
2006
+ "learning_rate": 2.233340970860608e-05,
2007
+ "loss": 0.0085,
2008
+ "step": 2330
2009
+ },
2010
+ {
2011
+ "epoch": 3.6013851481338977,
2012
+ "grad_norm": 0.23123833537101746,
2013
+ "learning_rate": 2.1886933298312125e-05,
2014
+ "loss": 0.0151,
2015
+ "step": 2340
2016
+ },
2017
+ {
2018
+ "epoch": 3.616775682954983,
2019
+ "grad_norm": 0.17446036636829376,
2020
+ "learning_rate": 2.1443711041827503e-05,
2021
+ "loss": 0.0081,
2022
+ "step": 2350
2023
+ },
2024
+ {
2025
+ "epoch": 3.616775682954983,
2026
+ "eval_loss": 0.043476805090904236,
2027
+ "eval_runtime": 185.8129,
2028
+ "eval_samples_per_second": 6.221,
2029
+ "eval_steps_per_second": 6.221,
2030
+ "step": 2350
2031
+ },
2032
+ {
2033
+ "epoch": 3.6321662177760676,
2034
+ "grad_norm": 0.21171227097511292,
2035
+ "learning_rate": 2.1003794243174252e-05,
2036
+ "loss": 0.0159,
2037
+ "step": 2360
2038
+ },
2039
+ {
2040
+ "epoch": 3.647556752597153,
2041
+ "grad_norm": 0.20531825721263885,
2042
+ "learning_rate": 2.0567233823759886e-05,
2043
+ "loss": 0.0094,
2044
+ "step": 2370
2045
+ },
2046
+ {
2047
+ "epoch": 3.6629472874182376,
2048
+ "grad_norm": 0.20440693199634552,
2049
+ "learning_rate": 2.0134080316483113e-05,
2050
+ "loss": 0.013,
2051
+ "step": 2380
2052
+ },
2053
+ {
2054
+ "epoch": 3.678337822239323,
2055
+ "grad_norm": 0.4047004282474518,
2056
+ "learning_rate": 1.970438385988452e-05,
2057
+ "loss": 0.0153,
2058
+ "step": 2390
2059
+ },
2060
+ {
2061
+ "epoch": 3.693728357060408,
2062
+ "grad_norm": 0.08073116838932037,
2063
+ "learning_rate": 1.927819419234292e-05,
2064
+ "loss": 0.0132,
2065
+ "step": 2400
2066
+ },
2067
+ {
2068
+ "epoch": 3.693728357060408,
2069
+ "eval_loss": 0.04118052124977112,
2070
+ "eval_runtime": 185.9242,
2071
+ "eval_samples_per_second": 6.218,
2072
+ "eval_steps_per_second": 6.218,
2073
+ "step": 2400
2074
+ },
2075
+ {
2076
+ "epoch": 3.709118891881493,
2077
+ "grad_norm": 0.36109527945518494,
2078
+ "learning_rate": 1.885556064631801e-05,
2079
+ "loss": 0.011,
2080
+ "step": 2410
2081
+ },
2082
+ {
2083
+ "epoch": 3.724509426702578,
2084
+ "grad_norm": 0.29550692439079285,
2085
+ "learning_rate": 1.843653214264003e-05,
2086
+ "loss": 0.0091,
2087
+ "step": 2420
2088
+ },
2089
+ {
2090
+ "epoch": 3.7398999615236628,
2091
+ "grad_norm": 0.6761743426322937,
2092
+ "learning_rate": 1.8021157184847087e-05,
2093
+ "loss": 0.0147,
2094
+ "step": 2430
2095
+ },
2096
+ {
2097
+ "epoch": 3.755290496344748,
2098
+ "grad_norm": 0.38532111048698425,
2099
+ "learning_rate": 1.7609483853570668e-05,
2100
+ "loss": 0.0086,
2101
+ "step": 2440
2102
+ },
2103
+ {
2104
+ "epoch": 3.770681031165833,
2105
+ "grad_norm": 0.2847141921520233,
2106
+ "learning_rate": 1.720155980097034e-05,
2107
+ "loss": 0.0111,
2108
+ "step": 2450
2109
+ },
2110
+ {
2111
+ "epoch": 3.770681031165833,
2112
+ "eval_loss": 0.04333437979221344,
2113
+ "eval_runtime": 185.5961,
2114
+ "eval_samples_per_second": 6.229,
2115
+ "eval_steps_per_second": 6.229,
2116
+ "step": 2450
2117
+ },
2118
+ {
2119
+ "epoch": 3.786071565986918,
2120
+ "grad_norm": 0.22558213770389557,
2121
+ "learning_rate": 1.6797432245217736e-05,
2122
+ "loss": 0.0113,
2123
+ "step": 2460
2124
+ },
2125
+ {
2126
+ "epoch": 3.801462100808003,
2127
+ "grad_norm": 0.13944610953330994,
2128
+ "learning_rate": 1.6397147965031072e-05,
2129
+ "loss": 0.0076,
2130
+ "step": 2470
2131
+ },
2132
+ {
2133
+ "epoch": 3.816852635629088,
2134
+ "grad_norm": 0.32348164916038513,
2135
+ "learning_rate": 1.600075329426033e-05,
2136
+ "loss": 0.012,
2137
+ "step": 2480
2138
+ },
2139
+ {
2140
+ "epoch": 3.832243170450173,
2141
+ "grad_norm": 0.556498646736145,
2142
+ "learning_rate": 1.560829411652403e-05,
2143
+ "loss": 0.0137,
2144
+ "step": 2490
2145
+ },
2146
+ {
2147
+ "epoch": 3.8476337052712584,
2148
+ "grad_norm": 0.19787055253982544,
2149
+ "learning_rate": 1.521981585989809e-05,
2150
+ "loss": 0.0069,
2151
+ "step": 2500
2152
+ },
2153
+ {
2154
+ "epoch": 3.8476337052712584,
2155
+ "eval_loss": 0.044614341109991074,
2156
+ "eval_runtime": 184.6686,
2157
+ "eval_samples_per_second": 6.26,
2158
+ "eval_steps_per_second": 6.26,
2159
+ "step": 2500
2160
+ },
2161
+ {
2162
+ "epoch": 3.863024240092343,
2163
+ "grad_norm": 0.23233471810817719,
2164
+ "learning_rate": 1.4835363491657412e-05,
2165
+ "loss": 0.0141,
2166
+ "step": 2510
2167
+ },
2168
+ {
2169
+ "epoch": 3.8784147749134283,
2170
+ "grad_norm": 0.8727635741233826,
2171
+ "learning_rate": 1.4454981513070791e-05,
2172
+ "loss": 0.0062,
2173
+ "step": 2520
2174
+ },
2175
+ {
2176
+ "epoch": 3.893805309734513,
2177
+ "grad_norm": 0.01985669508576393,
2178
+ "learning_rate": 1.4078713954249873e-05,
2179
+ "loss": 0.0093,
2180
+ "step": 2530
2181
+ },
2182
+ {
2183
+ "epoch": 3.9091958445555983,
2184
+ "grad_norm": 0.19380433857440948,
2185
+ "learning_rate": 1.3706604369052434e-05,
2186
+ "loss": 0.0059,
2187
+ "step": 2540
2188
+ },
2189
+ {
2190
+ "epoch": 3.9245863793766835,
2191
+ "grad_norm": 0.30975109338760376,
2192
+ "learning_rate": 1.3338695830041047e-05,
2193
+ "loss": 0.0135,
2194
+ "step": 2550
2195
+ },
2196
+ {
2197
+ "epoch": 3.9245863793766835,
2198
+ "eval_loss": 0.04540552943944931,
2199
+ "eval_runtime": 183.9066,
2200
+ "eval_samples_per_second": 6.286,
2201
+ "eval_steps_per_second": 6.286,
2202
+ "step": 2550
2203
+ },
2204
+ {
2205
+ "epoch": 3.9399769141977683,
2206
+ "grad_norm": 0.36627084016799927,
2207
+ "learning_rate": 1.2975030923497262e-05,
2208
+ "loss": 0.0127,
2209
+ "step": 2560
2210
+ },
2211
+ {
2212
+ "epoch": 3.9553674490188535,
2213
+ "grad_norm": 0.3993094861507416,
2214
+ "learning_rate": 1.2615651744492151e-05,
2215
+ "loss": 0.008,
2216
+ "step": 2570
2217
+ },
2218
+ {
2219
+ "epoch": 3.9707579838399383,
2220
+ "grad_norm": 0.0302486140280962,
2221
+ "learning_rate": 1.2260599892013719e-05,
2222
+ "loss": 0.014,
2223
+ "step": 2580
2224
+ },
2225
+ {
2226
+ "epoch": 3.9861485186610235,
2227
+ "grad_norm": 0.4973717927932739,
2228
+ "learning_rate": 1.1909916464151715e-05,
2229
+ "loss": 0.009,
2230
+ "step": 2590
2231
+ },
2232
+ {
2233
+ "epoch": 4.001539053482109,
2234
+ "grad_norm": 0.07611800730228424,
2235
+ "learning_rate": 1.1563642053340406e-05,
2236
+ "loss": 0.0093,
2237
+ "step": 2600
2238
+ },
2239
+ {
2240
+ "epoch": 4.001539053482109,
2241
+ "eval_loss": 0.04523477330803871,
2242
+ "eval_runtime": 182.4267,
2243
+ "eval_samples_per_second": 6.337,
2244
+ "eval_steps_per_second": 6.337,
2245
+ "step": 2600
2246
+ },
2247
+ {
2248
+ "epoch": 4.016929588303194,
2249
+ "grad_norm": 0.04856440797448158,
2250
+ "learning_rate": 1.1221816741659964e-05,
2251
+ "loss": 0.0061,
2252
+ "step": 2610
2253
+ },
2254
+ {
2255
+ "epoch": 4.032320123124278,
2256
+ "grad_norm": 0.335890531539917,
2257
+ "learning_rate": 1.0884480096196803e-05,
2258
+ "loss": 0.0027,
2259
+ "step": 2620
2260
+ },
2261
+ {
2262
+ "epoch": 4.047710657945363,
2263
+ "grad_norm": 0.3047681748867035,
2264
+ "learning_rate": 1.0551671164463666e-05,
2265
+ "loss": 0.0032,
2266
+ "step": 2630
2267
+ },
2268
+ {
2269
+ "epoch": 4.063101192766449,
2270
+ "grad_norm": 0.0912618488073349,
2271
+ "learning_rate": 1.0223428469879736e-05,
2272
+ "loss": 0.0058,
2273
+ "step": 2640
2274
+ },
2275
+ {
2276
+ "epoch": 4.078491727587534,
2277
+ "grad_norm": 0.07931726425886154,
2278
+ "learning_rate": 9.899790007311455e-06,
2279
+ "loss": 0.0024,
2280
+ "step": 2650
2281
+ },
2282
+ {
2283
+ "epoch": 4.078491727587534,
2284
+ "eval_loss": 0.04883251711726189,
2285
+ "eval_runtime": 180.2492,
2286
+ "eval_samples_per_second": 6.413,
2287
+ "eval_steps_per_second": 6.413,
2288
+ "step": 2650
2289
+ },
2290
+ {
2291
+ "epoch": 4.093882262408619,
2292
+ "grad_norm": 0.5609334111213684,
2293
+ "learning_rate": 9.580793238674573e-06,
2294
+ "loss": 0.0065,
2295
+ "step": 2660
2296
+ },
2297
+ {
2298
+ "epoch": 4.109272797229703,
2299
+ "grad_norm": 0.7794962525367737,
2300
+ "learning_rate": 9.266475088597781e-06,
2301
+ "loss": 0.0035,
2302
+ "step": 2670
2303
+ },
2304
+ {
2305
+ "epoch": 4.124663332050789,
2306
+ "grad_norm": 0.09867623448371887,
2307
+ "learning_rate": 8.956871940148681e-06,
2308
+ "loss": 0.0035,
2309
+ "step": 2680
2310
+ },
2311
+ {
2312
+ "epoch": 4.140053866871874,
2313
+ "grad_norm": 0.08890987932682037,
2314
+ "learning_rate": 8.65201963062225e-06,
2315
+ "loss": 0.0042,
2316
+ "step": 2690
2317
+ },
2318
+ {
2319
+ "epoch": 4.155444401692959,
2320
+ "grad_norm": 0.17334403097629547,
2321
+ "learning_rate": 8.351953447392674e-06,
2322
+ "loss": 0.0082,
2323
+ "step": 2700
2324
+ },
2325
+ {
2326
+ "epoch": 4.155444401692959,
2327
+ "eval_loss": 0.05498456954956055,
2328
+ "eval_runtime": 177.9616,
2329
+ "eval_samples_per_second": 6.496,
2330
+ "eval_steps_per_second": 6.496,
2331
+ "step": 2700
2332
+ },
2333
+ {
2334
+ "epoch": 4.170834936514044,
2335
+ "grad_norm": 0.4304162561893463,
2336
+ "learning_rate": 8.056708123828738e-06,
2337
+ "loss": 0.0058,
2338
+ "step": 2710
2339
+ },
2340
+ {
2341
+ "epoch": 4.186225471335129,
2342
+ "grad_norm": 0.22083640098571777,
2343
+ "learning_rate": 7.76631783527334e-06,
2344
+ "loss": 0.0107,
2345
+ "step": 2720
2346
+ },
2347
+ {
2348
+ "epoch": 4.201616006156214,
2349
+ "grad_norm": 0.32587379217147827,
2350
+ "learning_rate": 7.4808161950876145e-06,
2351
+ "loss": 0.0059,
2352
+ "step": 2730
2353
+ },
2354
+ {
2355
+ "epoch": 4.217006540977299,
2356
+ "grad_norm": 0.9534060955047607,
2357
+ "learning_rate": 7.200236250760111e-06,
2358
+ "loss": 0.0066,
2359
+ "step": 2740
2360
+ },
2361
+ {
2362
+ "epoch": 4.232397075798384,
2363
+ "grad_norm": 0.18303728103637695,
2364
+ "learning_rate": 6.924610480081478e-06,
2365
+ "loss": 0.004,
2366
+ "step": 2750
2367
+ },
2368
+ {
2369
+ "epoch": 4.232397075798384,
2370
+ "eval_loss": 0.05399877950549126,
2371
+ "eval_runtime": 176.8479,
2372
+ "eval_samples_per_second": 6.537,
2373
+ "eval_steps_per_second": 6.537,
2374
+ "step": 2750
2375
+ },
2376
+ {
2377
+ "epoch": 4.247787610619469,
2378
+ "grad_norm": 0.08475390076637268,
2379
+ "learning_rate": 6.6539707873850774e-06,
2380
+ "loss": 0.002,
2381
+ "step": 2760
2382
+ },
2383
+ {
2384
+ "epoch": 4.263178145440554,
2385
+ "grad_norm": 0.046780169010162354,
2386
+ "learning_rate": 6.3883484998539525e-06,
2387
+ "loss": 0.0034,
2388
+ "step": 2770
2389
+ },
2390
+ {
2391
+ "epoch": 4.278568680261639,
2392
+ "grad_norm": 0.37187516689300537,
2393
+ "learning_rate": 6.127774363894667e-06,
2394
+ "loss": 0.0029,
2395
+ "step": 2780
2396
+ },
2397
+ {
2398
+ "epoch": 4.293959215082724,
2399
+ "grad_norm": 0.22455869615077972,
2400
+ "learning_rate": 5.872278541578352e-06,
2401
+ "loss": 0.0036,
2402
+ "step": 2790
2403
+ },
2404
+ {
2405
+ "epoch": 4.309349749903809,
2406
+ "grad_norm": 0.1463429480791092,
2407
+ "learning_rate": 5.6218906071493275e-06,
2408
+ "loss": 0.0044,
2409
+ "step": 2800
2410
+ },
2411
+ {
2412
+ "epoch": 4.309349749903809,
2413
+ "eval_loss": 0.0570867583155632,
2414
+ "eval_runtime": 176.453,
2415
+ "eval_samples_per_second": 6.551,
2416
+ "eval_steps_per_second": 6.551,
2417
+ "step": 2800
2418
+ },
2419
+ {
2420
+ "epoch": 4.324740284724895,
2421
+ "grad_norm": 0.4433397054672241,
2422
+ "learning_rate": 5.376639543601858e-06,
2423
+ "loss": 0.0045,
2424
+ "step": 2810
2425
+ },
2426
+ {
2427
+ "epoch": 4.340130819545979,
2428
+ "grad_norm": 0.1657050997018814,
2429
+ "learning_rate": 5.136553739325256e-06,
2430
+ "loss": 0.0031,
2431
+ "step": 2820
2432
+ },
2433
+ {
2434
+ "epoch": 4.355521354367064,
2435
+ "grad_norm": 0.11662856489419937,
2436
+ "learning_rate": 4.901660984817908e-06,
2437
+ "loss": 0.0026,
2438
+ "step": 2830
2439
+ },
2440
+ {
2441
+ "epoch": 4.370911889188149,
2442
+ "grad_norm": 0.02125265821814537,
2443
+ "learning_rate": 4.671988469470434e-06,
2444
+ "loss": 0.0035,
2445
+ "step": 2840
2446
+ },
2447
+ {
2448
+ "epoch": 4.3863024240092345,
2449
+ "grad_norm": 0.05928665027022362,
2450
+ "learning_rate": 4.447562778418435e-06,
2451
+ "loss": 0.0027,
2452
+ "step": 2850
2453
+ },
2454
+ {
2455
+ "epoch": 4.3863024240092345,
2456
+ "eval_loss": 0.059105079621076584,
2457
+ "eval_runtime": 174.6544,
2458
+ "eval_samples_per_second": 6.619,
2459
+ "eval_steps_per_second": 6.619,
2460
+ "step": 2850
2461
+ },
2462
+ {
2463
+ "epoch": 4.40169295883032,
2464
+ "grad_norm": 0.26842960715293884,
2465
+ "learning_rate": 4.228409889465218e-06,
2466
+ "loss": 0.0024,
2467
+ "step": 2860
2468
+ },
2469
+ {
2470
+ "epoch": 4.417083493651404,
2471
+ "grad_norm": 0.06822570413351059,
2472
+ "learning_rate": 4.014555170074824e-06,
2473
+ "loss": 0.0018,
2474
+ "step": 2870
2475
+ },
2476
+ {
2477
+ "epoch": 4.432474028472489,
2478
+ "grad_norm": 0.06828371435403824,
2479
+ "learning_rate": 3.8060233744356633e-06,
2480
+ "loss": 0.0095,
2481
+ "step": 2880
2482
+ },
2483
+ {
2484
+ "epoch": 4.4478645632935745,
2485
+ "grad_norm": 0.03534894064068794,
2486
+ "learning_rate": 3.602838640595152e-06,
2487
+ "loss": 0.0033,
2488
+ "step": 2890
2489
+ },
2490
+ {
2491
+ "epoch": 4.46325509811466,
2492
+ "grad_norm": 0.36536815762519836,
2493
+ "learning_rate": 3.4050244876656866e-06,
2494
+ "loss": 0.0044,
2495
+ "step": 2900
2496
+ },
2497
+ {
2498
+ "epoch": 4.46325509811466,
2499
+ "eval_loss": 0.059850871562957764,
2500
+ "eval_runtime": 175.0039,
2501
+ "eval_samples_per_second": 6.606,
2502
+ "eval_steps_per_second": 6.606,
2503
+ "step": 2900
2504
+ },
2505
+ {
2506
+ "epoch": 4.478645632935745,
2507
+ "grad_norm": 0.12761013209819794,
2508
+ "learning_rate": 3.2126038131022552e-06,
2509
+ "loss": 0.0113,
2510
+ "step": 2910
2511
+ },
2512
+ {
2513
+ "epoch": 4.494036167756829,
2514
+ "grad_norm": 0.09695135056972504,
2515
+ "learning_rate": 3.025598890051995e-06,
2516
+ "loss": 0.0043,
2517
+ "step": 2920
2518
+ },
2519
+ {
2520
+ "epoch": 4.5094267025779144,
2521
+ "grad_norm": 0.29140061140060425,
2522
+ "learning_rate": 2.8440313647760288e-06,
2523
+ "loss": 0.0029,
2524
+ "step": 2930
2525
+ },
2526
+ {
2527
+ "epoch": 4.524817237399,
2528
+ "grad_norm": 0.38758528232574463,
2529
+ "learning_rate": 2.6679222541438397e-06,
2530
+ "loss": 0.0065,
2531
+ "step": 2940
2532
+ },
2533
+ {
2534
+ "epoch": 4.540207772220085,
2535
+ "grad_norm": 0.011333267204463482,
2536
+ "learning_rate": 2.4972919432005582e-06,
2537
+ "loss": 0.0017,
2538
+ "step": 2950
2539
+ },
2540
+ {
2541
+ "epoch": 4.540207772220085,
2542
+ "eval_loss": 0.05833715572953224,
2543
+ "eval_runtime": 174.9986,
2544
+ "eval_samples_per_second": 6.606,
2545
+ "eval_steps_per_second": 6.606,
2546
+ "step": 2950
2547
+ },
2548
+ {
2549
+ "epoch": 4.555598307041169,
2550
+ "grad_norm": 0.10328371077775955,
2551
+ "learning_rate": 2.3321601828073135e-06,
2552
+ "loss": 0.0027,
2553
+ "step": 2960
2554
+ },
2555
+ {
2556
+ "epoch": 4.570988841862254,
2557
+ "grad_norm": 0.07473993301391602,
2558
+ "learning_rate": 2.1725460873550317e-06,
2559
+ "loss": 0.0074,
2560
+ "step": 2970
2561
+ },
2562
+ {
2563
+ "epoch": 4.58637937668334,
2564
+ "grad_norm": 0.0183301642537117,
2565
+ "learning_rate": 2.0184681325519096e-06,
2566
+ "loss": 0.0054,
2567
+ "step": 2980
2568
+ },
2569
+ {
2570
+ "epoch": 4.601769911504425,
2571
+ "grad_norm": 0.2049105167388916,
2572
+ "learning_rate": 1.869944153284786e-06,
2573
+ "loss": 0.0055,
2574
+ "step": 2990
2575
+ },
2576
+ {
2577
+ "epoch": 4.61716044632551,
2578
+ "grad_norm": 0.04020959138870239,
2579
+ "learning_rate": 1.7269913415547456e-06,
2580
+ "loss": 0.0034,
2581
+ "step": 3000
2582
+ },
2583
+ {
2584
+ "epoch": 4.61716044632551,
2585
+ "eval_loss": 0.05813543125987053,
2586
+ "eval_runtime": 174.7446,
2587
+ "eval_samples_per_second": 6.615,
2588
+ "eval_steps_per_second": 6.615,
2589
+ "step": 3000
2590
+ },
2591
+ {
2592
+ "epoch": 4.632550981146595,
2593
+ "grad_norm": 0.20188899338245392,
2594
+ "learning_rate": 1.589626244487069e-06,
2595
+ "loss": 0.0026,
2596
+ "step": 3010
2597
+ },
2598
+ {
2599
+ "epoch": 4.64794151596768,
2600
+ "grad_norm": 0.2812189757823944,
2601
+ "learning_rate": 1.4578647624158726e-06,
2602
+ "loss": 0.0069,
2603
+ "step": 3020
2604
+ },
2605
+ {
2606
+ "epoch": 4.663332050788765,
2607
+ "grad_norm": 0.8022979497909546,
2608
+ "learning_rate": 1.3317221470436293e-06,
2609
+ "loss": 0.0059,
2610
+ "step": 3030
2611
+ },
2612
+ {
2613
+ "epoch": 4.67872258560985,
2614
+ "grad_norm": 0.02248234860599041,
2615
+ "learning_rate": 1.2112129996757315e-06,
2616
+ "loss": 0.0091,
2617
+ "step": 3040
2618
+ },
2619
+ {
2620
+ "epoch": 4.694113120430935,
2621
+ "grad_norm": 0.00878127757459879,
2622
+ "learning_rate": 1.0963512695303546e-06,
2623
+ "loss": 0.0048,
2624
+ "step": 3050
2625
+ },
2626
+ {
2627
+ "epoch": 4.694113120430935,
2628
+ "eval_loss": 0.05782487243413925,
2629
+ "eval_runtime": 174.7306,
2630
+ "eval_samples_per_second": 6.616,
2631
+ "eval_steps_per_second": 6.616,
2632
+ "step": 3050
2633
+ },
2634
+ {
2635
+ "epoch": 4.7095036552520195,
2636
+ "grad_norm": 0.05645116791129112,
2637
+ "learning_rate": 9.871502521237975e-07,
2638
+ "loss": 0.0032,
2639
+ "step": 3060
2640
+ },
2641
+ {
2642
+ "epoch": 4.724894190073105,
2643
+ "grad_norm": 0.3131750822067261,
2644
+ "learning_rate": 8.83622587731514e-07,
2645
+ "loss": 0.0033,
2646
+ "step": 3070
2647
+ },
2648
+ {
2649
+ "epoch": 4.74028472489419,
2650
+ "grad_norm": 0.44069525599479675,
2651
+ "learning_rate": 7.857802599249564e-07,
2652
+ "loss": 0.0107,
2653
+ "step": 3080
2654
+ },
2655
+ {
2656
+ "epoch": 4.755675259715275,
2657
+ "grad_norm": 0.14901208877563477,
2658
+ "learning_rate": 6.936345941844335e-07,
2659
+ "loss": 0.0038,
2660
+ "step": 3090
2661
+ },
2662
+ {
2663
+ "epoch": 4.77106579453636,
2664
+ "grad_norm": 0.11920231580734253,
2665
+ "learning_rate": 6.071962565881939e-07,
2666
+ "loss": 0.0051,
2667
+ "step": 3100
2668
+ },
2669
+ {
2670
+ "epoch": 4.77106579453636,
2671
+ "eval_loss": 0.0577433742582798,
2672
+ "eval_runtime": 174.4067,
2673
+ "eval_samples_per_second": 6.628,
2674
+ "eval_steps_per_second": 6.628,
2675
+ "step": 3100
2676
+ },
2677
+ {
2678
+ "epoch": 4.786456329357446,
2679
+ "grad_norm": 0.17919094860553741,
2680
+ "learning_rate": 5.264752525777961e-07,
2681
+ "loss": 0.0095,
2682
+ "step": 3110
2683
+ },
2684
+ {
2685
+ "epoch": 4.80184686417853,
2686
+ "grad_norm": 0.10345309972763062,
2687
+ "learning_rate": 4.5148092579991863e-07,
2688
+ "loss": 0.002,
2689
+ "step": 3120
2690
+ },
2691
+ {
2692
+ "epoch": 4.817237398999615,
2693
+ "grad_norm": 0.03707447648048401,
2694
+ "learning_rate": 3.822219570248531e-07,
2695
+ "loss": 0.006,
2696
+ "step": 3130
2697
+ },
2698
+ {
2699
+ "epoch": 4.8326279338207,
2700
+ "grad_norm": 0.24922269582748413,
2701
+ "learning_rate": 3.187063631416742e-07,
2702
+ "loss": 0.0026,
2703
+ "step": 3140
2704
+ },
2705
+ {
2706
+ "epoch": 4.8480184686417855,
2707
+ "grad_norm": 0.47316935658454895,
2708
+ "learning_rate": 2.6094149623024365e-07,
2709
+ "loss": 0.0053,
2710
+ "step": 3150
2711
+ },
2712
+ {
2713
+ "epoch": 4.8480184686417855,
2714
+ "eval_loss": 0.057770997285842896,
2715
+ "eval_runtime": 174.5817,
2716
+ "eval_samples_per_second": 6.622,
2717
+ "eval_steps_per_second": 6.622,
2718
+ "step": 3150
2719
+ },
2720
+ {
2721
+ "epoch": 4.86340900346287,
2722
+ "grad_norm": 0.2129555642604828,
2723
+ "learning_rate": 2.0893404271022376e-07,
2724
+ "loss": 0.0058,
2725
+ "step": 3160
2726
+ },
2727
+ {
2728
+ "epoch": 4.878799538283955,
2729
+ "grad_norm": 0.31666478514671326,
2730
+ "learning_rate": 1.626900225670691e-07,
2731
+ "loss": 0.0041,
2732
+ "step": 3170
2733
+ },
2734
+ {
2735
+ "epoch": 4.89419007310504,
2736
+ "grad_norm": 0.07376430183649063,
2737
+ "learning_rate": 1.2221478865524493e-07,
2738
+ "loss": 0.0024,
2739
+ "step": 3180
2740
+ },
2741
+ {
2742
+ "epoch": 4.9095806079261255,
2743
+ "grad_norm": 0.031059809029102325,
2744
+ "learning_rate": 8.751302607857836e-08,
2745
+ "loss": 0.0053,
2746
+ "step": 3190
2747
+ },
2748
+ {
2749
+ "epoch": 4.924971142747211,
2750
+ "grad_norm": 0.037241578102111816,
2751
+ "learning_rate": 5.8588751647975506e-08,
2752
+ "loss": 0.0033,
2753
+ "step": 3200
2754
+ },
2755
+ {
2756
+ "epoch": 4.924971142747211,
2757
+ "eval_loss": 0.057740841060876846,
2758
+ "eval_runtime": 174.3938,
2759
+ "eval_samples_per_second": 6.629,
2760
+ "eval_steps_per_second": 6.629,
2761
+ "step": 3200
2762
+ },
2763
+ {
2764
+ "epoch": 4.940361677568296,
2765
+ "grad_norm": 0.2316117137670517,
2766
+ "learning_rate": 3.544531341646007e-08,
2767
+ "loss": 0.0061,
2768
+ "step": 3210
2769
+ },
2770
+ {
2771
+ "epoch": 4.95575221238938,
2772
+ "grad_norm": 0.10855795443058014,
2773
+ "learning_rate": 1.808539029161116e-08,
2774
+ "loss": 0.0039,
2775
+ "step": 3220
2776
+ },
2777
+ {
2778
+ "epoch": 4.9711427472104655,
2779
+ "grad_norm": 0.48546239733695984,
2780
+ "learning_rate": 6.510991725500182e-09,
2781
+ "loss": 0.0058,
2782
+ "step": 3230
2783
+ },
2784
+ {
2785
+ "epoch": 4.986533282031551,
2786
+ "grad_norm": 0.07362986356019974,
2787
+ "learning_rate": 7.234574820769169e-10,
2788
+ "loss": 0.0044,
2789
+ "step": 3240
2790
+ },
2791
+ {
2792
+ "epoch": 4.994228549442093,
2793
+ "step": 3245,
2794
+ "total_flos": 8.1511813636463e+17,
2795
+ "train_loss": 0.04558033469306715,
2796
+ "train_runtime": 40942.202,
2797
+ "train_samples_per_second": 1.27,
2798
+ "train_steps_per_second": 0.079
2799
+ }
2800
+ ],
2801
+ "logging_steps": 10,
2802
+ "max_steps": 3245,
2803
+ "num_input_tokens_seen": 0,
2804
+ "num_train_epochs": 5,
2805
+ "save_steps": 50,
2806
+ "stateful_callbacks": {
2807
+ "TrainerControl": {
2808
+ "args": {
2809
+ "should_epoch_stop": false,
2810
+ "should_evaluate": false,
2811
+ "should_log": false,
2812
+ "should_save": true,
2813
+ "should_training_stop": true
2814
+ },
2815
+ "attributes": {}
2816
+ }
2817
+ },
2818
+ "total_flos": 8.1511813636463e+17,
2819
+ "train_batch_size": 1,
2820
+ "trial_name": null,
2821
+ "trial_params": null
2822
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold1/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:460ddaa0054fb58db1c7fc01e35d2b66fe1d6f8565617e2468ee89b2d4efa51b
3
+ size 5624
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold1/training_eval_loss.png ADDED
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold1/training_loss.png ADDED