jjee2 commited on
Commit
f6c3b98
·
verified ·
1 Parent(s): 707897f

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

Browse files
.gitattributes CHANGED
@@ -97,3 +97,4 @@ denbeo__c06ff044-8c9d-4eed-ae11-6f3c8ca2542e/tokenizer.json filter=lfs diff=lfs
97
  RAG-Gym__Direct-MedQA-SFT/tokenizer.json filter=lfs diff=lfs merge=lfs -text
98
  lhong4759__ac11856d-78c8-4956-9dd4-f2022250559f/tokenizer.json filter=lfs diff=lfs merge=lfs -text
99
  chchen__Llama-3.1-8B-Instruct-PsyCourse-fold5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
97
  RAG-Gym__Direct-MedQA-SFT/tokenizer.json filter=lfs diff=lfs merge=lfs -text
98
  lhong4759__ac11856d-78c8-4956-9dd4-f2022250559f/tokenizer.json filter=lfs diff=lfs merge=lfs -text
99
  chchen__Llama-3.1-8B-Instruct-PsyCourse-fold5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
100
+ chchen__Llama-3.1-8B-Instruct-PsyCourse-fold6/tokenizer.json filter=lfs diff=lfs merge=lfs -text
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold6/.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold6/README.md ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-fold6
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Llama-3.1-8B-Instruct-PsyCourse-fold6
18
+
19
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the course-train-fold6 dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.0368
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
+ | 0.6045 | 0.0751 | 50 | 0.4191 |
56
+ | 0.118 | 0.1502 | 100 | 0.0976 |
57
+ | 0.075 | 0.2254 | 150 | 0.0908 |
58
+ | 0.0475 | 0.3005 | 200 | 0.0555 |
59
+ | 0.0612 | 0.3756 | 250 | 0.0530 |
60
+ | 0.043 | 0.4507 | 300 | 0.0526 |
61
+ | 0.0497 | 0.5258 | 350 | 0.0503 |
62
+ | 0.049 | 0.6009 | 400 | 0.0481 |
63
+ | 0.0541 | 0.6761 | 450 | 0.0477 |
64
+ | 0.0494 | 0.7512 | 500 | 0.0432 |
65
+ | 0.0556 | 0.8263 | 550 | 0.0414 |
66
+ | 0.0398 | 0.9014 | 600 | 0.0415 |
67
+ | 0.0535 | 0.9765 | 650 | 0.0429 |
68
+ | 0.0383 | 1.0516 | 700 | 0.0438 |
69
+ | 0.0317 | 1.1268 | 750 | 0.0409 |
70
+ | 0.0311 | 1.2019 | 800 | 0.0410 |
71
+ | 0.0351 | 1.2770 | 850 | 0.0398 |
72
+ | 0.0309 | 1.3521 | 900 | 0.0372 |
73
+ | 0.0373 | 1.4272 | 950 | 0.0383 |
74
+ | 0.0295 | 1.5023 | 1000 | 0.0397 |
75
+ | 0.0349 | 1.5775 | 1050 | 0.0408 |
76
+ | 0.026 | 1.6526 | 1100 | 0.0410 |
77
+ | 0.0305 | 1.7277 | 1150 | 0.0390 |
78
+ | 0.0332 | 1.8028 | 1200 | 0.0385 |
79
+ | 0.0304 | 1.8779 | 1250 | 0.0379 |
80
+ | 0.0497 | 1.9531 | 1300 | 0.0392 |
81
+ | 0.0183 | 2.0282 | 1350 | 0.0412 |
82
+ | 0.0269 | 2.1033 | 1400 | 0.0381 |
83
+ | 0.0299 | 2.1784 | 1450 | 0.0379 |
84
+ | 0.0129 | 2.2535 | 1500 | 0.0434 |
85
+ | 0.0203 | 2.3286 | 1550 | 0.0383 |
86
+ | 0.0221 | 2.4038 | 1600 | 0.0397 |
87
+ | 0.023 | 2.4789 | 1650 | 0.0413 |
88
+ | 0.0257 | 2.5540 | 1700 | 0.0409 |
89
+ | 0.0241 | 2.6291 | 1750 | 0.0400 |
90
+ | 0.0258 | 2.7042 | 1800 | 0.0405 |
91
+ | 0.021 | 2.7793 | 1850 | 0.0392 |
92
+ | 0.0253 | 2.8545 | 1900 | 0.0368 |
93
+ | 0.018 | 2.9296 | 1950 | 0.0392 |
94
+ | 0.0112 | 3.0047 | 2000 | 0.0407 |
95
+ | 0.0082 | 3.0798 | 2050 | 0.0478 |
96
+ | 0.0127 | 3.1549 | 2100 | 0.0460 |
97
+ | 0.0112 | 3.2300 | 2150 | 0.0449 |
98
+ | 0.0145 | 3.3052 | 2200 | 0.0452 |
99
+ | 0.0086 | 3.3803 | 2250 | 0.0451 |
100
+ | 0.0161 | 3.4554 | 2300 | 0.0490 |
101
+ | 0.0134 | 3.5305 | 2350 | 0.0465 |
102
+ | 0.009 | 3.6056 | 2400 | 0.0461 |
103
+ | 0.0056 | 3.6808 | 2450 | 0.0480 |
104
+ | 0.0069 | 3.7559 | 2500 | 0.0490 |
105
+ | 0.007 | 3.8310 | 2550 | 0.0489 |
106
+ | 0.0147 | 3.9061 | 2600 | 0.0480 |
107
+ | 0.0123 | 3.9812 | 2650 | 0.0474 |
108
+ | 0.0053 | 4.0563 | 2700 | 0.0529 |
109
+ | 0.0064 | 4.1315 | 2750 | 0.0571 |
110
+ | 0.0064 | 4.2066 | 2800 | 0.0590 |
111
+ | 0.0038 | 4.2817 | 2850 | 0.0607 |
112
+ | 0.0011 | 4.3568 | 2900 | 0.0627 |
113
+ | 0.0034 | 4.4319 | 2950 | 0.0627 |
114
+ | 0.0063 | 4.5070 | 3000 | 0.0623 |
115
+ | 0.0033 | 4.5822 | 3050 | 0.0635 |
116
+ | 0.0048 | 4.6573 | 3100 | 0.0643 |
117
+ | 0.0044 | 4.7324 | 3150 | 0.0636 |
118
+ | 0.0031 | 4.8075 | 3200 | 0.0636 |
119
+ | 0.0022 | 4.8826 | 3250 | 0.0639 |
120
+ | 0.0078 | 4.9577 | 3300 | 0.0638 |
121
+
122
+
123
+ ### Framework versions
124
+
125
+ - PEFT 0.12.0
126
+ - Transformers 4.46.1
127
+ - Pytorch 2.5.1+cu124
128
+ - Datasets 3.1.0
129
+ - Tokenizers 0.20.3
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold6/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "up_proj",
24
+ "gate_proj",
25
+ "v_proj",
26
+ "down_proj",
27
+ "k_proj",
28
+ "o_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold6/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e854b5ca60bdb084deb285fd89319b2f6d25c7d574a5c2e4dd3dc09d1bb991c
3
+ size 83945296
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold6/all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.995305164319249,
3
+ "eval_loss": 0.036843445152044296,
4
+ "eval_runtime": 157.1721,
5
+ "eval_samples_per_second": 7.533,
6
+ "eval_steps_per_second": 7.533,
7
+ "total_flos": 8.345060490986127e+17,
8
+ "train_loss": 0.04504659976081965,
9
+ "train_runtime": 35784.009,
10
+ "train_samples_per_second": 1.488,
11
+ "train_steps_per_second": 0.093
12
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold6/eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.995305164319249,
3
+ "eval_loss": 0.036843445152044296,
4
+ "eval_runtime": 157.1721,
5
+ "eval_samples_per_second": 7.533,
6
+ "eval_steps_per_second": 7.533
7
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold6/llama3_lora_sft.yaml ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ### model
2
+ model_name_or_path: meta-llama/Llama-3.1-8B-Instruct
3
+ trust_remote_code: true
4
+
5
+ ### method
6
+ stage: sft
7
+ do_train: true
8
+ finetuning_type: lora
9
+ lora_target: all
10
+
11
+ ### dataset
12
+ dataset: course-train-fold6
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/fold6
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-fold6
29
+ load_best_model_at_end: true
30
+
31
+ ### train
32
+ per_device_train_batch_size: 1
33
+ gradient_accumulation_steps: 16
34
+ learning_rate: 1.0e-4
35
+ num_train_epochs: 5.0
36
+ lr_scheduler_type: cosine
37
+ warmup_ratio: 0.1
38
+ bf16: true
39
+ ddp_timeout: 180000000
40
+ enable_liger_kernel: true
41
+
42
+ ### eval
43
+ val_size: 0.1
44
+ per_device_eval_batch_size: 1
45
+ eval_strategy: steps
46
+ eval_steps: 50
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold6/special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eot_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|eom_id|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<|begin_of_text|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "<|eot_id|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": "<|eot_id|>"
33
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold6/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold6/tokenizer_config.json ADDED
@@ -0,0 +1,2069 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "additional_special_tokens": [
2053
+ "<|eot_id|>",
2054
+ "<|eom_id|>"
2055
+ ],
2056
+ "bos_token": "<|begin_of_text|>",
2057
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2058
+ "clean_up_tokenization_spaces": true,
2059
+ "eos_token": "<|eot_id|>",
2060
+ "model_input_names": [
2061
+ "input_ids",
2062
+ "attention_mask"
2063
+ ],
2064
+ "model_max_length": 131072,
2065
+ "pad_token": "<|eot_id|>",
2066
+ "padding_side": "right",
2067
+ "split_special_tokens": false,
2068
+ "tokenizer_class": "PreTrainedTokenizerFast"
2069
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold6/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.995305164319249,
3
+ "total_flos": 8.345060490986127e+17,
4
+ "train_loss": 0.04504659976081965,
5
+ "train_runtime": 35784.009,
6
+ "train_samples_per_second": 1.488,
7
+ "train_steps_per_second": 0.093
8
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold6/trainer_log.jsonl ADDED
@@ -0,0 +1,399 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 3325, "loss": 1.5464, "lr": 3.003003003003003e-06, "epoch": 0.015023474178403756, "percentage": 0.3, "elapsed_time": "0:01:17", "remaining_time": "7:05:26"}
2
+ {"current_steps": 20, "total_steps": 3325, "loss": 1.597, "lr": 6.006006006006006e-06, "epoch": 0.03004694835680751, "percentage": 0.6, "elapsed_time": "0:02:32", "remaining_time": "6:59:31"}
3
+ {"current_steps": 30, "total_steps": 3325, "loss": 1.4497, "lr": 9.00900900900901e-06, "epoch": 0.04507042253521127, "percentage": 0.9, "elapsed_time": "0:03:47", "remaining_time": "6:56:34"}
4
+ {"current_steps": 40, "total_steps": 3325, "loss": 0.9009, "lr": 1.2012012012012012e-05, "epoch": 0.06009389671361502, "percentage": 1.2, "elapsed_time": "0:05:03", "remaining_time": "6:55:09"}
5
+ {"current_steps": 50, "total_steps": 3325, "loss": 0.6045, "lr": 1.5015015015015016e-05, "epoch": 0.07511737089201878, "percentage": 1.5, "elapsed_time": "0:06:18", "remaining_time": "6:53:09"}
6
+ {"current_steps": 50, "total_steps": 3325, "eval_loss": 0.41910141706466675, "epoch": 0.07511737089201878, "percentage": 1.5, "elapsed_time": "0:08:54", "remaining_time": "9:43:47"}
7
+ {"current_steps": 60, "total_steps": 3325, "loss": 0.402, "lr": 1.801801801801802e-05, "epoch": 0.09014084507042254, "percentage": 1.8, "elapsed_time": "0:10:15", "remaining_time": "9:17:56"}
8
+ {"current_steps": 70, "total_steps": 3325, "loss": 0.2368, "lr": 2.102102102102102e-05, "epoch": 0.10516431924882629, "percentage": 2.11, "elapsed_time": "0:11:30", "remaining_time": "8:54:50"}
9
+ {"current_steps": 80, "total_steps": 3325, "loss": 0.1741, "lr": 2.4024024024024024e-05, "epoch": 0.12018779342723004, "percentage": 2.41, "elapsed_time": "0:12:45", "remaining_time": "8:37:33"}
10
+ {"current_steps": 90, "total_steps": 3325, "loss": 0.1089, "lr": 2.702702702702703e-05, "epoch": 0.1352112676056338, "percentage": 2.71, "elapsed_time": "0:14:00", "remaining_time": "8:23:39"}
11
+ {"current_steps": 100, "total_steps": 3325, "loss": 0.118, "lr": 3.0030030030030033e-05, "epoch": 0.15023474178403756, "percentage": 3.01, "elapsed_time": "0:15:15", "remaining_time": "8:12:20"}
12
+ {"current_steps": 100, "total_steps": 3325, "eval_loss": 0.09762203693389893, "epoch": 0.15023474178403756, "percentage": 3.01, "elapsed_time": "0:17:52", "remaining_time": "9:36:26"}
13
+ {"current_steps": 110, "total_steps": 3325, "loss": 0.1111, "lr": 3.3033033033033035e-05, "epoch": 0.1652582159624413, "percentage": 3.31, "elapsed_time": "0:19:12", "remaining_time": "9:21:24"}
14
+ {"current_steps": 120, "total_steps": 3325, "loss": 0.0988, "lr": 3.603603603603604e-05, "epoch": 0.18028169014084508, "percentage": 3.61, "elapsed_time": "0:20:27", "remaining_time": "9:06:32"}
15
+ {"current_steps": 130, "total_steps": 3325, "loss": 0.0874, "lr": 3.903903903903904e-05, "epoch": 0.19530516431924883, "percentage": 3.91, "elapsed_time": "0:21:42", "remaining_time": "8:53:41"}
16
+ {"current_steps": 140, "total_steps": 3325, "loss": 0.0904, "lr": 4.204204204204204e-05, "epoch": 0.21032863849765257, "percentage": 4.21, "elapsed_time": "0:22:58", "remaining_time": "8:42:36"}
17
+ {"current_steps": 150, "total_steps": 3325, "loss": 0.075, "lr": 4.5045045045045046e-05, "epoch": 0.22535211267605634, "percentage": 4.51, "elapsed_time": "0:24:14", "remaining_time": "8:32:57"}
18
+ {"current_steps": 150, "total_steps": 3325, "eval_loss": 0.09080640226602554, "epoch": 0.22535211267605634, "percentage": 4.51, "elapsed_time": "0:26:50", "remaining_time": "9:28:07"}
19
+ {"current_steps": 160, "total_steps": 3325, "loss": 0.0712, "lr": 4.804804804804805e-05, "epoch": 0.2403755868544601, "percentage": 4.81, "elapsed_time": "0:28:10", "remaining_time": "9:17:17"}
20
+ {"current_steps": 170, "total_steps": 3325, "loss": 0.0496, "lr": 5.105105105105106e-05, "epoch": 0.25539906103286386, "percentage": 5.11, "elapsed_time": "0:29:25", "remaining_time": "9:06:07"}
21
+ {"current_steps": 180, "total_steps": 3325, "loss": 0.0628, "lr": 5.405405405405406e-05, "epoch": 0.2704225352112676, "percentage": 5.41, "elapsed_time": "0:30:40", "remaining_time": "8:56:03"}
22
+ {"current_steps": 190, "total_steps": 3325, "loss": 0.0582, "lr": 5.705705705705706e-05, "epoch": 0.28544600938967135, "percentage": 5.71, "elapsed_time": "0:31:55", "remaining_time": "8:46:53"}
23
+ {"current_steps": 200, "total_steps": 3325, "loss": 0.0475, "lr": 6.0060060060060066e-05, "epoch": 0.3004694835680751, "percentage": 6.02, "elapsed_time": "0:33:11", "remaining_time": "8:38:34"}
24
+ {"current_steps": 200, "total_steps": 3325, "eval_loss": 0.05551699176430702, "epoch": 0.3004694835680751, "percentage": 6.02, "elapsed_time": "0:35:47", "remaining_time": "9:19:16"}
25
+ {"current_steps": 210, "total_steps": 3325, "loss": 0.0529, "lr": 6.306306306306306e-05, "epoch": 0.3154929577464789, "percentage": 6.32, "elapsed_time": "0:37:08", "remaining_time": "9:10:53"}
26
+ {"current_steps": 220, "total_steps": 3325, "loss": 0.0564, "lr": 6.606606606606607e-05, "epoch": 0.3305164319248826, "percentage": 6.62, "elapsed_time": "0:38:23", "remaining_time": "9:01:53"}
27
+ {"current_steps": 230, "total_steps": 3325, "loss": 0.0473, "lr": 6.906906906906907e-05, "epoch": 0.3455399061032864, "percentage": 6.92, "elapsed_time": "0:39:38", "remaining_time": "8:53:30"}
28
+ {"current_steps": 240, "total_steps": 3325, "loss": 0.0651, "lr": 7.207207207207208e-05, "epoch": 0.36056338028169016, "percentage": 7.22, "elapsed_time": "0:40:54", "remaining_time": "8:45:47"}
29
+ {"current_steps": 250, "total_steps": 3325, "loss": 0.0612, "lr": 7.507507507507507e-05, "epoch": 0.3755868544600939, "percentage": 7.52, "elapsed_time": "0:42:09", "remaining_time": "8:38:32"}
30
+ {"current_steps": 250, "total_steps": 3325, "eval_loss": 0.05300073325634003, "epoch": 0.3755868544600939, "percentage": 7.52, "elapsed_time": "0:44:45", "remaining_time": "9:10:34"}
31
+ {"current_steps": 260, "total_steps": 3325, "loss": 0.0529, "lr": 7.807807807807808e-05, "epoch": 0.39061032863849765, "percentage": 7.82, "elapsed_time": "0:46:06", "remaining_time": "9:03:28"}
32
+ {"current_steps": 270, "total_steps": 3325, "loss": 0.0609, "lr": 8.108108108108109e-05, "epoch": 0.4056338028169014, "percentage": 8.12, "elapsed_time": "0:47:21", "remaining_time": "8:55:52"}
33
+ {"current_steps": 280, "total_steps": 3325, "loss": 0.0577, "lr": 8.408408408408409e-05, "epoch": 0.42065727699530514, "percentage": 8.42, "elapsed_time": "0:48:36", "remaining_time": "8:48:41"}
34
+ {"current_steps": 290, "total_steps": 3325, "loss": 0.0572, "lr": 8.70870870870871e-05, "epoch": 0.4356807511737089, "percentage": 8.72, "elapsed_time": "0:49:52", "remaining_time": "8:41:54"}
35
+ {"current_steps": 300, "total_steps": 3325, "loss": 0.043, "lr": 9.009009009009009e-05, "epoch": 0.4507042253521127, "percentage": 9.02, "elapsed_time": "0:51:07", "remaining_time": "8:35:33"}
36
+ {"current_steps": 300, "total_steps": 3325, "eval_loss": 0.05256583169102669, "epoch": 0.4507042253521127, "percentage": 9.02, "elapsed_time": "0:53:44", "remaining_time": "9:01:49"}
37
+ {"current_steps": 310, "total_steps": 3325, "loss": 0.0439, "lr": 9.30930930930931e-05, "epoch": 0.46572769953051646, "percentage": 9.32, "elapsed_time": "0:55:04", "remaining_time": "8:55:34"}
38
+ {"current_steps": 320, "total_steps": 3325, "loss": 0.0597, "lr": 9.60960960960961e-05, "epoch": 0.4807511737089202, "percentage": 9.62, "elapsed_time": "0:56:19", "remaining_time": "8:48:57"}
39
+ {"current_steps": 330, "total_steps": 3325, "loss": 0.0553, "lr": 9.90990990990991e-05, "epoch": 0.49577464788732395, "percentage": 9.92, "elapsed_time": "0:57:35", "remaining_time": "8:42:37"}
40
+ {"current_steps": 340, "total_steps": 3325, "loss": 0.0614, "lr": 9.999864944989638e-05, "epoch": 0.5107981220657277, "percentage": 10.23, "elapsed_time": "0:58:50", "remaining_time": "8:36:34"}
41
+ {"current_steps": 350, "total_steps": 3325, "loss": 0.0497, "lr": 9.999203468625017e-05, "epoch": 0.5258215962441315, "percentage": 10.53, "elapsed_time": "1:00:05", "remaining_time": "8:30:46"}
42
+ {"current_steps": 350, "total_steps": 3325, "eval_loss": 0.05027875676751137, "epoch": 0.5258215962441315, "percentage": 10.53, "elapsed_time": "1:02:41", "remaining_time": "8:52:56"}
43
+ {"current_steps": 360, "total_steps": 3325, "loss": 0.0614, "lr": 9.997990837719421e-05, "epoch": 0.5408450704225352, "percentage": 10.83, "elapsed_time": "1:04:02", "remaining_time": "8:47:27"}
44
+ {"current_steps": 370, "total_steps": 3325, "loss": 0.0446, "lr": 9.996227185963554e-05, "epoch": 0.5558685446009389, "percentage": 11.13, "elapsed_time": "1:05:18", "remaining_time": "8:41:32"}
45
+ {"current_steps": 380, "total_steps": 3325, "loss": 0.0513, "lr": 9.993912707797329e-05, "epoch": 0.5708920187793427, "percentage": 11.43, "elapsed_time": "1:06:33", "remaining_time": "8:35:48"}
46
+ {"current_steps": 390, "total_steps": 3325, "loss": 0.0433, "lr": 9.99104765838842e-05, "epoch": 0.5859154929577465, "percentage": 11.73, "elapsed_time": "1:07:48", "remaining_time": "8:30:19"}
47
+ {"current_steps": 400, "total_steps": 3325, "loss": 0.049, "lr": 9.987632353604151e-05, "epoch": 0.6009389671361502, "percentage": 12.03, "elapsed_time": "1:09:04", "remaining_time": "8:25:03"}
48
+ {"current_steps": 400, "total_steps": 3325, "eval_loss": 0.04805321246385574, "epoch": 0.6009389671361502, "percentage": 12.03, "elapsed_time": "1:11:40", "remaining_time": "8:44:06"}
49
+ {"current_steps": 410, "total_steps": 3325, "loss": 0.0469, "lr": 9.98366716997665e-05, "epoch": 0.615962441314554, "percentage": 12.33, "elapsed_time": "1:13:01", "remaining_time": "8:39:10"}
50
+ {"current_steps": 420, "total_steps": 3325, "loss": 0.0437, "lr": 9.979152544661354e-05, "epoch": 0.6309859154929578, "percentage": 12.63, "elapsed_time": "1:14:16", "remaining_time": "8:33:46"}
51
+ {"current_steps": 430, "total_steps": 3325, "loss": 0.0479, "lr": 9.974088975388802e-05, "epoch": 0.6460093896713615, "percentage": 12.93, "elapsed_time": "1:15:32", "remaining_time": "8:28:33"}
52
+ {"current_steps": 440, "total_steps": 3325, "loss": 0.0452, "lr": 9.968477020409766e-05, "epoch": 0.6610328638497652, "percentage": 13.23, "elapsed_time": "1:16:47", "remaining_time": "8:23:33"}
53
+ {"current_steps": 450, "total_steps": 3325, "loss": 0.0541, "lr": 9.962317298433705e-05, "epoch": 0.676056338028169, "percentage": 13.53, "elapsed_time": "1:18:02", "remaining_time": "8:18:38"}
54
+ {"current_steps": 450, "total_steps": 3325, "eval_loss": 0.047716788947582245, "epoch": 0.676056338028169, "percentage": 13.53, "elapsed_time": "1:20:39", "remaining_time": "8:35:18"}
55
+ {"current_steps": 460, "total_steps": 3325, "loss": 0.0589, "lr": 9.955610488560551e-05, "epoch": 0.6910798122065728, "percentage": 13.83, "elapsed_time": "1:21:59", "remaining_time": "8:30:41"}
56
+ {"current_steps": 470, "total_steps": 3325, "loss": 0.0583, "lr": 9.948357330205842e-05, "epoch": 0.7061032863849765, "percentage": 14.14, "elapsed_time": "1:23:14", "remaining_time": "8:25:41"}
57
+ {"current_steps": 480, "total_steps": 3325, "loss": 0.0329, "lr": 9.940558623019201e-05, "epoch": 0.7211267605633803, "percentage": 14.44, "elapsed_time": "1:24:30", "remaining_time": "8:20:51"}
58
+ {"current_steps": 490, "total_steps": 3325, "loss": 0.0501, "lr": 9.932215226796172e-05, "epoch": 0.7361502347417841, "percentage": 14.74, "elapsed_time": "1:25:45", "remaining_time": "8:16:09"}
59
+ {"current_steps": 500, "total_steps": 3325, "loss": 0.0494, "lr": 9.923328061383435e-05, "epoch": 0.7511737089201878, "percentage": 15.04, "elapsed_time": "1:27:00", "remaining_time": "8:11:36"}
60
+ {"current_steps": 500, "total_steps": 3325, "eval_loss": 0.043219637125730515, "epoch": 0.7511737089201878, "percentage": 15.04, "elapsed_time": "1:29:36", "remaining_time": "8:26:19"}
61
+ {"current_steps": 510, "total_steps": 3325, "loss": 0.0445, "lr": 9.913898106577393e-05, "epoch": 0.7661971830985915, "percentage": 15.34, "elapsed_time": "1:30:56", "remaining_time": "8:22:00"}
62
+ {"current_steps": 520, "total_steps": 3325, "loss": 0.0389, "lr": 9.903926402016153e-05, "epoch": 0.7812206572769953, "percentage": 15.64, "elapsed_time": "1:32:12", "remaining_time": "8:17:23"}
63
+ {"current_steps": 530, "total_steps": 3325, "loss": 0.0436, "lr": 9.893414047064897e-05, "epoch": 0.7962441314553991, "percentage": 15.94, "elapsed_time": "1:33:28", "remaining_time": "8:12:54"}
64
+ {"current_steps": 540, "total_steps": 3325, "loss": 0.043, "lr": 9.88236220069469e-05, "epoch": 0.8112676056338028, "percentage": 16.24, "elapsed_time": "1:34:43", "remaining_time": "8:08:30"}
65
+ {"current_steps": 550, "total_steps": 3325, "loss": 0.0556, "lr": 9.870772081354705e-05, "epoch": 0.8262910798122066, "percentage": 16.54, "elapsed_time": "1:35:58", "remaining_time": "8:04:15"}
66
+ {"current_steps": 550, "total_steps": 3325, "eval_loss": 0.04144579544663429, "epoch": 0.8262910798122066, "percentage": 16.54, "elapsed_time": "1:38:35", "remaining_time": "8:17:24"}
67
+ {"current_steps": 560, "total_steps": 3325, "loss": 0.0463, "lr": 9.858644966837878e-05, "epoch": 0.8413145539906103, "percentage": 16.84, "elapsed_time": "1:39:54", "remaining_time": "8:13:19"}
68
+ {"current_steps": 570, "total_steps": 3325, "loss": 0.0456, "lr": 9.845982194140051e-05, "epoch": 0.856338028169014, "percentage": 17.14, "elapsed_time": "1:41:10", "remaining_time": "8:09:00"}
69
+ {"current_steps": 580, "total_steps": 3325, "loss": 0.042, "lr": 9.832785159312559e-05, "epoch": 0.8713615023474178, "percentage": 17.44, "elapsed_time": "1:42:25", "remaining_time": "8:04:46"}
70
+ {"current_steps": 590, "total_steps": 3325, "loss": 0.04, "lr": 9.819055317308317e-05, "epoch": 0.8863849765258216, "percentage": 17.74, "elapsed_time": "1:43:41", "remaining_time": "8:00:38"}
71
+ {"current_steps": 600, "total_steps": 3325, "loss": 0.0398, "lr": 9.804794181821422e-05, "epoch": 0.9014084507042254, "percentage": 18.05, "elapsed_time": "1:44:56", "remaining_time": "7:56:37"}
72
+ {"current_steps": 600, "total_steps": 3325, "eval_loss": 0.04154442995786667, "epoch": 0.9014084507042254, "percentage": 18.05, "elapsed_time": "1:47:33", "remaining_time": "8:08:27"}
73
+ {"current_steps": 610, "total_steps": 3325, "loss": 0.0403, "lr": 9.790003325120261e-05, "epoch": 0.9164319248826291, "percentage": 18.35, "elapsed_time": "1:48:53", "remaining_time": "8:04:41"}
74
+ {"current_steps": 620, "total_steps": 3325, "loss": 0.0535, "lr": 9.774684377874178e-05, "epoch": 0.9314553990610329, "percentage": 18.65, "elapsed_time": "1:50:09", "remaining_time": "8:00:35"}
75
+ {"current_steps": 630, "total_steps": 3325, "loss": 0.0358, "lr": 9.758839028973692e-05, "epoch": 0.9464788732394366, "percentage": 18.95, "elapsed_time": "1:51:24", "remaining_time": "7:56:35"}
76
+ {"current_steps": 640, "total_steps": 3325, "loss": 0.043, "lr": 9.742469025344298e-05, "epoch": 0.9615023474178404, "percentage": 19.25, "elapsed_time": "1:52:39", "remaining_time": "7:52:39"}
77
+ {"current_steps": 650, "total_steps": 3325, "loss": 0.0535, "lr": 9.725576171753874e-05, "epoch": 0.9765258215962441, "percentage": 19.55, "elapsed_time": "1:53:55", "remaining_time": "7:48:49"}
78
+ {"current_steps": 650, "total_steps": 3325, "eval_loss": 0.04291123151779175, "epoch": 0.9765258215962441, "percentage": 19.55, "elapsed_time": "1:56:31", "remaining_time": "7:59:32"}
79
+ {"current_steps": 660, "total_steps": 3325, "loss": 0.0441, "lr": 9.708162330613708e-05, "epoch": 0.9915492957746479, "percentage": 19.85, "elapsed_time": "1:57:51", "remaining_time": "7:55:53"}
80
+ {"current_steps": 670, "total_steps": 3325, "loss": 0.0439, "lr": 9.690229421773167e-05, "epoch": 1.0065727699530516, "percentage": 20.15, "elapsed_time": "1:59:06", "remaining_time": "7:51:59"}
81
+ {"current_steps": 680, "total_steps": 3325, "loss": 0.0402, "lr": 9.67177942230804e-05, "epoch": 1.0215962441314554, "percentage": 20.45, "elapsed_time": "2:00:22", "remaining_time": "7:48:12"}
82
+ {"current_steps": 690, "total_steps": 3325, "loss": 0.0412, "lr": 9.652814366302568e-05, "epoch": 1.036619718309859, "percentage": 20.75, "elapsed_time": "2:01:37", "remaining_time": "7:44:29"}
83
+ {"current_steps": 700, "total_steps": 3325, "loss": 0.0383, "lr": 9.633336344625185e-05, "epoch": 1.051643192488263, "percentage": 21.05, "elapsed_time": "2:02:53", "remaining_time": "7:40:49"}
84
+ {"current_steps": 700, "total_steps": 3325, "eval_loss": 0.04375332221388817, "epoch": 1.051643192488263, "percentage": 21.05, "elapsed_time": "2:05:29", "remaining_time": "7:50:35"}
85
+ {"current_steps": 710, "total_steps": 3325, "loss": 0.0297, "lr": 9.61334750469801e-05, "epoch": 1.0666666666666667, "percentage": 21.35, "elapsed_time": "2:06:49", "remaining_time": "7:47:06"}
86
+ {"current_steps": 720, "total_steps": 3325, "loss": 0.0377, "lr": 9.592850050260089e-05, "epoch": 1.0816901408450703, "percentage": 21.65, "elapsed_time": "2:08:04", "remaining_time": "7:43:23"}
87
+ {"current_steps": 730, "total_steps": 3325, "loss": 0.0329, "lr": 9.571846241124446e-05, "epoch": 1.0967136150234742, "percentage": 21.95, "elapsed_time": "2:09:19", "remaining_time": "7:39:44"}
88
+ {"current_steps": 740, "total_steps": 3325, "loss": 0.0273, "lr": 9.55033839292893e-05, "epoch": 1.1117370892018779, "percentage": 22.26, "elapsed_time": "2:10:35", "remaining_time": "7:36:10"}
89
+ {"current_steps": 750, "total_steps": 3325, "loss": 0.0317, "lr": 9.52832887688093e-05, "epoch": 1.1267605633802817, "percentage": 22.56, "elapsed_time": "2:11:50", "remaining_time": "7:32:39"}
90
+ {"current_steps": 750, "total_steps": 3325, "eval_loss": 0.04088291898369789, "epoch": 1.1267605633802817, "percentage": 22.56, "elapsed_time": "2:14:26", "remaining_time": "7:41:36"}
91
+ {"current_steps": 760, "total_steps": 3325, "loss": 0.035, "lr": 9.50582011949595e-05, "epoch": 1.1417840375586854, "percentage": 22.86, "elapsed_time": "2:15:46", "remaining_time": "7:38:14"}
92
+ {"current_steps": 770, "total_steps": 3325, "loss": 0.038, "lr": 9.482814602330084e-05, "epoch": 1.1568075117370893, "percentage": 23.16, "elapsed_time": "2:17:01", "remaining_time": "7:34:41"}
93
+ {"current_steps": 780, "total_steps": 3325, "loss": 0.0402, "lr": 9.459314861706435e-05, "epoch": 1.171830985915493, "percentage": 23.46, "elapsed_time": "2:18:17", "remaining_time": "7:31:11"}
94
+ {"current_steps": 790, "total_steps": 3325, "loss": 0.0313, "lr": 9.435323488435488e-05, "epoch": 1.1868544600938966, "percentage": 23.76, "elapsed_time": "2:19:32", "remaining_time": "7:27:45"}
95
+ {"current_steps": 800, "total_steps": 3325, "loss": 0.0311, "lr": 9.410843127529473e-05, "epoch": 1.2018779342723005, "percentage": 24.06, "elapsed_time": "2:20:47", "remaining_time": "7:24:23"}
96
+ {"current_steps": 800, "total_steps": 3325, "eval_loss": 0.04096408188343048, "epoch": 1.2018779342723005, "percentage": 24.06, "elapsed_time": "2:23:24", "remaining_time": "7:32:37"}
97
+ {"current_steps": 810, "total_steps": 3325, "loss": 0.0344, "lr": 9.385876477910765e-05, "epoch": 1.2169014084507042, "percentage": 24.36, "elapsed_time": "2:24:44", "remaining_time": "7:29:25"}
98
+ {"current_steps": 820, "total_steps": 3325, "loss": 0.0343, "lr": 9.360426292114314e-05, "epoch": 1.231924882629108, "percentage": 24.66, "elapsed_time": "2:26:00", "remaining_time": "7:26:01"}
99
+ {"current_steps": 830, "total_steps": 3325, "loss": 0.0294, "lr": 9.334495375984212e-05, "epoch": 1.2469483568075117, "percentage": 24.96, "elapsed_time": "2:27:15", "remaining_time": "7:22:40"}
100
+ {"current_steps": 840, "total_steps": 3325, "loss": 0.0337, "lr": 9.30808658836432e-05, "epoch": 1.2619718309859156, "percentage": 25.26, "elapsed_time": "2:28:31", "remaining_time": "7:19:21"}
101
+ {"current_steps": 850, "total_steps": 3325, "loss": 0.0351, "lr": 9.281202840783108e-05, "epoch": 1.2769953051643192, "percentage": 25.56, "elapsed_time": "2:29:46", "remaining_time": "7:16:05"}
102
+ {"current_steps": 850, "total_steps": 3325, "eval_loss": 0.03982950374484062, "epoch": 1.2769953051643192, "percentage": 25.56, "elapsed_time": "2:32:22", "remaining_time": "7:23:40"}
103
+ {"current_steps": 860, "total_steps": 3325, "loss": 0.0313, "lr": 9.253847097132655e-05, "epoch": 1.292018779342723, "percentage": 25.86, "elapsed_time": "2:33:42", "remaining_time": "7:20:33"}
104
+ {"current_steps": 870, "total_steps": 3325, "loss": 0.0323, "lr": 9.226022373341882e-05, "epoch": 1.3070422535211268, "percentage": 26.17, "elapsed_time": "2:34:57", "remaining_time": "7:17:16"}
105
+ {"current_steps": 880, "total_steps": 3325, "loss": 0.0299, "lr": 9.19773173704406e-05, "epoch": 1.3220657276995305, "percentage": 26.47, "elapsed_time": "2:36:12", "remaining_time": "7:14:01"}
106
+ {"current_steps": 890, "total_steps": 3325, "loss": 0.037, "lr": 9.168978307238594e-05, "epoch": 1.3370892018779343, "percentage": 26.77, "elapsed_time": "2:37:28", "remaining_time": "7:10:49"}
107
+ {"current_steps": 900, "total_steps": 3325, "loss": 0.0309, "lr": 9.13976525394717e-05, "epoch": 1.352112676056338, "percentage": 27.07, "elapsed_time": "2:38:43", "remaining_time": "7:07:40"}
108
+ {"current_steps": 900, "total_steps": 3325, "eval_loss": 0.037233345210552216, "epoch": 1.352112676056338, "percentage": 27.07, "elapsed_time": "2:41:19", "remaining_time": "7:14:41"}
109
+ {"current_steps": 910, "total_steps": 3325, "loss": 0.0264, "lr": 9.110095797864263e-05, "epoch": 1.3671361502347419, "percentage": 27.37, "elapsed_time": "2:42:40", "remaining_time": "7:11:42"}
110
+ {"current_steps": 920, "total_steps": 3325, "loss": 0.0371, "lr": 9.079973210002051e-05, "epoch": 1.3821596244131455, "percentage": 27.67, "elapsed_time": "2:43:55", "remaining_time": "7:08:31"}
111
+ {"current_steps": 930, "total_steps": 3325, "loss": 0.0389, "lr": 9.049400811329807e-05, "epoch": 1.3971830985915492, "percentage": 27.97, "elapsed_time": "2:45:10", "remaining_time": "7:05:23"}
112
+ {"current_steps": 940, "total_steps": 3325, "loss": 0.0296, "lr": 9.01838197240775e-05, "epoch": 1.412206572769953, "percentage": 28.27, "elapsed_time": "2:46:26", "remaining_time": "7:02:16"}
113
+ {"current_steps": 950, "total_steps": 3325, "loss": 0.0373, "lr": 8.986920113015461e-05, "epoch": 1.4272300469483568, "percentage": 28.57, "elapsed_time": "2:47:41", "remaining_time": "6:59:13"}
114
+ {"current_steps": 950, "total_steps": 3325, "eval_loss": 0.03834960237145424, "epoch": 1.4272300469483568, "percentage": 28.57, "elapsed_time": "2:50:17", "remaining_time": "7:05:44"}
115
+ {"current_steps": 960, "total_steps": 3325, "loss": 0.0244, "lr": 8.955018701774846e-05, "epoch": 1.4422535211267606, "percentage": 28.87, "elapsed_time": "2:51:38", "remaining_time": "7:02:49"}
116
+ {"current_steps": 970, "total_steps": 3325, "loss": 0.0413, "lr": 8.922681255767731e-05, "epoch": 1.4572769953051643, "percentage": 29.17, "elapsed_time": "2:52:53", "remaining_time": "6:59:45"}
117
+ {"current_steps": 980, "total_steps": 3325, "loss": 0.0359, "lr": 8.889911340148112e-05, "epoch": 1.4723004694835682, "percentage": 29.47, "elapsed_time": "2:54:09", "remaining_time": "6:56:43"}
118
+ {"current_steps": 990, "total_steps": 3325, "loss": 0.0336, "lr": 8.856712567749095e-05, "epoch": 1.4873239436619718, "percentage": 29.77, "elapsed_time": "2:55:24", "remaining_time": "6:53:42"}
119
+ {"current_steps": 1000, "total_steps": 3325, "loss": 0.0295, "lr": 8.82308859868459e-05, "epoch": 1.5023474178403755, "percentage": 30.08, "elapsed_time": "2:56:39", "remaining_time": "6:50:44"}
120
+ {"current_steps": 1000, "total_steps": 3325, "eval_loss": 0.039744190871715546, "epoch": 1.5023474178403755, "percentage": 30.08, "elapsed_time": "2:59:15", "remaining_time": "6:56:47"}
121
+ {"current_steps": 1010, "total_steps": 3325, "loss": 0.0335, "lr": 8.789043139945795e-05, "epoch": 1.5173708920187794, "percentage": 30.38, "elapsed_time": "3:00:35", "remaining_time": "6:53:56"}
122
+ {"current_steps": 1020, "total_steps": 3325, "loss": 0.0391, "lr": 8.754579944992491e-05, "epoch": 1.532394366197183, "percentage": 30.68, "elapsed_time": "3:01:51", "remaining_time": "6:50:57"}
123
+ {"current_steps": 1030, "total_steps": 3325, "loss": 0.035, "lr": 8.719702813339248e-05, "epoch": 1.5474178403755867, "percentage": 30.98, "elapsed_time": "3:03:06", "remaining_time": "6:48:00"}
124
+ {"current_steps": 1040, "total_steps": 3325, "loss": 0.0322, "lr": 8.684415590136518e-05, "epoch": 1.5624413145539906, "percentage": 31.28, "elapsed_time": "3:04:22", "remaining_time": "6:45:04"}
125
+ {"current_steps": 1050, "total_steps": 3325, "loss": 0.0349, "lr": 8.648722165746722e-05, "epoch": 1.5774647887323945, "percentage": 31.58, "elapsed_time": "3:05:37", "remaining_time": "6:42:11"}
126
+ {"current_steps": 1050, "total_steps": 3325, "eval_loss": 0.04082873836159706, "epoch": 1.5774647887323945, "percentage": 31.58, "elapsed_time": "3:08:13", "remaining_time": "6:47:49"}
127
+ {"current_steps": 1060, "total_steps": 3325, "loss": 0.0299, "lr": 8.61262647531534e-05, "epoch": 1.5924882629107981, "percentage": 31.88, "elapsed_time": "3:09:33", "remaining_time": "6:45:03"}
128
+ {"current_steps": 1070, "total_steps": 3325, "loss": 0.0372, "lr": 8.576132498337068e-05, "epoch": 1.6075117370892018, "percentage": 32.18, "elapsed_time": "3:10:49", "remaining_time": "6:42:09"}
129
+ {"current_steps": 1080, "total_steps": 3325, "loss": 0.0332, "lr": 8.539244258217088e-05, "epoch": 1.6225352112676057, "percentage": 32.48, "elapsed_time": "3:12:05", "remaining_time": "6:39:17"}
130
+ {"current_steps": 1090, "total_steps": 3325, "loss": 0.0365, "lr": 8.501965821827485e-05, "epoch": 1.6375586854460094, "percentage": 32.78, "elapsed_time": "3:13:20", "remaining_time": "6:36:26"}
131
+ {"current_steps": 1100, "total_steps": 3325, "loss": 0.026, "lr": 8.464301299058892e-05, "epoch": 1.652582159624413, "percentage": 33.08, "elapsed_time": "3:14:36", "remaining_time": "6:33:37"}
132
+ {"current_steps": 1100, "total_steps": 3325, "eval_loss": 0.04096033051609993, "epoch": 1.652582159624413, "percentage": 33.08, "elapsed_time": "3:17:12", "remaining_time": "6:38:53"}
133
+ {"current_steps": 1110, "total_steps": 3325, "loss": 0.0279, "lr": 8.426254842367374e-05, "epoch": 1.667605633802817, "percentage": 33.38, "elapsed_time": "3:18:32", "remaining_time": "6:36:11"}
134
+ {"current_steps": 1120, "total_steps": 3325, "loss": 0.0388, "lr": 8.387830646316623e-05, "epoch": 1.6826291079812208, "percentage": 33.68, "elapsed_time": "3:19:48", "remaining_time": "6:33:21"}
135
+ {"current_steps": 1130, "total_steps": 3325, "loss": 0.028, "lr": 8.349032947115525e-05, "epoch": 1.6976525821596244, "percentage": 33.98, "elapsed_time": "3:21:03", "remaining_time": "6:30:33"}
136
+ {"current_steps": 1140, "total_steps": 3325, "loss": 0.0468, "lr": 8.309866022151107e-05, "epoch": 1.712676056338028, "percentage": 34.29, "elapsed_time": "3:22:19", "remaining_time": "6:27:46"}
137
+ {"current_steps": 1150, "total_steps": 3325, "loss": 0.0305, "lr": 8.270334189516983e-05, "epoch": 1.727699530516432, "percentage": 34.59, "elapsed_time": "3:23:34", "remaining_time": "6:25:01"}
138
+ {"current_steps": 1150, "total_steps": 3325, "eval_loss": 0.039029572159051895, "epoch": 1.727699530516432, "percentage": 34.59, "elapsed_time": "3:26:10", "remaining_time": "6:29:56"}
139
+ {"current_steps": 1160, "total_steps": 3325, "loss": 0.0466, "lr": 8.230441807537277e-05, "epoch": 1.7427230046948357, "percentage": 34.89, "elapsed_time": "3:27:31", "remaining_time": "6:27:18"}
140
+ {"current_steps": 1170, "total_steps": 3325, "loss": 0.0284, "lr": 8.190193274286122e-05, "epoch": 1.7577464788732393, "percentage": 35.19, "elapsed_time": "3:28:46", "remaining_time": "6:24:32"}
141
+ {"current_steps": 1180, "total_steps": 3325, "loss": 0.0347, "lr": 8.149593027102789e-05, "epoch": 1.7727699530516432, "percentage": 35.49, "elapsed_time": "3:30:02", "remaining_time": "6:21:47"}
142
+ {"current_steps": 1190, "total_steps": 3325, "loss": 0.0277, "lr": 8.108645542102469e-05, "epoch": 1.787793427230047, "percentage": 35.79, "elapsed_time": "3:31:17", "remaining_time": "6:19:04"}
143
+ {"current_steps": 1200, "total_steps": 3325, "loss": 0.0332, "lr": 8.067355333682798e-05, "epoch": 1.8028169014084507, "percentage": 36.09, "elapsed_time": "3:32:32", "remaining_time": "6:16:22"}
144
+ {"current_steps": 1200, "total_steps": 3325, "eval_loss": 0.03854435682296753, "epoch": 1.8028169014084507, "percentage": 36.09, "elapsed_time": "3:35:08", "remaining_time": "6:20:59"}
145
+ {"current_steps": 1210, "total_steps": 3325, "loss": 0.0242, "lr": 8.025726954026138e-05, "epoch": 1.8178403755868544, "percentage": 36.39, "elapsed_time": "3:36:29", "remaining_time": "6:18:25"}
146
+ {"current_steps": 1220, "total_steps": 3325, "loss": 0.034, "lr": 7.983764992597716e-05, "epoch": 1.8328638497652583, "percentage": 36.69, "elapsed_time": "3:37:45", "remaining_time": "6:15:43"}
147
+ {"current_steps": 1230, "total_steps": 3325, "loss": 0.0314, "lr": 7.94147407563964e-05, "epoch": 1.847887323943662, "percentage": 36.99, "elapsed_time": "3:39:00", "remaining_time": "6:13:01"}
148
+ {"current_steps": 1240, "total_steps": 3325, "loss": 0.0348, "lr": 7.89885886566086e-05, "epoch": 1.8629107981220656, "percentage": 37.29, "elapsed_time": "3:40:16", "remaining_time": "6:10:22"}
149
+ {"current_steps": 1250, "total_steps": 3325, "loss": 0.0304, "lr": 7.855924060923141e-05, "epoch": 1.8779342723004695, "percentage": 37.59, "elapsed_time": "3:41:31", "remaining_time": "6:07:43"}
150
+ {"current_steps": 1250, "total_steps": 3325, "eval_loss": 0.03792616352438927, "epoch": 1.8779342723004695, "percentage": 37.59, "elapsed_time": "3:44:07", "remaining_time": "6:12:03"}
151
+ {"current_steps": 1260, "total_steps": 3325, "loss": 0.0364, "lr": 7.812674394923077e-05, "epoch": 1.8929577464788734, "percentage": 37.89, "elapsed_time": "3:45:27", "remaining_time": "6:09:30"}
152
+ {"current_steps": 1270, "total_steps": 3325, "loss": 0.0357, "lr": 7.769114635870231e-05, "epoch": 1.907981220657277, "percentage": 38.2, "elapsed_time": "3:46:42", "remaining_time": "6:06:51"}
153
+ {"current_steps": 1280, "total_steps": 3325, "loss": 0.0317, "lr": 7.725249586161463e-05, "epoch": 1.9230046948356807, "percentage": 38.5, "elapsed_time": "3:47:57", "remaining_time": "6:04:12"}
154
+ {"current_steps": 1290, "total_steps": 3325, "loss": 0.0276, "lr": 7.68108408185145e-05, "epoch": 1.9380281690140846, "percentage": 38.8, "elapsed_time": "3:49:13", "remaining_time": "6:01:36"}
155
+ {"current_steps": 1300, "total_steps": 3325, "loss": 0.0497, "lr": 7.636622992119536e-05, "epoch": 1.9530516431924883, "percentage": 39.1, "elapsed_time": "3:50:29", "remaining_time": "5:59:01"}
156
+ {"current_steps": 1300, "total_steps": 3325, "eval_loss": 0.039196692407131195, "epoch": 1.9530516431924883, "percentage": 39.1, "elapsed_time": "3:53:05", "remaining_time": "6:03:05"}
157
+ {"current_steps": 1310, "total_steps": 3325, "loss": 0.036, "lr": 7.591871218732902e-05, "epoch": 1.968075117370892, "percentage": 39.4, "elapsed_time": "3:54:25", "remaining_time": "6:00:34"}
158
+ {"current_steps": 1320, "total_steps": 3325, "loss": 0.0413, "lr": 7.54683369550616e-05, "epoch": 1.9830985915492958, "percentage": 39.7, "elapsed_time": "3:55:41", "remaining_time": "5:57:59"}
159
+ {"current_steps": 1330, "total_steps": 3325, "loss": 0.0295, "lr": 7.501515387757404e-05, "epoch": 1.9981220657276997, "percentage": 40.0, "elapsed_time": "3:56:56", "remaining_time": "5:55:24"}
160
+ {"current_steps": 1340, "total_steps": 3325, "loss": 0.0365, "lr": 7.455921291760796e-05, "epoch": 2.013145539906103, "percentage": 40.3, "elapsed_time": "3:58:11", "remaining_time": "5:52:50"}
161
+ {"current_steps": 1350, "total_steps": 3325, "loss": 0.0183, "lr": 7.410056434195725e-05, "epoch": 2.028169014084507, "percentage": 40.6, "elapsed_time": "3:59:26", "remaining_time": "5:50:18"}
162
+ {"current_steps": 1350, "total_steps": 3325, "eval_loss": 0.04124961793422699, "epoch": 2.028169014084507, "percentage": 40.6, "elapsed_time": "4:02:02", "remaining_time": "5:54:06"}
163
+ {"current_steps": 1360, "total_steps": 3325, "loss": 0.0264, "lr": 7.363925871592629e-05, "epoch": 2.043192488262911, "percentage": 40.9, "elapsed_time": "4:03:23", "remaining_time": "5:51:39"}
164
+ {"current_steps": 1370, "total_steps": 3325, "loss": 0.0239, "lr": 7.317534689775528e-05, "epoch": 2.0582159624413148, "percentage": 41.2, "elapsed_time": "4:04:38", "remaining_time": "5:49:06"}
165
+ {"current_steps": 1380, "total_steps": 3325, "loss": 0.0175, "lr": 7.270888003301304e-05, "epoch": 2.073239436619718, "percentage": 41.5, "elapsed_time": "4:05:53", "remaining_time": "5:46:34"}
166
+ {"current_steps": 1390, "total_steps": 3325, "loss": 0.022, "lr": 7.22399095489584e-05, "epoch": 2.088262910798122, "percentage": 41.8, "elapsed_time": "4:07:09", "remaining_time": "5:44:03"}
167
+ {"current_steps": 1400, "total_steps": 3325, "loss": 0.0269, "lr": 7.176848714887042e-05, "epoch": 2.103286384976526, "percentage": 42.11, "elapsed_time": "4:08:24", "remaining_time": "5:41:33"}
168
+ {"current_steps": 1400, "total_steps": 3325, "eval_loss": 0.038102250546216965, "epoch": 2.103286384976526, "percentage": 42.11, "elapsed_time": "4:11:00", "remaining_time": "5:45:08"}
169
+ {"current_steps": 1410, "total_steps": 3325, "loss": 0.0251, "lr": 7.129466480634806e-05, "epoch": 2.1183098591549294, "percentage": 42.41, "elapsed_time": "4:12:21", "remaining_time": "5:42:44"}
170
+ {"current_steps": 1420, "total_steps": 3325, "loss": 0.0208, "lr": 7.081849475958042e-05, "epoch": 2.1333333333333333, "percentage": 42.71, "elapsed_time": "4:13:36", "remaining_time": "5:40:13"}
171
+ {"current_steps": 1430, "total_steps": 3325, "loss": 0.0243, "lr": 7.034002950558723e-05, "epoch": 2.148356807511737, "percentage": 43.01, "elapsed_time": "4:14:51", "remaining_time": "5:37:44"}
172
+ {"current_steps": 1440, "total_steps": 3325, "loss": 0.0253, "lr": 6.985932179443144e-05, "epoch": 2.1633802816901406, "percentage": 43.31, "elapsed_time": "4:16:07", "remaining_time": "5:35:16"}
173
+ {"current_steps": 1450, "total_steps": 3325, "loss": 0.0299, "lr": 6.937642462340342e-05, "epoch": 2.1784037558685445, "percentage": 43.61, "elapsed_time": "4:17:22", "remaining_time": "5:32:48"}
174
+ {"current_steps": 1450, "total_steps": 3325, "eval_loss": 0.0379047654569149, "epoch": 2.1784037558685445, "percentage": 43.61, "elapsed_time": "4:19:58", "remaining_time": "5:36:11"}
175
+ {"current_steps": 1460, "total_steps": 3325, "loss": 0.0184, "lr": 6.889139123117817e-05, "epoch": 2.1934272300469484, "percentage": 43.91, "elapsed_time": "4:21:18", "remaining_time": "5:33:47"}
176
+ {"current_steps": 1470, "total_steps": 3325, "loss": 0.0249, "lr": 6.840427509194575e-05, "epoch": 2.2084507042253523, "percentage": 44.21, "elapsed_time": "4:22:34", "remaining_time": "5:31:20"}
177
+ {"current_steps": 1480, "total_steps": 3325, "loss": 0.0165, "lr": 6.791512990951597e-05, "epoch": 2.2234741784037557, "percentage": 44.51, "elapsed_time": "4:23:49", "remaining_time": "5:28:53"}
178
+ {"current_steps": 1490, "total_steps": 3325, "loss": 0.0262, "lr": 6.74240096113975e-05, "epoch": 2.2384976525821596, "percentage": 44.81, "elapsed_time": "4:25:04", "remaining_time": "5:26:27"}
179
+ {"current_steps": 1500, "total_steps": 3325, "loss": 0.0129, "lr": 6.693096834285256e-05, "epoch": 2.2535211267605635, "percentage": 45.11, "elapsed_time": "4:26:20", "remaining_time": "5:24:02"}
180
+ {"current_steps": 1500, "total_steps": 3325, "eval_loss": 0.04337477684020996, "epoch": 2.2535211267605635, "percentage": 45.11, "elapsed_time": "4:28:56", "remaining_time": "5:27:12"}
181
+ {"current_steps": 1510, "total_steps": 3325, "loss": 0.0238, "lr": 6.643606046092732e-05, "epoch": 2.2685446009389674, "percentage": 45.41, "elapsed_time": "4:30:16", "remaining_time": "5:24:51"}
182
+ {"current_steps": 1520, "total_steps": 3325, "loss": 0.0257, "lr": 6.593934052845929e-05, "epoch": 2.283568075117371, "percentage": 45.71, "elapsed_time": "4:31:31", "remaining_time": "5:22:26"}
183
+ {"current_steps": 1530, "total_steps": 3325, "loss": 0.0268, "lr": 6.544086330806181e-05, "epoch": 2.2985915492957747, "percentage": 46.02, "elapsed_time": "4:32:46", "remaining_time": "5:20:01"}
184
+ {"current_steps": 1540, "total_steps": 3325, "loss": 0.0245, "lr": 6.494068375608646e-05, "epoch": 2.3136150234741786, "percentage": 46.32, "elapsed_time": "4:34:02", "remaining_time": "5:17:37"}
185
+ {"current_steps": 1550, "total_steps": 3325, "loss": 0.0203, "lr": 6.443885701656432e-05, "epoch": 2.328638497652582, "percentage": 46.62, "elapsed_time": "4:35:17", "remaining_time": "5:15:15"}
186
+ {"current_steps": 1550, "total_steps": 3325, "eval_loss": 0.03834431990981102, "epoch": 2.328638497652582, "percentage": 46.62, "elapsed_time": "4:37:53", "remaining_time": "5:18:14"}
187
+ {"current_steps": 1560, "total_steps": 3325, "loss": 0.0187, "lr": 6.393543841512632e-05, "epoch": 2.343661971830986, "percentage": 46.92, "elapsed_time": "4:39:13", "remaining_time": "5:15:55"}
188
+ {"current_steps": 1570, "total_steps": 3325, "loss": 0.0143, "lr": 6.343048345290386e-05, "epoch": 2.35868544600939, "percentage": 47.22, "elapsed_time": "4:40:28", "remaining_time": "5:13:32"}
189
+ {"current_steps": 1580, "total_steps": 3325, "loss": 0.0306, "lr": 6.292404780040961e-05, "epoch": 2.3737089201877932, "percentage": 47.52, "elapsed_time": "4:41:44", "remaining_time": "5:11:09"}
190
+ {"current_steps": 1590, "total_steps": 3325, "loss": 0.0198, "lr": 6.241618729140018e-05, "epoch": 2.388732394366197, "percentage": 47.82, "elapsed_time": "4:42:59", "remaining_time": "5:08:48"}
191
+ {"current_steps": 1600, "total_steps": 3325, "loss": 0.0221, "lr": 6.190695791672042e-05, "epoch": 2.403755868544601, "percentage": 48.12, "elapsed_time": "4:44:15", "remaining_time": "5:06:27"}
192
+ {"current_steps": 1600, "total_steps": 3325, "eval_loss": 0.03971394523978233, "epoch": 2.403755868544601, "percentage": 48.12, "elapsed_time": "4:46:51", "remaining_time": "5:09:16"}
193
+ {"current_steps": 1610, "total_steps": 3325, "loss": 0.0194, "lr": 6.139641581813052e-05, "epoch": 2.418779342723005, "percentage": 48.42, "elapsed_time": "4:48:11", "remaining_time": "5:06:59"}
194
+ {"current_steps": 1620, "total_steps": 3325, "loss": 0.0206, "lr": 6.088461728211642e-05, "epoch": 2.4338028169014083, "percentage": 48.72, "elapsed_time": "4:49:27", "remaining_time": "5:04:38"}
195
+ {"current_steps": 1630, "total_steps": 3325, "loss": 0.0151, "lr": 6.0371618733684474e-05, "epoch": 2.448826291079812, "percentage": 49.02, "elapsed_time": "4:50:42", "remaining_time": "5:02:18"}
196
+ {"current_steps": 1640, "total_steps": 3325, "loss": 0.0214, "lr": 5.9857476730140485e-05, "epoch": 2.463849765258216, "percentage": 49.32, "elapsed_time": "4:51:57", "remaining_time": "4:59:58"}
197
+ {"current_steps": 1650, "total_steps": 3325, "loss": 0.023, "lr": 5.9342247954854466e-05, "epoch": 2.4788732394366195, "percentage": 49.62, "elapsed_time": "4:53:13", "remaining_time": "4:57:39"}
198
+ {"current_steps": 1650, "total_steps": 3325, "eval_loss": 0.041283123195171356, "epoch": 2.4788732394366195, "percentage": 49.62, "elapsed_time": "4:55:49", "remaining_time": "5:00:18"}
199
+ {"current_steps": 1660, "total_steps": 3325, "loss": 0.0242, "lr": 5.8825989211011335e-05, "epoch": 2.4938967136150234, "percentage": 49.92, "elapsed_time": "4:57:09", "remaining_time": "4:58:02"}
200
+ {"current_steps": 1670, "total_steps": 3325, "loss": 0.0187, "lr": 5.830875741534852e-05, "epoch": 2.5089201877934273, "percentage": 50.23, "elapsed_time": "4:58:24", "remaining_time": "4:55:43"}
201
+ {"current_steps": 1680, "total_steps": 3325, "loss": 0.0259, "lr": 5.7790609591880826e-05, "epoch": 2.523943661971831, "percentage": 50.53, "elapsed_time": "4:59:40", "remaining_time": "4:53:25"}
202
+ {"current_steps": 1690, "total_steps": 3325, "loss": 0.0232, "lr": 5.727160286561386e-05, "epoch": 2.5389671361502346, "percentage": 50.83, "elapsed_time": "5:00:55", "remaining_time": "4:51:08"}
203
+ {"current_steps": 1700, "total_steps": 3325, "loss": 0.0257, "lr": 5.675179445624581e-05, "epoch": 2.5539906103286385, "percentage": 51.13, "elapsed_time": "5:02:11", "remaining_time": "4:48:51"}
204
+ {"current_steps": 1700, "total_steps": 3325, "eval_loss": 0.04087158292531967, "epoch": 2.5539906103286385, "percentage": 51.13, "elapsed_time": "5:04:48", "remaining_time": "4:51:21"}
205
+ {"current_steps": 1710, "total_steps": 3325, "loss": 0.018, "lr": 5.62312416718593e-05, "epoch": 2.5690140845070424, "percentage": 51.43, "elapsed_time": "5:06:07", "remaining_time": "4:49:07"}
206
+ {"current_steps": 1720, "total_steps": 3325, "loss": 0.0238, "lr": 5.5710001902603116e-05, "epoch": 2.584037558685446, "percentage": 51.73, "elapsed_time": "5:07:23", "remaining_time": "4:46:50"}
207
+ {"current_steps": 1730, "total_steps": 3325, "loss": 0.0213, "lr": 5.5188132614365094e-05, "epoch": 2.5990610328638497, "percentage": 52.03, "elapsed_time": "5:08:38", "remaining_time": "4:44:33"}
208
+ {"current_steps": 1740, "total_steps": 3325, "loss": 0.0214, "lr": 5.4665691342436565e-05, "epoch": 2.6140845070422536, "percentage": 52.33, "elapsed_time": "5:09:54", "remaining_time": "4:42:18"}
209
+ {"current_steps": 1750, "total_steps": 3325, "loss": 0.0241, "lr": 5.414273568516919e-05, "epoch": 2.629107981220657, "percentage": 52.63, "elapsed_time": "5:11:10", "remaining_time": "4:40:03"}
210
+ {"current_steps": 1750, "total_steps": 3325, "eval_loss": 0.03998855501413345, "epoch": 2.629107981220657, "percentage": 52.63, "elapsed_time": "5:13:46", "remaining_time": "4:42:23"}
211
+ {"current_steps": 1760, "total_steps": 3325, "loss": 0.0201, "lr": 5.361932329762481e-05, "epoch": 2.644131455399061, "percentage": 52.93, "elapsed_time": "5:15:06", "remaining_time": "4:40:11"}
212
+ {"current_steps": 1770, "total_steps": 3325, "loss": 0.0228, "lr": 5.309551188521914e-05, "epoch": 2.659154929577465, "percentage": 53.23, "elapsed_time": "5:16:22", "remaining_time": "4:37:56"}
213
+ {"current_steps": 1780, "total_steps": 3325, "loss": 0.0162, "lr": 5.2571359197359704e-05, "epoch": 2.6741784037558687, "percentage": 53.53, "elapsed_time": "5:17:37", "remaining_time": "4:35:41"}
214
+ {"current_steps": 1790, "total_steps": 3325, "loss": 0.0173, "lr": 5.2046923021079175e-05, "epoch": 2.6892018779342726, "percentage": 53.83, "elapsed_time": "5:18:53", "remaining_time": "4:33:27"}
215
+ {"current_steps": 1800, "total_steps": 3325, "loss": 0.0258, "lr": 5.1522261174664346e-05, "epoch": 2.704225352112676, "percentage": 54.14, "elapsed_time": "5:20:08", "remaining_time": "4:31:13"}
216
+ {"current_steps": 1800, "total_steps": 3325, "eval_loss": 0.040539611130952835, "epoch": 2.704225352112676, "percentage": 54.14, "elapsed_time": "5:22:45", "remaining_time": "4:33:26"}
217
+ {"current_steps": 1810, "total_steps": 3325, "loss": 0.035, "lr": 5.0997431501281835e-05, "epoch": 2.71924882629108, "percentage": 54.44, "elapsed_time": "5:24:05", "remaining_time": "4:31:16"}
218
+ {"current_steps": 1820, "total_steps": 3325, "loss": 0.0223, "lr": 5.0472491862600915e-05, "epoch": 2.7342723004694838, "percentage": 54.74, "elapsed_time": "5:25:20", "remaining_time": "4:29:02"}
219
+ {"current_steps": 1830, "total_steps": 3325, "loss": 0.0264, "lr": 4.994750013241435e-05, "epoch": 2.749295774647887, "percentage": 55.04, "elapsed_time": "5:26:36", "remaining_time": "4:26:49"}
220
+ {"current_steps": 1840, "total_steps": 3325, "loss": 0.0242, "lr": 4.9422514190257974e-05, "epoch": 2.764319248826291, "percentage": 55.34, "elapsed_time": "5:27:52", "remaining_time": "4:24:36"}
221
+ {"current_steps": 1850, "total_steps": 3325, "loss": 0.021, "lr": 4.88975919150294e-05, "epoch": 2.779342723004695, "percentage": 55.64, "elapsed_time": "5:29:07", "remaining_time": "4:22:24"}
222
+ {"current_steps": 1850, "total_steps": 3325, "eval_loss": 0.03918106481432915, "epoch": 2.779342723004695, "percentage": 55.64, "elapsed_time": "5:31:44", "remaining_time": "4:24:29"}
223
+ {"current_steps": 1860, "total_steps": 3325, "loss": 0.0257, "lr": 4.83727911786071e-05, "epoch": 2.7943661971830984, "percentage": 55.94, "elapsed_time": "5:33:05", "remaining_time": "4:22:20"}
224
+ {"current_steps": 1870, "total_steps": 3325, "loss": 0.0237, "lr": 4.7848169839470145e-05, "epoch": 2.8093896713615023, "percentage": 56.24, "elapsed_time": "5:34:20", "remaining_time": "4:20:08"}
225
+ {"current_steps": 1880, "total_steps": 3325, "loss": 0.0271, "lr": 4.7323785736319244e-05, "epoch": 2.824413145539906, "percentage": 56.54, "elapsed_time": "5:35:35", "remaining_time": "4:17:56"}
226
+ {"current_steps": 1890, "total_steps": 3325, "loss": 0.0234, "lr": 4.679969668170024e-05, "epoch": 2.8394366197183096, "percentage": 56.84, "elapsed_time": "5:36:51", "remaining_time": "4:15:45"}
227
+ {"current_steps": 1900, "total_steps": 3325, "loss": 0.0253, "lr": 4.627596045563031e-05, "epoch": 2.8544600938967135, "percentage": 57.14, "elapsed_time": "5:38:06", "remaining_time": "4:13:34"}
228
+ {"current_steps": 1900, "total_steps": 3325, "eval_loss": 0.036843445152044296, "epoch": 2.8544600938967135, "percentage": 57.14, "elapsed_time": "5:40:43", "remaining_time": "4:15:32"}
229
+ {"current_steps": 1910, "total_steps": 3325, "loss": 0.0156, "lr": 4.575263479922783e-05, "epoch": 2.8694835680751174, "percentage": 57.44, "elapsed_time": "5:42:03", "remaining_time": "4:13:24"}
230
+ {"current_steps": 1920, "total_steps": 3325, "loss": 0.0142, "lr": 4.522977740834651e-05, "epoch": 2.8845070422535213, "percentage": 57.74, "elapsed_time": "5:43:19", "remaining_time": "4:11:13"}
231
+ {"current_steps": 1930, "total_steps": 3325, "loss": 0.0169, "lr": 4.4707445927214456e-05, "epoch": 2.8995305164319247, "percentage": 58.05, "elapsed_time": "5:44:34", "remaining_time": "4:09:03"}
232
+ {"current_steps": 1940, "total_steps": 3325, "loss": 0.0255, "lr": 4.4185697942079115e-05, "epoch": 2.9145539906103286, "percentage": 58.35, "elapsed_time": "5:45:50", "remaining_time": "4:06:54"}
233
+ {"current_steps": 1950, "total_steps": 3325, "loss": 0.018, "lr": 4.366459097485832e-05, "epoch": 2.9295774647887325, "percentage": 58.65, "elapsed_time": "5:47:05", "remaining_time": "4:04:44"}
234
+ {"current_steps": 1950, "total_steps": 3325, "eval_loss": 0.03921648487448692, "epoch": 2.9295774647887325, "percentage": 58.65, "elapsed_time": "5:49:42", "remaining_time": "4:06:35"}
235
+ {"current_steps": 1960, "total_steps": 3325, "loss": 0.0263, "lr": 4.314418247679866e-05, "epoch": 2.9446009389671364, "percentage": 58.95, "elapsed_time": "5:51:03", "remaining_time": "4:04:29"}
236
+ {"current_steps": 1970, "total_steps": 3325, "loss": 0.014, "lr": 4.26245298221416e-05, "epoch": 2.95962441314554, "percentage": 59.25, "elapsed_time": "5:52:19", "remaining_time": "4:02:19"}
237
+ {"current_steps": 1980, "total_steps": 3325, "loss": 0.0176, "lr": 4.2105690301798014e-05, "epoch": 2.9746478873239437, "percentage": 59.55, "elapsed_time": "5:53:34", "remaining_time": "4:00:10"}
238
+ {"current_steps": 1990, "total_steps": 3325, "loss": 0.0177, "lr": 4.158772111703194e-05, "epoch": 2.9896713615023476, "percentage": 59.85, "elapsed_time": "5:54:50", "remaining_time": "3:58:02"}
239
+ {"current_steps": 2000, "total_steps": 3325, "loss": 0.0112, "lr": 4.107067937315429e-05, "epoch": 3.004694835680751, "percentage": 60.15, "elapsed_time": "5:56:05", "remaining_time": "3:55:54"}
240
+ {"current_steps": 2000, "total_steps": 3325, "eval_loss": 0.04066740348935127, "epoch": 3.004694835680751, "percentage": 60.15, "elapsed_time": "5:58:42", "remaining_time": "3:57:38"}
241
+ {"current_steps": 2010, "total_steps": 3325, "loss": 0.0121, "lr": 4.055462207322698e-05, "epoch": 3.019718309859155, "percentage": 60.45, "elapsed_time": "6:00:03", "remaining_time": "3:55:33"}
242
+ {"current_steps": 2020, "total_steps": 3325, "loss": 0.0118, "lr": 4.003960611177855e-05, "epoch": 3.034741784037559, "percentage": 60.75, "elapsed_time": "6:01:18", "remaining_time": "3:53:25"}
243
+ {"current_steps": 2030, "total_steps": 3325, "loss": 0.0097, "lr": 3.952568826853152e-05, "epoch": 3.0497652582159622, "percentage": 61.05, "elapsed_time": "6:02:34", "remaining_time": "3:51:17"}
244
+ {"current_steps": 2040, "total_steps": 3325, "loss": 0.0079, "lr": 3.901292520214256e-05, "epoch": 3.064788732394366, "percentage": 61.35, "elapsed_time": "6:03:50", "remaining_time": "3:49:10"}
245
+ {"current_steps": 2050, "total_steps": 3325, "loss": 0.0082, "lr": 3.850137344395598e-05, "epoch": 3.07981220657277, "percentage": 61.65, "elapsed_time": "6:05:05", "remaining_time": "3:47:04"}
246
+ {"current_steps": 2050, "total_steps": 3325, "eval_loss": 0.047751668840646744, "epoch": 3.07981220657277, "percentage": 61.65, "elapsed_time": "6:07:43", "remaining_time": "3:48:42"}
247
+ {"current_steps": 2060, "total_steps": 3325, "loss": 0.011, "lr": 3.799108939177118e-05, "epoch": 3.094835680751174, "percentage": 61.95, "elapsed_time": "6:09:03", "remaining_time": "3:46:37"}
248
+ {"current_steps": 2070, "total_steps": 3325, "loss": 0.0098, "lr": 3.7482129303624934e-05, "epoch": 3.1098591549295773, "percentage": 62.26, "elapsed_time": "6:10:19", "remaining_time": "3:44:31"}
249
+ {"current_steps": 2080, "total_steps": 3325, "loss": 0.0123, "lr": 3.697454929158901e-05, "epoch": 3.124882629107981, "percentage": 62.56, "elapsed_time": "6:11:34", "remaining_time": "3:42:24"}
250
+ {"current_steps": 2090, "total_steps": 3325, "loss": 0.0155, "lr": 3.6468405315583854e-05, "epoch": 3.139906103286385, "percentage": 62.86, "elapsed_time": "6:12:50", "remaining_time": "3:40:18"}
251
+ {"current_steps": 2100, "total_steps": 3325, "loss": 0.0127, "lr": 3.59637531772092e-05, "epoch": 3.1549295774647885, "percentage": 63.16, "elapsed_time": "6:14:05", "remaining_time": "3:38:13"}
252
+ {"current_steps": 2100, "total_steps": 3325, "eval_loss": 0.046006690710783005, "epoch": 3.1549295774647885, "percentage": 63.16, "elapsed_time": "6:16:43", "remaining_time": "3:39:45"}
253
+ {"current_steps": 2110, "total_steps": 3325, "loss": 0.0048, "lr": 3.546064851359192e-05, "epoch": 3.1699530516431924, "percentage": 63.46, "elapsed_time": "6:18:03", "remaining_time": "3:37:41"}
254
+ {"current_steps": 2120, "total_steps": 3325, "loss": 0.0125, "lr": 3.495914679125212e-05, "epoch": 3.1849765258215963, "percentage": 63.76, "elapsed_time": "6:19:18", "remaining_time": "3:35:35"}
255
+ {"current_steps": 2130, "total_steps": 3325, "loss": 0.0102, "lr": 3.445930329998819e-05, "epoch": 3.2, "percentage": 64.06, "elapsed_time": "6:20:34", "remaining_time": "3:33:30"}
256
+ {"current_steps": 2140, "total_steps": 3325, "loss": 0.0173, "lr": 3.396117314678097e-05, "epoch": 3.2150234741784036, "percentage": 64.36, "elapsed_time": "6:21:50", "remaining_time": "3:31:26"}
257
+ {"current_steps": 2150, "total_steps": 3325, "loss": 0.0112, "lr": 3.3464811249718474e-05, "epoch": 3.2300469483568075, "percentage": 64.66, "elapsed_time": "6:23:05", "remaining_time": "3:29:21"}
258
+ {"current_steps": 2150, "total_steps": 3325, "eval_loss": 0.04488084837794304, "epoch": 3.2300469483568075, "percentage": 64.66, "elapsed_time": "6:25:43", "remaining_time": "3:30:48"}
259
+ {"current_steps": 2160, "total_steps": 3325, "loss": 0.0128, "lr": 3.297027233194114e-05, "epoch": 3.2450704225352114, "percentage": 64.96, "elapsed_time": "6:27:03", "remaining_time": "3:28:45"}
260
+ {"current_steps": 2170, "total_steps": 3325, "loss": 0.01, "lr": 3.2477610915608704e-05, "epoch": 3.260093896713615, "percentage": 65.26, "elapsed_time": "6:28:19", "remaining_time": "3:26:41"}
261
+ {"current_steps": 2180, "total_steps": 3325, "loss": 0.014, "lr": 3.1986881315889315e-05, "epoch": 3.2751173708920187, "percentage": 65.56, "elapsed_time": "6:29:34", "remaining_time": "3:24:36"}
262
+ {"current_steps": 2190, "total_steps": 3325, "loss": 0.0174, "lr": 3.149813763497124e-05, "epoch": 3.2901408450704226, "percentage": 65.86, "elapsed_time": "6:30:50", "remaining_time": "3:22:33"}
263
+ {"current_steps": 2200, "total_steps": 3325, "loss": 0.0145, "lr": 3.101143375609818e-05, "epoch": 3.3051643192488265, "percentage": 66.17, "elapsed_time": "6:32:06", "remaining_time": "3:20:30"}
264
+ {"current_steps": 2200, "total_steps": 3325, "eval_loss": 0.04522354528307915, "epoch": 3.3051643192488265, "percentage": 66.17, "elapsed_time": "6:34:43", "remaining_time": "3:21:51"}
265
+ {"current_steps": 2210, "total_steps": 3325, "loss": 0.0143, "lr": 3.0526823337628915e-05, "epoch": 3.32018779342723, "percentage": 66.47, "elapsed_time": "6:36:03", "remaining_time": "3:19:49"}
266
+ {"current_steps": 2220, "total_steps": 3325, "loss": 0.0094, "lr": 3.004435980712129e-05, "epoch": 3.335211267605634, "percentage": 66.77, "elapsed_time": "6:37:18", "remaining_time": "3:17:45"}
267
+ {"current_steps": 2230, "total_steps": 3325, "loss": 0.0133, "lr": 2.9564096355442116e-05, "epoch": 3.3502347417840377, "percentage": 67.07, "elapsed_time": "6:38:34", "remaining_time": "3:15:42"}
268
+ {"current_steps": 2240, "total_steps": 3325, "loss": 0.0143, "lr": 2.9086085930902824e-05, "epoch": 3.365258215962441, "percentage": 67.37, "elapsed_time": "6:39:50", "remaining_time": "3:13:40"}
269
+ {"current_steps": 2250, "total_steps": 3325, "loss": 0.0086, "lr": 2.8610381233422058e-05, "epoch": 3.380281690140845, "percentage": 67.67, "elapsed_time": "6:41:05", "remaining_time": "3:11:37"}
270
+ {"current_steps": 2250, "total_steps": 3325, "eval_loss": 0.04514958709478378, "epoch": 3.380281690140845, "percentage": 67.67, "elapsed_time": "6:43:43", "remaining_time": "3:12:53"}
271
+ {"current_steps": 2260, "total_steps": 3325, "loss": 0.0106, "lr": 2.8137034708715592e-05, "epoch": 3.395305164319249, "percentage": 67.97, "elapsed_time": "6:45:02", "remaining_time": "3:10:52"}
272
+ {"current_steps": 2270, "total_steps": 3325, "loss": 0.0066, "lr": 2.7666098542514273e-05, "epoch": 3.4103286384976528, "percentage": 68.27, "elapsed_time": "6:46:18", "remaining_time": "3:08:49"}
273
+ {"current_steps": 2280, "total_steps": 3325, "loss": 0.0117, "lr": 2.719762465481055e-05, "epoch": 3.425352112676056, "percentage": 68.57, "elapsed_time": "6:47:33", "remaining_time": "3:06:47"}
274
+ {"current_steps": 2290, "total_steps": 3325, "loss": 0.0133, "lr": 2.6731664694134473e-05, "epoch": 3.44037558685446, "percentage": 68.87, "elapsed_time": "6:48:48", "remaining_time": "3:04:46"}
275
+ {"current_steps": 2300, "total_steps": 3325, "loss": 0.0161, "lr": 2.6268270031859476e-05, "epoch": 3.455399061032864, "percentage": 69.17, "elapsed_time": "6:50:04", "remaining_time": "3:02:45"}
276
+ {"current_steps": 2300, "total_steps": 3325, "eval_loss": 0.04896237701177597, "epoch": 3.455399061032864, "percentage": 69.17, "elapsed_time": "6:52:42", "remaining_time": "3:03:55"}
277
+ {"current_steps": 2310, "total_steps": 3325, "loss": 0.0108, "lr": 2.580749175653877e-05, "epoch": 3.4704225352112674, "percentage": 69.47, "elapsed_time": "6:54:02", "remaining_time": "3:01:55"}
278
+ {"current_steps": 2320, "total_steps": 3325, "loss": 0.0124, "lr": 2.5349380668272905e-05, "epoch": 3.4854460093896713, "percentage": 69.77, "elapsed_time": "6:55:17", "remaining_time": "2:59:54"}
279
+ {"current_steps": 2330, "total_steps": 3325, "loss": 0.013, "lr": 2.489398727310908e-05, "epoch": 3.500469483568075, "percentage": 70.08, "elapsed_time": "6:56:33", "remaining_time": "2:57:53"}
280
+ {"current_steps": 2340, "total_steps": 3325, "loss": 0.0107, "lr": 2.4441361777473066e-05, "epoch": 3.5154929577464786, "percentage": 70.38, "elapsed_time": "6:57:49", "remaining_time": "2:55:52"}
281
+ {"current_steps": 2350, "total_steps": 3325, "loss": 0.0134, "lr": 2.3991554082633912e-05, "epoch": 3.5305164319248825, "percentage": 70.68, "elapsed_time": "6:59:04", "remaining_time": "2:53:52"}
282
+ {"current_steps": 2350, "total_steps": 3325, "eval_loss": 0.04652281105518341, "epoch": 3.5305164319248825, "percentage": 70.68, "elapsed_time": "7:01:42", "remaining_time": "2:54:57"}
283
+ {"current_steps": 2360, "total_steps": 3325, "loss": 0.0088, "lr": 2.354461377920239e-05, "epoch": 3.5455399061032864, "percentage": 70.98, "elapsed_time": "7:03:02", "remaining_time": "2:52:58"}
284
+ {"current_steps": 2370, "total_steps": 3325, "loss": 0.0115, "lr": 2.3100590141663807e-05, "epoch": 3.5605633802816903, "percentage": 71.28, "elapsed_time": "7:04:18", "remaining_time": "2:50:58"}
285
+ {"current_steps": 2380, "total_steps": 3325, "loss": 0.0182, "lr": 2.265953212294551e-05, "epoch": 3.575586854460094, "percentage": 71.58, "elapsed_time": "7:05:33", "remaining_time": "2:48:58"}
286
+ {"current_steps": 2390, "total_steps": 3325, "loss": 0.0164, "lr": 2.2221488349019903e-05, "epoch": 3.5906103286384976, "percentage": 71.88, "elapsed_time": "7:06:48", "remaining_time": "2:46:58"}
287
+ {"current_steps": 2400, "total_steps": 3325, "loss": 0.009, "lr": 2.1786507113543457e-05, "epoch": 3.6056338028169015, "percentage": 72.18, "elapsed_time": "7:08:04", "remaining_time": "2:44:59"}
288
+ {"current_steps": 2400, "total_steps": 3325, "eval_loss": 0.04605977609753609, "epoch": 3.6056338028169015, "percentage": 72.18, "elapsed_time": "7:10:42", "remaining_time": "2:46:00"}
289
+ {"current_steps": 2410, "total_steps": 3325, "loss": 0.0176, "lr": 2.1354636372532523e-05, "epoch": 3.6206572769953054, "percentage": 72.48, "elapsed_time": "7:12:02", "remaining_time": "2:44:02"}
290
+ {"current_steps": 2420, "total_steps": 3325, "loss": 0.0101, "lr": 2.092592373907617e-05, "epoch": 3.635680751173709, "percentage": 72.78, "elapsed_time": "7:13:18", "remaining_time": "2:42:02"}
291
+ {"current_steps": 2430, "total_steps": 3325, "loss": 0.0075, "lr": 2.0500416478086932e-05, "epoch": 3.6507042253521127, "percentage": 73.08, "elapsed_time": "7:14:34", "remaining_time": "2:40:03"}
292
+ {"current_steps": 2440, "total_steps": 3325, "loss": 0.0117, "lr": 2.0078161501089954e-05, "epoch": 3.6657276995305166, "percentage": 73.38, "elapsed_time": "7:15:50", "remaining_time": "2:38:04"}
293
+ {"current_steps": 2450, "total_steps": 3325, "loss": 0.0056, "lr": 1.9659205361050982e-05, "epoch": 3.68075117370892, "percentage": 73.68, "elapsed_time": "7:17:06", "remaining_time": "2:36:06"}
294
+ {"current_steps": 2450, "total_steps": 3325, "eval_loss": 0.04802750423550606, "epoch": 3.68075117370892, "percentage": 73.68, "elapsed_time": "7:19:43", "remaining_time": "2:37:02"}
295
+ {"current_steps": 2460, "total_steps": 3325, "loss": 0.0154, "lr": 1.924359424724408e-05, "epoch": 3.695774647887324, "percentage": 73.98, "elapsed_time": "7:21:04", "remaining_time": "2:35:05"}
296
+ {"current_steps": 2470, "total_steps": 3325, "loss": 0.0145, "lr": 1.8831373980159296e-05, "epoch": 3.710798122065728, "percentage": 74.29, "elapsed_time": "7:22:19", "remaining_time": "2:33:06"}
297
+ {"current_steps": 2480, "total_steps": 3325, "loss": 0.0063, "lr": 1.8422590006450947e-05, "epoch": 3.7258215962441312, "percentage": 74.59, "elapsed_time": "7:23:35", "remaining_time": "2:31:08"}
298
+ {"current_steps": 2490, "total_steps": 3325, "loss": 0.0089, "lr": 1.801728739392731e-05, "epoch": 3.740845070422535, "percentage": 74.89, "elapsed_time": "7:24:51", "remaining_time": "2:29:10"}
299
+ {"current_steps": 2500, "total_steps": 3325, "loss": 0.0069, "lr": 1.7615510826581904e-05, "epoch": 3.755868544600939, "percentage": 75.19, "elapsed_time": "7:26:06", "remaining_time": "2:27:13"}
300
+ {"current_steps": 2500, "total_steps": 3325, "eval_loss": 0.04896940663456917, "epoch": 3.755868544600939, "percentage": 75.19, "elapsed_time": "7:28:44", "remaining_time": "2:28:05"}
301
+ {"current_steps": 2510, "total_steps": 3325, "loss": 0.0164, "lr": 1.7217304599667146e-05, "epoch": 3.770892018779343, "percentage": 75.49, "elapsed_time": "7:30:04", "remaining_time": "2:26:08"}
302
+ {"current_steps": 2520, "total_steps": 3325, "loss": 0.01, "lr": 1.6822712614810893e-05, "epoch": 3.7859154929577463, "percentage": 75.79, "elapsed_time": "7:31:20", "remaining_time": "2:24:10"}
303
+ {"current_steps": 2530, "total_steps": 3325, "loss": 0.0117, "lr": 1.643177837517631e-05, "epoch": 3.80093896713615, "percentage": 76.09, "elapsed_time": "7:32:36", "remaining_time": "2:22:13"}
304
+ {"current_steps": 2540, "total_steps": 3325, "loss": 0.0108, "lr": 1.6044544980665767e-05, "epoch": 3.815962441314554, "percentage": 76.39, "elapsed_time": "7:33:51", "remaining_time": "2:20:16"}
305
+ {"current_steps": 2550, "total_steps": 3325, "loss": 0.007, "lr": 1.5661055123169126e-05, "epoch": 3.830985915492958, "percentage": 76.69, "elapsed_time": "7:35:07", "remaining_time": "2:18:19"}
306
+ {"current_steps": 2550, "total_steps": 3325, "eval_loss": 0.04891159385442734, "epoch": 3.830985915492958, "percentage": 76.69, "elapsed_time": "7:37:45", "remaining_time": "2:19:07"}
307
+ {"current_steps": 2560, "total_steps": 3325, "loss": 0.0079, "lr": 1.5281351081856974e-05, "epoch": 3.8460093896713614, "percentage": 76.99, "elapsed_time": "7:39:05", "remaining_time": "2:17:11"}
308
+ {"current_steps": 2570, "total_steps": 3325, "loss": 0.0075, "lr": 1.4905474718519491e-05, "epoch": 3.8610328638497653, "percentage": 77.29, "elapsed_time": "7:40:21", "remaining_time": "2:15:14"}
309
+ {"current_steps": 2580, "total_steps": 3325, "loss": 0.0106, "lr": 1.453346747295119e-05, "epoch": 3.876056338028169, "percentage": 77.59, "elapsed_time": "7:41:36", "remaining_time": "2:13:17"}
310
+ {"current_steps": 2590, "total_steps": 3325, "loss": 0.0117, "lr": 1.4165370358382274e-05, "epoch": 3.8910798122065726, "percentage": 77.89, "elapsed_time": "7:42:52", "remaining_time": "2:11:21"}
311
+ {"current_steps": 2600, "total_steps": 3325, "loss": 0.0147, "lr": 1.3801223956956994e-05, "epoch": 3.9061032863849765, "percentage": 78.2, "elapsed_time": "7:44:07", "remaining_time": "2:09:25"}
312
+ {"current_steps": 2600, "total_steps": 3325, "eval_loss": 0.048022232949733734, "epoch": 3.9061032863849765, "percentage": 78.2, "elapsed_time": "7:46:45", "remaining_time": "2:10:09"}
313
+ {"current_steps": 2610, "total_steps": 3325, "loss": 0.0101, "lr": 1.344106841525946e-05, "epoch": 3.9211267605633804, "percentage": 78.5, "elapsed_time": "7:48:05", "remaining_time": "2:08:13"}
314
+ {"current_steps": 2620, "total_steps": 3325, "loss": 0.0111, "lr": 1.3084943439887659e-05, "epoch": 3.936150234741784, "percentage": 78.8, "elapsed_time": "7:49:20", "remaining_time": "2:06:17"}
315
+ {"current_steps": 2630, "total_steps": 3325, "loss": 0.0069, "lr": 1.273288829307579e-05, "epoch": 3.9511737089201877, "percentage": 79.1, "elapsed_time": "7:50:36", "remaining_time": "2:04:21"}
316
+ {"current_steps": 2640, "total_steps": 3325, "loss": 0.0073, "lr": 1.2384941788365622e-05, "epoch": 3.9661971830985916, "percentage": 79.4, "elapsed_time": "7:51:52", "remaining_time": "2:02:26"}
317
+ {"current_steps": 2650, "total_steps": 3325, "loss": 0.0123, "lr": 1.2041142286327477e-05, "epoch": 3.981220657276995, "percentage": 79.7, "elapsed_time": "7:53:08", "remaining_time": "2:00:31"}
318
+ {"current_steps": 2650, "total_steps": 3325, "eval_loss": 0.0474095456302166, "epoch": 3.981220657276995, "percentage": 79.7, "elapsed_time": "7:55:46", "remaining_time": "2:01:11"}
319
+ {"current_steps": 2660, "total_steps": 3325, "loss": 0.0058, "lr": 1.170152769033095e-05, "epoch": 3.996244131455399, "percentage": 80.0, "elapsed_time": "7:57:06", "remaining_time": "1:59:16"}
320
+ {"current_steps": 2670, "total_steps": 3325, "loss": 0.0066, "lr": 1.1366135442366127e-05, "epoch": 4.011267605633803, "percentage": 80.3, "elapsed_time": "7:58:22", "remaining_time": "1:57:21"}
321
+ {"current_steps": 2680, "total_steps": 3325, "loss": 0.0061, "lr": 1.103500251891571e-05, "epoch": 4.026291079812206, "percentage": 80.6, "elapsed_time": "7:59:38", "remaining_time": "1:55:26"}
322
+ {"current_steps": 2690, "total_steps": 3325, "loss": 0.0042, "lr": 1.0708165426878325e-05, "epoch": 4.041314553990611, "percentage": 80.9, "elapsed_time": "8:00:54", "remaining_time": "1:53:31"}
323
+ {"current_steps": 2700, "total_steps": 3325, "loss": 0.0053, "lr": 1.0385660199543812e-05, "epoch": 4.056338028169014, "percentage": 81.2, "elapsed_time": "8:02:10", "remaining_time": "1:51:36"}
324
+ {"current_steps": 2700, "total_steps": 3325, "eval_loss": 0.05291583761572838, "epoch": 4.056338028169014, "percentage": 81.2, "elapsed_time": "8:04:48", "remaining_time": "1:52:13"}
325
+ {"current_steps": 2710, "total_steps": 3325, "loss": 0.0037, "lr": 1.0067522392620537e-05, "epoch": 4.0713615023474174, "percentage": 81.5, "elapsed_time": "8:06:08", "remaining_time": "1:50:19"}
326
+ {"current_steps": 2720, "total_steps": 3325, "loss": 0.0084, "lr": 9.753787080315385e-06, "epoch": 4.086384976525822, "percentage": 81.8, "elapsed_time": "8:07:24", "remaining_time": "1:48:24"}
327
+ {"current_steps": 2730, "total_steps": 3325, "loss": 0.0051, "lr": 9.444488851467042e-06, "epoch": 4.101408450704225, "percentage": 82.11, "elapsed_time": "8:08:39", "remaining_time": "1:46:30"}
328
+ {"current_steps": 2740, "total_steps": 3325, "loss": 0.0043, "lr": 9.139661805732435e-06, "epoch": 4.1164319248826295, "percentage": 82.41, "elapsed_time": "8:09:55", "remaining_time": "1:44:36"}
329
+ {"current_steps": 2750, "total_steps": 3325, "loss": 0.0064, "lr": 8.839339549827397e-06, "epoch": 4.131455399061033, "percentage": 82.71, "elapsed_time": "8:11:11", "remaining_time": "1:42:42"}
330
+ {"current_steps": 2750, "total_steps": 3325, "eval_loss": 0.05712565779685974, "epoch": 4.131455399061033, "percentage": 82.71, "elapsed_time": "8:13:49", "remaining_time": "1:43:15"}
331
+ {"current_steps": 2760, "total_steps": 3325, "loss": 0.0045, "lr": 8.543555193821634e-06, "epoch": 4.146478873239436, "percentage": 83.01, "elapsed_time": "8:15:09", "remaining_time": "1:41:21"}
332
+ {"current_steps": 2770, "total_steps": 3325, "loss": 0.0032, "lr": 8.252341347488251e-06, "epoch": 4.161502347417841, "percentage": 83.31, "elapsed_time": "8:16:25", "remaining_time": "1:39:27"}
333
+ {"current_steps": 2780, "total_steps": 3325, "loss": 0.005, "lr": 7.965730116708681e-06, "epoch": 4.176525821596244, "percentage": 83.61, "elapsed_time": "8:17:40", "remaining_time": "1:37:34"}
334
+ {"current_steps": 2790, "total_steps": 3325, "loss": 0.0025, "lr": 7.68375309993304e-06, "epoch": 4.191549295774648, "percentage": 83.91, "elapsed_time": "8:18:56", "remaining_time": "1:35:40"}
335
+ {"current_steps": 2800, "total_steps": 3325, "loss": 0.0064, "lr": 7.406441384696372e-06, "epoch": 4.206572769953052, "percentage": 84.21, "elapsed_time": "8:20:12", "remaining_time": "1:33:47"}
336
+ {"current_steps": 2800, "total_steps": 3325, "eval_loss": 0.05896175280213356, "epoch": 4.206572769953052, "percentage": 84.21, "elapsed_time": "8:22:49", "remaining_time": "1:34:16"}
337
+ {"current_steps": 2810, "total_steps": 3325, "loss": 0.0088, "lr": 7.133825544191464e-06, "epoch": 4.221596244131455, "percentage": 84.51, "elapsed_time": "8:24:10", "remaining_time": "1:32:24"}
338
+ {"current_steps": 2820, "total_steps": 3325, "loss": 0.0019, "lr": 6.865935633897996e-06, "epoch": 4.236619718309859, "percentage": 84.81, "elapsed_time": "8:25:26", "remaining_time": "1:30:30"}
339
+ {"current_steps": 2830, "total_steps": 3325, "loss": 0.0057, "lr": 6.602801188269081e-06, "epoch": 4.251643192488263, "percentage": 85.11, "elapsed_time": "8:26:41", "remaining_time": "1:28:37"}
340
+ {"current_steps": 2840, "total_steps": 3325, "loss": 0.0029, "lr": 6.344451217475183e-06, "epoch": 4.266666666666667, "percentage": 85.41, "elapsed_time": "8:27:57", "remaining_time": "1:26:44"}
341
+ {"current_steps": 2850, "total_steps": 3325, "loss": 0.0038, "lr": 6.090914204205655e-06, "epoch": 4.28169014084507, "percentage": 85.71, "elapsed_time": "8:29:12", "remaining_time": "1:24:52"}
342
+ {"current_steps": 2850, "total_steps": 3325, "eval_loss": 0.060705944895744324, "epoch": 4.28169014084507, "percentage": 85.71, "elapsed_time": "8:31:50", "remaining_time": "1:25:18"}
343
+ {"current_steps": 2860, "total_steps": 3325, "loss": 0.0029, "lr": 5.842218100528679e-06, "epoch": 4.296713615023474, "percentage": 86.02, "elapsed_time": "8:33:11", "remaining_time": "1:23:26"}
344
+ {"current_steps": 2870, "total_steps": 3325, "loss": 0.0041, "lr": 5.598390324809555e-06, "epoch": 4.311737089201878, "percentage": 86.32, "elapsed_time": "8:34:27", "remaining_time": "1:21:33"}
345
+ {"current_steps": 2880, "total_steps": 3325, "loss": 0.0048, "lr": 5.359457758687841e-06, "epoch": 4.326760563380281, "percentage": 86.62, "elapsed_time": "8:35:43", "remaining_time": "1:19:41"}
346
+ {"current_steps": 2890, "total_steps": 3325, "loss": 0.0088, "lr": 5.125446744113743e-06, "epoch": 4.341784037558686, "percentage": 86.92, "elapsed_time": "8:36:58", "remaining_time": "1:17:48"}
347
+ {"current_steps": 2900, "total_steps": 3325, "loss": 0.0011, "lr": 4.896383080443934e-06, "epoch": 4.356807511737089, "percentage": 87.22, "elapsed_time": "8:38:14", "remaining_time": "1:15:56"}
348
+ {"current_steps": 2900, "total_steps": 3325, "eval_loss": 0.06272595375776291, "epoch": 4.356807511737089, "percentage": 87.22, "elapsed_time": "8:40:52", "remaining_time": "1:16:20"}
349
+ {"current_steps": 2910, "total_steps": 3325, "loss": 0.0053, "lr": 4.672292021597174e-06, "epoch": 4.371830985915493, "percentage": 87.52, "elapsed_time": "8:42:12", "remaining_time": "1:14:28"}
350
+ {"current_steps": 2920, "total_steps": 3325, "loss": 0.0055, "lr": 4.4531982732702145e-06, "epoch": 4.386854460093897, "percentage": 87.82, "elapsed_time": "8:43:28", "remaining_time": "1:12:36"}
351
+ {"current_steps": 2930, "total_steps": 3325, "loss": 0.0045, "lr": 4.239125990213883e-06, "epoch": 4.4018779342723, "percentage": 88.12, "elapsed_time": "8:44:44", "remaining_time": "1:10:44"}
352
+ {"current_steps": 2940, "total_steps": 3325, "loss": 0.001, "lr": 4.030098773570174e-06, "epoch": 4.416901408450705, "percentage": 88.42, "elapsed_time": "8:46:00", "remaining_time": "1:08:52"}
353
+ {"current_steps": 2950, "total_steps": 3325, "loss": 0.0034, "lr": 3.826139668270234e-06, "epoch": 4.431924882629108, "percentage": 88.72, "elapsed_time": "8:47:15", "remaining_time": "1:07:01"}
354
+ {"current_steps": 2950, "total_steps": 3325, "eval_loss": 0.06274248659610748, "epoch": 4.431924882629108, "percentage": 88.72, "elapsed_time": "8:49:53", "remaining_time": "1:07:21"}
355
+ {"current_steps": 2960, "total_steps": 3325, "loss": 0.0074, "lr": 3.6272711604936504e-06, "epoch": 4.446948356807511, "percentage": 89.02, "elapsed_time": "8:51:14", "remaining_time": "1:05:30"}
356
+ {"current_steps": 2970, "total_steps": 3325, "loss": 0.0033, "lr": 3.433515175189428e-06, "epoch": 4.461971830985916, "percentage": 89.32, "elapsed_time": "8:52:30", "remaining_time": "1:03:38"}
357
+ {"current_steps": 2980, "total_steps": 3325, "loss": 0.0093, "lr": 3.2448930736588e-06, "epoch": 4.476995305164319, "percentage": 89.62, "elapsed_time": "8:53:45", "remaining_time": "1:01:47"}
358
+ {"current_steps": 2990, "total_steps": 3325, "loss": 0.0031, "lr": 3.061425651200117e-06, "epoch": 4.492018779342723, "percentage": 89.92, "elapsed_time": "8:55:01", "remaining_time": "0:59:56"}
359
+ {"current_steps": 3000, "total_steps": 3325, "loss": 0.0063, "lr": 2.883133134816296e-06, "epoch": 4.507042253521127, "percentage": 90.23, "elapsed_time": "8:56:16", "remaining_time": "0:58:05"}
360
+ {"current_steps": 3000, "total_steps": 3325, "eval_loss": 0.062312256544828415, "epoch": 4.507042253521127, "percentage": 90.23, "elapsed_time": "8:58:54", "remaining_time": "0:58:22"}
361
+ {"current_steps": 3010, "total_steps": 3325, "loss": 0.0026, "lr": 2.7100351809847326e-06, "epoch": 4.52206572769953, "percentage": 90.53, "elapsed_time": "9:00:14", "remaining_time": "0:56:32"}
362
+ {"current_steps": 3020, "total_steps": 3325, "loss": 0.0026, "lr": 2.542150873490251e-06, "epoch": 4.537089201877935, "percentage": 90.83, "elapsed_time": "9:01:30", "remaining_time": "0:54:41"}
363
+ {"current_steps": 3030, "total_steps": 3325, "loss": 0.0039, "lr": 2.3794987213211383e-06, "epoch": 4.552112676056338, "percentage": 91.13, "elapsed_time": "9:02:46", "remaining_time": "0:52:50"}
364
+ {"current_steps": 3040, "total_steps": 3325, "loss": 0.0041, "lr": 2.222096656628547e-06, "epoch": 4.567136150234742, "percentage": 91.43, "elapsed_time": "9:04:02", "remaining_time": "0:51:00"}
365
+ {"current_steps": 3050, "total_steps": 3325, "loss": 0.0033, "lr": 2.0699620327495174e-06, "epoch": 4.582159624413146, "percentage": 91.73, "elapsed_time": "9:05:18", "remaining_time": "0:49:09"}
366
+ {"current_steps": 3050, "total_steps": 3325, "eval_loss": 0.06346932053565979, "epoch": 4.582159624413146, "percentage": 91.73, "elapsed_time": "9:07:56", "remaining_time": "0:49:24"}
367
+ {"current_steps": 3060, "total_steps": 3325, "loss": 0.0014, "lr": 1.9231116222937996e-06, "epoch": 4.597183098591549, "percentage": 92.03, "elapsed_time": "9:09:17", "remaining_time": "0:47:34"}
368
+ {"current_steps": 3070, "total_steps": 3325, "loss": 0.0022, "lr": 1.7815616152946523e-06, "epoch": 4.612206572769953, "percentage": 92.33, "elapsed_time": "9:10:33", "remaining_time": "0:45:43"}
369
+ {"current_steps": 3080, "total_steps": 3325, "loss": 0.0016, "lr": 1.6453276174240195e-06, "epoch": 4.627230046948357, "percentage": 92.63, "elapsed_time": "9:11:48", "remaining_time": "0:43:53"}
370
+ {"current_steps": 3090, "total_steps": 3325, "loss": 0.0032, "lr": 1.5144246482719114e-06, "epoch": 4.642253521126761, "percentage": 92.93, "elapsed_time": "9:13:04", "remaining_time": "0:42:03"}
371
+ {"current_steps": 3100, "total_steps": 3325, "loss": 0.0048, "lr": 1.3888671396905805e-06, "epoch": 4.657276995305164, "percentage": 93.23, "elapsed_time": "9:14:20", "remaining_time": "0:40:14"}
372
+ {"current_steps": 3100, "total_steps": 3325, "eval_loss": 0.06427957862615585, "epoch": 4.657276995305164, "percentage": 93.23, "elapsed_time": "9:16:58", "remaining_time": "0:40:25"}
373
+ {"current_steps": 3110, "total_steps": 3325, "loss": 0.0075, "lr": 1.2686689342034431e-06, "epoch": 4.672300469483568, "percentage": 93.53, "elapsed_time": "9:18:18", "remaining_time": "0:38:35"}
374
+ {"current_steps": 3120, "total_steps": 3325, "loss": 0.0058, "lr": 1.1538432834789227e-06, "epoch": 4.687323943661972, "percentage": 93.83, "elapsed_time": "9:19:34", "remaining_time": "0:36:46"}
375
+ {"current_steps": 3130, "total_steps": 3325, "loss": 0.0041, "lr": 1.044402846869491e-06, "epoch": 4.702347417840375, "percentage": 94.14, "elapsed_time": "9:20:49", "remaining_time": "0:34:56"}
376
+ {"current_steps": 3140, "total_steps": 3325, "loss": 0.003, "lr": 9.403596900160073e-07, "epoch": 4.71737089201878, "percentage": 94.44, "elapsed_time": "9:22:05", "remaining_time": "0:33:06"}
377
+ {"current_steps": 3150, "total_steps": 3325, "loss": 0.0044, "lr": 8.417252835174749e-07, "epoch": 4.732394366197183, "percentage": 94.74, "elapsed_time": "9:23:21", "remaining_time": "0:31:17"}
378
+ {"current_steps": 3150, "total_steps": 3325, "eval_loss": 0.06363623589277267, "epoch": 4.732394366197183, "percentage": 94.74, "elapsed_time": "9:25:58", "remaining_time": "0:31:26"}
379
+ {"current_steps": 3160, "total_steps": 3325, "loss": 0.0079, "lr": 7.48510501666455e-07, "epoch": 4.7474178403755865, "percentage": 95.04, "elapsed_time": "9:27:20", "remaining_time": "0:29:37"}
380
+ {"current_steps": 3170, "total_steps": 3325, "loss": 0.0041, "lr": 6.607256212501578e-07, "epoch": 4.762441314553991, "percentage": 95.34, "elapsed_time": "9:28:35", "remaining_time": "0:27:48"}
381
+ {"current_steps": 3180, "total_steps": 3325, "loss": 0.005, "lr": 5.783803204174654e-07, "epoch": 4.777464788732394, "percentage": 95.64, "elapsed_time": "9:29:51", "remaining_time": "0:25:59"}
382
+ {"current_steps": 3190, "total_steps": 3325, "loss": 0.0027, "lr": 5.014836776119358e-07, "epoch": 4.792488262910798, "percentage": 95.94, "elapsed_time": "9:31:07", "remaining_time": "0:24:10"}
383
+ {"current_steps": 3200, "total_steps": 3325, "loss": 0.0031, "lr": 4.300441705708924e-07, "epoch": 4.807511737089202, "percentage": 96.24, "elapsed_time": "9:32:23", "remaining_time": "0:22:21"}
384
+ {"current_steps": 3200, "total_steps": 3325, "eval_loss": 0.06359302997589111, "epoch": 4.807511737089202, "percentage": 96.24, "elapsed_time": "9:35:00", "remaining_time": "0:22:27"}
385
+ {"current_steps": 3210, "total_steps": 3325, "loss": 0.0047, "lr": 3.6406967539078796e-07, "epoch": 4.822535211267605, "percentage": 96.54, "elapsed_time": "9:36:21", "remaining_time": "0:20:38"}
386
+ {"current_steps": 3220, "total_steps": 3325, "loss": 0.004, "lr": 3.0356746565887715e-07, "epoch": 4.83755868544601, "percentage": 96.84, "elapsed_time": "9:37:37", "remaining_time": "0:18:50"}
387
+ {"current_steps": 3230, "total_steps": 3325, "loss": 0.0031, "lr": 2.485442116513026e-07, "epoch": 4.852582159624413, "percentage": 97.14, "elapsed_time": "9:38:53", "remaining_time": "0:17:01"}
388
+ {"current_steps": 3240, "total_steps": 3325, "loss": 0.0087, "lr": 1.9900597959770507e-07, "epoch": 4.867605633802817, "percentage": 97.44, "elapsed_time": "9:40:09", "remaining_time": "0:15:13"}
389
+ {"current_steps": 3250, "total_steps": 3325, "loss": 0.0022, "lr": 1.5495823101245866e-07, "epoch": 4.882629107981221, "percentage": 97.74, "elapsed_time": "9:41:25", "remaining_time": "0:13:25"}
390
+ {"current_steps": 3250, "total_steps": 3325, "eval_loss": 0.06390237808227539, "epoch": 4.882629107981221, "percentage": 97.74, "elapsed_time": "9:44:03", "remaining_time": "0:13:28"}
391
+ {"current_steps": 3260, "total_steps": 3325, "loss": 0.006, "lr": 1.164058220925135e-07, "epoch": 4.897652582159624, "percentage": 98.05, "elapsed_time": "9:45:24", "remaining_time": "0:11:40"}
392
+ {"current_steps": 3270, "total_steps": 3325, "loss": 0.0067, "lr": 8.335300318201844e-08, "epoch": 4.912676056338028, "percentage": 98.35, "elapsed_time": "9:46:39", "remaining_time": "0:09:52"}
393
+ {"current_steps": 3280, "total_steps": 3325, "loss": 0.008, "lr": 5.5803418303745917e-08, "epoch": 4.927699530516432, "percentage": 98.65, "elapsed_time": "9:47:54", "remaining_time": "0:08:03"}
394
+ {"current_steps": 3290, "total_steps": 3325, "loss": 0.0015, "lr": 3.3760104757313284e-08, "epoch": 4.942723004694836, "percentage": 98.95, "elapsed_time": "9:49:10", "remaining_time": "0:06:16"}
395
+ {"current_steps": 3300, "total_steps": 3325, "loss": 0.0078, "lr": 1.7225492784345156e-08, "epoch": 4.957746478873239, "percentage": 99.25, "elapsed_time": "9:50:26", "remaining_time": "0:04:28"}
396
+ {"current_steps": 3300, "total_steps": 3325, "eval_loss": 0.06379479169845581, "epoch": 4.957746478873239, "percentage": 99.25, "elapsed_time": "9:53:04", "remaining_time": "0:04:29"}
397
+ {"current_steps": 3310, "total_steps": 3325, "loss": 0.006, "lr": 6.201405300532148e-09, "epoch": 4.972769953051643, "percentage": 99.55, "elapsed_time": "9:54:25", "remaining_time": "0:02:41"}
398
+ {"current_steps": 3320, "total_steps": 3325, "loss": 0.0032, "lr": 6.890576946805282e-10, "epoch": 4.987793427230047, "percentage": 99.85, "elapsed_time": "9:55:41", "remaining_time": "0:00:53"}
399
+ {"current_steps": 3325, "total_steps": 3325, "epoch": 4.995305164319249, "percentage": 100.0, "elapsed_time": "9:56:24", "remaining_time": "0:00:00"}
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold6/trainer_state.json ADDED
@@ -0,0 +1,2894 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.036843445152044296,
3
+ "best_model_checkpoint": "saves/psy-course/Llama-3.1-8B-Instruct/train/fold6/checkpoint-1900",
4
+ "epoch": 4.995305164319249,
5
+ "eval_steps": 50,
6
+ "global_step": 3325,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.015023474178403756,
13
+ "grad_norm": 4.304145336151123,
14
+ "learning_rate": 3.003003003003003e-06,
15
+ "loss": 1.5464,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.03004694835680751,
20
+ "grad_norm": 5.03688907623291,
21
+ "learning_rate": 6.006006006006006e-06,
22
+ "loss": 1.597,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.04507042253521127,
27
+ "grad_norm": 5.86588191986084,
28
+ "learning_rate": 9.00900900900901e-06,
29
+ "loss": 1.4497,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.06009389671361502,
34
+ "grad_norm": 2.099303722381592,
35
+ "learning_rate": 1.2012012012012012e-05,
36
+ "loss": 0.9009,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.07511737089201878,
41
+ "grad_norm": 1.6121171712875366,
42
+ "learning_rate": 1.5015015015015016e-05,
43
+ "loss": 0.6045,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.07511737089201878,
48
+ "eval_loss": 0.41910141706466675,
49
+ "eval_runtime": 156.3169,
50
+ "eval_samples_per_second": 7.574,
51
+ "eval_steps_per_second": 7.574,
52
+ "step": 50
53
+ },
54
+ {
55
+ "epoch": 0.09014084507042254,
56
+ "grad_norm": 1.1837172508239746,
57
+ "learning_rate": 1.801801801801802e-05,
58
+ "loss": 0.402,
59
+ "step": 60
60
+ },
61
+ {
62
+ "epoch": 0.10516431924882629,
63
+ "grad_norm": 0.9849412441253662,
64
+ "learning_rate": 2.102102102102102e-05,
65
+ "loss": 0.2368,
66
+ "step": 70
67
+ },
68
+ {
69
+ "epoch": 0.12018779342723004,
70
+ "grad_norm": 0.8895949721336365,
71
+ "learning_rate": 2.4024024024024024e-05,
72
+ "loss": 0.1741,
73
+ "step": 80
74
+ },
75
+ {
76
+ "epoch": 0.1352112676056338,
77
+ "grad_norm": 0.9555579423904419,
78
+ "learning_rate": 2.702702702702703e-05,
79
+ "loss": 0.1089,
80
+ "step": 90
81
+ },
82
+ {
83
+ "epoch": 0.15023474178403756,
84
+ "grad_norm": 0.7877600193023682,
85
+ "learning_rate": 3.0030030030030033e-05,
86
+ "loss": 0.118,
87
+ "step": 100
88
+ },
89
+ {
90
+ "epoch": 0.15023474178403756,
91
+ "eval_loss": 0.09762203693389893,
92
+ "eval_runtime": 156.4651,
93
+ "eval_samples_per_second": 7.567,
94
+ "eval_steps_per_second": 7.567,
95
+ "step": 100
96
+ },
97
+ {
98
+ "epoch": 0.1652582159624413,
99
+ "grad_norm": 1.2528424263000488,
100
+ "learning_rate": 3.3033033033033035e-05,
101
+ "loss": 0.1111,
102
+ "step": 110
103
+ },
104
+ {
105
+ "epoch": 0.18028169014084508,
106
+ "grad_norm": 0.836103618144989,
107
+ "learning_rate": 3.603603603603604e-05,
108
+ "loss": 0.0988,
109
+ "step": 120
110
+ },
111
+ {
112
+ "epoch": 0.19530516431924883,
113
+ "grad_norm": 1.0173139572143555,
114
+ "learning_rate": 3.903903903903904e-05,
115
+ "loss": 0.0874,
116
+ "step": 130
117
+ },
118
+ {
119
+ "epoch": 0.21032863849765257,
120
+ "grad_norm": 0.4798429012298584,
121
+ "learning_rate": 4.204204204204204e-05,
122
+ "loss": 0.0904,
123
+ "step": 140
124
+ },
125
+ {
126
+ "epoch": 0.22535211267605634,
127
+ "grad_norm": 0.6175504922866821,
128
+ "learning_rate": 4.5045045045045046e-05,
129
+ "loss": 0.075,
130
+ "step": 150
131
+ },
132
+ {
133
+ "epoch": 0.22535211267605634,
134
+ "eval_loss": 0.09080640226602554,
135
+ "eval_runtime": 156.3504,
136
+ "eval_samples_per_second": 7.573,
137
+ "eval_steps_per_second": 7.573,
138
+ "step": 150
139
+ },
140
+ {
141
+ "epoch": 0.2403755868544601,
142
+ "grad_norm": 0.8490262031555176,
143
+ "learning_rate": 4.804804804804805e-05,
144
+ "loss": 0.0712,
145
+ "step": 160
146
+ },
147
+ {
148
+ "epoch": 0.25539906103286386,
149
+ "grad_norm": 1.1651703119277954,
150
+ "learning_rate": 5.105105105105106e-05,
151
+ "loss": 0.0496,
152
+ "step": 170
153
+ },
154
+ {
155
+ "epoch": 0.2704225352112676,
156
+ "grad_norm": 0.9137387275695801,
157
+ "learning_rate": 5.405405405405406e-05,
158
+ "loss": 0.0628,
159
+ "step": 180
160
+ },
161
+ {
162
+ "epoch": 0.28544600938967135,
163
+ "grad_norm": 0.6661922931671143,
164
+ "learning_rate": 5.705705705705706e-05,
165
+ "loss": 0.0582,
166
+ "step": 190
167
+ },
168
+ {
169
+ "epoch": 0.3004694835680751,
170
+ "grad_norm": 0.47193077206611633,
171
+ "learning_rate": 6.0060060060060066e-05,
172
+ "loss": 0.0475,
173
+ "step": 200
174
+ },
175
+ {
176
+ "epoch": 0.3004694835680751,
177
+ "eval_loss": 0.05551699176430702,
178
+ "eval_runtime": 156.3208,
179
+ "eval_samples_per_second": 7.574,
180
+ "eval_steps_per_second": 7.574,
181
+ "step": 200
182
+ },
183
+ {
184
+ "epoch": 0.3154929577464789,
185
+ "grad_norm": 0.5054419636726379,
186
+ "learning_rate": 6.306306306306306e-05,
187
+ "loss": 0.0529,
188
+ "step": 210
189
+ },
190
+ {
191
+ "epoch": 0.3305164319248826,
192
+ "grad_norm": 0.4073943793773651,
193
+ "learning_rate": 6.606606606606607e-05,
194
+ "loss": 0.0564,
195
+ "step": 220
196
+ },
197
+ {
198
+ "epoch": 0.3455399061032864,
199
+ "grad_norm": 0.5814553499221802,
200
+ "learning_rate": 6.906906906906907e-05,
201
+ "loss": 0.0473,
202
+ "step": 230
203
+ },
204
+ {
205
+ "epoch": 0.36056338028169016,
206
+ "grad_norm": 0.730743944644928,
207
+ "learning_rate": 7.207207207207208e-05,
208
+ "loss": 0.0651,
209
+ "step": 240
210
+ },
211
+ {
212
+ "epoch": 0.3755868544600939,
213
+ "grad_norm": 0.6487244963645935,
214
+ "learning_rate": 7.507507507507507e-05,
215
+ "loss": 0.0612,
216
+ "step": 250
217
+ },
218
+ {
219
+ "epoch": 0.3755868544600939,
220
+ "eval_loss": 0.05300073325634003,
221
+ "eval_runtime": 156.331,
222
+ "eval_samples_per_second": 7.574,
223
+ "eval_steps_per_second": 7.574,
224
+ "step": 250
225
+ },
226
+ {
227
+ "epoch": 0.39061032863849765,
228
+ "grad_norm": 0.3846875727176666,
229
+ "learning_rate": 7.807807807807808e-05,
230
+ "loss": 0.0529,
231
+ "step": 260
232
+ },
233
+ {
234
+ "epoch": 0.4056338028169014,
235
+ "grad_norm": 0.8112801909446716,
236
+ "learning_rate": 8.108108108108109e-05,
237
+ "loss": 0.0609,
238
+ "step": 270
239
+ },
240
+ {
241
+ "epoch": 0.42065727699530514,
242
+ "grad_norm": 0.22141359746456146,
243
+ "learning_rate": 8.408408408408409e-05,
244
+ "loss": 0.0577,
245
+ "step": 280
246
+ },
247
+ {
248
+ "epoch": 0.4356807511737089,
249
+ "grad_norm": 1.3037300109863281,
250
+ "learning_rate": 8.70870870870871e-05,
251
+ "loss": 0.0572,
252
+ "step": 290
253
+ },
254
+ {
255
+ "epoch": 0.4507042253521127,
256
+ "grad_norm": 1.0784958600997925,
257
+ "learning_rate": 9.009009009009009e-05,
258
+ "loss": 0.043,
259
+ "step": 300
260
+ },
261
+ {
262
+ "epoch": 0.4507042253521127,
263
+ "eval_loss": 0.05256583169102669,
264
+ "eval_runtime": 156.2659,
265
+ "eval_samples_per_second": 7.577,
266
+ "eval_steps_per_second": 7.577,
267
+ "step": 300
268
+ },
269
+ {
270
+ "epoch": 0.46572769953051646,
271
+ "grad_norm": 0.4775850176811218,
272
+ "learning_rate": 9.30930930930931e-05,
273
+ "loss": 0.0439,
274
+ "step": 310
275
+ },
276
+ {
277
+ "epoch": 0.4807511737089202,
278
+ "grad_norm": 0.4602857232093811,
279
+ "learning_rate": 9.60960960960961e-05,
280
+ "loss": 0.0597,
281
+ "step": 320
282
+ },
283
+ {
284
+ "epoch": 0.49577464788732395,
285
+ "grad_norm": 0.6467078924179077,
286
+ "learning_rate": 9.90990990990991e-05,
287
+ "loss": 0.0553,
288
+ "step": 330
289
+ },
290
+ {
291
+ "epoch": 0.5107981220657277,
292
+ "grad_norm": 0.5899861454963684,
293
+ "learning_rate": 9.999864944989638e-05,
294
+ "loss": 0.0614,
295
+ "step": 340
296
+ },
297
+ {
298
+ "epoch": 0.5258215962441315,
299
+ "grad_norm": 0.3560892939567566,
300
+ "learning_rate": 9.999203468625017e-05,
301
+ "loss": 0.0497,
302
+ "step": 350
303
+ },
304
+ {
305
+ "epoch": 0.5258215962441315,
306
+ "eval_loss": 0.05027875676751137,
307
+ "eval_runtime": 156.4383,
308
+ "eval_samples_per_second": 7.568,
309
+ "eval_steps_per_second": 7.568,
310
+ "step": 350
311
+ },
312
+ {
313
+ "epoch": 0.5408450704225352,
314
+ "grad_norm": 1.0397191047668457,
315
+ "learning_rate": 9.997990837719421e-05,
316
+ "loss": 0.0614,
317
+ "step": 360
318
+ },
319
+ {
320
+ "epoch": 0.5558685446009389,
321
+ "grad_norm": 0.3409489095211029,
322
+ "learning_rate": 9.996227185963554e-05,
323
+ "loss": 0.0446,
324
+ "step": 370
325
+ },
326
+ {
327
+ "epoch": 0.5708920187793427,
328
+ "grad_norm": 0.6183903217315674,
329
+ "learning_rate": 9.993912707797329e-05,
330
+ "loss": 0.0513,
331
+ "step": 380
332
+ },
333
+ {
334
+ "epoch": 0.5859154929577465,
335
+ "grad_norm": 0.36344006657600403,
336
+ "learning_rate": 9.99104765838842e-05,
337
+ "loss": 0.0433,
338
+ "step": 390
339
+ },
340
+ {
341
+ "epoch": 0.6009389671361502,
342
+ "grad_norm": 0.2808699309825897,
343
+ "learning_rate": 9.987632353604151e-05,
344
+ "loss": 0.049,
345
+ "step": 400
346
+ },
347
+ {
348
+ "epoch": 0.6009389671361502,
349
+ "eval_loss": 0.04805321246385574,
350
+ "eval_runtime": 156.401,
351
+ "eval_samples_per_second": 7.57,
352
+ "eval_steps_per_second": 7.57,
353
+ "step": 400
354
+ },
355
+ {
356
+ "epoch": 0.615962441314554,
357
+ "grad_norm": 0.41244831681251526,
358
+ "learning_rate": 9.98366716997665e-05,
359
+ "loss": 0.0469,
360
+ "step": 410
361
+ },
362
+ {
363
+ "epoch": 0.6309859154929578,
364
+ "grad_norm": 0.4227665960788727,
365
+ "learning_rate": 9.979152544661354e-05,
366
+ "loss": 0.0437,
367
+ "step": 420
368
+ },
369
+ {
370
+ "epoch": 0.6460093896713615,
371
+ "grad_norm": 0.5011832118034363,
372
+ "learning_rate": 9.974088975388802e-05,
373
+ "loss": 0.0479,
374
+ "step": 430
375
+ },
376
+ {
377
+ "epoch": 0.6610328638497652,
378
+ "grad_norm": 0.47126173973083496,
379
+ "learning_rate": 9.968477020409766e-05,
380
+ "loss": 0.0452,
381
+ "step": 440
382
+ },
383
+ {
384
+ "epoch": 0.676056338028169,
385
+ "grad_norm": 0.4116508364677429,
386
+ "learning_rate": 9.962317298433705e-05,
387
+ "loss": 0.0541,
388
+ "step": 450
389
+ },
390
+ {
391
+ "epoch": 0.676056338028169,
392
+ "eval_loss": 0.047716788947582245,
393
+ "eval_runtime": 156.3995,
394
+ "eval_samples_per_second": 7.57,
395
+ "eval_steps_per_second": 7.57,
396
+ "step": 450
397
+ },
398
+ {
399
+ "epoch": 0.6910798122065728,
400
+ "grad_norm": 0.2776816785335541,
401
+ "learning_rate": 9.955610488560551e-05,
402
+ "loss": 0.0589,
403
+ "step": 460
404
+ },
405
+ {
406
+ "epoch": 0.7061032863849765,
407
+ "grad_norm": 0.5058294534683228,
408
+ "learning_rate": 9.948357330205842e-05,
409
+ "loss": 0.0583,
410
+ "step": 470
411
+ },
412
+ {
413
+ "epoch": 0.7211267605633803,
414
+ "grad_norm": 0.22229774296283722,
415
+ "learning_rate": 9.940558623019201e-05,
416
+ "loss": 0.0329,
417
+ "step": 480
418
+ },
419
+ {
420
+ "epoch": 0.7361502347417841,
421
+ "grad_norm": 0.33905524015426636,
422
+ "learning_rate": 9.932215226796172e-05,
423
+ "loss": 0.0501,
424
+ "step": 490
425
+ },
426
+ {
427
+ "epoch": 0.7511737089201878,
428
+ "grad_norm": 0.2562945783138275,
429
+ "learning_rate": 9.923328061383435e-05,
430
+ "loss": 0.0494,
431
+ "step": 500
432
+ },
433
+ {
434
+ "epoch": 0.7511737089201878,
435
+ "eval_loss": 0.043219637125730515,
436
+ "eval_runtime": 156.322,
437
+ "eval_samples_per_second": 7.574,
438
+ "eval_steps_per_second": 7.574,
439
+ "step": 500
440
+ },
441
+ {
442
+ "epoch": 0.7661971830985915,
443
+ "grad_norm": 0.18596145510673523,
444
+ "learning_rate": 9.913898106577393e-05,
445
+ "loss": 0.0445,
446
+ "step": 510
447
+ },
448
+ {
449
+ "epoch": 0.7812206572769953,
450
+ "grad_norm": 0.30711135268211365,
451
+ "learning_rate": 9.903926402016153e-05,
452
+ "loss": 0.0389,
453
+ "step": 520
454
+ },
455
+ {
456
+ "epoch": 0.7962441314553991,
457
+ "grad_norm": 0.21911293268203735,
458
+ "learning_rate": 9.893414047064897e-05,
459
+ "loss": 0.0436,
460
+ "step": 530
461
+ },
462
+ {
463
+ "epoch": 0.8112676056338028,
464
+ "grad_norm": 0.49014413356781006,
465
+ "learning_rate": 9.88236220069469e-05,
466
+ "loss": 0.043,
467
+ "step": 540
468
+ },
469
+ {
470
+ "epoch": 0.8262910798122066,
471
+ "grad_norm": 0.33901888132095337,
472
+ "learning_rate": 9.870772081354705e-05,
473
+ "loss": 0.0556,
474
+ "step": 550
475
+ },
476
+ {
477
+ "epoch": 0.8262910798122066,
478
+ "eval_loss": 0.04144579544663429,
479
+ "eval_runtime": 156.3463,
480
+ "eval_samples_per_second": 7.573,
481
+ "eval_steps_per_second": 7.573,
482
+ "step": 550
483
+ },
484
+ {
485
+ "epoch": 0.8413145539906103,
486
+ "grad_norm": 0.3239082098007202,
487
+ "learning_rate": 9.858644966837878e-05,
488
+ "loss": 0.0463,
489
+ "step": 560
490
+ },
491
+ {
492
+ "epoch": 0.856338028169014,
493
+ "grad_norm": 0.16826266050338745,
494
+ "learning_rate": 9.845982194140051e-05,
495
+ "loss": 0.0456,
496
+ "step": 570
497
+ },
498
+ {
499
+ "epoch": 0.8713615023474178,
500
+ "grad_norm": 0.28091156482696533,
501
+ "learning_rate": 9.832785159312559e-05,
502
+ "loss": 0.042,
503
+ "step": 580
504
+ },
505
+ {
506
+ "epoch": 0.8863849765258216,
507
+ "grad_norm": 0.29264500737190247,
508
+ "learning_rate": 9.819055317308317e-05,
509
+ "loss": 0.04,
510
+ "step": 590
511
+ },
512
+ {
513
+ "epoch": 0.9014084507042254,
514
+ "grad_norm": 0.30719348788261414,
515
+ "learning_rate": 9.804794181821422e-05,
516
+ "loss": 0.0398,
517
+ "step": 600
518
+ },
519
+ {
520
+ "epoch": 0.9014084507042254,
521
+ "eval_loss": 0.04154442995786667,
522
+ "eval_runtime": 156.3701,
523
+ "eval_samples_per_second": 7.572,
524
+ "eval_steps_per_second": 7.572,
525
+ "step": 600
526
+ },
527
+ {
528
+ "epoch": 0.9164319248826291,
529
+ "grad_norm": 0.18495255708694458,
530
+ "learning_rate": 9.790003325120261e-05,
531
+ "loss": 0.0403,
532
+ "step": 610
533
+ },
534
+ {
535
+ "epoch": 0.9314553990610329,
536
+ "grad_norm": 0.514930009841919,
537
+ "learning_rate": 9.774684377874178e-05,
538
+ "loss": 0.0535,
539
+ "step": 620
540
+ },
541
+ {
542
+ "epoch": 0.9464788732394366,
543
+ "grad_norm": 0.2771974503993988,
544
+ "learning_rate": 9.758839028973692e-05,
545
+ "loss": 0.0358,
546
+ "step": 630
547
+ },
548
+ {
549
+ "epoch": 0.9615023474178404,
550
+ "grad_norm": 0.2064761519432068,
551
+ "learning_rate": 9.742469025344298e-05,
552
+ "loss": 0.043,
553
+ "step": 640
554
+ },
555
+ {
556
+ "epoch": 0.9765258215962441,
557
+ "grad_norm": 0.22615325450897217,
558
+ "learning_rate": 9.725576171753874e-05,
559
+ "loss": 0.0535,
560
+ "step": 650
561
+ },
562
+ {
563
+ "epoch": 0.9765258215962441,
564
+ "eval_loss": 0.04291123151779175,
565
+ "eval_runtime": 156.3355,
566
+ "eval_samples_per_second": 7.573,
567
+ "eval_steps_per_second": 7.573,
568
+ "step": 650
569
+ },
570
+ {
571
+ "epoch": 0.9915492957746479,
572
+ "grad_norm": 0.9398748874664307,
573
+ "learning_rate": 9.708162330613708e-05,
574
+ "loss": 0.0441,
575
+ "step": 660
576
+ },
577
+ {
578
+ "epoch": 1.0065727699530516,
579
+ "grad_norm": 0.2263706773519516,
580
+ "learning_rate": 9.690229421773167e-05,
581
+ "loss": 0.0439,
582
+ "step": 670
583
+ },
584
+ {
585
+ "epoch": 1.0215962441314554,
586
+ "grad_norm": 0.3939422070980072,
587
+ "learning_rate": 9.67177942230804e-05,
588
+ "loss": 0.0402,
589
+ "step": 680
590
+ },
591
+ {
592
+ "epoch": 1.036619718309859,
593
+ "grad_norm": 0.4399869740009308,
594
+ "learning_rate": 9.652814366302568e-05,
595
+ "loss": 0.0412,
596
+ "step": 690
597
+ },
598
+ {
599
+ "epoch": 1.051643192488263,
600
+ "grad_norm": 0.29108133912086487,
601
+ "learning_rate": 9.633336344625185e-05,
602
+ "loss": 0.0383,
603
+ "step": 700
604
+ },
605
+ {
606
+ "epoch": 1.051643192488263,
607
+ "eval_loss": 0.04375332221388817,
608
+ "eval_runtime": 156.304,
609
+ "eval_samples_per_second": 7.575,
610
+ "eval_steps_per_second": 7.575,
611
+ "step": 700
612
+ },
613
+ {
614
+ "epoch": 1.0666666666666667,
615
+ "grad_norm": 0.41116732358932495,
616
+ "learning_rate": 9.61334750469801e-05,
617
+ "loss": 0.0297,
618
+ "step": 710
619
+ },
620
+ {
621
+ "epoch": 1.0816901408450703,
622
+ "grad_norm": 0.49311184883117676,
623
+ "learning_rate": 9.592850050260089e-05,
624
+ "loss": 0.0377,
625
+ "step": 720
626
+ },
627
+ {
628
+ "epoch": 1.0967136150234742,
629
+ "grad_norm": 0.20614486932754517,
630
+ "learning_rate": 9.571846241124446e-05,
631
+ "loss": 0.0329,
632
+ "step": 730
633
+ },
634
+ {
635
+ "epoch": 1.1117370892018779,
636
+ "grad_norm": 0.1830943077802658,
637
+ "learning_rate": 9.55033839292893e-05,
638
+ "loss": 0.0273,
639
+ "step": 740
640
+ },
641
+ {
642
+ "epoch": 1.1267605633802817,
643
+ "grad_norm": 0.49418705701828003,
644
+ "learning_rate": 9.52832887688093e-05,
645
+ "loss": 0.0317,
646
+ "step": 750
647
+ },
648
+ {
649
+ "epoch": 1.1267605633802817,
650
+ "eval_loss": 0.04088291898369789,
651
+ "eval_runtime": 156.2721,
652
+ "eval_samples_per_second": 7.577,
653
+ "eval_steps_per_second": 7.577,
654
+ "step": 750
655
+ },
656
+ {
657
+ "epoch": 1.1417840375586854,
658
+ "grad_norm": 0.43101999163627625,
659
+ "learning_rate": 9.50582011949595e-05,
660
+ "loss": 0.035,
661
+ "step": 760
662
+ },
663
+ {
664
+ "epoch": 1.1568075117370893,
665
+ "grad_norm": 0.19687387347221375,
666
+ "learning_rate": 9.482814602330084e-05,
667
+ "loss": 0.038,
668
+ "step": 770
669
+ },
670
+ {
671
+ "epoch": 1.171830985915493,
672
+ "grad_norm": 0.31862860918045044,
673
+ "learning_rate": 9.459314861706435e-05,
674
+ "loss": 0.0402,
675
+ "step": 780
676
+ },
677
+ {
678
+ "epoch": 1.1868544600938966,
679
+ "grad_norm": 0.18375325202941895,
680
+ "learning_rate": 9.435323488435488e-05,
681
+ "loss": 0.0313,
682
+ "step": 790
683
+ },
684
+ {
685
+ "epoch": 1.2018779342723005,
686
+ "grad_norm": 0.4344165027141571,
687
+ "learning_rate": 9.410843127529473e-05,
688
+ "loss": 0.0311,
689
+ "step": 800
690
+ },
691
+ {
692
+ "epoch": 1.2018779342723005,
693
+ "eval_loss": 0.04096408188343048,
694
+ "eval_runtime": 156.2708,
695
+ "eval_samples_per_second": 7.577,
696
+ "eval_steps_per_second": 7.577,
697
+ "step": 800
698
+ },
699
+ {
700
+ "epoch": 1.2169014084507042,
701
+ "grad_norm": 0.48818346858024597,
702
+ "learning_rate": 9.385876477910765e-05,
703
+ "loss": 0.0344,
704
+ "step": 810
705
+ },
706
+ {
707
+ "epoch": 1.231924882629108,
708
+ "grad_norm": 0.2184937298297882,
709
+ "learning_rate": 9.360426292114314e-05,
710
+ "loss": 0.0343,
711
+ "step": 820
712
+ },
713
+ {
714
+ "epoch": 1.2469483568075117,
715
+ "grad_norm": 0.3244076371192932,
716
+ "learning_rate": 9.334495375984212e-05,
717
+ "loss": 0.0294,
718
+ "step": 830
719
+ },
720
+ {
721
+ "epoch": 1.2619718309859156,
722
+ "grad_norm": 0.3577475845813751,
723
+ "learning_rate": 9.30808658836432e-05,
724
+ "loss": 0.0337,
725
+ "step": 840
726
+ },
727
+ {
728
+ "epoch": 1.2769953051643192,
729
+ "grad_norm": 0.5191630721092224,
730
+ "learning_rate": 9.281202840783108e-05,
731
+ "loss": 0.0351,
732
+ "step": 850
733
+ },
734
+ {
735
+ "epoch": 1.2769953051643192,
736
+ "eval_loss": 0.03982950374484062,
737
+ "eval_runtime": 156.3321,
738
+ "eval_samples_per_second": 7.574,
739
+ "eval_steps_per_second": 7.574,
740
+ "step": 850
741
+ },
742
+ {
743
+ "epoch": 1.292018779342723,
744
+ "grad_norm": 0.21748529374599457,
745
+ "learning_rate": 9.253847097132655e-05,
746
+ "loss": 0.0313,
747
+ "step": 860
748
+ },
749
+ {
750
+ "epoch": 1.3070422535211268,
751
+ "grad_norm": 0.18870031833648682,
752
+ "learning_rate": 9.226022373341882e-05,
753
+ "loss": 0.0323,
754
+ "step": 870
755
+ },
756
+ {
757
+ "epoch": 1.3220657276995305,
758
+ "grad_norm": 0.24485838413238525,
759
+ "learning_rate": 9.19773173704406e-05,
760
+ "loss": 0.0299,
761
+ "step": 880
762
+ },
763
+ {
764
+ "epoch": 1.3370892018779343,
765
+ "grad_norm": 0.6192132830619812,
766
+ "learning_rate": 9.168978307238594e-05,
767
+ "loss": 0.037,
768
+ "step": 890
769
+ },
770
+ {
771
+ "epoch": 1.352112676056338,
772
+ "grad_norm": 0.1277685910463333,
773
+ "learning_rate": 9.13976525394717e-05,
774
+ "loss": 0.0309,
775
+ "step": 900
776
+ },
777
+ {
778
+ "epoch": 1.352112676056338,
779
+ "eval_loss": 0.037233345210552216,
780
+ "eval_runtime": 156.3404,
781
+ "eval_samples_per_second": 7.573,
782
+ "eval_steps_per_second": 7.573,
783
+ "step": 900
784
+ },
785
+ {
786
+ "epoch": 1.3671361502347419,
787
+ "grad_norm": 0.17440356314182281,
788
+ "learning_rate": 9.110095797864263e-05,
789
+ "loss": 0.0264,
790
+ "step": 910
791
+ },
792
+ {
793
+ "epoch": 1.3821596244131455,
794
+ "grad_norm": 0.15580697357654572,
795
+ "learning_rate": 9.079973210002051e-05,
796
+ "loss": 0.0371,
797
+ "step": 920
798
+ },
799
+ {
800
+ "epoch": 1.3971830985915492,
801
+ "grad_norm": 0.2136790156364441,
802
+ "learning_rate": 9.049400811329807e-05,
803
+ "loss": 0.0389,
804
+ "step": 930
805
+ },
806
+ {
807
+ "epoch": 1.412206572769953,
808
+ "grad_norm": 0.32828402519226074,
809
+ "learning_rate": 9.01838197240775e-05,
810
+ "loss": 0.0296,
811
+ "step": 940
812
+ },
813
+ {
814
+ "epoch": 1.4272300469483568,
815
+ "grad_norm": 0.44386857748031616,
816
+ "learning_rate": 8.986920113015461e-05,
817
+ "loss": 0.0373,
818
+ "step": 950
819
+ },
820
+ {
821
+ "epoch": 1.4272300469483568,
822
+ "eval_loss": 0.03834960237145424,
823
+ "eval_runtime": 156.2587,
824
+ "eval_samples_per_second": 7.577,
825
+ "eval_steps_per_second": 7.577,
826
+ "step": 950
827
+ },
828
+ {
829
+ "epoch": 1.4422535211267606,
830
+ "grad_norm": 0.20402352511882782,
831
+ "learning_rate": 8.955018701774846e-05,
832
+ "loss": 0.0244,
833
+ "step": 960
834
+ },
835
+ {
836
+ "epoch": 1.4572769953051643,
837
+ "grad_norm": 0.3417670428752899,
838
+ "learning_rate": 8.922681255767731e-05,
839
+ "loss": 0.0413,
840
+ "step": 970
841
+ },
842
+ {
843
+ "epoch": 1.4723004694835682,
844
+ "grad_norm": 0.21933668851852417,
845
+ "learning_rate": 8.889911340148112e-05,
846
+ "loss": 0.0359,
847
+ "step": 980
848
+ },
849
+ {
850
+ "epoch": 1.4873239436619718,
851
+ "grad_norm": 0.1883007138967514,
852
+ "learning_rate": 8.856712567749095e-05,
853
+ "loss": 0.0336,
854
+ "step": 990
855
+ },
856
+ {
857
+ "epoch": 1.5023474178403755,
858
+ "grad_norm": 0.31359952688217163,
859
+ "learning_rate": 8.82308859868459e-05,
860
+ "loss": 0.0295,
861
+ "step": 1000
862
+ },
863
+ {
864
+ "epoch": 1.5023474178403755,
865
+ "eval_loss": 0.039744190871715546,
866
+ "eval_runtime": 156.3721,
867
+ "eval_samples_per_second": 7.572,
868
+ "eval_steps_per_second": 7.572,
869
+ "step": 1000
870
+ },
871
+ {
872
+ "epoch": 1.5173708920187794,
873
+ "grad_norm": 0.3432142734527588,
874
+ "learning_rate": 8.789043139945795e-05,
875
+ "loss": 0.0335,
876
+ "step": 1010
877
+ },
878
+ {
879
+ "epoch": 1.532394366197183,
880
+ "grad_norm": 0.16293199360370636,
881
+ "learning_rate": 8.754579944992491e-05,
882
+ "loss": 0.0391,
883
+ "step": 1020
884
+ },
885
+ {
886
+ "epoch": 1.5474178403755867,
887
+ "grad_norm": 0.20295502245426178,
888
+ "learning_rate": 8.719702813339248e-05,
889
+ "loss": 0.035,
890
+ "step": 1030
891
+ },
892
+ {
893
+ "epoch": 1.5624413145539906,
894
+ "grad_norm": 0.22714973986148834,
895
+ "learning_rate": 8.684415590136518e-05,
896
+ "loss": 0.0322,
897
+ "step": 1040
898
+ },
899
+ {
900
+ "epoch": 1.5774647887323945,
901
+ "grad_norm": 0.15775541961193085,
902
+ "learning_rate": 8.648722165746722e-05,
903
+ "loss": 0.0349,
904
+ "step": 1050
905
+ },
906
+ {
907
+ "epoch": 1.5774647887323945,
908
+ "eval_loss": 0.04082873836159706,
909
+ "eval_runtime": 156.2306,
910
+ "eval_samples_per_second": 7.579,
911
+ "eval_steps_per_second": 7.579,
912
+ "step": 1050
913
+ },
914
+ {
915
+ "epoch": 1.5924882629107981,
916
+ "grad_norm": 0.18249914050102234,
917
+ "learning_rate": 8.61262647531534e-05,
918
+ "loss": 0.0299,
919
+ "step": 1060
920
+ },
921
+ {
922
+ "epoch": 1.6075117370892018,
923
+ "grad_norm": 0.2968941330909729,
924
+ "learning_rate": 8.576132498337068e-05,
925
+ "loss": 0.0372,
926
+ "step": 1070
927
+ },
928
+ {
929
+ "epoch": 1.6225352112676057,
930
+ "grad_norm": 0.416565477848053,
931
+ "learning_rate": 8.539244258217088e-05,
932
+ "loss": 0.0332,
933
+ "step": 1080
934
+ },
935
+ {
936
+ "epoch": 1.6375586854460094,
937
+ "grad_norm": 0.23764647543430328,
938
+ "learning_rate": 8.501965821827485e-05,
939
+ "loss": 0.0365,
940
+ "step": 1090
941
+ },
942
+ {
943
+ "epoch": 1.652582159624413,
944
+ "grad_norm": 0.20299109816551208,
945
+ "learning_rate": 8.464301299058892e-05,
946
+ "loss": 0.026,
947
+ "step": 1100
948
+ },
949
+ {
950
+ "epoch": 1.652582159624413,
951
+ "eval_loss": 0.04096033051609993,
952
+ "eval_runtime": 156.3005,
953
+ "eval_samples_per_second": 7.575,
954
+ "eval_steps_per_second": 7.575,
955
+ "step": 1100
956
+ },
957
+ {
958
+ "epoch": 1.667605633802817,
959
+ "grad_norm": 0.2365420162677765,
960
+ "learning_rate": 8.426254842367374e-05,
961
+ "loss": 0.0279,
962
+ "step": 1110
963
+ },
964
+ {
965
+ "epoch": 1.6826291079812208,
966
+ "grad_norm": 0.26829490065574646,
967
+ "learning_rate": 8.387830646316623e-05,
968
+ "loss": 0.0388,
969
+ "step": 1120
970
+ },
971
+ {
972
+ "epoch": 1.6976525821596244,
973
+ "grad_norm": 0.39060696959495544,
974
+ "learning_rate": 8.349032947115525e-05,
975
+ "loss": 0.028,
976
+ "step": 1130
977
+ },
978
+ {
979
+ "epoch": 1.712676056338028,
980
+ "grad_norm": 0.3235212564468384,
981
+ "learning_rate": 8.309866022151107e-05,
982
+ "loss": 0.0468,
983
+ "step": 1140
984
+ },
985
+ {
986
+ "epoch": 1.727699530516432,
987
+ "grad_norm": 0.32556065917015076,
988
+ "learning_rate": 8.270334189516983e-05,
989
+ "loss": 0.0305,
990
+ "step": 1150
991
+ },
992
+ {
993
+ "epoch": 1.727699530516432,
994
+ "eval_loss": 0.039029572159051895,
995
+ "eval_runtime": 156.2235,
996
+ "eval_samples_per_second": 7.579,
997
+ "eval_steps_per_second": 7.579,
998
+ "step": 1150
999
+ },
1000
+ {
1001
+ "epoch": 1.7427230046948357,
1002
+ "grad_norm": 0.15808342397212982,
1003
+ "learning_rate": 8.230441807537277e-05,
1004
+ "loss": 0.0466,
1005
+ "step": 1160
1006
+ },
1007
+ {
1008
+ "epoch": 1.7577464788732393,
1009
+ "grad_norm": 0.15356343984603882,
1010
+ "learning_rate": 8.190193274286122e-05,
1011
+ "loss": 0.0284,
1012
+ "step": 1170
1013
+ },
1014
+ {
1015
+ "epoch": 1.7727699530516432,
1016
+ "grad_norm": 0.26693618297576904,
1017
+ "learning_rate": 8.149593027102789e-05,
1018
+ "loss": 0.0347,
1019
+ "step": 1180
1020
+ },
1021
+ {
1022
+ "epoch": 1.787793427230047,
1023
+ "grad_norm": 0.3144373595714569,
1024
+ "learning_rate": 8.108645542102469e-05,
1025
+ "loss": 0.0277,
1026
+ "step": 1190
1027
+ },
1028
+ {
1029
+ "epoch": 1.8028169014084507,
1030
+ "grad_norm": 0.26021772623062134,
1031
+ "learning_rate": 8.067355333682798e-05,
1032
+ "loss": 0.0332,
1033
+ "step": 1200
1034
+ },
1035
+ {
1036
+ "epoch": 1.8028169014084507,
1037
+ "eval_loss": 0.03854435682296753,
1038
+ "eval_runtime": 156.2279,
1039
+ "eval_samples_per_second": 7.579,
1040
+ "eval_steps_per_second": 7.579,
1041
+ "step": 1200
1042
+ },
1043
+ {
1044
+ "epoch": 1.8178403755868544,
1045
+ "grad_norm": 0.4863680303096771,
1046
+ "learning_rate": 8.025726954026138e-05,
1047
+ "loss": 0.0242,
1048
+ "step": 1210
1049
+ },
1050
+ {
1051
+ "epoch": 1.8328638497652583,
1052
+ "grad_norm": 0.5616618394851685,
1053
+ "learning_rate": 7.983764992597716e-05,
1054
+ "loss": 0.034,
1055
+ "step": 1220
1056
+ },
1057
+ {
1058
+ "epoch": 1.847887323943662,
1059
+ "grad_norm": 0.4086838662624359,
1060
+ "learning_rate": 7.94147407563964e-05,
1061
+ "loss": 0.0314,
1062
+ "step": 1230
1063
+ },
1064
+ {
1065
+ "epoch": 1.8629107981220656,
1066
+ "grad_norm": 0.2752532362937927,
1067
+ "learning_rate": 7.89885886566086e-05,
1068
+ "loss": 0.0348,
1069
+ "step": 1240
1070
+ },
1071
+ {
1072
+ "epoch": 1.8779342723004695,
1073
+ "grad_norm": 0.508071780204773,
1074
+ "learning_rate": 7.855924060923141e-05,
1075
+ "loss": 0.0304,
1076
+ "step": 1250
1077
+ },
1078
+ {
1079
+ "epoch": 1.8779342723004695,
1080
+ "eval_loss": 0.03792616352438927,
1081
+ "eval_runtime": 156.2438,
1082
+ "eval_samples_per_second": 7.578,
1083
+ "eval_steps_per_second": 7.578,
1084
+ "step": 1250
1085
+ },
1086
+ {
1087
+ "epoch": 1.8929577464788734,
1088
+ "grad_norm": 0.2151941955089569,
1089
+ "learning_rate": 7.812674394923077e-05,
1090
+ "loss": 0.0364,
1091
+ "step": 1260
1092
+ },
1093
+ {
1094
+ "epoch": 1.907981220657277,
1095
+ "grad_norm": 0.2420804798603058,
1096
+ "learning_rate": 7.769114635870231e-05,
1097
+ "loss": 0.0357,
1098
+ "step": 1270
1099
+ },
1100
+ {
1101
+ "epoch": 1.9230046948356807,
1102
+ "grad_norm": 0.37158623337745667,
1103
+ "learning_rate": 7.725249586161463e-05,
1104
+ "loss": 0.0317,
1105
+ "step": 1280
1106
+ },
1107
+ {
1108
+ "epoch": 1.9380281690140846,
1109
+ "grad_norm": 0.19411316514015198,
1110
+ "learning_rate": 7.68108408185145e-05,
1111
+ "loss": 0.0276,
1112
+ "step": 1290
1113
+ },
1114
+ {
1115
+ "epoch": 1.9530516431924883,
1116
+ "grad_norm": 0.2072768658399582,
1117
+ "learning_rate": 7.636622992119536e-05,
1118
+ "loss": 0.0497,
1119
+ "step": 1300
1120
+ },
1121
+ {
1122
+ "epoch": 1.9530516431924883,
1123
+ "eval_loss": 0.039196692407131195,
1124
+ "eval_runtime": 156.2151,
1125
+ "eval_samples_per_second": 7.579,
1126
+ "eval_steps_per_second": 7.579,
1127
+ "step": 1300
1128
+ },
1129
+ {
1130
+ "epoch": 1.968075117370892,
1131
+ "grad_norm": 0.30601534247398376,
1132
+ "learning_rate": 7.591871218732902e-05,
1133
+ "loss": 0.036,
1134
+ "step": 1310
1135
+ },
1136
+ {
1137
+ "epoch": 1.9830985915492958,
1138
+ "grad_norm": 0.2544531226158142,
1139
+ "learning_rate": 7.54683369550616e-05,
1140
+ "loss": 0.0413,
1141
+ "step": 1320
1142
+ },
1143
+ {
1144
+ "epoch": 1.9981220657276997,
1145
+ "grad_norm": 0.18643656373023987,
1146
+ "learning_rate": 7.501515387757404e-05,
1147
+ "loss": 0.0295,
1148
+ "step": 1330
1149
+ },
1150
+ {
1151
+ "epoch": 2.013145539906103,
1152
+ "grad_norm": 0.2908141016960144,
1153
+ "learning_rate": 7.455921291760796e-05,
1154
+ "loss": 0.0365,
1155
+ "step": 1340
1156
+ },
1157
+ {
1158
+ "epoch": 2.028169014084507,
1159
+ "grad_norm": 0.08652251958847046,
1160
+ "learning_rate": 7.410056434195725e-05,
1161
+ "loss": 0.0183,
1162
+ "step": 1350
1163
+ },
1164
+ {
1165
+ "epoch": 2.028169014084507,
1166
+ "eval_loss": 0.04124961793422699,
1167
+ "eval_runtime": 156.2014,
1168
+ "eval_samples_per_second": 7.58,
1169
+ "eval_steps_per_second": 7.58,
1170
+ "step": 1350
1171
+ },
1172
+ {
1173
+ "epoch": 2.043192488262911,
1174
+ "grad_norm": 0.231898233294487,
1175
+ "learning_rate": 7.363925871592629e-05,
1176
+ "loss": 0.0264,
1177
+ "step": 1360
1178
+ },
1179
+ {
1180
+ "epoch": 2.0582159624413148,
1181
+ "grad_norm": 0.15739409625530243,
1182
+ "learning_rate": 7.317534689775528e-05,
1183
+ "loss": 0.0239,
1184
+ "step": 1370
1185
+ },
1186
+ {
1187
+ "epoch": 2.073239436619718,
1188
+ "grad_norm": 0.16826321184635162,
1189
+ "learning_rate": 7.270888003301304e-05,
1190
+ "loss": 0.0175,
1191
+ "step": 1380
1192
+ },
1193
+ {
1194
+ "epoch": 2.088262910798122,
1195
+ "grad_norm": 0.5138995051383972,
1196
+ "learning_rate": 7.22399095489584e-05,
1197
+ "loss": 0.022,
1198
+ "step": 1390
1199
+ },
1200
+ {
1201
+ "epoch": 2.103286384976526,
1202
+ "grad_norm": 0.1792786568403244,
1203
+ "learning_rate": 7.176848714887042e-05,
1204
+ "loss": 0.0269,
1205
+ "step": 1400
1206
+ },
1207
+ {
1208
+ "epoch": 2.103286384976526,
1209
+ "eval_loss": 0.038102250546216965,
1210
+ "eval_runtime": 156.1612,
1211
+ "eval_samples_per_second": 7.582,
1212
+ "eval_steps_per_second": 7.582,
1213
+ "step": 1400
1214
+ },
1215
+ {
1216
+ "epoch": 2.1183098591549294,
1217
+ "grad_norm": 0.21858704090118408,
1218
+ "learning_rate": 7.129466480634806e-05,
1219
+ "loss": 0.0251,
1220
+ "step": 1410
1221
+ },
1222
+ {
1223
+ "epoch": 2.1333333333333333,
1224
+ "grad_norm": 0.2904298007488251,
1225
+ "learning_rate": 7.081849475958042e-05,
1226
+ "loss": 0.0208,
1227
+ "step": 1420
1228
+ },
1229
+ {
1230
+ "epoch": 2.148356807511737,
1231
+ "grad_norm": 0.4409976899623871,
1232
+ "learning_rate": 7.034002950558723e-05,
1233
+ "loss": 0.0243,
1234
+ "step": 1430
1235
+ },
1236
+ {
1237
+ "epoch": 2.1633802816901406,
1238
+ "grad_norm": 0.19713151454925537,
1239
+ "learning_rate": 6.985932179443144e-05,
1240
+ "loss": 0.0253,
1241
+ "step": 1440
1242
+ },
1243
+ {
1244
+ "epoch": 2.1784037558685445,
1245
+ "grad_norm": 0.24242573976516724,
1246
+ "learning_rate": 6.937642462340342e-05,
1247
+ "loss": 0.0299,
1248
+ "step": 1450
1249
+ },
1250
+ {
1251
+ "epoch": 2.1784037558685445,
1252
+ "eval_loss": 0.0379047654569149,
1253
+ "eval_runtime": 156.2912,
1254
+ "eval_samples_per_second": 7.576,
1255
+ "eval_steps_per_second": 7.576,
1256
+ "step": 1450
1257
+ },
1258
+ {
1259
+ "epoch": 2.1934272300469484,
1260
+ "grad_norm": 0.19243745505809784,
1261
+ "learning_rate": 6.889139123117817e-05,
1262
+ "loss": 0.0184,
1263
+ "step": 1460
1264
+ },
1265
+ {
1266
+ "epoch": 2.2084507042253523,
1267
+ "grad_norm": 0.2577214241027832,
1268
+ "learning_rate": 6.840427509194575e-05,
1269
+ "loss": 0.0249,
1270
+ "step": 1470
1271
+ },
1272
+ {
1273
+ "epoch": 2.2234741784037557,
1274
+ "grad_norm": 0.2908743917942047,
1275
+ "learning_rate": 6.791512990951597e-05,
1276
+ "loss": 0.0165,
1277
+ "step": 1480
1278
+ },
1279
+ {
1280
+ "epoch": 2.2384976525821596,
1281
+ "grad_norm": 0.6111800670623779,
1282
+ "learning_rate": 6.74240096113975e-05,
1283
+ "loss": 0.0262,
1284
+ "step": 1490
1285
+ },
1286
+ {
1287
+ "epoch": 2.2535211267605635,
1288
+ "grad_norm": 0.1613549441099167,
1289
+ "learning_rate": 6.693096834285256e-05,
1290
+ "loss": 0.0129,
1291
+ "step": 1500
1292
+ },
1293
+ {
1294
+ "epoch": 2.2535211267605635,
1295
+ "eval_loss": 0.04337477684020996,
1296
+ "eval_runtime": 156.2934,
1297
+ "eval_samples_per_second": 7.575,
1298
+ "eval_steps_per_second": 7.575,
1299
+ "step": 1500
1300
+ },
1301
+ {
1302
+ "epoch": 2.2685446009389674,
1303
+ "grad_norm": 0.40178021788597107,
1304
+ "learning_rate": 6.643606046092732e-05,
1305
+ "loss": 0.0238,
1306
+ "step": 1510
1307
+ },
1308
+ {
1309
+ "epoch": 2.283568075117371,
1310
+ "grad_norm": 0.18915718793869019,
1311
+ "learning_rate": 6.593934052845929e-05,
1312
+ "loss": 0.0257,
1313
+ "step": 1520
1314
+ },
1315
+ {
1316
+ "epoch": 2.2985915492957747,
1317
+ "grad_norm": 0.35349389910697937,
1318
+ "learning_rate": 6.544086330806181e-05,
1319
+ "loss": 0.0268,
1320
+ "step": 1530
1321
+ },
1322
+ {
1323
+ "epoch": 2.3136150234741786,
1324
+ "grad_norm": 0.15677450597286224,
1325
+ "learning_rate": 6.494068375608646e-05,
1326
+ "loss": 0.0245,
1327
+ "step": 1540
1328
+ },
1329
+ {
1330
+ "epoch": 2.328638497652582,
1331
+ "grad_norm": 0.2012639194726944,
1332
+ "learning_rate": 6.443885701656432e-05,
1333
+ "loss": 0.0203,
1334
+ "step": 1550
1335
+ },
1336
+ {
1337
+ "epoch": 2.328638497652582,
1338
+ "eval_loss": 0.03834431990981102,
1339
+ "eval_runtime": 156.2857,
1340
+ "eval_samples_per_second": 7.576,
1341
+ "eval_steps_per_second": 7.576,
1342
+ "step": 1550
1343
+ },
1344
+ {
1345
+ "epoch": 2.343661971830986,
1346
+ "grad_norm": 0.28499725461006165,
1347
+ "learning_rate": 6.393543841512632e-05,
1348
+ "loss": 0.0187,
1349
+ "step": 1560
1350
+ },
1351
+ {
1352
+ "epoch": 2.35868544600939,
1353
+ "grad_norm": 0.27369531989097595,
1354
+ "learning_rate": 6.343048345290386e-05,
1355
+ "loss": 0.0143,
1356
+ "step": 1570
1357
+ },
1358
+ {
1359
+ "epoch": 2.3737089201877932,
1360
+ "grad_norm": 0.31129664182662964,
1361
+ "learning_rate": 6.292404780040961e-05,
1362
+ "loss": 0.0306,
1363
+ "step": 1580
1364
+ },
1365
+ {
1366
+ "epoch": 2.388732394366197,
1367
+ "grad_norm": 0.43185606598854065,
1368
+ "learning_rate": 6.241618729140018e-05,
1369
+ "loss": 0.0198,
1370
+ "step": 1590
1371
+ },
1372
+ {
1373
+ "epoch": 2.403755868544601,
1374
+ "grad_norm": 0.32471033930778503,
1375
+ "learning_rate": 6.190695791672042e-05,
1376
+ "loss": 0.0221,
1377
+ "step": 1600
1378
+ },
1379
+ {
1380
+ "epoch": 2.403755868544601,
1381
+ "eval_loss": 0.03971394523978233,
1382
+ "eval_runtime": 156.3498,
1383
+ "eval_samples_per_second": 7.573,
1384
+ "eval_steps_per_second": 7.573,
1385
+ "step": 1600
1386
+ },
1387
+ {
1388
+ "epoch": 2.418779342723005,
1389
+ "grad_norm": 0.13160324096679688,
1390
+ "learning_rate": 6.139641581813052e-05,
1391
+ "loss": 0.0194,
1392
+ "step": 1610
1393
+ },
1394
+ {
1395
+ "epoch": 2.4338028169014083,
1396
+ "grad_norm": 0.1444709450006485,
1397
+ "learning_rate": 6.088461728211642e-05,
1398
+ "loss": 0.0206,
1399
+ "step": 1620
1400
+ },
1401
+ {
1402
+ "epoch": 2.448826291079812,
1403
+ "grad_norm": 0.3128149211406708,
1404
+ "learning_rate": 6.0371618733684474e-05,
1405
+ "loss": 0.0151,
1406
+ "step": 1630
1407
+ },
1408
+ {
1409
+ "epoch": 2.463849765258216,
1410
+ "grad_norm": 0.1301877200603485,
1411
+ "learning_rate": 5.9857476730140485e-05,
1412
+ "loss": 0.0214,
1413
+ "step": 1640
1414
+ },
1415
+ {
1416
+ "epoch": 2.4788732394366195,
1417
+ "grad_norm": 0.2600902020931244,
1418
+ "learning_rate": 5.9342247954854466e-05,
1419
+ "loss": 0.023,
1420
+ "step": 1650
1421
+ },
1422
+ {
1423
+ "epoch": 2.4788732394366195,
1424
+ "eval_loss": 0.041283123195171356,
1425
+ "eval_runtime": 156.3863,
1426
+ "eval_samples_per_second": 7.571,
1427
+ "eval_steps_per_second": 7.571,
1428
+ "step": 1650
1429
+ },
1430
+ {
1431
+ "epoch": 2.4938967136150234,
1432
+ "grad_norm": 0.20478318631649017,
1433
+ "learning_rate": 5.8825989211011335e-05,
1434
+ "loss": 0.0242,
1435
+ "step": 1660
1436
+ },
1437
+ {
1438
+ "epoch": 2.5089201877934273,
1439
+ "grad_norm": 0.212309792637825,
1440
+ "learning_rate": 5.830875741534852e-05,
1441
+ "loss": 0.0187,
1442
+ "step": 1670
1443
+ },
1444
+ {
1445
+ "epoch": 2.523943661971831,
1446
+ "grad_norm": 0.2569638192653656,
1447
+ "learning_rate": 5.7790609591880826e-05,
1448
+ "loss": 0.0259,
1449
+ "step": 1680
1450
+ },
1451
+ {
1452
+ "epoch": 2.5389671361502346,
1453
+ "grad_norm": 0.305275022983551,
1454
+ "learning_rate": 5.727160286561386e-05,
1455
+ "loss": 0.0232,
1456
+ "step": 1690
1457
+ },
1458
+ {
1459
+ "epoch": 2.5539906103286385,
1460
+ "grad_norm": 0.22980214655399323,
1461
+ "learning_rate": 5.675179445624581e-05,
1462
+ "loss": 0.0257,
1463
+ "step": 1700
1464
+ },
1465
+ {
1466
+ "epoch": 2.5539906103286385,
1467
+ "eval_loss": 0.04087158292531967,
1468
+ "eval_runtime": 156.4861,
1469
+ "eval_samples_per_second": 7.566,
1470
+ "eval_steps_per_second": 7.566,
1471
+ "step": 1700
1472
+ },
1473
+ {
1474
+ "epoch": 2.5690140845070424,
1475
+ "grad_norm": 0.13337288796901703,
1476
+ "learning_rate": 5.62312416718593e-05,
1477
+ "loss": 0.018,
1478
+ "step": 1710
1479
+ },
1480
+ {
1481
+ "epoch": 2.584037558685446,
1482
+ "grad_norm": 0.06781081855297089,
1483
+ "learning_rate": 5.5710001902603116e-05,
1484
+ "loss": 0.0238,
1485
+ "step": 1720
1486
+ },
1487
+ {
1488
+ "epoch": 2.5990610328638497,
1489
+ "grad_norm": 0.15210840106010437,
1490
+ "learning_rate": 5.5188132614365094e-05,
1491
+ "loss": 0.0213,
1492
+ "step": 1730
1493
+ },
1494
+ {
1495
+ "epoch": 2.6140845070422536,
1496
+ "grad_norm": 0.18319003283977509,
1497
+ "learning_rate": 5.4665691342436565e-05,
1498
+ "loss": 0.0214,
1499
+ "step": 1740
1500
+ },
1501
+ {
1502
+ "epoch": 2.629107981220657,
1503
+ "grad_norm": 0.382030189037323,
1504
+ "learning_rate": 5.414273568516919e-05,
1505
+ "loss": 0.0241,
1506
+ "step": 1750
1507
+ },
1508
+ {
1509
+ "epoch": 2.629107981220657,
1510
+ "eval_loss": 0.03998855501413345,
1511
+ "eval_runtime": 156.5463,
1512
+ "eval_samples_per_second": 7.563,
1513
+ "eval_steps_per_second": 7.563,
1514
+ "step": 1750
1515
+ },
1516
+ {
1517
+ "epoch": 2.644131455399061,
1518
+ "grad_norm": 0.26402246952056885,
1519
+ "learning_rate": 5.361932329762481e-05,
1520
+ "loss": 0.0201,
1521
+ "step": 1760
1522
+ },
1523
+ {
1524
+ "epoch": 2.659154929577465,
1525
+ "grad_norm": 0.1534145027399063,
1526
+ "learning_rate": 5.309551188521914e-05,
1527
+ "loss": 0.0228,
1528
+ "step": 1770
1529
+ },
1530
+ {
1531
+ "epoch": 2.6741784037558687,
1532
+ "grad_norm": 0.4438458979129791,
1533
+ "learning_rate": 5.2571359197359704e-05,
1534
+ "loss": 0.0162,
1535
+ "step": 1780
1536
+ },
1537
+ {
1538
+ "epoch": 2.6892018779342726,
1539
+ "grad_norm": 0.21595679223537445,
1540
+ "learning_rate": 5.2046923021079175e-05,
1541
+ "loss": 0.0173,
1542
+ "step": 1790
1543
+ },
1544
+ {
1545
+ "epoch": 2.704225352112676,
1546
+ "grad_norm": 0.4059389531612396,
1547
+ "learning_rate": 5.1522261174664346e-05,
1548
+ "loss": 0.0258,
1549
+ "step": 1800
1550
+ },
1551
+ {
1552
+ "epoch": 2.704225352112676,
1553
+ "eval_loss": 0.040539611130952835,
1554
+ "eval_runtime": 156.6429,
1555
+ "eval_samples_per_second": 7.559,
1556
+ "eval_steps_per_second": 7.559,
1557
+ "step": 1800
1558
+ },
1559
+ {
1560
+ "epoch": 2.71924882629108,
1561
+ "grad_norm": 0.8589577078819275,
1562
+ "learning_rate": 5.0997431501281835e-05,
1563
+ "loss": 0.035,
1564
+ "step": 1810
1565
+ },
1566
+ {
1567
+ "epoch": 2.7342723004694838,
1568
+ "grad_norm": 0.2879532277584076,
1569
+ "learning_rate": 5.0472491862600915e-05,
1570
+ "loss": 0.0223,
1571
+ "step": 1820
1572
+ },
1573
+ {
1574
+ "epoch": 2.749295774647887,
1575
+ "grad_norm": 0.3457850217819214,
1576
+ "learning_rate": 4.994750013241435e-05,
1577
+ "loss": 0.0264,
1578
+ "step": 1830
1579
+ },
1580
+ {
1581
+ "epoch": 2.764319248826291,
1582
+ "grad_norm": 0.29999199509620667,
1583
+ "learning_rate": 4.9422514190257974e-05,
1584
+ "loss": 0.0242,
1585
+ "step": 1840
1586
+ },
1587
+ {
1588
+ "epoch": 2.779342723004695,
1589
+ "grad_norm": 0.09458961337804794,
1590
+ "learning_rate": 4.88975919150294e-05,
1591
+ "loss": 0.021,
1592
+ "step": 1850
1593
+ },
1594
+ {
1595
+ "epoch": 2.779342723004695,
1596
+ "eval_loss": 0.03918106481432915,
1597
+ "eval_runtime": 156.9396,
1598
+ "eval_samples_per_second": 7.544,
1599
+ "eval_steps_per_second": 7.544,
1600
+ "step": 1850
1601
+ },
1602
+ {
1603
+ "epoch": 2.7943661971830984,
1604
+ "grad_norm": 0.2146388590335846,
1605
+ "learning_rate": 4.83727911786071e-05,
1606
+ "loss": 0.0257,
1607
+ "step": 1860
1608
+ },
1609
+ {
1610
+ "epoch": 2.8093896713615023,
1611
+ "grad_norm": 0.3507349193096161,
1612
+ "learning_rate": 4.7848169839470145e-05,
1613
+ "loss": 0.0237,
1614
+ "step": 1870
1615
+ },
1616
+ {
1617
+ "epoch": 2.824413145539906,
1618
+ "grad_norm": 0.14694459736347198,
1619
+ "learning_rate": 4.7323785736319244e-05,
1620
+ "loss": 0.0271,
1621
+ "step": 1880
1622
+ },
1623
+ {
1624
+ "epoch": 2.8394366197183096,
1625
+ "grad_norm": 0.16568858921527863,
1626
+ "learning_rate": 4.679969668170024e-05,
1627
+ "loss": 0.0234,
1628
+ "step": 1890
1629
+ },
1630
+ {
1631
+ "epoch": 2.8544600938967135,
1632
+ "grad_norm": 0.1532352864742279,
1633
+ "learning_rate": 4.627596045563031e-05,
1634
+ "loss": 0.0253,
1635
+ "step": 1900
1636
+ },
1637
+ {
1638
+ "epoch": 2.8544600938967135,
1639
+ "eval_loss": 0.036843445152044296,
1640
+ "eval_runtime": 157.0438,
1641
+ "eval_samples_per_second": 7.539,
1642
+ "eval_steps_per_second": 7.539,
1643
+ "step": 1900
1644
+ },
1645
+ {
1646
+ "epoch": 2.8694835680751174,
1647
+ "grad_norm": 0.22552986443042755,
1648
+ "learning_rate": 4.575263479922783e-05,
1649
+ "loss": 0.0156,
1650
+ "step": 1910
1651
+ },
1652
+ {
1653
+ "epoch": 2.8845070422535213,
1654
+ "grad_norm": 0.1421150416135788,
1655
+ "learning_rate": 4.522977740834651e-05,
1656
+ "loss": 0.0142,
1657
+ "step": 1920
1658
+ },
1659
+ {
1660
+ "epoch": 2.8995305164319247,
1661
+ "grad_norm": 0.2992912232875824,
1662
+ "learning_rate": 4.4707445927214456e-05,
1663
+ "loss": 0.0169,
1664
+ "step": 1930
1665
+ },
1666
+ {
1667
+ "epoch": 2.9145539906103286,
1668
+ "grad_norm": 0.1591469943523407,
1669
+ "learning_rate": 4.4185697942079115e-05,
1670
+ "loss": 0.0255,
1671
+ "step": 1940
1672
+ },
1673
+ {
1674
+ "epoch": 2.9295774647887325,
1675
+ "grad_norm": 0.13977603614330292,
1676
+ "learning_rate": 4.366459097485832e-05,
1677
+ "loss": 0.018,
1678
+ "step": 1950
1679
+ },
1680
+ {
1681
+ "epoch": 2.9295774647887325,
1682
+ "eval_loss": 0.03921648487448692,
1683
+ "eval_runtime": 157.0461,
1684
+ "eval_samples_per_second": 7.539,
1685
+ "eval_steps_per_second": 7.539,
1686
+ "step": 1950
1687
+ },
1688
+ {
1689
+ "epoch": 2.9446009389671364,
1690
+ "grad_norm": 0.3342364728450775,
1691
+ "learning_rate": 4.314418247679866e-05,
1692
+ "loss": 0.0263,
1693
+ "step": 1960
1694
+ },
1695
+ {
1696
+ "epoch": 2.95962441314554,
1697
+ "grad_norm": 0.24284552037715912,
1698
+ "learning_rate": 4.26245298221416e-05,
1699
+ "loss": 0.014,
1700
+ "step": 1970
1701
+ },
1702
+ {
1703
+ "epoch": 2.9746478873239437,
1704
+ "grad_norm": 0.15542685985565186,
1705
+ "learning_rate": 4.2105690301798014e-05,
1706
+ "loss": 0.0176,
1707
+ "step": 1980
1708
+ },
1709
+ {
1710
+ "epoch": 2.9896713615023476,
1711
+ "grad_norm": 0.24745222926139832,
1712
+ "learning_rate": 4.158772111703194e-05,
1713
+ "loss": 0.0177,
1714
+ "step": 1990
1715
+ },
1716
+ {
1717
+ "epoch": 3.004694835680751,
1718
+ "grad_norm": 0.07768896967172623,
1719
+ "learning_rate": 4.107067937315429e-05,
1720
+ "loss": 0.0112,
1721
+ "step": 2000
1722
+ },
1723
+ {
1724
+ "epoch": 3.004694835680751,
1725
+ "eval_loss": 0.04066740348935127,
1726
+ "eval_runtime": 157.2285,
1727
+ "eval_samples_per_second": 7.53,
1728
+ "eval_steps_per_second": 7.53,
1729
+ "step": 2000
1730
+ },
1731
+ {
1732
+ "epoch": 3.019718309859155,
1733
+ "grad_norm": 0.1813950091600418,
1734
+ "learning_rate": 4.055462207322698e-05,
1735
+ "loss": 0.0121,
1736
+ "step": 2010
1737
+ },
1738
+ {
1739
+ "epoch": 3.034741784037559,
1740
+ "grad_norm": 0.22787263989448547,
1741
+ "learning_rate": 4.003960611177855e-05,
1742
+ "loss": 0.0118,
1743
+ "step": 2020
1744
+ },
1745
+ {
1746
+ "epoch": 3.0497652582159622,
1747
+ "grad_norm": 0.19959565997123718,
1748
+ "learning_rate": 3.952568826853152e-05,
1749
+ "loss": 0.0097,
1750
+ "step": 2030
1751
+ },
1752
+ {
1753
+ "epoch": 3.064788732394366,
1754
+ "grad_norm": 0.0704595223069191,
1755
+ "learning_rate": 3.901292520214256e-05,
1756
+ "loss": 0.0079,
1757
+ "step": 2040
1758
+ },
1759
+ {
1760
+ "epoch": 3.07981220657277,
1761
+ "grad_norm": 0.4440910816192627,
1762
+ "learning_rate": 3.850137344395598e-05,
1763
+ "loss": 0.0082,
1764
+ "step": 2050
1765
+ },
1766
+ {
1767
+ "epoch": 3.07981220657277,
1768
+ "eval_loss": 0.047751668840646744,
1769
+ "eval_runtime": 157.4059,
1770
+ "eval_samples_per_second": 7.522,
1771
+ "eval_steps_per_second": 7.522,
1772
+ "step": 2050
1773
+ },
1774
+ {
1775
+ "epoch": 3.094835680751174,
1776
+ "grad_norm": 0.4817383885383606,
1777
+ "learning_rate": 3.799108939177118e-05,
1778
+ "loss": 0.011,
1779
+ "step": 2060
1780
+ },
1781
+ {
1782
+ "epoch": 3.1098591549295773,
1783
+ "grad_norm": 0.15736213326454163,
1784
+ "learning_rate": 3.7482129303624934e-05,
1785
+ "loss": 0.0098,
1786
+ "step": 2070
1787
+ },
1788
+ {
1789
+ "epoch": 3.124882629107981,
1790
+ "grad_norm": 0.3768656551837921,
1791
+ "learning_rate": 3.697454929158901e-05,
1792
+ "loss": 0.0123,
1793
+ "step": 2080
1794
+ },
1795
+ {
1796
+ "epoch": 3.139906103286385,
1797
+ "grad_norm": 0.37794822454452515,
1798
+ "learning_rate": 3.6468405315583854e-05,
1799
+ "loss": 0.0155,
1800
+ "step": 2090
1801
+ },
1802
+ {
1803
+ "epoch": 3.1549295774647885,
1804
+ "grad_norm": 0.47674834728240967,
1805
+ "learning_rate": 3.59637531772092e-05,
1806
+ "loss": 0.0127,
1807
+ "step": 2100
1808
+ },
1809
+ {
1810
+ "epoch": 3.1549295774647885,
1811
+ "eval_loss": 0.046006690710783005,
1812
+ "eval_runtime": 157.5212,
1813
+ "eval_samples_per_second": 7.516,
1814
+ "eval_steps_per_second": 7.516,
1815
+ "step": 2100
1816
+ },
1817
+ {
1818
+ "epoch": 3.1699530516431924,
1819
+ "grad_norm": 0.2169833481311798,
1820
+ "learning_rate": 3.546064851359192e-05,
1821
+ "loss": 0.0048,
1822
+ "step": 2110
1823
+ },
1824
+ {
1825
+ "epoch": 3.1849765258215963,
1826
+ "grad_norm": 0.12608371675014496,
1827
+ "learning_rate": 3.495914679125212e-05,
1828
+ "loss": 0.0125,
1829
+ "step": 2120
1830
+ },
1831
+ {
1832
+ "epoch": 3.2,
1833
+ "grad_norm": 0.21189413964748383,
1834
+ "learning_rate": 3.445930329998819e-05,
1835
+ "loss": 0.0102,
1836
+ "step": 2130
1837
+ },
1838
+ {
1839
+ "epoch": 3.2150234741784036,
1840
+ "grad_norm": 0.29917919635772705,
1841
+ "learning_rate": 3.396117314678097e-05,
1842
+ "loss": 0.0173,
1843
+ "step": 2140
1844
+ },
1845
+ {
1846
+ "epoch": 3.2300469483568075,
1847
+ "grad_norm": 0.29451966285705566,
1848
+ "learning_rate": 3.3464811249718474e-05,
1849
+ "loss": 0.0112,
1850
+ "step": 2150
1851
+ },
1852
+ {
1853
+ "epoch": 3.2300469483568075,
1854
+ "eval_loss": 0.04488084837794304,
1855
+ "eval_runtime": 157.4858,
1856
+ "eval_samples_per_second": 7.518,
1857
+ "eval_steps_per_second": 7.518,
1858
+ "step": 2150
1859
+ },
1860
+ {
1861
+ "epoch": 3.2450704225352114,
1862
+ "grad_norm": 0.1548345535993576,
1863
+ "learning_rate": 3.297027233194114e-05,
1864
+ "loss": 0.0128,
1865
+ "step": 2160
1866
+ },
1867
+ {
1868
+ "epoch": 3.260093896713615,
1869
+ "grad_norm": 0.08690305054187775,
1870
+ "learning_rate": 3.2477610915608704e-05,
1871
+ "loss": 0.01,
1872
+ "step": 2170
1873
+ },
1874
+ {
1875
+ "epoch": 3.2751173708920187,
1876
+ "grad_norm": 0.26383867859840393,
1877
+ "learning_rate": 3.1986881315889315e-05,
1878
+ "loss": 0.014,
1879
+ "step": 2180
1880
+ },
1881
+ {
1882
+ "epoch": 3.2901408450704226,
1883
+ "grad_norm": 0.4667436480522156,
1884
+ "learning_rate": 3.149813763497124e-05,
1885
+ "loss": 0.0174,
1886
+ "step": 2190
1887
+ },
1888
+ {
1889
+ "epoch": 3.3051643192488265,
1890
+ "grad_norm": 0.3968455493450165,
1891
+ "learning_rate": 3.101143375609818e-05,
1892
+ "loss": 0.0145,
1893
+ "step": 2200
1894
+ },
1895
+ {
1896
+ "epoch": 3.3051643192488265,
1897
+ "eval_loss": 0.04522354528307915,
1898
+ "eval_runtime": 157.475,
1899
+ "eval_samples_per_second": 7.519,
1900
+ "eval_steps_per_second": 7.519,
1901
+ "step": 2200
1902
+ },
1903
+ {
1904
+ "epoch": 3.32018779342723,
1905
+ "grad_norm": 0.2882903814315796,
1906
+ "learning_rate": 3.0526823337628915e-05,
1907
+ "loss": 0.0143,
1908
+ "step": 2210
1909
+ },
1910
+ {
1911
+ "epoch": 3.335211267605634,
1912
+ "grad_norm": 0.2159668207168579,
1913
+ "learning_rate": 3.004435980712129e-05,
1914
+ "loss": 0.0094,
1915
+ "step": 2220
1916
+ },
1917
+ {
1918
+ "epoch": 3.3502347417840377,
1919
+ "grad_norm": 0.6046177744865417,
1920
+ "learning_rate": 2.9564096355442116e-05,
1921
+ "loss": 0.0133,
1922
+ "step": 2230
1923
+ },
1924
+ {
1925
+ "epoch": 3.365258215962441,
1926
+ "grad_norm": 0.30788397789001465,
1927
+ "learning_rate": 2.9086085930902824e-05,
1928
+ "loss": 0.0143,
1929
+ "step": 2240
1930
+ },
1931
+ {
1932
+ "epoch": 3.380281690140845,
1933
+ "grad_norm": 0.3591701090335846,
1934
+ "learning_rate": 2.8610381233422058e-05,
1935
+ "loss": 0.0086,
1936
+ "step": 2250
1937
+ },
1938
+ {
1939
+ "epoch": 3.380281690140845,
1940
+ "eval_loss": 0.04514958709478378,
1941
+ "eval_runtime": 157.5469,
1942
+ "eval_samples_per_second": 7.515,
1943
+ "eval_steps_per_second": 7.515,
1944
+ "step": 2250
1945
+ },
1946
+ {
1947
+ "epoch": 3.395305164319249,
1948
+ "grad_norm": 0.18443742394447327,
1949
+ "learning_rate": 2.8137034708715592e-05,
1950
+ "loss": 0.0106,
1951
+ "step": 2260
1952
+ },
1953
+ {
1954
+ "epoch": 3.4103286384976528,
1955
+ "grad_norm": 0.02844012901186943,
1956
+ "learning_rate": 2.7666098542514273e-05,
1957
+ "loss": 0.0066,
1958
+ "step": 2270
1959
+ },
1960
+ {
1961
+ "epoch": 3.425352112676056,
1962
+ "grad_norm": 0.5778037309646606,
1963
+ "learning_rate": 2.719762465481055e-05,
1964
+ "loss": 0.0117,
1965
+ "step": 2280
1966
+ },
1967
+ {
1968
+ "epoch": 3.44037558685446,
1969
+ "grad_norm": 0.17093347012996674,
1970
+ "learning_rate": 2.6731664694134473e-05,
1971
+ "loss": 0.0133,
1972
+ "step": 2290
1973
+ },
1974
+ {
1975
+ "epoch": 3.455399061032864,
1976
+ "grad_norm": 0.5244073271751404,
1977
+ "learning_rate": 2.6268270031859476e-05,
1978
+ "loss": 0.0161,
1979
+ "step": 2300
1980
+ },
1981
+ {
1982
+ "epoch": 3.455399061032864,
1983
+ "eval_loss": 0.04896237701177597,
1984
+ "eval_runtime": 157.594,
1985
+ "eval_samples_per_second": 7.513,
1986
+ "eval_steps_per_second": 7.513,
1987
+ "step": 2300
1988
+ },
1989
+ {
1990
+ "epoch": 3.4704225352112674,
1991
+ "grad_norm": 0.5648406147956848,
1992
+ "learning_rate": 2.580749175653877e-05,
1993
+ "loss": 0.0108,
1994
+ "step": 2310
1995
+ },
1996
+ {
1997
+ "epoch": 3.4854460093896713,
1998
+ "grad_norm": 0.5017344355583191,
1999
+ "learning_rate": 2.5349380668272905e-05,
2000
+ "loss": 0.0124,
2001
+ "step": 2320
2002
+ },
2003
+ {
2004
+ "epoch": 3.500469483568075,
2005
+ "grad_norm": 0.1720559000968933,
2006
+ "learning_rate": 2.489398727310908e-05,
2007
+ "loss": 0.013,
2008
+ "step": 2330
2009
+ },
2010
+ {
2011
+ "epoch": 3.5154929577464786,
2012
+ "grad_norm": 0.34457623958587646,
2013
+ "learning_rate": 2.4441361777473066e-05,
2014
+ "loss": 0.0107,
2015
+ "step": 2340
2016
+ },
2017
+ {
2018
+ "epoch": 3.5305164319248825,
2019
+ "grad_norm": 0.8733149766921997,
2020
+ "learning_rate": 2.3991554082633912e-05,
2021
+ "loss": 0.0134,
2022
+ "step": 2350
2023
+ },
2024
+ {
2025
+ "epoch": 3.5305164319248825,
2026
+ "eval_loss": 0.04652281105518341,
2027
+ "eval_runtime": 157.7619,
2028
+ "eval_samples_per_second": 7.505,
2029
+ "eval_steps_per_second": 7.505,
2030
+ "step": 2350
2031
+ },
2032
+ {
2033
+ "epoch": 3.5455399061032864,
2034
+ "grad_norm": 0.13055922091007233,
2035
+ "learning_rate": 2.354461377920239e-05,
2036
+ "loss": 0.0088,
2037
+ "step": 2360
2038
+ },
2039
+ {
2040
+ "epoch": 3.5605633802816903,
2041
+ "grad_norm": 0.20548763871192932,
2042
+ "learning_rate": 2.3100590141663807e-05,
2043
+ "loss": 0.0115,
2044
+ "step": 2370
2045
+ },
2046
+ {
2047
+ "epoch": 3.575586854460094,
2048
+ "grad_norm": 0.3360619843006134,
2049
+ "learning_rate": 2.265953212294551e-05,
2050
+ "loss": 0.0182,
2051
+ "step": 2380
2052
+ },
2053
+ {
2054
+ "epoch": 3.5906103286384976,
2055
+ "grad_norm": 0.6770099401473999,
2056
+ "learning_rate": 2.2221488349019903e-05,
2057
+ "loss": 0.0164,
2058
+ "step": 2390
2059
+ },
2060
+ {
2061
+ "epoch": 3.6056338028169015,
2062
+ "grad_norm": 0.31347426772117615,
2063
+ "learning_rate": 2.1786507113543457e-05,
2064
+ "loss": 0.009,
2065
+ "step": 2400
2066
+ },
2067
+ {
2068
+ "epoch": 3.6056338028169015,
2069
+ "eval_loss": 0.04605977609753609,
2070
+ "eval_runtime": 157.7592,
2071
+ "eval_samples_per_second": 7.505,
2072
+ "eval_steps_per_second": 7.505,
2073
+ "step": 2400
2074
+ },
2075
+ {
2076
+ "epoch": 3.6206572769953054,
2077
+ "grad_norm": 0.13689975440502167,
2078
+ "learning_rate": 2.1354636372532523e-05,
2079
+ "loss": 0.0176,
2080
+ "step": 2410
2081
+ },
2082
+ {
2083
+ "epoch": 3.635680751173709,
2084
+ "grad_norm": 0.2913866937160492,
2085
+ "learning_rate": 2.092592373907617e-05,
2086
+ "loss": 0.0101,
2087
+ "step": 2420
2088
+ },
2089
+ {
2090
+ "epoch": 3.6507042253521127,
2091
+ "grad_norm": 0.37444183230400085,
2092
+ "learning_rate": 2.0500416478086932e-05,
2093
+ "loss": 0.0075,
2094
+ "step": 2430
2095
+ },
2096
+ {
2097
+ "epoch": 3.6657276995305166,
2098
+ "grad_norm": 0.42321744561195374,
2099
+ "learning_rate": 2.0078161501089954e-05,
2100
+ "loss": 0.0117,
2101
+ "step": 2440
2102
+ },
2103
+ {
2104
+ "epoch": 3.68075117370892,
2105
+ "grad_norm": 0.15104345977306366,
2106
+ "learning_rate": 1.9659205361050982e-05,
2107
+ "loss": 0.0056,
2108
+ "step": 2450
2109
+ },
2110
+ {
2111
+ "epoch": 3.68075117370892,
2112
+ "eval_loss": 0.04802750423550606,
2113
+ "eval_runtime": 157.7669,
2114
+ "eval_samples_per_second": 7.505,
2115
+ "eval_steps_per_second": 7.505,
2116
+ "step": 2450
2117
+ },
2118
+ {
2119
+ "epoch": 3.695774647887324,
2120
+ "grad_norm": 0.15667098760604858,
2121
+ "learning_rate": 1.924359424724408e-05,
2122
+ "loss": 0.0154,
2123
+ "step": 2460
2124
+ },
2125
+ {
2126
+ "epoch": 3.710798122065728,
2127
+ "grad_norm": 0.49284836649894714,
2128
+ "learning_rate": 1.8831373980159296e-05,
2129
+ "loss": 0.0145,
2130
+ "step": 2470
2131
+ },
2132
+ {
2133
+ "epoch": 3.7258215962441312,
2134
+ "grad_norm": 0.22378303110599518,
2135
+ "learning_rate": 1.8422590006450947e-05,
2136
+ "loss": 0.0063,
2137
+ "step": 2480
2138
+ },
2139
+ {
2140
+ "epoch": 3.740845070422535,
2141
+ "grad_norm": 0.20172594487667084,
2142
+ "learning_rate": 1.801728739392731e-05,
2143
+ "loss": 0.0089,
2144
+ "step": 2490
2145
+ },
2146
+ {
2147
+ "epoch": 3.755868544600939,
2148
+ "grad_norm": 0.2898995280265808,
2149
+ "learning_rate": 1.7615510826581904e-05,
2150
+ "loss": 0.0069,
2151
+ "step": 2500
2152
+ },
2153
+ {
2154
+ "epoch": 3.755868544600939,
2155
+ "eval_loss": 0.04896940663456917,
2156
+ "eval_runtime": 157.7817,
2157
+ "eval_samples_per_second": 7.504,
2158
+ "eval_steps_per_second": 7.504,
2159
+ "step": 2500
2160
+ },
2161
+ {
2162
+ "epoch": 3.770892018779343,
2163
+ "grad_norm": 0.32213857769966125,
2164
+ "learning_rate": 1.7217304599667146e-05,
2165
+ "loss": 0.0164,
2166
+ "step": 2510
2167
+ },
2168
+ {
2169
+ "epoch": 3.7859154929577463,
2170
+ "grad_norm": 0.06365455687046051,
2171
+ "learning_rate": 1.6822712614810893e-05,
2172
+ "loss": 0.01,
2173
+ "step": 2520
2174
+ },
2175
+ {
2176
+ "epoch": 3.80093896713615,
2177
+ "grad_norm": 0.2050347775220871,
2178
+ "learning_rate": 1.643177837517631e-05,
2179
+ "loss": 0.0117,
2180
+ "step": 2530
2181
+ },
2182
+ {
2183
+ "epoch": 3.815962441314554,
2184
+ "grad_norm": 0.40109461545944214,
2185
+ "learning_rate": 1.6044544980665767e-05,
2186
+ "loss": 0.0108,
2187
+ "step": 2540
2188
+ },
2189
+ {
2190
+ "epoch": 3.830985915492958,
2191
+ "grad_norm": 0.5502837300300598,
2192
+ "learning_rate": 1.5661055123169126e-05,
2193
+ "loss": 0.007,
2194
+ "step": 2550
2195
+ },
2196
+ {
2197
+ "epoch": 3.830985915492958,
2198
+ "eval_loss": 0.04891159385442734,
2199
+ "eval_runtime": 157.7489,
2200
+ "eval_samples_per_second": 7.506,
2201
+ "eval_steps_per_second": 7.506,
2202
+ "step": 2550
2203
+ },
2204
+ {
2205
+ "epoch": 3.8460093896713614,
2206
+ "grad_norm": 0.17208245396614075,
2207
+ "learning_rate": 1.5281351081856974e-05,
2208
+ "loss": 0.0079,
2209
+ "step": 2560
2210
+ },
2211
+ {
2212
+ "epoch": 3.8610328638497653,
2213
+ "grad_norm": 0.2847214639186859,
2214
+ "learning_rate": 1.4905474718519491e-05,
2215
+ "loss": 0.0075,
2216
+ "step": 2570
2217
+ },
2218
+ {
2219
+ "epoch": 3.876056338028169,
2220
+ "grad_norm": 0.36303362250328064,
2221
+ "learning_rate": 1.453346747295119e-05,
2222
+ "loss": 0.0106,
2223
+ "step": 2580
2224
+ },
2225
+ {
2226
+ "epoch": 3.8910798122065726,
2227
+ "grad_norm": 0.09206058084964752,
2228
+ "learning_rate": 1.4165370358382274e-05,
2229
+ "loss": 0.0117,
2230
+ "step": 2590
2231
+ },
2232
+ {
2233
+ "epoch": 3.9061032863849765,
2234
+ "grad_norm": 0.7500032782554626,
2235
+ "learning_rate": 1.3801223956956994e-05,
2236
+ "loss": 0.0147,
2237
+ "step": 2600
2238
+ },
2239
+ {
2240
+ "epoch": 3.9061032863849765,
2241
+ "eval_loss": 0.048022232949733734,
2242
+ "eval_runtime": 157.7412,
2243
+ "eval_samples_per_second": 7.506,
2244
+ "eval_steps_per_second": 7.506,
2245
+ "step": 2600
2246
+ },
2247
+ {
2248
+ "epoch": 3.9211267605633804,
2249
+ "grad_norm": 0.37353694438934326,
2250
+ "learning_rate": 1.344106841525946e-05,
2251
+ "loss": 0.0101,
2252
+ "step": 2610
2253
+ },
2254
+ {
2255
+ "epoch": 3.936150234741784,
2256
+ "grad_norm": 0.3442070484161377,
2257
+ "learning_rate": 1.3084943439887659e-05,
2258
+ "loss": 0.0111,
2259
+ "step": 2620
2260
+ },
2261
+ {
2262
+ "epoch": 3.9511737089201877,
2263
+ "grad_norm": 0.17266932129859924,
2264
+ "learning_rate": 1.273288829307579e-05,
2265
+ "loss": 0.0069,
2266
+ "step": 2630
2267
+ },
2268
+ {
2269
+ "epoch": 3.9661971830985916,
2270
+ "grad_norm": 0.09121805429458618,
2271
+ "learning_rate": 1.2384941788365622e-05,
2272
+ "loss": 0.0073,
2273
+ "step": 2640
2274
+ },
2275
+ {
2276
+ "epoch": 3.981220657276995,
2277
+ "grad_norm": 0.37061765789985657,
2278
+ "learning_rate": 1.2041142286327477e-05,
2279
+ "loss": 0.0123,
2280
+ "step": 2650
2281
+ },
2282
+ {
2283
+ "epoch": 3.981220657276995,
2284
+ "eval_loss": 0.0474095456302166,
2285
+ "eval_runtime": 157.8962,
2286
+ "eval_samples_per_second": 7.499,
2287
+ "eval_steps_per_second": 7.499,
2288
+ "step": 2650
2289
+ },
2290
+ {
2291
+ "epoch": 3.996244131455399,
2292
+ "grad_norm": 0.28421324491500854,
2293
+ "learning_rate": 1.170152769033095e-05,
2294
+ "loss": 0.0058,
2295
+ "step": 2660
2296
+ },
2297
+ {
2298
+ "epoch": 4.011267605633803,
2299
+ "grad_norm": 0.1725592464208603,
2300
+ "learning_rate": 1.1366135442366127e-05,
2301
+ "loss": 0.0066,
2302
+ "step": 2670
2303
+ },
2304
+ {
2305
+ "epoch": 4.026291079812206,
2306
+ "grad_norm": 0.144903302192688,
2307
+ "learning_rate": 1.103500251891571e-05,
2308
+ "loss": 0.0061,
2309
+ "step": 2680
2310
+ },
2311
+ {
2312
+ "epoch": 4.041314553990611,
2313
+ "grad_norm": 0.09540867805480957,
2314
+ "learning_rate": 1.0708165426878325e-05,
2315
+ "loss": 0.0042,
2316
+ "step": 2690
2317
+ },
2318
+ {
2319
+ "epoch": 4.056338028169014,
2320
+ "grad_norm": 0.04649324715137482,
2321
+ "learning_rate": 1.0385660199543812e-05,
2322
+ "loss": 0.0053,
2323
+ "step": 2700
2324
+ },
2325
+ {
2326
+ "epoch": 4.056338028169014,
2327
+ "eval_loss": 0.05291583761572838,
2328
+ "eval_runtime": 157.9865,
2329
+ "eval_samples_per_second": 7.494,
2330
+ "eval_steps_per_second": 7.494,
2331
+ "step": 2700
2332
+ },
2333
+ {
2334
+ "epoch": 4.0713615023474174,
2335
+ "grad_norm": 0.020398231223225594,
2336
+ "learning_rate": 1.0067522392620537e-05,
2337
+ "loss": 0.0037,
2338
+ "step": 2710
2339
+ },
2340
+ {
2341
+ "epoch": 4.086384976525822,
2342
+ "grad_norm": 0.25772586464881897,
2343
+ "learning_rate": 9.753787080315385e-06,
2344
+ "loss": 0.0084,
2345
+ "step": 2720
2346
+ },
2347
+ {
2348
+ "epoch": 4.101408450704225,
2349
+ "grad_norm": 0.0540861040353775,
2350
+ "learning_rate": 9.444488851467042e-06,
2351
+ "loss": 0.0051,
2352
+ "step": 2730
2353
+ },
2354
+ {
2355
+ "epoch": 4.1164319248826295,
2356
+ "grad_norm": 0.19499164819717407,
2357
+ "learning_rate": 9.139661805732435e-06,
2358
+ "loss": 0.0043,
2359
+ "step": 2740
2360
+ },
2361
+ {
2362
+ "epoch": 4.131455399061033,
2363
+ "grad_norm": 0.46163612604141235,
2364
+ "learning_rate": 8.839339549827397e-06,
2365
+ "loss": 0.0064,
2366
+ "step": 2750
2367
+ },
2368
+ {
2369
+ "epoch": 4.131455399061033,
2370
+ "eval_loss": 0.05712565779685974,
2371
+ "eval_runtime": 157.9487,
2372
+ "eval_samples_per_second": 7.496,
2373
+ "eval_steps_per_second": 7.496,
2374
+ "step": 2750
2375
+ },
2376
+ {
2377
+ "epoch": 4.146478873239436,
2378
+ "grad_norm": 0.07052065432071686,
2379
+ "learning_rate": 8.543555193821634e-06,
2380
+ "loss": 0.0045,
2381
+ "step": 2760
2382
+ },
2383
+ {
2384
+ "epoch": 4.161502347417841,
2385
+ "grad_norm": 0.3251402974128723,
2386
+ "learning_rate": 8.252341347488251e-06,
2387
+ "loss": 0.0032,
2388
+ "step": 2770
2389
+ },
2390
+ {
2391
+ "epoch": 4.176525821596244,
2392
+ "grad_norm": 0.21811746060848236,
2393
+ "learning_rate": 7.965730116708681e-06,
2394
+ "loss": 0.005,
2395
+ "step": 2780
2396
+ },
2397
+ {
2398
+ "epoch": 4.191549295774648,
2399
+ "grad_norm": 0.08314239978790283,
2400
+ "learning_rate": 7.68375309993304e-06,
2401
+ "loss": 0.0025,
2402
+ "step": 2790
2403
+ },
2404
+ {
2405
+ "epoch": 4.206572769953052,
2406
+ "grad_norm": 0.07649940252304077,
2407
+ "learning_rate": 7.406441384696372e-06,
2408
+ "loss": 0.0064,
2409
+ "step": 2800
2410
+ },
2411
+ {
2412
+ "epoch": 4.206572769953052,
2413
+ "eval_loss": 0.05896175280213356,
2414
+ "eval_runtime": 157.6893,
2415
+ "eval_samples_per_second": 7.508,
2416
+ "eval_steps_per_second": 7.508,
2417
+ "step": 2800
2418
+ },
2419
+ {
2420
+ "epoch": 4.221596244131455,
2421
+ "grad_norm": 0.14924947917461395,
2422
+ "learning_rate": 7.133825544191464e-06,
2423
+ "loss": 0.0088,
2424
+ "step": 2810
2425
+ },
2426
+ {
2427
+ "epoch": 4.236619718309859,
2428
+ "grad_norm": 0.07150545716285706,
2429
+ "learning_rate": 6.865935633897996e-06,
2430
+ "loss": 0.0019,
2431
+ "step": 2820
2432
+ },
2433
+ {
2434
+ "epoch": 4.251643192488263,
2435
+ "grad_norm": 0.13238117098808289,
2436
+ "learning_rate": 6.602801188269081e-06,
2437
+ "loss": 0.0057,
2438
+ "step": 2830
2439
+ },
2440
+ {
2441
+ "epoch": 4.266666666666667,
2442
+ "grad_norm": 0.182158961892128,
2443
+ "learning_rate": 6.344451217475183e-06,
2444
+ "loss": 0.0029,
2445
+ "step": 2840
2446
+ },
2447
+ {
2448
+ "epoch": 4.28169014084507,
2449
+ "grad_norm": 0.12668107450008392,
2450
+ "learning_rate": 6.090914204205655e-06,
2451
+ "loss": 0.0038,
2452
+ "step": 2850
2453
+ },
2454
+ {
2455
+ "epoch": 4.28169014084507,
2456
+ "eval_loss": 0.060705944895744324,
2457
+ "eval_runtime": 157.8239,
2458
+ "eval_samples_per_second": 7.502,
2459
+ "eval_steps_per_second": 7.502,
2460
+ "step": 2850
2461
+ },
2462
+ {
2463
+ "epoch": 4.296713615023474,
2464
+ "grad_norm": 0.22536417841911316,
2465
+ "learning_rate": 5.842218100528679e-06,
2466
+ "loss": 0.0029,
2467
+ "step": 2860
2468
+ },
2469
+ {
2470
+ "epoch": 4.311737089201878,
2471
+ "grad_norm": 0.2726947069168091,
2472
+ "learning_rate": 5.598390324809555e-06,
2473
+ "loss": 0.0041,
2474
+ "step": 2870
2475
+ },
2476
+ {
2477
+ "epoch": 4.326760563380281,
2478
+ "grad_norm": 0.3938266634941101,
2479
+ "learning_rate": 5.359457758687841e-06,
2480
+ "loss": 0.0048,
2481
+ "step": 2880
2482
+ },
2483
+ {
2484
+ "epoch": 4.341784037558686,
2485
+ "grad_norm": 0.29681265354156494,
2486
+ "learning_rate": 5.125446744113743e-06,
2487
+ "loss": 0.0088,
2488
+ "step": 2890
2489
+ },
2490
+ {
2491
+ "epoch": 4.356807511737089,
2492
+ "grad_norm": 0.08293790370225906,
2493
+ "learning_rate": 4.896383080443934e-06,
2494
+ "loss": 0.0011,
2495
+ "step": 2900
2496
+ },
2497
+ {
2498
+ "epoch": 4.356807511737089,
2499
+ "eval_loss": 0.06272595375776291,
2500
+ "eval_runtime": 157.9854,
2501
+ "eval_samples_per_second": 7.494,
2502
+ "eval_steps_per_second": 7.494,
2503
+ "step": 2900
2504
+ },
2505
+ {
2506
+ "epoch": 4.371830985915493,
2507
+ "grad_norm": 0.15698398649692535,
2508
+ "learning_rate": 4.672292021597174e-06,
2509
+ "loss": 0.0053,
2510
+ "step": 2910
2511
+ },
2512
+ {
2513
+ "epoch": 4.386854460093897,
2514
+ "grad_norm": 0.25638025999069214,
2515
+ "learning_rate": 4.4531982732702145e-06,
2516
+ "loss": 0.0055,
2517
+ "step": 2920
2518
+ },
2519
+ {
2520
+ "epoch": 4.4018779342723,
2521
+ "grad_norm": 0.1589283049106598,
2522
+ "learning_rate": 4.239125990213883e-06,
2523
+ "loss": 0.0045,
2524
+ "step": 2930
2525
+ },
2526
+ {
2527
+ "epoch": 4.416901408450705,
2528
+ "grad_norm": 0.06673490256071091,
2529
+ "learning_rate": 4.030098773570174e-06,
2530
+ "loss": 0.001,
2531
+ "step": 2940
2532
+ },
2533
+ {
2534
+ "epoch": 4.431924882629108,
2535
+ "grad_norm": 0.12453540414571762,
2536
+ "learning_rate": 3.826139668270234e-06,
2537
+ "loss": 0.0034,
2538
+ "step": 2950
2539
+ },
2540
+ {
2541
+ "epoch": 4.431924882629108,
2542
+ "eval_loss": 0.06274248659610748,
2543
+ "eval_runtime": 157.8646,
2544
+ "eval_samples_per_second": 7.5,
2545
+ "eval_steps_per_second": 7.5,
2546
+ "step": 2950
2547
+ },
2548
+ {
2549
+ "epoch": 4.446948356807511,
2550
+ "grad_norm": 0.18250524997711182,
2551
+ "learning_rate": 3.6272711604936504e-06,
2552
+ "loss": 0.0074,
2553
+ "step": 2960
2554
+ },
2555
+ {
2556
+ "epoch": 4.461971830985916,
2557
+ "grad_norm": 0.026577528566122055,
2558
+ "learning_rate": 3.433515175189428e-06,
2559
+ "loss": 0.0033,
2560
+ "step": 2970
2561
+ },
2562
+ {
2563
+ "epoch": 4.476995305164319,
2564
+ "grad_norm": 0.03135993331670761,
2565
+ "learning_rate": 3.2448930736588e-06,
2566
+ "loss": 0.0093,
2567
+ "step": 2980
2568
+ },
2569
+ {
2570
+ "epoch": 4.492018779342723,
2571
+ "grad_norm": 0.054898951202631,
2572
+ "learning_rate": 3.061425651200117e-06,
2573
+ "loss": 0.0031,
2574
+ "step": 2990
2575
+ },
2576
+ {
2577
+ "epoch": 4.507042253521127,
2578
+ "grad_norm": 0.12721896171569824,
2579
+ "learning_rate": 2.883133134816296e-06,
2580
+ "loss": 0.0063,
2581
+ "step": 3000
2582
+ },
2583
+ {
2584
+ "epoch": 4.507042253521127,
2585
+ "eval_loss": 0.062312256544828415,
2586
+ "eval_runtime": 157.8769,
2587
+ "eval_samples_per_second": 7.5,
2588
+ "eval_steps_per_second": 7.5,
2589
+ "step": 3000
2590
+ },
2591
+ {
2592
+ "epoch": 4.52206572769953,
2593
+ "grad_norm": 0.050971172749996185,
2594
+ "learning_rate": 2.7100351809847326e-06,
2595
+ "loss": 0.0026,
2596
+ "step": 3010
2597
+ },
2598
+ {
2599
+ "epoch": 4.537089201877935,
2600
+ "grad_norm": 0.06001908332109451,
2601
+ "learning_rate": 2.542150873490251e-06,
2602
+ "loss": 0.0026,
2603
+ "step": 3020
2604
+ },
2605
+ {
2606
+ "epoch": 4.552112676056338,
2607
+ "grad_norm": 0.1522800624370575,
2608
+ "learning_rate": 2.3794987213211383e-06,
2609
+ "loss": 0.0039,
2610
+ "step": 3030
2611
+ },
2612
+ {
2613
+ "epoch": 4.567136150234742,
2614
+ "grad_norm": 0.19140265882015228,
2615
+ "learning_rate": 2.222096656628547e-06,
2616
+ "loss": 0.0041,
2617
+ "step": 3040
2618
+ },
2619
+ {
2620
+ "epoch": 4.582159624413146,
2621
+ "grad_norm": 0.031790439039468765,
2622
+ "learning_rate": 2.0699620327495174e-06,
2623
+ "loss": 0.0033,
2624
+ "step": 3050
2625
+ },
2626
+ {
2627
+ "epoch": 4.582159624413146,
2628
+ "eval_loss": 0.06346932053565979,
2629
+ "eval_runtime": 157.947,
2630
+ "eval_samples_per_second": 7.496,
2631
+ "eval_steps_per_second": 7.496,
2632
+ "step": 3050
2633
+ },
2634
+ {
2635
+ "epoch": 4.597183098591549,
2636
+ "grad_norm": 0.011058680713176727,
2637
+ "learning_rate": 1.9231116222937996e-06,
2638
+ "loss": 0.0014,
2639
+ "step": 3060
2640
+ },
2641
+ {
2642
+ "epoch": 4.612206572769953,
2643
+ "grad_norm": 0.051989588886499405,
2644
+ "learning_rate": 1.7815616152946523e-06,
2645
+ "loss": 0.0022,
2646
+ "step": 3070
2647
+ },
2648
+ {
2649
+ "epoch": 4.627230046948357,
2650
+ "grad_norm": 0.28735625743865967,
2651
+ "learning_rate": 1.6453276174240195e-06,
2652
+ "loss": 0.0016,
2653
+ "step": 3080
2654
+ },
2655
+ {
2656
+ "epoch": 4.642253521126761,
2657
+ "grad_norm": 0.7765727043151855,
2658
+ "learning_rate": 1.5144246482719114e-06,
2659
+ "loss": 0.0032,
2660
+ "step": 3090
2661
+ },
2662
+ {
2663
+ "epoch": 4.657276995305164,
2664
+ "grad_norm": 0.16394619643688202,
2665
+ "learning_rate": 1.3888671396905805e-06,
2666
+ "loss": 0.0048,
2667
+ "step": 3100
2668
+ },
2669
+ {
2670
+ "epoch": 4.657276995305164,
2671
+ "eval_loss": 0.06427957862615585,
2672
+ "eval_runtime": 157.8435,
2673
+ "eval_samples_per_second": 7.501,
2674
+ "eval_steps_per_second": 7.501,
2675
+ "step": 3100
2676
+ },
2677
+ {
2678
+ "epoch": 4.672300469483568,
2679
+ "grad_norm": 0.07136521488428116,
2680
+ "learning_rate": 1.2686689342034431e-06,
2681
+ "loss": 0.0075,
2682
+ "step": 3110
2683
+ },
2684
+ {
2685
+ "epoch": 4.687323943661972,
2686
+ "grad_norm": 0.06406821310520172,
2687
+ "learning_rate": 1.1538432834789227e-06,
2688
+ "loss": 0.0058,
2689
+ "step": 3120
2690
+ },
2691
+ {
2692
+ "epoch": 4.702347417840375,
2693
+ "grad_norm": 0.42130792140960693,
2694
+ "learning_rate": 1.044402846869491e-06,
2695
+ "loss": 0.0041,
2696
+ "step": 3130
2697
+ },
2698
+ {
2699
+ "epoch": 4.71737089201878,
2700
+ "grad_norm": 0.6147840023040771,
2701
+ "learning_rate": 9.403596900160073e-07,
2702
+ "loss": 0.003,
2703
+ "step": 3140
2704
+ },
2705
+ {
2706
+ "epoch": 4.732394366197183,
2707
+ "grad_norm": 0.4716566205024719,
2708
+ "learning_rate": 8.417252835174749e-07,
2709
+ "loss": 0.0044,
2710
+ "step": 3150
2711
+ },
2712
+ {
2713
+ "epoch": 4.732394366197183,
2714
+ "eval_loss": 0.06363623589277267,
2715
+ "eval_runtime": 157.8646,
2716
+ "eval_samples_per_second": 7.5,
2717
+ "eval_steps_per_second": 7.5,
2718
+ "step": 3150
2719
+ },
2720
+ {
2721
+ "epoch": 4.7474178403755865,
2722
+ "grad_norm": 0.2807024419307709,
2723
+ "learning_rate": 7.48510501666455e-07,
2724
+ "loss": 0.0079,
2725
+ "step": 3160
2726
+ },
2727
+ {
2728
+ "epoch": 4.762441314553991,
2729
+ "grad_norm": 0.3779400587081909,
2730
+ "learning_rate": 6.607256212501578e-07,
2731
+ "loss": 0.0041,
2732
+ "step": 3170
2733
+ },
2734
+ {
2735
+ "epoch": 4.777464788732394,
2736
+ "grad_norm": 0.3377034068107605,
2737
+ "learning_rate": 5.783803204174654e-07,
2738
+ "loss": 0.005,
2739
+ "step": 3180
2740
+ },
2741
+ {
2742
+ "epoch": 4.792488262910798,
2743
+ "grad_norm": 0.15139789879322052,
2744
+ "learning_rate": 5.014836776119358e-07,
2745
+ "loss": 0.0027,
2746
+ "step": 3190
2747
+ },
2748
+ {
2749
+ "epoch": 4.807511737089202,
2750
+ "grad_norm": 0.15307891368865967,
2751
+ "learning_rate": 4.300441705708924e-07,
2752
+ "loss": 0.0031,
2753
+ "step": 3200
2754
+ },
2755
+ {
2756
+ "epoch": 4.807511737089202,
2757
+ "eval_loss": 0.06359302997589111,
2758
+ "eval_runtime": 157.9251,
2759
+ "eval_samples_per_second": 7.497,
2760
+ "eval_steps_per_second": 7.497,
2761
+ "step": 3200
2762
+ },
2763
+ {
2764
+ "epoch": 4.822535211267605,
2765
+ "grad_norm": 0.28907057642936707,
2766
+ "learning_rate": 3.6406967539078796e-07,
2767
+ "loss": 0.0047,
2768
+ "step": 3210
2769
+ },
2770
+ {
2771
+ "epoch": 4.83755868544601,
2772
+ "grad_norm": 0.10809265822172165,
2773
+ "learning_rate": 3.0356746565887715e-07,
2774
+ "loss": 0.004,
2775
+ "step": 3220
2776
+ },
2777
+ {
2778
+ "epoch": 4.852582159624413,
2779
+ "grad_norm": 0.07856517285108566,
2780
+ "learning_rate": 2.485442116513026e-07,
2781
+ "loss": 0.0031,
2782
+ "step": 3230
2783
+ },
2784
+ {
2785
+ "epoch": 4.867605633802817,
2786
+ "grad_norm": 0.5275461673736572,
2787
+ "learning_rate": 1.9900597959770507e-07,
2788
+ "loss": 0.0087,
2789
+ "step": 3240
2790
+ },
2791
+ {
2792
+ "epoch": 4.882629107981221,
2793
+ "grad_norm": 0.014800317585468292,
2794
+ "learning_rate": 1.5495823101245866e-07,
2795
+ "loss": 0.0022,
2796
+ "step": 3250
2797
+ },
2798
+ {
2799
+ "epoch": 4.882629107981221,
2800
+ "eval_loss": 0.06390237808227539,
2801
+ "eval_runtime": 157.8776,
2802
+ "eval_samples_per_second": 7.499,
2803
+ "eval_steps_per_second": 7.499,
2804
+ "step": 3250
2805
+ },
2806
+ {
2807
+ "epoch": 4.897652582159624,
2808
+ "grad_norm": 0.04556208476424217,
2809
+ "learning_rate": 1.164058220925135e-07,
2810
+ "loss": 0.006,
2811
+ "step": 3260
2812
+ },
2813
+ {
2814
+ "epoch": 4.912676056338028,
2815
+ "grad_norm": 0.20600998401641846,
2816
+ "learning_rate": 8.335300318201844e-08,
2817
+ "loss": 0.0067,
2818
+ "step": 3270
2819
+ },
2820
+ {
2821
+ "epoch": 4.927699530516432,
2822
+ "grad_norm": 0.8991699814796448,
2823
+ "learning_rate": 5.5803418303745917e-08,
2824
+ "loss": 0.008,
2825
+ "step": 3280
2826
+ },
2827
+ {
2828
+ "epoch": 4.942723004694836,
2829
+ "grad_norm": 0.015831077471375465,
2830
+ "learning_rate": 3.3760104757313284e-08,
2831
+ "loss": 0.0015,
2832
+ "step": 3290
2833
+ },
2834
+ {
2835
+ "epoch": 4.957746478873239,
2836
+ "grad_norm": 0.1406923532485962,
2837
+ "learning_rate": 1.7225492784345156e-08,
2838
+ "loss": 0.0078,
2839
+ "step": 3300
2840
+ },
2841
+ {
2842
+ "epoch": 4.957746478873239,
2843
+ "eval_loss": 0.06379479169845581,
2844
+ "eval_runtime": 157.8707,
2845
+ "eval_samples_per_second": 7.5,
2846
+ "eval_steps_per_second": 7.5,
2847
+ "step": 3300
2848
+ },
2849
+ {
2850
+ "epoch": 4.972769953051643,
2851
+ "grad_norm": 0.062291864305734634,
2852
+ "learning_rate": 6.201405300532148e-09,
2853
+ "loss": 0.006,
2854
+ "step": 3310
2855
+ },
2856
+ {
2857
+ "epoch": 4.987793427230047,
2858
+ "grad_norm": 2.030796527862549,
2859
+ "learning_rate": 6.890576946805282e-10,
2860
+ "loss": 0.0032,
2861
+ "step": 3320
2862
+ },
2863
+ {
2864
+ "epoch": 4.995305164319249,
2865
+ "step": 3325,
2866
+ "total_flos": 8.345060490986127e+17,
2867
+ "train_loss": 0.04504659976081965,
2868
+ "train_runtime": 35784.009,
2869
+ "train_samples_per_second": 1.488,
2870
+ "train_steps_per_second": 0.093
2871
+ }
2872
+ ],
2873
+ "logging_steps": 10,
2874
+ "max_steps": 3325,
2875
+ "num_input_tokens_seen": 0,
2876
+ "num_train_epochs": 5,
2877
+ "save_steps": 50,
2878
+ "stateful_callbacks": {
2879
+ "TrainerControl": {
2880
+ "args": {
2881
+ "should_epoch_stop": false,
2882
+ "should_evaluate": false,
2883
+ "should_log": false,
2884
+ "should_save": true,
2885
+ "should_training_stop": true
2886
+ },
2887
+ "attributes": {}
2888
+ }
2889
+ },
2890
+ "total_flos": 8.345060490986127e+17,
2891
+ "train_batch_size": 1,
2892
+ "trial_name": null,
2893
+ "trial_params": null
2894
+ }
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold6/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03b0cd71c66834275054495a138568ebb01c7c1079728a75fedd459b576a7e9c
3
+ size 5624
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold6/training_eval_loss.png ADDED
chchen__Llama-3.1-8B-Instruct-PsyCourse-fold6/training_loss.png ADDED