TaiGary commited on
Commit
0c4fbc9
·
verified ·
1 Parent(s): d9e74b3

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* 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
 
 
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
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: meta-llama/Llama-3.3-70B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: MATH_training_Qwen2.5-32B-Instruct
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
+ # MATH_training_Qwen2.5-32B-Instruct
18
+
19
+ This model is a fine-tuned version of [meta-llama/Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) on the MATH_training_Qwen2.5-32B-Instruct dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.1284
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
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - total_train_batch_size: 4
47
+ - total_eval_batch_size: 4
48
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 2.0
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:-----:|:----:|:---------------:|
57
+ | 0.117 | 1.25 | 200 | 0.1356 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - PEFT 0.12.0
63
+ - Transformers 4.46.1
64
+ - Pytorch 2.5.1+cu124
65
+ - Datasets 3.1.0
66
+ - Tokenizers 0.20.3
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-3.3-70B-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
+ "k_proj",
24
+ "o_proj",
25
+ "down_proj",
26
+ "q_proj",
27
+ "up_proj",
28
+ "v_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c64152f80f903e9061fee5e0dcf1596b73cf2ccfdac10e0dfc950245d9d602bd
3
+ size 207244392
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_loss": 0.12842905521392822,
4
+ "eval_runtime": 15.5557,
5
+ "eval_samples_per_second": 0.45,
6
+ "eval_steps_per_second": 0.129,
7
+ "total_flos": 1567061767618560.0,
8
+ "train_loss": 0.15366401586215944,
9
+ "train_runtime": 5710.924,
10
+ "train_samples_per_second": 0.224,
11
+ "train_steps_per_second": 0.056
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_loss": 0.12842905521392822,
4
+ "eval_runtime": 15.5557,
5
+ "eval_samples_per_second": 0.45,
6
+ "eval_steps_per_second": 0.129
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2066 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<|begin_of_text|>",
2053
+ "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",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|finetune_right_pad_id|>",
2063
+ "padding_side": "right",
2064
+ "split_special_tokens": false,
2065
+ "tokenizer_class": "PreTrainedTokenizerFast"
2066
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 1567061767618560.0,
4
+ "train_loss": 0.15366401586215944,
5
+ "train_runtime": 5710.924,
6
+ "train_samples_per_second": 0.224,
7
+ "train_steps_per_second": 0.056
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,322 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 320, "loss": 0.508, "lr": 3.125e-06, "epoch": 0.00625, "percentage": 0.31, "elapsed_time": "0:00:27", "remaining_time": "2:25:16"}
2
+ {"current_steps": 2, "total_steps": 320, "loss": 0.3989, "lr": 6.25e-06, "epoch": 0.0125, "percentage": 0.62, "elapsed_time": "0:00:44", "remaining_time": "1:57:50"}
3
+ {"current_steps": 3, "total_steps": 320, "loss": 0.3526, "lr": 9.375000000000001e-06, "epoch": 0.01875, "percentage": 0.94, "elapsed_time": "0:01:01", "remaining_time": "1:48:31"}
4
+ {"current_steps": 4, "total_steps": 320, "loss": 0.3927, "lr": 1.25e-05, "epoch": 0.025, "percentage": 1.25, "elapsed_time": "0:01:18", "remaining_time": "1:43:44"}
5
+ {"current_steps": 5, "total_steps": 320, "loss": 0.3232, "lr": 1.5625e-05, "epoch": 0.03125, "percentage": 1.56, "elapsed_time": "0:01:35", "remaining_time": "1:40:47"}
6
+ {"current_steps": 6, "total_steps": 320, "loss": 0.3486, "lr": 1.8750000000000002e-05, "epoch": 0.0375, "percentage": 1.88, "elapsed_time": "0:01:53", "remaining_time": "1:38:42"}
7
+ {"current_steps": 7, "total_steps": 320, "loss": 0.3894, "lr": 2.1875e-05, "epoch": 0.04375, "percentage": 2.19, "elapsed_time": "0:02:10", "remaining_time": "1:37:07"}
8
+ {"current_steps": 8, "total_steps": 320, "loss": 0.3606, "lr": 2.5e-05, "epoch": 0.05, "percentage": 2.5, "elapsed_time": "0:02:27", "remaining_time": "1:35:52"}
9
+ {"current_steps": 9, "total_steps": 320, "loss": 0.3323, "lr": 2.8125000000000003e-05, "epoch": 0.05625, "percentage": 2.81, "elapsed_time": "0:02:44", "remaining_time": "1:34:48"}
10
+ {"current_steps": 10, "total_steps": 320, "loss": 0.3689, "lr": 3.125e-05, "epoch": 0.0625, "percentage": 3.12, "elapsed_time": "0:03:01", "remaining_time": "1:33:54"}
11
+ {"current_steps": 11, "total_steps": 320, "loss": 0.3825, "lr": 3.4375e-05, "epoch": 0.06875, "percentage": 3.44, "elapsed_time": "0:03:18", "remaining_time": "1:33:06"}
12
+ {"current_steps": 12, "total_steps": 320, "loss": 0.3368, "lr": 3.7500000000000003e-05, "epoch": 0.075, "percentage": 3.75, "elapsed_time": "0:03:35", "remaining_time": "1:32:23"}
13
+ {"current_steps": 13, "total_steps": 320, "loss": 0.3345, "lr": 4.0625000000000005e-05, "epoch": 0.08125, "percentage": 4.06, "elapsed_time": "0:03:53", "remaining_time": "1:31:44"}
14
+ {"current_steps": 14, "total_steps": 320, "loss": 0.3176, "lr": 4.375e-05, "epoch": 0.0875, "percentage": 4.38, "elapsed_time": "0:04:10", "remaining_time": "1:31:19"}
15
+ {"current_steps": 15, "total_steps": 320, "loss": 0.3136, "lr": 4.6875e-05, "epoch": 0.09375, "percentage": 4.69, "elapsed_time": "0:04:27", "remaining_time": "1:30:45"}
16
+ {"current_steps": 16, "total_steps": 320, "loss": 0.2986, "lr": 5e-05, "epoch": 0.1, "percentage": 5.0, "elapsed_time": "0:04:44", "remaining_time": "1:30:13"}
17
+ {"current_steps": 17, "total_steps": 320, "loss": 0.2691, "lr": 5.3125000000000004e-05, "epoch": 0.10625, "percentage": 5.31, "elapsed_time": "0:05:02", "remaining_time": "1:29:48"}
18
+ {"current_steps": 18, "total_steps": 320, "loss": 0.3044, "lr": 5.6250000000000005e-05, "epoch": 0.1125, "percentage": 5.62, "elapsed_time": "0:05:19", "remaining_time": "1:29:19"}
19
+ {"current_steps": 19, "total_steps": 320, "loss": 0.232, "lr": 5.9375e-05, "epoch": 0.11875, "percentage": 5.94, "elapsed_time": "0:05:36", "remaining_time": "1:28:52"}
20
+ {"current_steps": 20, "total_steps": 320, "loss": 0.237, "lr": 6.25e-05, "epoch": 0.125, "percentage": 6.25, "elapsed_time": "0:05:53", "remaining_time": "1:28:25"}
21
+ {"current_steps": 21, "total_steps": 320, "loss": 0.2708, "lr": 6.562500000000001e-05, "epoch": 0.13125, "percentage": 6.56, "elapsed_time": "0:06:10", "remaining_time": "1:28:00"}
22
+ {"current_steps": 22, "total_steps": 320, "loss": 0.2334, "lr": 6.875e-05, "epoch": 0.1375, "percentage": 6.88, "elapsed_time": "0:06:27", "remaining_time": "1:27:35"}
23
+ {"current_steps": 23, "total_steps": 320, "loss": 0.1994, "lr": 7.1875e-05, "epoch": 0.14375, "percentage": 7.19, "elapsed_time": "0:06:45", "remaining_time": "1:27:11"}
24
+ {"current_steps": 24, "total_steps": 320, "loss": 0.2253, "lr": 7.500000000000001e-05, "epoch": 0.15, "percentage": 7.5, "elapsed_time": "0:07:02", "remaining_time": "1:26:47"}
25
+ {"current_steps": 25, "total_steps": 320, "loss": 0.2677, "lr": 7.8125e-05, "epoch": 0.15625, "percentage": 7.81, "elapsed_time": "0:07:19", "remaining_time": "1:26:24"}
26
+ {"current_steps": 26, "total_steps": 320, "loss": 0.1909, "lr": 8.125000000000001e-05, "epoch": 0.1625, "percentage": 8.12, "elapsed_time": "0:07:36", "remaining_time": "1:26:01"}
27
+ {"current_steps": 27, "total_steps": 320, "loss": 0.2352, "lr": 8.4375e-05, "epoch": 0.16875, "percentage": 8.44, "elapsed_time": "0:07:53", "remaining_time": "1:25:39"}
28
+ {"current_steps": 28, "total_steps": 320, "loss": 0.2312, "lr": 8.75e-05, "epoch": 0.175, "percentage": 8.75, "elapsed_time": "0:08:10", "remaining_time": "1:25:16"}
29
+ {"current_steps": 29, "total_steps": 320, "loss": 0.2571, "lr": 9.062500000000001e-05, "epoch": 0.18125, "percentage": 9.06, "elapsed_time": "0:08:27", "remaining_time": "1:24:54"}
30
+ {"current_steps": 30, "total_steps": 320, "loss": 0.2181, "lr": 9.375e-05, "epoch": 0.1875, "percentage": 9.38, "elapsed_time": "0:08:44", "remaining_time": "1:24:33"}
31
+ {"current_steps": 31, "total_steps": 320, "loss": 0.1768, "lr": 9.687500000000001e-05, "epoch": 0.19375, "percentage": 9.69, "elapsed_time": "0:09:01", "remaining_time": "1:24:12"}
32
+ {"current_steps": 32, "total_steps": 320, "loss": 0.1995, "lr": 0.0001, "epoch": 0.2, "percentage": 10.0, "elapsed_time": "0:09:19", "remaining_time": "1:23:51"}
33
+ {"current_steps": 33, "total_steps": 320, "loss": 0.2344, "lr": 9.999702525000749e-05, "epoch": 0.20625, "percentage": 10.31, "elapsed_time": "0:09:36", "remaining_time": "1:23:30"}
34
+ {"current_steps": 34, "total_steps": 320, "loss": 0.1581, "lr": 9.998810135399546e-05, "epoch": 0.2125, "percentage": 10.62, "elapsed_time": "0:09:53", "remaining_time": "1:23:10"}
35
+ {"current_steps": 35, "total_steps": 320, "loss": 0.2129, "lr": 9.997322937381829e-05, "epoch": 0.21875, "percentage": 10.94, "elapsed_time": "0:10:10", "remaining_time": "1:22:49"}
36
+ {"current_steps": 36, "total_steps": 320, "loss": 0.1837, "lr": 9.99524110790929e-05, "epoch": 0.225, "percentage": 11.25, "elapsed_time": "0:10:27", "remaining_time": "1:22:29"}
37
+ {"current_steps": 37, "total_steps": 320, "loss": 0.1881, "lr": 9.992564894698816e-05, "epoch": 0.23125, "percentage": 11.56, "elapsed_time": "0:10:44", "remaining_time": "1:22:09"}
38
+ {"current_steps": 38, "total_steps": 320, "loss": 0.1837, "lr": 9.989294616193017e-05, "epoch": 0.2375, "percentage": 11.88, "elapsed_time": "0:11:01", "remaining_time": "1:21:49"}
39
+ {"current_steps": 39, "total_steps": 320, "loss": 0.1918, "lr": 9.985430661522333e-05, "epoch": 0.24375, "percentage": 12.19, "elapsed_time": "0:11:18", "remaining_time": "1:21:29"}
40
+ {"current_steps": 40, "total_steps": 320, "loss": 0.1823, "lr": 9.980973490458728e-05, "epoch": 0.25, "percentage": 12.5, "elapsed_time": "0:11:35", "remaining_time": "1:21:10"}
41
+ {"current_steps": 41, "total_steps": 320, "loss": 0.2191, "lr": 9.975923633360985e-05, "epoch": 0.25625, "percentage": 12.81, "elapsed_time": "0:11:52", "remaining_time": "1:20:50"}
42
+ {"current_steps": 42, "total_steps": 320, "loss": 0.1671, "lr": 9.970281691111598e-05, "epoch": 0.2625, "percentage": 13.12, "elapsed_time": "0:12:09", "remaining_time": "1:20:31"}
43
+ {"current_steps": 43, "total_steps": 320, "loss": 0.1445, "lr": 9.964048335045275e-05, "epoch": 0.26875, "percentage": 13.44, "elapsed_time": "0:12:27", "remaining_time": "1:20:12"}
44
+ {"current_steps": 44, "total_steps": 320, "loss": 0.1883, "lr": 9.957224306869053e-05, "epoch": 0.275, "percentage": 13.75, "elapsed_time": "0:12:44", "remaining_time": "1:19:54"}
45
+ {"current_steps": 45, "total_steps": 320, "loss": 0.1912, "lr": 9.949810418574039e-05, "epoch": 0.28125, "percentage": 14.06, "elapsed_time": "0:13:01", "remaining_time": "1:19:35"}
46
+ {"current_steps": 46, "total_steps": 320, "loss": 0.1781, "lr": 9.941807552338804e-05, "epoch": 0.2875, "percentage": 14.37, "elapsed_time": "0:13:18", "remaining_time": "1:19:16"}
47
+ {"current_steps": 47, "total_steps": 320, "loss": 0.1741, "lr": 9.933216660424395e-05, "epoch": 0.29375, "percentage": 14.69, "elapsed_time": "0:13:35", "remaining_time": "1:18:58"}
48
+ {"current_steps": 48, "total_steps": 320, "loss": 0.1862, "lr": 9.924038765061042e-05, "epoch": 0.3, "percentage": 15.0, "elapsed_time": "0:13:52", "remaining_time": "1:18:39"}
49
+ {"current_steps": 49, "total_steps": 320, "loss": 0.1948, "lr": 9.914274958326505e-05, "epoch": 0.30625, "percentage": 15.31, "elapsed_time": "0:14:09", "remaining_time": "1:18:21"}
50
+ {"current_steps": 50, "total_steps": 320, "loss": 0.1387, "lr": 9.903926402016153e-05, "epoch": 0.3125, "percentage": 15.62, "elapsed_time": "0:14:27", "remaining_time": "1:18:02"}
51
+ {"current_steps": 51, "total_steps": 320, "loss": 0.1897, "lr": 9.892994327504693e-05, "epoch": 0.31875, "percentage": 15.94, "elapsed_time": "0:14:44", "remaining_time": "1:17:44"}
52
+ {"current_steps": 52, "total_steps": 320, "loss": 0.1878, "lr": 9.881480035599667e-05, "epoch": 0.325, "percentage": 16.25, "elapsed_time": "0:15:01", "remaining_time": "1:17:25"}
53
+ {"current_steps": 53, "total_steps": 320, "loss": 0.194, "lr": 9.869384896386668e-05, "epoch": 0.33125, "percentage": 16.56, "elapsed_time": "0:15:18", "remaining_time": "1:17:07"}
54
+ {"current_steps": 54, "total_steps": 320, "loss": 0.1881, "lr": 9.856710349066307e-05, "epoch": 0.3375, "percentage": 16.88, "elapsed_time": "0:15:35", "remaining_time": "1:16:48"}
55
+ {"current_steps": 55, "total_steps": 320, "loss": 0.2129, "lr": 9.843457901782967e-05, "epoch": 0.34375, "percentage": 17.19, "elapsed_time": "0:15:52", "remaining_time": "1:16:30"}
56
+ {"current_steps": 56, "total_steps": 320, "loss": 0.187, "lr": 9.829629131445342e-05, "epoch": 0.35, "percentage": 17.5, "elapsed_time": "0:16:09", "remaining_time": "1:16:11"}
57
+ {"current_steps": 57, "total_steps": 320, "loss": 0.1952, "lr": 9.815225683538814e-05, "epoch": 0.35625, "percentage": 17.81, "elapsed_time": "0:16:26", "remaining_time": "1:15:53"}
58
+ {"current_steps": 58, "total_steps": 320, "loss": 0.1722, "lr": 9.800249271929645e-05, "epoch": 0.3625, "percentage": 18.12, "elapsed_time": "0:16:43", "remaining_time": "1:15:35"}
59
+ {"current_steps": 59, "total_steps": 320, "loss": 0.1852, "lr": 9.784701678661045e-05, "epoch": 0.36875, "percentage": 18.44, "elapsed_time": "0:17:01", "remaining_time": "1:15:16"}
60
+ {"current_steps": 60, "total_steps": 320, "loss": 0.1861, "lr": 9.768584753741134e-05, "epoch": 0.375, "percentage": 18.75, "elapsed_time": "0:17:18", "remaining_time": "1:14:58"}
61
+ {"current_steps": 61, "total_steps": 320, "loss": 0.1681, "lr": 9.751900414922805e-05, "epoch": 0.38125, "percentage": 19.06, "elapsed_time": "0:17:35", "remaining_time": "1:14:40"}
62
+ {"current_steps": 62, "total_steps": 320, "loss": 0.1768, "lr": 9.73465064747553e-05, "epoch": 0.3875, "percentage": 19.38, "elapsed_time": "0:17:52", "remaining_time": "1:14:22"}
63
+ {"current_steps": 63, "total_steps": 320, "loss": 0.1592, "lr": 9.716837503949127e-05, "epoch": 0.39375, "percentage": 19.69, "elapsed_time": "0:18:09", "remaining_time": "1:14:04"}
64
+ {"current_steps": 64, "total_steps": 320, "loss": 0.2007, "lr": 9.698463103929542e-05, "epoch": 0.4, "percentage": 20.0, "elapsed_time": "0:18:26", "remaining_time": "1:13:46"}
65
+ {"current_steps": 65, "total_steps": 320, "loss": 0.1499, "lr": 9.67952963378663e-05, "epoch": 0.40625, "percentage": 20.31, "elapsed_time": "0:18:43", "remaining_time": "1:13:28"}
66
+ {"current_steps": 66, "total_steps": 320, "loss": 0.1702, "lr": 9.660039346413994e-05, "epoch": 0.4125, "percentage": 20.62, "elapsed_time": "0:19:00", "remaining_time": "1:13:10"}
67
+ {"current_steps": 67, "total_steps": 320, "loss": 0.172, "lr": 9.639994560960923e-05, "epoch": 0.41875, "percentage": 20.94, "elapsed_time": "0:19:17", "remaining_time": "1:12:52"}
68
+ {"current_steps": 68, "total_steps": 320, "loss": 0.1363, "lr": 9.619397662556435e-05, "epoch": 0.425, "percentage": 21.25, "elapsed_time": "0:19:35", "remaining_time": "1:12:34"}
69
+ {"current_steps": 69, "total_steps": 320, "loss": 0.1664, "lr": 9.598251102025461e-05, "epoch": 0.43125, "percentage": 21.56, "elapsed_time": "0:19:52", "remaining_time": "1:12:16"}
70
+ {"current_steps": 70, "total_steps": 320, "loss": 0.1439, "lr": 9.576557395597236e-05, "epoch": 0.4375, "percentage": 21.88, "elapsed_time": "0:20:09", "remaining_time": "1:11:58"}
71
+ {"current_steps": 71, "total_steps": 320, "loss": 0.1526, "lr": 9.554319124605879e-05, "epoch": 0.44375, "percentage": 22.19, "elapsed_time": "0:20:26", "remaining_time": "1:11:41"}
72
+ {"current_steps": 72, "total_steps": 320, "loss": 0.1514, "lr": 9.53153893518325e-05, "epoch": 0.45, "percentage": 22.5, "elapsed_time": "0:20:43", "remaining_time": "1:11:23"}
73
+ {"current_steps": 73, "total_steps": 320, "loss": 0.1481, "lr": 9.508219537944081e-05, "epoch": 0.45625, "percentage": 22.81, "elapsed_time": "0:21:00", "remaining_time": "1:11:05"}
74
+ {"current_steps": 74, "total_steps": 320, "loss": 0.1552, "lr": 9.484363707663442e-05, "epoch": 0.4625, "percentage": 23.12, "elapsed_time": "0:21:17", "remaining_time": "1:10:48"}
75
+ {"current_steps": 75, "total_steps": 320, "loss": 0.1533, "lr": 9.459974282946571e-05, "epoch": 0.46875, "percentage": 23.44, "elapsed_time": "0:21:35", "remaining_time": "1:10:30"}
76
+ {"current_steps": 76, "total_steps": 320, "loss": 0.15, "lr": 9.435054165891109e-05, "epoch": 0.475, "percentage": 23.75, "elapsed_time": "0:21:52", "remaining_time": "1:10:12"}
77
+ {"current_steps": 77, "total_steps": 320, "loss": 0.1633, "lr": 9.409606321741775e-05, "epoch": 0.48125, "percentage": 24.06, "elapsed_time": "0:22:09", "remaining_time": "1:09:55"}
78
+ {"current_steps": 78, "total_steps": 320, "loss": 0.1675, "lr": 9.38363377853754e-05, "epoch": 0.4875, "percentage": 24.38, "elapsed_time": "0:22:26", "remaining_time": "1:09:37"}
79
+ {"current_steps": 79, "total_steps": 320, "loss": 0.1649, "lr": 9.357139626751308e-05, "epoch": 0.49375, "percentage": 24.69, "elapsed_time": "0:22:43", "remaining_time": "1:09:19"}
80
+ {"current_steps": 80, "total_steps": 320, "loss": 0.1818, "lr": 9.330127018922194e-05, "epoch": 0.5, "percentage": 25.0, "elapsed_time": "0:23:00", "remaining_time": "1:09:02"}
81
+ {"current_steps": 81, "total_steps": 320, "loss": 0.1535, "lr": 9.302599169280395e-05, "epoch": 0.50625, "percentage": 25.31, "elapsed_time": "0:23:17", "remaining_time": "1:08:44"}
82
+ {"current_steps": 82, "total_steps": 320, "loss": 0.1573, "lr": 9.274559353364734e-05, "epoch": 0.5125, "percentage": 25.62, "elapsed_time": "0:23:34", "remaining_time": "1:08:26"}
83
+ {"current_steps": 83, "total_steps": 320, "loss": 0.1552, "lr": 9.246010907632895e-05, "epoch": 0.51875, "percentage": 25.94, "elapsed_time": "0:23:51", "remaining_time": "1:08:08"}
84
+ {"current_steps": 84, "total_steps": 320, "loss": 0.1348, "lr": 9.21695722906443e-05, "epoch": 0.525, "percentage": 26.25, "elapsed_time": "0:24:08", "remaining_time": "1:07:50"}
85
+ {"current_steps": 85, "total_steps": 320, "loss": 0.1541, "lr": 9.18740177475654e-05, "epoch": 0.53125, "percentage": 26.56, "elapsed_time": "0:24:26", "remaining_time": "1:07:33"}
86
+ {"current_steps": 86, "total_steps": 320, "loss": 0.1584, "lr": 9.157348061512727e-05, "epoch": 0.5375, "percentage": 26.88, "elapsed_time": "0:24:43", "remaining_time": "1:07:15"}
87
+ {"current_steps": 87, "total_steps": 320, "loss": 0.1558, "lr": 9.126799665424319e-05, "epoch": 0.54375, "percentage": 27.19, "elapsed_time": "0:25:00", "remaining_time": "1:06:57"}
88
+ {"current_steps": 88, "total_steps": 320, "loss": 0.178, "lr": 9.09576022144496e-05, "epoch": 0.55, "percentage": 27.5, "elapsed_time": "0:25:17", "remaining_time": "1:06:39"}
89
+ {"current_steps": 89, "total_steps": 320, "loss": 0.1382, "lr": 9.064233422958077e-05, "epoch": 0.55625, "percentage": 27.81, "elapsed_time": "0:25:34", "remaining_time": "1:06:22"}
90
+ {"current_steps": 90, "total_steps": 320, "loss": 0.2028, "lr": 9.032223021337414e-05, "epoch": 0.5625, "percentage": 28.12, "elapsed_time": "0:25:51", "remaining_time": "1:06:04"}
91
+ {"current_steps": 91, "total_steps": 320, "loss": 0.1564, "lr": 8.999732825500648e-05, "epoch": 0.56875, "percentage": 28.44, "elapsed_time": "0:26:08", "remaining_time": "1:05:46"}
92
+ {"current_steps": 92, "total_steps": 320, "loss": 0.1748, "lr": 8.966766701456177e-05, "epoch": 0.575, "percentage": 28.75, "elapsed_time": "0:26:25", "remaining_time": "1:05:29"}
93
+ {"current_steps": 93, "total_steps": 320, "loss": 0.166, "lr": 8.933328571843084e-05, "epoch": 0.58125, "percentage": 29.06, "elapsed_time": "0:26:42", "remaining_time": "1:05:11"}
94
+ {"current_steps": 94, "total_steps": 320, "loss": 0.1371, "lr": 8.899422415464409e-05, "epoch": 0.5875, "percentage": 29.38, "elapsed_time": "0:26:59", "remaining_time": "1:04:54"}
95
+ {"current_steps": 95, "total_steps": 320, "loss": 0.1695, "lr": 8.865052266813685e-05, "epoch": 0.59375, "percentage": 29.69, "elapsed_time": "0:27:16", "remaining_time": "1:04:36"}
96
+ {"current_steps": 96, "total_steps": 320, "loss": 0.1397, "lr": 8.83022221559489e-05, "epoch": 0.6, "percentage": 30.0, "elapsed_time": "0:27:33", "remaining_time": "1:04:18"}
97
+ {"current_steps": 97, "total_steps": 320, "loss": 0.1475, "lr": 8.79493640623581e-05, "epoch": 0.60625, "percentage": 30.31, "elapsed_time": "0:27:50", "remaining_time": "1:04:01"}
98
+ {"current_steps": 98, "total_steps": 320, "loss": 0.1455, "lr": 8.759199037394887e-05, "epoch": 0.6125, "percentage": 30.63, "elapsed_time": "0:28:08", "remaining_time": "1:03:44"}
99
+ {"current_steps": 99, "total_steps": 320, "loss": 0.155, "lr": 8.723014361461632e-05, "epoch": 0.61875, "percentage": 30.94, "elapsed_time": "0:28:25", "remaining_time": "1:03:27"}
100
+ {"current_steps": 100, "total_steps": 320, "loss": 0.14, "lr": 8.68638668405062e-05, "epoch": 0.625, "percentage": 31.25, "elapsed_time": "0:28:43", "remaining_time": "1:03:11"}
101
+ {"current_steps": 101, "total_steps": 320, "loss": 0.1268, "lr": 8.649320363489179e-05, "epoch": 0.63125, "percentage": 31.56, "elapsed_time": "0:29:00", "remaining_time": "1:02:53"}
102
+ {"current_steps": 102, "total_steps": 320, "loss": 0.174, "lr": 8.611819810298778e-05, "epoch": 0.6375, "percentage": 31.87, "elapsed_time": "0:29:17", "remaining_time": "1:02:36"}
103
+ {"current_steps": 103, "total_steps": 320, "loss": 0.1314, "lr": 8.573889486670233e-05, "epoch": 0.64375, "percentage": 32.19, "elapsed_time": "0:29:34", "remaining_time": "1:02:19"}
104
+ {"current_steps": 104, "total_steps": 320, "loss": 0.1563, "lr": 8.535533905932738e-05, "epoch": 0.65, "percentage": 32.5, "elapsed_time": "0:29:51", "remaining_time": "1:02:01"}
105
+ {"current_steps": 105, "total_steps": 320, "loss": 0.2076, "lr": 8.496757632016836e-05, "epoch": 0.65625, "percentage": 32.81, "elapsed_time": "0:30:09", "remaining_time": "1:01:44"}
106
+ {"current_steps": 106, "total_steps": 320, "loss": 0.1516, "lr": 8.457565278911348e-05, "epoch": 0.6625, "percentage": 33.12, "elapsed_time": "0:30:26", "remaining_time": "1:01:26"}
107
+ {"current_steps": 107, "total_steps": 320, "loss": 0.163, "lr": 8.417961510114356e-05, "epoch": 0.66875, "percentage": 33.44, "elapsed_time": "0:30:43", "remaining_time": "1:01:09"}
108
+ {"current_steps": 108, "total_steps": 320, "loss": 0.1351, "lr": 8.377951038078302e-05, "epoch": 0.675, "percentage": 33.75, "elapsed_time": "0:31:00", "remaining_time": "1:00:51"}
109
+ {"current_steps": 109, "total_steps": 320, "loss": 0.1181, "lr": 8.337538623649237e-05, "epoch": 0.68125, "percentage": 34.06, "elapsed_time": "0:31:17", "remaining_time": "1:00:34"}
110
+ {"current_steps": 110, "total_steps": 320, "loss": 0.1404, "lr": 8.296729075500344e-05, "epoch": 0.6875, "percentage": 34.38, "elapsed_time": "0:31:34", "remaining_time": "1:00:16"}
111
+ {"current_steps": 111, "total_steps": 320, "loss": 0.1746, "lr": 8.255527249559746e-05, "epoch": 0.69375, "percentage": 34.69, "elapsed_time": "0:31:51", "remaining_time": "0:59:59"}
112
+ {"current_steps": 112, "total_steps": 320, "loss": 0.1724, "lr": 8.213938048432697e-05, "epoch": 0.7, "percentage": 35.0, "elapsed_time": "0:32:08", "remaining_time": "0:59:41"}
113
+ {"current_steps": 113, "total_steps": 320, "loss": 0.1469, "lr": 8.171966420818228e-05, "epoch": 0.70625, "percentage": 35.31, "elapsed_time": "0:32:25", "remaining_time": "0:59:24"}
114
+ {"current_steps": 114, "total_steps": 320, "loss": 0.1692, "lr": 8.129617360920296e-05, "epoch": 0.7125, "percentage": 35.62, "elapsed_time": "0:32:42", "remaining_time": "0:59:06"}
115
+ {"current_steps": 115, "total_steps": 320, "loss": 0.145, "lr": 8.086895907853526e-05, "epoch": 0.71875, "percentage": 35.94, "elapsed_time": "0:32:59", "remaining_time": "0:58:49"}
116
+ {"current_steps": 116, "total_steps": 320, "loss": 0.1401, "lr": 8.043807145043604e-05, "epoch": 0.725, "percentage": 36.25, "elapsed_time": "0:33:17", "remaining_time": "0:58:31"}
117
+ {"current_steps": 117, "total_steps": 320, "loss": 0.1289, "lr": 8.000356199622405e-05, "epoch": 0.73125, "percentage": 36.56, "elapsed_time": "0:33:34", "remaining_time": "0:58:14"}
118
+ {"current_steps": 118, "total_steps": 320, "loss": 0.1191, "lr": 7.956548241817912e-05, "epoch": 0.7375, "percentage": 36.88, "elapsed_time": "0:33:51", "remaining_time": "0:57:57"}
119
+ {"current_steps": 119, "total_steps": 320, "loss": 0.1679, "lr": 7.912388484339012e-05, "epoch": 0.74375, "percentage": 37.19, "elapsed_time": "0:34:08", "remaining_time": "0:57:39"}
120
+ {"current_steps": 120, "total_steps": 320, "loss": 0.1455, "lr": 7.86788218175523e-05, "epoch": 0.75, "percentage": 37.5, "elapsed_time": "0:34:25", "remaining_time": "0:57:22"}
121
+ {"current_steps": 121, "total_steps": 320, "loss": 0.1387, "lr": 7.823034629871503e-05, "epoch": 0.75625, "percentage": 37.81, "elapsed_time": "0:34:42", "remaining_time": "0:57:04"}
122
+ {"current_steps": 122, "total_steps": 320, "loss": 0.1595, "lr": 7.777851165098012e-05, "epoch": 0.7625, "percentage": 38.12, "elapsed_time": "0:34:59", "remaining_time": "0:56:47"}
123
+ {"current_steps": 123, "total_steps": 320, "loss": 0.1591, "lr": 7.732337163815217e-05, "epoch": 0.76875, "percentage": 38.44, "elapsed_time": "0:35:16", "remaining_time": "0:56:30"}
124
+ {"current_steps": 124, "total_steps": 320, "loss": 0.1623, "lr": 7.68649804173412e-05, "epoch": 0.775, "percentage": 38.75, "elapsed_time": "0:35:33", "remaining_time": "0:56:12"}
125
+ {"current_steps": 125, "total_steps": 320, "loss": 0.155, "lr": 7.64033925325184e-05, "epoch": 0.78125, "percentage": 39.06, "elapsed_time": "0:35:51", "remaining_time": "0:55:55"}
126
+ {"current_steps": 126, "total_steps": 320, "loss": 0.1524, "lr": 7.593866290802608e-05, "epoch": 0.7875, "percentage": 39.38, "elapsed_time": "0:36:08", "remaining_time": "0:55:38"}
127
+ {"current_steps": 127, "total_steps": 320, "loss": 0.1599, "lr": 7.54708468420421e-05, "epoch": 0.79375, "percentage": 39.69, "elapsed_time": "0:36:25", "remaining_time": "0:55:20"}
128
+ {"current_steps": 128, "total_steps": 320, "loss": 0.1554, "lr": 7.500000000000001e-05, "epoch": 0.8, "percentage": 40.0, "elapsed_time": "0:36:42", "remaining_time": "0:55:03"}
129
+ {"current_steps": 129, "total_steps": 320, "loss": 0.1538, "lr": 7.45261784079654e-05, "epoch": 0.80625, "percentage": 40.31, "elapsed_time": "0:36:59", "remaining_time": "0:54:46"}
130
+ {"current_steps": 130, "total_steps": 320, "loss": 0.1525, "lr": 7.404943844596939e-05, "epoch": 0.8125, "percentage": 40.62, "elapsed_time": "0:37:16", "remaining_time": "0:54:29"}
131
+ {"current_steps": 131, "total_steps": 320, "loss": 0.1478, "lr": 7.35698368412999e-05, "epoch": 0.81875, "percentage": 40.94, "elapsed_time": "0:37:33", "remaining_time": "0:54:11"}
132
+ {"current_steps": 132, "total_steps": 320, "loss": 0.1484, "lr": 7.308743066175172e-05, "epoch": 0.825, "percentage": 41.25, "elapsed_time": "0:37:50", "remaining_time": "0:53:54"}
133
+ {"current_steps": 133, "total_steps": 320, "loss": 0.124, "lr": 7.2602277308836e-05, "epoch": 0.83125, "percentage": 41.56, "elapsed_time": "0:38:08", "remaining_time": "0:53:36"}
134
+ {"current_steps": 134, "total_steps": 320, "loss": 0.1422, "lr": 7.211443451095007e-05, "epoch": 0.8375, "percentage": 41.88, "elapsed_time": "0:38:25", "remaining_time": "0:53:19"}
135
+ {"current_steps": 135, "total_steps": 320, "loss": 0.1488, "lr": 7.162396031650831e-05, "epoch": 0.84375, "percentage": 42.19, "elapsed_time": "0:38:42", "remaining_time": "0:53:02"}
136
+ {"current_steps": 136, "total_steps": 320, "loss": 0.1227, "lr": 7.113091308703498e-05, "epoch": 0.85, "percentage": 42.5, "elapsed_time": "0:38:59", "remaining_time": "0:52:44"}
137
+ {"current_steps": 137, "total_steps": 320, "loss": 0.1397, "lr": 7.063535149021973e-05, "epoch": 0.85625, "percentage": 42.81, "elapsed_time": "0:39:16", "remaining_time": "0:52:27"}
138
+ {"current_steps": 138, "total_steps": 320, "loss": 0.1489, "lr": 7.013733449293687e-05, "epoch": 0.8625, "percentage": 43.12, "elapsed_time": "0:39:33", "remaining_time": "0:52:10"}
139
+ {"current_steps": 139, "total_steps": 320, "loss": 0.1625, "lr": 6.96369213542287e-05, "epoch": 0.86875, "percentage": 43.44, "elapsed_time": "0:39:50", "remaining_time": "0:51:52"}
140
+ {"current_steps": 140, "total_steps": 320, "loss": 0.1575, "lr": 6.91341716182545e-05, "epoch": 0.875, "percentage": 43.75, "elapsed_time": "0:40:07", "remaining_time": "0:51:35"}
141
+ {"current_steps": 141, "total_steps": 320, "loss": 0.1367, "lr": 6.862914510720515e-05, "epoch": 0.88125, "percentage": 44.06, "elapsed_time": "0:40:24", "remaining_time": "0:51:18"}
142
+ {"current_steps": 142, "total_steps": 320, "loss": 0.1269, "lr": 6.812190191418508e-05, "epoch": 0.8875, "percentage": 44.38, "elapsed_time": "0:40:41", "remaining_time": "0:51:00"}
143
+ {"current_steps": 143, "total_steps": 320, "loss": 0.1653, "lr": 6.761250239606169e-05, "epoch": 0.89375, "percentage": 44.69, "elapsed_time": "0:40:58", "remaining_time": "0:50:43"}
144
+ {"current_steps": 144, "total_steps": 320, "loss": 0.163, "lr": 6.710100716628344e-05, "epoch": 0.9, "percentage": 45.0, "elapsed_time": "0:41:15", "remaining_time": "0:50:25"}
145
+ {"current_steps": 145, "total_steps": 320, "loss": 0.1372, "lr": 6.658747708766762e-05, "epoch": 0.90625, "percentage": 45.31, "elapsed_time": "0:41:32", "remaining_time": "0:50:08"}
146
+ {"current_steps": 146, "total_steps": 320, "loss": 0.1666, "lr": 6.607197326515808e-05, "epoch": 0.9125, "percentage": 45.62, "elapsed_time": "0:41:49", "remaining_time": "0:49:51"}
147
+ {"current_steps": 147, "total_steps": 320, "loss": 0.1608, "lr": 6.555455703855454e-05, "epoch": 0.91875, "percentage": 45.94, "elapsed_time": "0:42:07", "remaining_time": "0:49:34"}
148
+ {"current_steps": 148, "total_steps": 320, "loss": 0.1358, "lr": 6.503528997521366e-05, "epoch": 0.925, "percentage": 46.25, "elapsed_time": "0:42:24", "remaining_time": "0:49:16"}
149
+ {"current_steps": 149, "total_steps": 320, "loss": 0.1467, "lr": 6.451423386272312e-05, "epoch": 0.93125, "percentage": 46.56, "elapsed_time": "0:42:41", "remaining_time": "0:48:59"}
150
+ {"current_steps": 150, "total_steps": 320, "loss": 0.1602, "lr": 6.399145070154961e-05, "epoch": 0.9375, "percentage": 46.88, "elapsed_time": "0:42:58", "remaining_time": "0:48:42"}
151
+ {"current_steps": 151, "total_steps": 320, "loss": 0.1491, "lr": 6.346700269766132e-05, "epoch": 0.94375, "percentage": 47.19, "elapsed_time": "0:43:15", "remaining_time": "0:48:24"}
152
+ {"current_steps": 152, "total_steps": 320, "loss": 0.1503, "lr": 6.294095225512603e-05, "epoch": 0.95, "percentage": 47.5, "elapsed_time": "0:43:32", "remaining_time": "0:48:07"}
153
+ {"current_steps": 153, "total_steps": 320, "loss": 0.1394, "lr": 6.241336196868582e-05, "epoch": 0.95625, "percentage": 47.81, "elapsed_time": "0:43:49", "remaining_time": "0:47:50"}
154
+ {"current_steps": 154, "total_steps": 320, "loss": 0.1471, "lr": 6.188429461630866e-05, "epoch": 0.9625, "percentage": 48.12, "elapsed_time": "0:44:06", "remaining_time": "0:47:33"}
155
+ {"current_steps": 155, "total_steps": 320, "loss": 0.1163, "lr": 6.135381315171867e-05, "epoch": 0.96875, "percentage": 48.44, "elapsed_time": "0:44:24", "remaining_time": "0:47:15"}
156
+ {"current_steps": 156, "total_steps": 320, "loss": 0.1414, "lr": 6.0821980696905146e-05, "epoch": 0.975, "percentage": 48.75, "elapsed_time": "0:44:41", "remaining_time": "0:46:58"}
157
+ {"current_steps": 157, "total_steps": 320, "loss": 0.1371, "lr": 6.0288860534611745e-05, "epoch": 0.98125, "percentage": 49.06, "elapsed_time": "0:44:58", "remaining_time": "0:46:41"}
158
+ {"current_steps": 158, "total_steps": 320, "loss": 0.1591, "lr": 5.9754516100806423e-05, "epoch": 0.9875, "percentage": 49.38, "elapsed_time": "0:45:15", "remaining_time": "0:46:24"}
159
+ {"current_steps": 159, "total_steps": 320, "loss": 0.1136, "lr": 5.9219010977133173e-05, "epoch": 0.99375, "percentage": 49.69, "elapsed_time": "0:45:32", "remaining_time": "0:46:06"}
160
+ {"current_steps": 160, "total_steps": 320, "loss": 0.1355, "lr": 5.868240888334653e-05, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:45:49", "remaining_time": "0:45:49"}
161
+ {"current_steps": 161, "total_steps": 320, "loss": 0.1389, "lr": 5.814477366972945e-05, "epoch": 1.00625, "percentage": 50.31, "elapsed_time": "0:46:06", "remaining_time": "0:45:32"}
162
+ {"current_steps": 162, "total_steps": 320, "loss": 0.1278, "lr": 5.7606169309495836e-05, "epoch": 1.0125, "percentage": 50.62, "elapsed_time": "0:46:23", "remaining_time": "0:45:15"}
163
+ {"current_steps": 163, "total_steps": 320, "loss": 0.1266, "lr": 5.706665989117839e-05, "epoch": 1.01875, "percentage": 50.94, "elapsed_time": "0:46:40", "remaining_time": "0:44:57"}
164
+ {"current_steps": 164, "total_steps": 320, "loss": 0.1344, "lr": 5.6526309611002594e-05, "epoch": 1.025, "percentage": 51.25, "elapsed_time": "0:46:58", "remaining_time": "0:44:40"}
165
+ {"current_steps": 165, "total_steps": 320, "loss": 0.11, "lr": 5.5985182765248126e-05, "epoch": 1.03125, "percentage": 51.56, "elapsed_time": "0:47:15", "remaining_time": "0:44:23"}
166
+ {"current_steps": 166, "total_steps": 320, "loss": 0.1177, "lr": 5.544334374259823e-05, "epoch": 1.0375, "percentage": 51.88, "elapsed_time": "0:47:32", "remaining_time": "0:44:05"}
167
+ {"current_steps": 167, "total_steps": 320, "loss": 0.1519, "lr": 5.490085701647805e-05, "epoch": 1.04375, "percentage": 52.19, "elapsed_time": "0:47:49", "remaining_time": "0:43:48"}
168
+ {"current_steps": 168, "total_steps": 320, "loss": 0.1388, "lr": 5.435778713738292e-05, "epoch": 1.05, "percentage": 52.5, "elapsed_time": "0:48:06", "remaining_time": "0:43:31"}
169
+ {"current_steps": 169, "total_steps": 320, "loss": 0.1315, "lr": 5.381419872519763e-05, "epoch": 1.05625, "percentage": 52.81, "elapsed_time": "0:48:23", "remaining_time": "0:43:14"}
170
+ {"current_steps": 170, "total_steps": 320, "loss": 0.1513, "lr": 5.327015646150716e-05, "epoch": 1.0625, "percentage": 53.12, "elapsed_time": "0:48:40", "remaining_time": "0:42:56"}
171
+ {"current_steps": 171, "total_steps": 320, "loss": 0.1265, "lr": 5.2725725081900325e-05, "epoch": 1.06875, "percentage": 53.44, "elapsed_time": "0:48:57", "remaining_time": "0:42:39"}
172
+ {"current_steps": 172, "total_steps": 320, "loss": 0.1346, "lr": 5.218096936826681e-05, "epoch": 1.075, "percentage": 53.75, "elapsed_time": "0:49:14", "remaining_time": "0:42:22"}
173
+ {"current_steps": 173, "total_steps": 320, "loss": 0.1129, "lr": 5.1635954141088813e-05, "epoch": 1.08125, "percentage": 54.06, "elapsed_time": "0:49:31", "remaining_time": "0:42:05"}
174
+ {"current_steps": 174, "total_steps": 320, "loss": 0.1031, "lr": 5.1090744251728064e-05, "epoch": 1.0875, "percentage": 54.37, "elapsed_time": "0:49:48", "remaining_time": "0:41:47"}
175
+ {"current_steps": 175, "total_steps": 320, "loss": 0.1093, "lr": 5.054540457470912e-05, "epoch": 1.09375, "percentage": 54.69, "elapsed_time": "0:50:05", "remaining_time": "0:41:30"}
176
+ {"current_steps": 176, "total_steps": 320, "loss": 0.1283, "lr": 5e-05, "epoch": 1.1, "percentage": 55.0, "elapsed_time": "0:50:22", "remaining_time": "0:41:13"}
177
+ {"current_steps": 177, "total_steps": 320, "loss": 0.1163, "lr": 4.945459542529089e-05, "epoch": 1.10625, "percentage": 55.31, "elapsed_time": "0:50:40", "remaining_time": "0:40:56"}
178
+ {"current_steps": 178, "total_steps": 320, "loss": 0.1188, "lr": 4.890925574827195e-05, "epoch": 1.1125, "percentage": 55.62, "elapsed_time": "0:50:57", "remaining_time": "0:40:38"}
179
+ {"current_steps": 179, "total_steps": 320, "loss": 0.1742, "lr": 4.83640458589112e-05, "epoch": 1.11875, "percentage": 55.94, "elapsed_time": "0:51:14", "remaining_time": "0:40:21"}
180
+ {"current_steps": 180, "total_steps": 320, "loss": 0.1217, "lr": 4.781903063173321e-05, "epoch": 1.125, "percentage": 56.25, "elapsed_time": "0:51:31", "remaining_time": "0:40:04"}
181
+ {"current_steps": 181, "total_steps": 320, "loss": 0.1047, "lr": 4.727427491809968e-05, "epoch": 1.13125, "percentage": 56.56, "elapsed_time": "0:51:48", "remaining_time": "0:39:47"}
182
+ {"current_steps": 182, "total_steps": 320, "loss": 0.1288, "lr": 4.6729843538492847e-05, "epoch": 1.1375, "percentage": 56.88, "elapsed_time": "0:52:05", "remaining_time": "0:39:30"}
183
+ {"current_steps": 183, "total_steps": 320, "loss": 0.1123, "lr": 4.618580127480238e-05, "epoch": 1.14375, "percentage": 57.19, "elapsed_time": "0:52:22", "remaining_time": "0:39:12"}
184
+ {"current_steps": 184, "total_steps": 320, "loss": 0.1096, "lr": 4.564221286261709e-05, "epoch": 1.15, "percentage": 57.5, "elapsed_time": "0:52:40", "remaining_time": "0:38:55"}
185
+ {"current_steps": 185, "total_steps": 320, "loss": 0.1237, "lr": 4.509914298352197e-05, "epoch": 1.15625, "percentage": 57.81, "elapsed_time": "0:52:57", "remaining_time": "0:38:38"}
186
+ {"current_steps": 186, "total_steps": 320, "loss": 0.1256, "lr": 4.4556656257401786e-05, "epoch": 1.1625, "percentage": 58.13, "elapsed_time": "0:53:14", "remaining_time": "0:38:21"}
187
+ {"current_steps": 187, "total_steps": 320, "loss": 0.087, "lr": 4.4014817234751885e-05, "epoch": 1.16875, "percentage": 58.44, "elapsed_time": "0:53:32", "remaining_time": "0:38:04"}
188
+ {"current_steps": 188, "total_steps": 320, "loss": 0.132, "lr": 4.347369038899744e-05, "epoch": 1.175, "percentage": 58.75, "elapsed_time": "0:53:49", "remaining_time": "0:37:47"}
189
+ {"current_steps": 189, "total_steps": 320, "loss": 0.1342, "lr": 4.2933340108821644e-05, "epoch": 1.18125, "percentage": 59.06, "elapsed_time": "0:54:06", "remaining_time": "0:37:30"}
190
+ {"current_steps": 190, "total_steps": 320, "loss": 0.1144, "lr": 4.239383069050417e-05, "epoch": 1.1875, "percentage": 59.38, "elapsed_time": "0:54:23", "remaining_time": "0:37:13"}
191
+ {"current_steps": 191, "total_steps": 320, "loss": 0.11, "lr": 4.185522633027057e-05, "epoch": 1.19375, "percentage": 59.69, "elapsed_time": "0:54:40", "remaining_time": "0:36:55"}
192
+ {"current_steps": 192, "total_steps": 320, "loss": 0.1256, "lr": 4.131759111665349e-05, "epoch": 1.2, "percentage": 60.0, "elapsed_time": "0:54:57", "remaining_time": "0:36:38"}
193
+ {"current_steps": 193, "total_steps": 320, "loss": 0.1387, "lr": 4.078098902286683e-05, "epoch": 1.20625, "percentage": 60.31, "elapsed_time": "0:55:15", "remaining_time": "0:36:21"}
194
+ {"current_steps": 194, "total_steps": 320, "loss": 0.1154, "lr": 4.0245483899193595e-05, "epoch": 1.2125, "percentage": 60.62, "elapsed_time": "0:55:32", "remaining_time": "0:36:04"}
195
+ {"current_steps": 195, "total_steps": 320, "loss": 0.1277, "lr": 3.971113946538826e-05, "epoch": 1.21875, "percentage": 60.94, "elapsed_time": "0:55:49", "remaining_time": "0:35:46"}
196
+ {"current_steps": 196, "total_steps": 320, "loss": 0.1245, "lr": 3.917801930309486e-05, "epoch": 1.225, "percentage": 61.25, "elapsed_time": "0:56:06", "remaining_time": "0:35:29"}
197
+ {"current_steps": 197, "total_steps": 320, "loss": 0.1149, "lr": 3.864618684828134e-05, "epoch": 1.23125, "percentage": 61.56, "elapsed_time": "0:56:23", "remaining_time": "0:35:12"}
198
+ {"current_steps": 198, "total_steps": 320, "loss": 0.1137, "lr": 3.8115705383691355e-05, "epoch": 1.2375, "percentage": 61.88, "elapsed_time": "0:56:40", "remaining_time": "0:34:55"}
199
+ {"current_steps": 199, "total_steps": 320, "loss": 0.1411, "lr": 3.758663803131418e-05, "epoch": 1.24375, "percentage": 62.19, "elapsed_time": "0:56:57", "remaining_time": "0:34:38"}
200
+ {"current_steps": 200, "total_steps": 320, "loss": 0.117, "lr": 3.705904774487396e-05, "epoch": 1.25, "percentage": 62.5, "elapsed_time": "0:57:14", "remaining_time": "0:34:20"}
201
+ {"current_steps": 200, "total_steps": 320, "eval_loss": 0.13555637001991272, "epoch": 1.25, "percentage": 62.5, "elapsed_time": "0:57:29", "remaining_time": "0:34:29"}
202
+ {"current_steps": 201, "total_steps": 320, "loss": 0.1317, "lr": 3.65329973023387e-05, "epoch": 1.25625, "percentage": 62.81, "elapsed_time": "0:57:47", "remaining_time": "0:34:13"}
203
+ {"current_steps": 202, "total_steps": 320, "loss": 0.1485, "lr": 3.60085492984504e-05, "epoch": 1.2625, "percentage": 63.12, "elapsed_time": "0:58:04", "remaining_time": "0:33:55"}
204
+ {"current_steps": 203, "total_steps": 320, "loss": 0.127, "lr": 3.5485766137276894e-05, "epoch": 1.26875, "percentage": 63.44, "elapsed_time": "0:58:22", "remaining_time": "0:33:38"}
205
+ {"current_steps": 204, "total_steps": 320, "loss": 0.1298, "lr": 3.4964710024786354e-05, "epoch": 1.275, "percentage": 63.75, "elapsed_time": "0:58:39", "remaining_time": "0:33:21"}
206
+ {"current_steps": 205, "total_steps": 320, "loss": 0.1218, "lr": 3.4445442961445464e-05, "epoch": 1.28125, "percentage": 64.06, "elapsed_time": "0:58:56", "remaining_time": "0:33:03"}
207
+ {"current_steps": 206, "total_steps": 320, "loss": 0.0911, "lr": 3.392802673484193e-05, "epoch": 1.2875, "percentage": 64.38, "elapsed_time": "0:59:13", "remaining_time": "0:32:46"}
208
+ {"current_steps": 207, "total_steps": 320, "loss": 0.1105, "lr": 3.341252291233241e-05, "epoch": 1.29375, "percentage": 64.69, "elapsed_time": "0:59:30", "remaining_time": "0:32:29"}
209
+ {"current_steps": 208, "total_steps": 320, "loss": 0.157, "lr": 3.289899283371657e-05, "epoch": 1.3, "percentage": 65.0, "elapsed_time": "0:59:47", "remaining_time": "0:32:11"}
210
+ {"current_steps": 209, "total_steps": 320, "loss": 0.1167, "lr": 3.2387497603938326e-05, "epoch": 1.30625, "percentage": 65.31, "elapsed_time": "1:00:04", "remaining_time": "0:31:54"}
211
+ {"current_steps": 210, "total_steps": 320, "loss": 0.1267, "lr": 3.1878098085814924e-05, "epoch": 1.3125, "percentage": 65.62, "elapsed_time": "1:00:21", "remaining_time": "0:31:37"}
212
+ {"current_steps": 211, "total_steps": 320, "loss": 0.1405, "lr": 3.137085489279485e-05, "epoch": 1.31875, "percentage": 65.94, "elapsed_time": "1:00:38", "remaining_time": "0:31:19"}
213
+ {"current_steps": 212, "total_steps": 320, "loss": 0.1454, "lr": 3.086582838174551e-05, "epoch": 1.325, "percentage": 66.25, "elapsed_time": "1:00:55", "remaining_time": "0:31:02"}
214
+ {"current_steps": 213, "total_steps": 320, "loss": 0.1228, "lr": 3.0363078645771303e-05, "epoch": 1.33125, "percentage": 66.56, "elapsed_time": "1:01:12", "remaining_time": "0:30:45"}
215
+ {"current_steps": 214, "total_steps": 320, "loss": 0.1155, "lr": 2.9862665507063147e-05, "epoch": 1.3375, "percentage": 66.88, "elapsed_time": "1:01:30", "remaining_time": "0:30:27"}
216
+ {"current_steps": 215, "total_steps": 320, "loss": 0.114, "lr": 2.936464850978027e-05, "epoch": 1.34375, "percentage": 67.19, "elapsed_time": "1:01:47", "remaining_time": "0:30:10"}
217
+ {"current_steps": 216, "total_steps": 320, "loss": 0.131, "lr": 2.886908691296504e-05, "epoch": 1.35, "percentage": 67.5, "elapsed_time": "1:02:04", "remaining_time": "0:29:53"}
218
+ {"current_steps": 217, "total_steps": 320, "loss": 0.118, "lr": 2.8376039683491686e-05, "epoch": 1.35625, "percentage": 67.81, "elapsed_time": "1:02:21", "remaining_time": "0:29:35"}
219
+ {"current_steps": 218, "total_steps": 320, "loss": 0.1206, "lr": 2.7885565489049946e-05, "epoch": 1.3625, "percentage": 68.12, "elapsed_time": "1:02:38", "remaining_time": "0:29:18"}
220
+ {"current_steps": 219, "total_steps": 320, "loss": 0.1196, "lr": 2.7397722691164018e-05, "epoch": 1.36875, "percentage": 68.44, "elapsed_time": "1:02:55", "remaining_time": "0:29:01"}
221
+ {"current_steps": 220, "total_steps": 320, "loss": 0.1257, "lr": 2.6912569338248315e-05, "epoch": 1.375, "percentage": 68.75, "elapsed_time": "1:03:12", "remaining_time": "0:28:43"}
222
+ {"current_steps": 221, "total_steps": 320, "loss": 0.1078, "lr": 2.6430163158700115e-05, "epoch": 1.38125, "percentage": 69.06, "elapsed_time": "1:03:29", "remaining_time": "0:28:26"}
223
+ {"current_steps": 222, "total_steps": 320, "loss": 0.1039, "lr": 2.595056155403063e-05, "epoch": 1.3875, "percentage": 69.38, "elapsed_time": "1:03:47", "remaining_time": "0:28:09"}
224
+ {"current_steps": 223, "total_steps": 320, "loss": 0.1044, "lr": 2.54738215920346e-05, "epoch": 1.39375, "percentage": 69.69, "elapsed_time": "1:04:04", "remaining_time": "0:27:52"}
225
+ {"current_steps": 224, "total_steps": 320, "loss": 0.1152, "lr": 2.500000000000001e-05, "epoch": 1.4, "percentage": 70.0, "elapsed_time": "1:04:21", "remaining_time": "0:27:34"}
226
+ {"current_steps": 225, "total_steps": 320, "loss": 0.1234, "lr": 2.4529153157957913e-05, "epoch": 1.40625, "percentage": 70.31, "elapsed_time": "1:04:38", "remaining_time": "0:27:17"}
227
+ {"current_steps": 226, "total_steps": 320, "loss": 0.1193, "lr": 2.4061337091973918e-05, "epoch": 1.4125, "percentage": 70.62, "elapsed_time": "1:04:55", "remaining_time": "0:27:00"}
228
+ {"current_steps": 227, "total_steps": 320, "loss": 0.1452, "lr": 2.3596607467481603e-05, "epoch": 1.41875, "percentage": 70.94, "elapsed_time": "1:05:12", "remaining_time": "0:26:43"}
229
+ {"current_steps": 228, "total_steps": 320, "loss": 0.0936, "lr": 2.3135019582658802e-05, "epoch": 1.425, "percentage": 71.25, "elapsed_time": "1:05:29", "remaining_time": "0:26:25"}
230
+ {"current_steps": 229, "total_steps": 320, "loss": 0.1194, "lr": 2.2676628361847836e-05, "epoch": 1.43125, "percentage": 71.56, "elapsed_time": "1:05:46", "remaining_time": "0:26:08"}
231
+ {"current_steps": 230, "total_steps": 320, "loss": 0.1328, "lr": 2.2221488349019903e-05, "epoch": 1.4375, "percentage": 71.88, "elapsed_time": "1:06:04", "remaining_time": "0:25:51"}
232
+ {"current_steps": 231, "total_steps": 320, "loss": 0.1079, "lr": 2.176965370128498e-05, "epoch": 1.44375, "percentage": 72.19, "elapsed_time": "1:06:21", "remaining_time": "0:25:33"}
233
+ {"current_steps": 232, "total_steps": 320, "loss": 0.1225, "lr": 2.132117818244771e-05, "epoch": 1.45, "percentage": 72.5, "elapsed_time": "1:06:38", "remaining_time": "0:25:16"}
234
+ {"current_steps": 233, "total_steps": 320, "loss": 0.1521, "lr": 2.08761151566099e-05, "epoch": 1.45625, "percentage": 72.81, "elapsed_time": "1:06:55", "remaining_time": "0:24:59"}
235
+ {"current_steps": 234, "total_steps": 320, "loss": 0.1214, "lr": 2.0434517581820896e-05, "epoch": 1.4625, "percentage": 73.12, "elapsed_time": "1:07:12", "remaining_time": "0:24:42"}
236
+ {"current_steps": 235, "total_steps": 320, "loss": 0.1305, "lr": 1.999643800377596e-05, "epoch": 1.46875, "percentage": 73.44, "elapsed_time": "1:07:29", "remaining_time": "0:24:24"}
237
+ {"current_steps": 236, "total_steps": 320, "loss": 0.1259, "lr": 1.9561928549563968e-05, "epoch": 1.475, "percentage": 73.75, "elapsed_time": "1:07:46", "remaining_time": "0:24:07"}
238
+ {"current_steps": 237, "total_steps": 320, "loss": 0.1313, "lr": 1.913104092146476e-05, "epoch": 1.48125, "percentage": 74.06, "elapsed_time": "1:08:03", "remaining_time": "0:23:50"}
239
+ {"current_steps": 238, "total_steps": 320, "loss": 0.1082, "lr": 1.8703826390797048e-05, "epoch": 1.4875, "percentage": 74.38, "elapsed_time": "1:08:20", "remaining_time": "0:23:32"}
240
+ {"current_steps": 239, "total_steps": 320, "loss": 0.1254, "lr": 1.8280335791817733e-05, "epoch": 1.49375, "percentage": 74.69, "elapsed_time": "1:08:37", "remaining_time": "0:23:15"}
241
+ {"current_steps": 240, "total_steps": 320, "loss": 0.0976, "lr": 1.7860619515673033e-05, "epoch": 1.5, "percentage": 75.0, "elapsed_time": "1:08:54", "remaining_time": "0:22:58"}
242
+ {"current_steps": 241, "total_steps": 320, "loss": 0.118, "lr": 1.7444727504402553e-05, "epoch": 1.50625, "percentage": 75.31, "elapsed_time": "1:09:12", "remaining_time": "0:22:41"}
243
+ {"current_steps": 242, "total_steps": 320, "loss": 0.1221, "lr": 1.703270924499656e-05, "epoch": 1.5125, "percentage": 75.62, "elapsed_time": "1:09:29", "remaining_time": "0:22:23"}
244
+ {"current_steps": 243, "total_steps": 320, "loss": 0.1415, "lr": 1.662461376350764e-05, "epoch": 1.51875, "percentage": 75.94, "elapsed_time": "1:09:46", "remaining_time": "0:22:06"}
245
+ {"current_steps": 244, "total_steps": 320, "loss": 0.1241, "lr": 1.622048961921699e-05, "epoch": 1.525, "percentage": 76.25, "elapsed_time": "1:10:03", "remaining_time": "0:21:49"}
246
+ {"current_steps": 245, "total_steps": 320, "loss": 0.1109, "lr": 1.5820384898856434e-05, "epoch": 1.53125, "percentage": 76.56, "elapsed_time": "1:10:20", "remaining_time": "0:21:31"}
247
+ {"current_steps": 246, "total_steps": 320, "loss": 0.1171, "lr": 1.5424347210886538e-05, "epoch": 1.5375, "percentage": 76.88, "elapsed_time": "1:10:37", "remaining_time": "0:21:14"}
248
+ {"current_steps": 247, "total_steps": 320, "loss": 0.1087, "lr": 1.5032423679831642e-05, "epoch": 1.54375, "percentage": 77.19, "elapsed_time": "1:10:54", "remaining_time": "0:20:57"}
249
+ {"current_steps": 248, "total_steps": 320, "loss": 0.1228, "lr": 1.4644660940672627e-05, "epoch": 1.55, "percentage": 77.5, "elapsed_time": "1:11:11", "remaining_time": "0:20:40"}
250
+ {"current_steps": 249, "total_steps": 320, "loss": 0.1217, "lr": 1.4261105133297692e-05, "epoch": 1.55625, "percentage": 77.81, "elapsed_time": "1:11:28", "remaining_time": "0:20:22"}
251
+ {"current_steps": 250, "total_steps": 320, "loss": 0.1114, "lr": 1.3881801897012225e-05, "epoch": 1.5625, "percentage": 78.12, "elapsed_time": "1:11:46", "remaining_time": "0:20:05"}
252
+ {"current_steps": 251, "total_steps": 320, "loss": 0.1022, "lr": 1.3506796365108232e-05, "epoch": 1.56875, "percentage": 78.44, "elapsed_time": "1:12:03", "remaining_time": "0:19:48"}
253
+ {"current_steps": 252, "total_steps": 320, "loss": 0.1114, "lr": 1.3136133159493802e-05, "epoch": 1.575, "percentage": 78.75, "elapsed_time": "1:12:20", "remaining_time": "0:19:31"}
254
+ {"current_steps": 253, "total_steps": 320, "loss": 0.1183, "lr": 1.2769856385383688e-05, "epoch": 1.58125, "percentage": 79.06, "elapsed_time": "1:12:37", "remaining_time": "0:19:13"}
255
+ {"current_steps": 254, "total_steps": 320, "loss": 0.1152, "lr": 1.2408009626051137e-05, "epoch": 1.5875, "percentage": 79.38, "elapsed_time": "1:12:54", "remaining_time": "0:18:56"}
256
+ {"current_steps": 255, "total_steps": 320, "loss": 0.0925, "lr": 1.2050635937641908e-05, "epoch": 1.59375, "percentage": 79.69, "elapsed_time": "1:13:11", "remaining_time": "0:18:39"}
257
+ {"current_steps": 256, "total_steps": 320, "loss": 0.1283, "lr": 1.1697777844051105e-05, "epoch": 1.6, "percentage": 80.0, "elapsed_time": "1:13:28", "remaining_time": "0:18:22"}
258
+ {"current_steps": 257, "total_steps": 320, "loss": 0.13, "lr": 1.134947733186315e-05, "epoch": 1.60625, "percentage": 80.31, "elapsed_time": "1:13:46", "remaining_time": "0:18:04"}
259
+ {"current_steps": 258, "total_steps": 320, "loss": 0.1107, "lr": 1.100577584535592e-05, "epoch": 1.6125, "percentage": 80.62, "elapsed_time": "1:14:03", "remaining_time": "0:17:47"}
260
+ {"current_steps": 259, "total_steps": 320, "loss": 0.1061, "lr": 1.0666714281569151e-05, "epoch": 1.61875, "percentage": 80.94, "elapsed_time": "1:14:20", "remaining_time": "0:17:30"}
261
+ {"current_steps": 260, "total_steps": 320, "loss": 0.1151, "lr": 1.0332332985438248e-05, "epoch": 1.625, "percentage": 81.25, "elapsed_time": "1:14:37", "remaining_time": "0:17:13"}
262
+ {"current_steps": 261, "total_steps": 320, "loss": 0.1288, "lr": 1.000267174499352e-05, "epoch": 1.63125, "percentage": 81.56, "elapsed_time": "1:14:54", "remaining_time": "0:16:55"}
263
+ {"current_steps": 262, "total_steps": 320, "loss": 0.1096, "lr": 9.677769786625867e-06, "epoch": 1.6375, "percentage": 81.88, "elapsed_time": "1:15:11", "remaining_time": "0:16:38"}
264
+ {"current_steps": 263, "total_steps": 320, "loss": 0.0998, "lr": 9.357665770419244e-06, "epoch": 1.64375, "percentage": 82.19, "elapsed_time": "1:15:28", "remaining_time": "0:16:21"}
265
+ {"current_steps": 264, "total_steps": 320, "loss": 0.1083, "lr": 9.042397785550405e-06, "epoch": 1.65, "percentage": 82.5, "elapsed_time": "1:15:45", "remaining_time": "0:16:04"}
266
+ {"current_steps": 265, "total_steps": 320, "loss": 0.118, "lr": 8.732003345756811e-06, "epoch": 1.65625, "percentage": 82.81, "elapsed_time": "1:16:02", "remaining_time": "0:15:46"}
267
+ {"current_steps": 266, "total_steps": 320, "loss": 0.1088, "lr": 8.426519384872733e-06, "epoch": 1.6625, "percentage": 83.12, "elapsed_time": "1:16:19", "remaining_time": "0:15:29"}
268
+ {"current_steps": 267, "total_steps": 320, "loss": 0.1239, "lr": 8.125982252434611e-06, "epoch": 1.66875, "percentage": 83.44, "elapsed_time": "1:16:36", "remaining_time": "0:15:12"}
269
+ {"current_steps": 268, "total_steps": 320, "loss": 0.1164, "lr": 7.830427709355725e-06, "epoch": 1.675, "percentage": 83.75, "elapsed_time": "1:16:54", "remaining_time": "0:14:55"}
270
+ {"current_steps": 269, "total_steps": 320, "loss": 0.0855, "lr": 7.539890923671062e-06, "epoch": 1.68125, "percentage": 84.06, "elapsed_time": "1:17:11", "remaining_time": "0:14:38"}
271
+ {"current_steps": 270, "total_steps": 320, "loss": 0.1395, "lr": 7.2544064663526815e-06, "epoch": 1.6875, "percentage": 84.38, "elapsed_time": "1:17:28", "remaining_time": "0:14:20"}
272
+ {"current_steps": 271, "total_steps": 320, "loss": 0.1081, "lr": 6.974008307196056e-06, "epoch": 1.69375, "percentage": 84.69, "elapsed_time": "1:17:45", "remaining_time": "0:14:03"}
273
+ {"current_steps": 272, "total_steps": 320, "loss": 0.1358, "lr": 6.698729810778065e-06, "epoch": 1.7, "percentage": 85.0, "elapsed_time": "1:18:02", "remaining_time": "0:13:46"}
274
+ {"current_steps": 273, "total_steps": 320, "loss": 0.1208, "lr": 6.428603732486937e-06, "epoch": 1.70625, "percentage": 85.31, "elapsed_time": "1:18:20", "remaining_time": "0:13:29"}
275
+ {"current_steps": 274, "total_steps": 320, "loss": 0.1208, "lr": 6.163662214624616e-06, "epoch": 1.7125, "percentage": 85.62, "elapsed_time": "1:18:37", "remaining_time": "0:13:11"}
276
+ {"current_steps": 275, "total_steps": 320, "loss": 0.0961, "lr": 5.903936782582253e-06, "epoch": 1.71875, "percentage": 85.94, "elapsed_time": "1:18:54", "remaining_time": "0:12:54"}
277
+ {"current_steps": 276, "total_steps": 320, "loss": 0.1328, "lr": 5.649458341088915e-06, "epoch": 1.725, "percentage": 86.25, "elapsed_time": "1:19:11", "remaining_time": "0:12:37"}
278
+ {"current_steps": 277, "total_steps": 320, "loss": 0.1137, "lr": 5.400257170534295e-06, "epoch": 1.73125, "percentage": 86.56, "elapsed_time": "1:19:28", "remaining_time": "0:12:20"}
279
+ {"current_steps": 278, "total_steps": 320, "loss": 0.0963, "lr": 5.156362923365588e-06, "epoch": 1.7375, "percentage": 86.88, "elapsed_time": "1:19:46", "remaining_time": "0:12:03"}
280
+ {"current_steps": 279, "total_steps": 320, "loss": 0.1299, "lr": 4.917804620559202e-06, "epoch": 1.74375, "percentage": 87.19, "elapsed_time": "1:20:03", "remaining_time": "0:11:45"}
281
+ {"current_steps": 280, "total_steps": 320, "loss": 0.1003, "lr": 4.684610648167503e-06, "epoch": 1.75, "percentage": 87.5, "elapsed_time": "1:20:20", "remaining_time": "0:11:28"}
282
+ {"current_steps": 281, "total_steps": 320, "loss": 0.1005, "lr": 4.456808753941205e-06, "epoch": 1.75625, "percentage": 87.81, "elapsed_time": "1:20:37", "remaining_time": "0:11:11"}
283
+ {"current_steps": 282, "total_steps": 320, "loss": 0.1184, "lr": 4.234426044027645e-06, "epoch": 1.7625, "percentage": 88.12, "elapsed_time": "1:20:54", "remaining_time": "0:10:54"}
284
+ {"current_steps": 283, "total_steps": 320, "loss": 0.1083, "lr": 4.017488979745387e-06, "epoch": 1.76875, "percentage": 88.44, "elapsed_time": "1:21:11", "remaining_time": "0:10:36"}
285
+ {"current_steps": 284, "total_steps": 320, "loss": 0.1349, "lr": 3.8060233744356633e-06, "epoch": 1.775, "percentage": 88.75, "elapsed_time": "1:21:28", "remaining_time": "0:10:19"}
286
+ {"current_steps": 285, "total_steps": 320, "loss": 0.1189, "lr": 3.600054390390778e-06, "epoch": 1.78125, "percentage": 89.06, "elapsed_time": "1:21:45", "remaining_time": "0:10:02"}
287
+ {"current_steps": 286, "total_steps": 320, "loss": 0.1124, "lr": 3.3996065358600782e-06, "epoch": 1.7875, "percentage": 89.38, "elapsed_time": "1:22:03", "remaining_time": "0:09:45"}
288
+ {"current_steps": 287, "total_steps": 320, "loss": 0.1242, "lr": 3.2047036621337236e-06, "epoch": 1.79375, "percentage": 89.69, "elapsed_time": "1:22:20", "remaining_time": "0:09:28"}
289
+ {"current_steps": 288, "total_steps": 320, "loss": 0.1269, "lr": 3.0153689607045845e-06, "epoch": 1.8, "percentage": 90.0, "elapsed_time": "1:22:37", "remaining_time": "0:09:10"}
290
+ {"current_steps": 289, "total_steps": 320, "loss": 0.108, "lr": 2.8316249605087386e-06, "epoch": 1.80625, "percentage": 90.31, "elapsed_time": "1:22:54", "remaining_time": "0:08:53"}
291
+ {"current_steps": 290, "total_steps": 320, "loss": 0.104, "lr": 2.653493525244721e-06, "epoch": 1.8125, "percentage": 90.62, "elapsed_time": "1:23:11", "remaining_time": "0:08:36"}
292
+ {"current_steps": 291, "total_steps": 320, "loss": 0.1227, "lr": 2.4809958507719444e-06, "epoch": 1.81875, "percentage": 90.94, "elapsed_time": "1:23:28", "remaining_time": "0:08:19"}
293
+ {"current_steps": 292, "total_steps": 320, "loss": 0.1122, "lr": 2.314152462588659e-06, "epoch": 1.825, "percentage": 91.25, "elapsed_time": "1:23:45", "remaining_time": "0:08:01"}
294
+ {"current_steps": 293, "total_steps": 320, "loss": 0.1206, "lr": 2.152983213389559e-06, "epoch": 1.83125, "percentage": 91.56, "elapsed_time": "1:24:02", "remaining_time": "0:07:44"}
295
+ {"current_steps": 294, "total_steps": 320, "loss": 0.0849, "lr": 1.99750728070357e-06, "epoch": 1.8375, "percentage": 91.88, "elapsed_time": "1:24:19", "remaining_time": "0:07:27"}
296
+ {"current_steps": 295, "total_steps": 320, "loss": 0.1168, "lr": 1.8477431646118648e-06, "epoch": 1.84375, "percentage": 92.19, "elapsed_time": "1:24:36", "remaining_time": "0:07:10"}
297
+ {"current_steps": 296, "total_steps": 320, "loss": 0.1002, "lr": 1.70370868554659e-06, "epoch": 1.85, "percentage": 92.5, "elapsed_time": "1:24:53", "remaining_time": "0:06:53"}
298
+ {"current_steps": 297, "total_steps": 320, "loss": 0.1204, "lr": 1.565420982170346e-06, "epoch": 1.85625, "percentage": 92.81, "elapsed_time": "1:25:11", "remaining_time": "0:06:35"}
299
+ {"current_steps": 298, "total_steps": 320, "loss": 0.1052, "lr": 1.4328965093369283e-06, "epoch": 1.8625, "percentage": 93.12, "elapsed_time": "1:25:28", "remaining_time": "0:06:18"}
300
+ {"current_steps": 299, "total_steps": 320, "loss": 0.1185, "lr": 1.3061510361333185e-06, "epoch": 1.86875, "percentage": 93.44, "elapsed_time": "1:25:45", "remaining_time": "0:06:01"}
301
+ {"current_steps": 300, "total_steps": 320, "loss": 0.1372, "lr": 1.1851996440033319e-06, "epoch": 1.875, "percentage": 93.75, "elapsed_time": "1:26:02", "remaining_time": "0:05:44"}
302
+ {"current_steps": 301, "total_steps": 320, "loss": 0.1374, "lr": 1.0700567249530834e-06, "epoch": 1.88125, "percentage": 94.06, "elapsed_time": "1:27:49", "remaining_time": "0:05:32"}
303
+ {"current_steps": 302, "total_steps": 320, "loss": 0.1265, "lr": 9.607359798384785e-07, "epoch": 1.8875, "percentage": 94.38, "elapsed_time": "1:28:07", "remaining_time": "0:05:15"}
304
+ {"current_steps": 303, "total_steps": 320, "loss": 0.1156, "lr": 8.572504167349449e-07, "epoch": 1.89375, "percentage": 94.69, "elapsed_time": "1:28:24", "remaining_time": "0:04:57"}
305
+ {"current_steps": 304, "total_steps": 320, "loss": 0.1131, "lr": 7.596123493895991e-07, "epoch": 1.9, "percentage": 95.0, "elapsed_time": "1:28:41", "remaining_time": "0:04:40"}
306
+ {"current_steps": 305, "total_steps": 320, "loss": 0.1212, "lr": 6.678333957560512e-07, "epoch": 1.90625, "percentage": 95.31, "elapsed_time": "1:28:58", "remaining_time": "0:04:22"}
307
+ {"current_steps": 306, "total_steps": 320, "loss": 0.1249, "lr": 5.81924476611967e-07, "epoch": 1.9125, "percentage": 95.62, "elapsed_time": "1:29:16", "remaining_time": "0:04:05"}
308
+ {"current_steps": 307, "total_steps": 320, "loss": 0.1123, "lr": 5.018958142596065e-07, "epoch": 1.91875, "percentage": 95.94, "elapsed_time": "1:29:33", "remaining_time": "0:03:47"}
309
+ {"current_steps": 308, "total_steps": 320, "loss": 0.1017, "lr": 4.277569313094809e-07, "epoch": 1.925, "percentage": 96.25, "elapsed_time": "1:29:50", "remaining_time": "0:03:30"}
310
+ {"current_steps": 309, "total_steps": 320, "loss": 0.1265, "lr": 3.59516649547248e-07, "epoch": 1.93125, "percentage": 96.56, "elapsed_time": "1:30:07", "remaining_time": "0:03:12"}
311
+ {"current_steps": 310, "total_steps": 320, "loss": 0.139, "lr": 2.971830888840177e-07, "epoch": 1.9375, "percentage": 96.88, "elapsed_time": "1:30:24", "remaining_time": "0:02:54"}
312
+ {"current_steps": 311, "total_steps": 320, "loss": 0.1015, "lr": 2.407636663901591e-07, "epoch": 1.94375, "percentage": 97.19, "elapsed_time": "1:30:42", "remaining_time": "0:02:37"}
313
+ {"current_steps": 312, "total_steps": 320, "loss": 0.1294, "lr": 1.9026509541272275e-07, "epoch": 1.95, "percentage": 97.5, "elapsed_time": "1:30:59", "remaining_time": "0:02:19"}
314
+ {"current_steps": 313, "total_steps": 320, "loss": 0.1282, "lr": 1.4569338477666838e-07, "epoch": 1.95625, "percentage": 97.81, "elapsed_time": "1:31:16", "remaining_time": "0:02:02"}
315
+ {"current_steps": 314, "total_steps": 320, "loss": 0.1103, "lr": 1.0705383806982606e-07, "epoch": 1.9625, "percentage": 98.12, "elapsed_time": "1:31:33", "remaining_time": "0:01:44"}
316
+ {"current_steps": 315, "total_steps": 320, "loss": 0.1114, "lr": 7.43510530118452e-08, "epoch": 1.96875, "percentage": 98.44, "elapsed_time": "1:31:51", "remaining_time": "0:01:27"}
317
+ {"current_steps": 316, "total_steps": 320, "loss": 0.1202, "lr": 4.7588920907110094e-08, "epoch": 1.975, "percentage": 98.75, "elapsed_time": "1:32:08", "remaining_time": "0:01:09"}
318
+ {"current_steps": 317, "total_steps": 320, "loss": 0.1172, "lr": 2.6770626181715773e-08, "epoch": 1.98125, "percentage": 99.06, "elapsed_time": "1:32:25", "remaining_time": "0:00:52"}
319
+ {"current_steps": 318, "total_steps": 320, "loss": 0.1239, "lr": 1.189864600454338e-08, "epoch": 1.9875, "percentage": 99.38, "elapsed_time": "1:32:42", "remaining_time": "0:00:34"}
320
+ {"current_steps": 319, "total_steps": 320, "loss": 0.1275, "lr": 2.974749992512571e-09, "epoch": 1.99375, "percentage": 99.69, "elapsed_time": "1:32:59", "remaining_time": "0:00:17"}
321
+ {"current_steps": 320, "total_steps": 320, "loss": 0.1243, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "1:33:16", "remaining_time": "0:00:00"}
322
+ {"current_steps": 320, "total_steps": 320, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "1:35:10", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,2290 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 200,
6
+ "global_step": 320,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.00625,
13
+ "grad_norm": 0.40599126920339407,
14
+ "learning_rate": 3.125e-06,
15
+ "loss": 0.508,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0125,
20
+ "grad_norm": 0.16174971893093387,
21
+ "learning_rate": 6.25e-06,
22
+ "loss": 0.3989,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.01875,
27
+ "grad_norm": 0.13980982904548378,
28
+ "learning_rate": 9.375000000000001e-06,
29
+ "loss": 0.3526,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.025,
34
+ "grad_norm": 0.27727799449785184,
35
+ "learning_rate": 1.25e-05,
36
+ "loss": 0.3927,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.03125,
41
+ "grad_norm": 0.1157104063128156,
42
+ "learning_rate": 1.5625e-05,
43
+ "loss": 0.3232,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.0375,
48
+ "grad_norm": 0.14945724236967864,
49
+ "learning_rate": 1.8750000000000002e-05,
50
+ "loss": 0.3486,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.04375,
55
+ "grad_norm": 0.1806281329991288,
56
+ "learning_rate": 2.1875e-05,
57
+ "loss": 0.3894,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.05,
62
+ "grad_norm": 0.16431928934147372,
63
+ "learning_rate": 2.5e-05,
64
+ "loss": 0.3606,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.05625,
69
+ "grad_norm": 0.15979437230246274,
70
+ "learning_rate": 2.8125000000000003e-05,
71
+ "loss": 0.3323,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.0625,
76
+ "grad_norm": 0.2004445206673931,
77
+ "learning_rate": 3.125e-05,
78
+ "loss": 0.3689,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.06875,
83
+ "grad_norm": 0.20835456635890684,
84
+ "learning_rate": 3.4375e-05,
85
+ "loss": 0.3825,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.075,
90
+ "grad_norm": 0.18507055166360947,
91
+ "learning_rate": 3.7500000000000003e-05,
92
+ "loss": 0.3368,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.08125,
97
+ "grad_norm": 0.21673005959559813,
98
+ "learning_rate": 4.0625000000000005e-05,
99
+ "loss": 0.3345,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.0875,
104
+ "grad_norm": 0.17167000281963693,
105
+ "learning_rate": 4.375e-05,
106
+ "loss": 0.3176,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.09375,
111
+ "grad_norm": 0.19654075830086185,
112
+ "learning_rate": 4.6875e-05,
113
+ "loss": 0.3136,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.1,
118
+ "grad_norm": 0.16056560874254397,
119
+ "learning_rate": 5e-05,
120
+ "loss": 0.2986,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.10625,
125
+ "grad_norm": 0.14196579272732793,
126
+ "learning_rate": 5.3125000000000004e-05,
127
+ "loss": 0.2691,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.1125,
132
+ "grad_norm": 0.15400147007847648,
133
+ "learning_rate": 5.6250000000000005e-05,
134
+ "loss": 0.3044,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.11875,
139
+ "grad_norm": 0.10944808517977976,
140
+ "learning_rate": 5.9375e-05,
141
+ "loss": 0.232,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.125,
146
+ "grad_norm": 0.11702109032620692,
147
+ "learning_rate": 6.25e-05,
148
+ "loss": 0.237,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.13125,
153
+ "grad_norm": 0.13599177017428848,
154
+ "learning_rate": 6.562500000000001e-05,
155
+ "loss": 0.2708,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.1375,
160
+ "grad_norm": 0.10113783542128998,
161
+ "learning_rate": 6.875e-05,
162
+ "loss": 0.2334,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.14375,
167
+ "grad_norm": 0.07723777905374925,
168
+ "learning_rate": 7.1875e-05,
169
+ "loss": 0.1994,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.15,
174
+ "grad_norm": 0.08703618197718174,
175
+ "learning_rate": 7.500000000000001e-05,
176
+ "loss": 0.2253,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.15625,
181
+ "grad_norm": 0.11206045033884303,
182
+ "learning_rate": 7.8125e-05,
183
+ "loss": 0.2677,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.1625,
188
+ "grad_norm": 0.08484274071341459,
189
+ "learning_rate": 8.125000000000001e-05,
190
+ "loss": 0.1909,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.16875,
195
+ "grad_norm": 0.13523622669439594,
196
+ "learning_rate": 8.4375e-05,
197
+ "loss": 0.2352,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.175,
202
+ "grad_norm": 0.0979564733902834,
203
+ "learning_rate": 8.75e-05,
204
+ "loss": 0.2312,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.18125,
209
+ "grad_norm": 0.10257710940833924,
210
+ "learning_rate": 9.062500000000001e-05,
211
+ "loss": 0.2571,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.1875,
216
+ "grad_norm": 0.09612386608372053,
217
+ "learning_rate": 9.375e-05,
218
+ "loss": 0.2181,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.19375,
223
+ "grad_norm": 0.08223867478377872,
224
+ "learning_rate": 9.687500000000001e-05,
225
+ "loss": 0.1768,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.2,
230
+ "grad_norm": 0.08986243609911292,
231
+ "learning_rate": 0.0001,
232
+ "loss": 0.1995,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.20625,
237
+ "grad_norm": 0.22662504165100472,
238
+ "learning_rate": 9.999702525000749e-05,
239
+ "loss": 0.2344,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.2125,
244
+ "grad_norm": 0.11694951154367994,
245
+ "learning_rate": 9.998810135399546e-05,
246
+ "loss": 0.1581,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.21875,
251
+ "grad_norm": 0.10469730042736397,
252
+ "learning_rate": 9.997322937381829e-05,
253
+ "loss": 0.2129,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.225,
258
+ "grad_norm": 0.09098907134196822,
259
+ "learning_rate": 9.99524110790929e-05,
260
+ "loss": 0.1837,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.23125,
265
+ "grad_norm": 0.10818262125011802,
266
+ "learning_rate": 9.992564894698816e-05,
267
+ "loss": 0.1881,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.2375,
272
+ "grad_norm": 0.09073616923032347,
273
+ "learning_rate": 9.989294616193017e-05,
274
+ "loss": 0.1837,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.24375,
279
+ "grad_norm": 0.08876555004490387,
280
+ "learning_rate": 9.985430661522333e-05,
281
+ "loss": 0.1918,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.25,
286
+ "grad_norm": 0.1046229015794259,
287
+ "learning_rate": 9.980973490458728e-05,
288
+ "loss": 0.1823,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.25625,
293
+ "grad_norm": 0.10749279775724821,
294
+ "learning_rate": 9.975923633360985e-05,
295
+ "loss": 0.2191,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.2625,
300
+ "grad_norm": 0.07655181308042079,
301
+ "learning_rate": 9.970281691111598e-05,
302
+ "loss": 0.1671,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.26875,
307
+ "grad_norm": 0.06987142581471417,
308
+ "learning_rate": 9.964048335045275e-05,
309
+ "loss": 0.1445,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.275,
314
+ "grad_norm": 0.08578476236740849,
315
+ "learning_rate": 9.957224306869053e-05,
316
+ "loss": 0.1883,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.28125,
321
+ "grad_norm": 0.08735769756820697,
322
+ "learning_rate": 9.949810418574039e-05,
323
+ "loss": 0.1912,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.2875,
328
+ "grad_norm": 0.08454191122193365,
329
+ "learning_rate": 9.941807552338804e-05,
330
+ "loss": 0.1781,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.29375,
335
+ "grad_norm": 0.07561417915639863,
336
+ "learning_rate": 9.933216660424395e-05,
337
+ "loss": 0.1741,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.3,
342
+ "grad_norm": 0.0908845677740239,
343
+ "learning_rate": 9.924038765061042e-05,
344
+ "loss": 0.1862,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.30625,
349
+ "grad_norm": 0.08957984885995234,
350
+ "learning_rate": 9.914274958326505e-05,
351
+ "loss": 0.1948,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.3125,
356
+ "grad_norm": 0.06721787175218842,
357
+ "learning_rate": 9.903926402016153e-05,
358
+ "loss": 0.1387,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.31875,
363
+ "grad_norm": 0.07776287708078782,
364
+ "learning_rate": 9.892994327504693e-05,
365
+ "loss": 0.1897,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.325,
370
+ "grad_norm": 0.0792915804134436,
371
+ "learning_rate": 9.881480035599667e-05,
372
+ "loss": 0.1878,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.33125,
377
+ "grad_norm": 0.11195588138897727,
378
+ "learning_rate": 9.869384896386668e-05,
379
+ "loss": 0.194,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.3375,
384
+ "grad_norm": 0.10744243347143223,
385
+ "learning_rate": 9.856710349066307e-05,
386
+ "loss": 0.1881,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.34375,
391
+ "grad_norm": 0.1162711120696835,
392
+ "learning_rate": 9.843457901782967e-05,
393
+ "loss": 0.2129,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.35,
398
+ "grad_norm": 0.08320344631618402,
399
+ "learning_rate": 9.829629131445342e-05,
400
+ "loss": 0.187,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.35625,
405
+ "grad_norm": 0.08853925634789721,
406
+ "learning_rate": 9.815225683538814e-05,
407
+ "loss": 0.1952,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.3625,
412
+ "grad_norm": 0.08064278407146641,
413
+ "learning_rate": 9.800249271929645e-05,
414
+ "loss": 0.1722,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.36875,
419
+ "grad_norm": 0.08627992209736293,
420
+ "learning_rate": 9.784701678661045e-05,
421
+ "loss": 0.1852,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.375,
426
+ "grad_norm": 0.08472663945575681,
427
+ "learning_rate": 9.768584753741134e-05,
428
+ "loss": 0.1861,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.38125,
433
+ "grad_norm": 0.0706516311545354,
434
+ "learning_rate": 9.751900414922805e-05,
435
+ "loss": 0.1681,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.3875,
440
+ "grad_norm": 0.07830536169386694,
441
+ "learning_rate": 9.73465064747553e-05,
442
+ "loss": 0.1768,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.39375,
447
+ "grad_norm": 0.07870447814947025,
448
+ "learning_rate": 9.716837503949127e-05,
449
+ "loss": 0.1592,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.4,
454
+ "grad_norm": 0.11475798771048969,
455
+ "learning_rate": 9.698463103929542e-05,
456
+ "loss": 0.2007,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.40625,
461
+ "grad_norm": 0.09295937705194224,
462
+ "learning_rate": 9.67952963378663e-05,
463
+ "loss": 0.1499,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.4125,
468
+ "grad_norm": 0.09326386653332064,
469
+ "learning_rate": 9.660039346413994e-05,
470
+ "loss": 0.1702,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.41875,
475
+ "grad_norm": 0.08131260921217849,
476
+ "learning_rate": 9.639994560960923e-05,
477
+ "loss": 0.172,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.425,
482
+ "grad_norm": 0.07365872216537292,
483
+ "learning_rate": 9.619397662556435e-05,
484
+ "loss": 0.1363,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.43125,
489
+ "grad_norm": 0.0834833164127378,
490
+ "learning_rate": 9.598251102025461e-05,
491
+ "loss": 0.1664,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.4375,
496
+ "grad_norm": 0.07655054737496132,
497
+ "learning_rate": 9.576557395597236e-05,
498
+ "loss": 0.1439,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.44375,
503
+ "grad_norm": 0.09641298517325338,
504
+ "learning_rate": 9.554319124605879e-05,
505
+ "loss": 0.1526,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.45,
510
+ "grad_norm": 0.07985464053948435,
511
+ "learning_rate": 9.53153893518325e-05,
512
+ "loss": 0.1514,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.45625,
517
+ "grad_norm": 0.08227789931433875,
518
+ "learning_rate": 9.508219537944081e-05,
519
+ "loss": 0.1481,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.4625,
524
+ "grad_norm": 0.07992014265398506,
525
+ "learning_rate": 9.484363707663442e-05,
526
+ "loss": 0.1552,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.46875,
531
+ "grad_norm": 0.08428886519848619,
532
+ "learning_rate": 9.459974282946571e-05,
533
+ "loss": 0.1533,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.475,
538
+ "grad_norm": 0.07999237487858113,
539
+ "learning_rate": 9.435054165891109e-05,
540
+ "loss": 0.15,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.48125,
545
+ "grad_norm": 0.08663635431835072,
546
+ "learning_rate": 9.409606321741775e-05,
547
+ "loss": 0.1633,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.4875,
552
+ "grad_norm": 0.10421286796237919,
553
+ "learning_rate": 9.38363377853754e-05,
554
+ "loss": 0.1675,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.49375,
559
+ "grad_norm": 0.08371956698091174,
560
+ "learning_rate": 9.357139626751308e-05,
561
+ "loss": 0.1649,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.5,
566
+ "grad_norm": 0.11576971658648634,
567
+ "learning_rate": 9.330127018922194e-05,
568
+ "loss": 0.1818,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.50625,
573
+ "grad_norm": 0.09180205457837495,
574
+ "learning_rate": 9.302599169280395e-05,
575
+ "loss": 0.1535,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.5125,
580
+ "grad_norm": 0.11143842983351335,
581
+ "learning_rate": 9.274559353364734e-05,
582
+ "loss": 0.1573,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.51875,
587
+ "grad_norm": 0.08382222694709042,
588
+ "learning_rate": 9.246010907632895e-05,
589
+ "loss": 0.1552,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.525,
594
+ "grad_norm": 0.08169820823619627,
595
+ "learning_rate": 9.21695722906443e-05,
596
+ "loss": 0.1348,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.53125,
601
+ "grad_norm": 0.09264402945807464,
602
+ "learning_rate": 9.18740177475654e-05,
603
+ "loss": 0.1541,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.5375,
608
+ "grad_norm": 0.12035173607425367,
609
+ "learning_rate": 9.157348061512727e-05,
610
+ "loss": 0.1584,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.54375,
615
+ "grad_norm": 0.0933034733005768,
616
+ "learning_rate": 9.126799665424319e-05,
617
+ "loss": 0.1558,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.55,
622
+ "grad_norm": 0.09983789678085002,
623
+ "learning_rate": 9.09576022144496e-05,
624
+ "loss": 0.178,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.55625,
629
+ "grad_norm": 0.08824386686645358,
630
+ "learning_rate": 9.064233422958077e-05,
631
+ "loss": 0.1382,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.5625,
636
+ "grad_norm": 0.12496408760397422,
637
+ "learning_rate": 9.032223021337414e-05,
638
+ "loss": 0.2028,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.56875,
643
+ "grad_norm": 0.08896745045700023,
644
+ "learning_rate": 8.999732825500648e-05,
645
+ "loss": 0.1564,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.575,
650
+ "grad_norm": 0.1051267783567327,
651
+ "learning_rate": 8.966766701456177e-05,
652
+ "loss": 0.1748,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.58125,
657
+ "grad_norm": 0.1068446272490391,
658
+ "learning_rate": 8.933328571843084e-05,
659
+ "loss": 0.166,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.5875,
664
+ "grad_norm": 0.09693703827165154,
665
+ "learning_rate": 8.899422415464409e-05,
666
+ "loss": 0.1371,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.59375,
671
+ "grad_norm": 0.11397584234437574,
672
+ "learning_rate": 8.865052266813685e-05,
673
+ "loss": 0.1695,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.6,
678
+ "grad_norm": 0.08309347621522221,
679
+ "learning_rate": 8.83022221559489e-05,
680
+ "loss": 0.1397,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.60625,
685
+ "grad_norm": 0.09441073972154676,
686
+ "learning_rate": 8.79493640623581e-05,
687
+ "loss": 0.1475,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.6125,
692
+ "grad_norm": 0.10017885648608761,
693
+ "learning_rate": 8.759199037394887e-05,
694
+ "loss": 0.1455,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.61875,
699
+ "grad_norm": 0.09389095525738553,
700
+ "learning_rate": 8.723014361461632e-05,
701
+ "loss": 0.155,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.625,
706
+ "grad_norm": 0.08794088850259763,
707
+ "learning_rate": 8.68638668405062e-05,
708
+ "loss": 0.14,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.63125,
713
+ "grad_norm": 0.08768231254617773,
714
+ "learning_rate": 8.649320363489179e-05,
715
+ "loss": 0.1268,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.6375,
720
+ "grad_norm": 0.10989824440042859,
721
+ "learning_rate": 8.611819810298778e-05,
722
+ "loss": 0.174,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.64375,
727
+ "grad_norm": 0.09207703015396494,
728
+ "learning_rate": 8.573889486670233e-05,
729
+ "loss": 0.1314,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.65,
734
+ "grad_norm": 0.10433836170510401,
735
+ "learning_rate": 8.535533905932738e-05,
736
+ "loss": 0.1563,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.65625,
741
+ "grad_norm": 0.1394424066715557,
742
+ "learning_rate": 8.496757632016836e-05,
743
+ "loss": 0.2076,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.6625,
748
+ "grad_norm": 0.09605746900221901,
749
+ "learning_rate": 8.457565278911348e-05,
750
+ "loss": 0.1516,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.66875,
755
+ "grad_norm": 0.09934008188904551,
756
+ "learning_rate": 8.417961510114356e-05,
757
+ "loss": 0.163,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.675,
762
+ "grad_norm": 0.096551403883122,
763
+ "learning_rate": 8.377951038078302e-05,
764
+ "loss": 0.1351,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.68125,
769
+ "grad_norm": 0.09261714349099234,
770
+ "learning_rate": 8.337538623649237e-05,
771
+ "loss": 0.1181,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.6875,
776
+ "grad_norm": 0.09869545197682032,
777
+ "learning_rate": 8.296729075500344e-05,
778
+ "loss": 0.1404,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.69375,
783
+ "grad_norm": 0.17566063934542003,
784
+ "learning_rate": 8.255527249559746e-05,
785
+ "loss": 0.1746,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.7,
790
+ "grad_norm": 0.11448964041640074,
791
+ "learning_rate": 8.213938048432697e-05,
792
+ "loss": 0.1724,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.70625,
797
+ "grad_norm": 0.09940589194936707,
798
+ "learning_rate": 8.171966420818228e-05,
799
+ "loss": 0.1469,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.7125,
804
+ "grad_norm": 0.09560062944611337,
805
+ "learning_rate": 8.129617360920296e-05,
806
+ "loss": 0.1692,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.71875,
811
+ "grad_norm": 0.11078503759259131,
812
+ "learning_rate": 8.086895907853526e-05,
813
+ "loss": 0.145,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.725,
818
+ "grad_norm": 0.10258735833050488,
819
+ "learning_rate": 8.043807145043604e-05,
820
+ "loss": 0.1401,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.73125,
825
+ "grad_norm": 0.09522206054276056,
826
+ "learning_rate": 8.000356199622405e-05,
827
+ "loss": 0.1289,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.7375,
832
+ "grad_norm": 0.13908178309980257,
833
+ "learning_rate": 7.956548241817912e-05,
834
+ "loss": 0.1191,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.74375,
839
+ "grad_norm": 0.10074203716975204,
840
+ "learning_rate": 7.912388484339012e-05,
841
+ "loss": 0.1679,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.75,
846
+ "grad_norm": 0.09900042130140317,
847
+ "learning_rate": 7.86788218175523e-05,
848
+ "loss": 0.1455,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.75625,
853
+ "grad_norm": 0.09784130256143893,
854
+ "learning_rate": 7.823034629871503e-05,
855
+ "loss": 0.1387,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.7625,
860
+ "grad_norm": 0.10874950463645312,
861
+ "learning_rate": 7.777851165098012e-05,
862
+ "loss": 0.1595,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.76875,
867
+ "grad_norm": 0.108024736321919,
868
+ "learning_rate": 7.732337163815217e-05,
869
+ "loss": 0.1591,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.775,
874
+ "grad_norm": 0.10774049198035004,
875
+ "learning_rate": 7.68649804173412e-05,
876
+ "loss": 0.1623,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.78125,
881
+ "grad_norm": 0.1071299904224286,
882
+ "learning_rate": 7.64033925325184e-05,
883
+ "loss": 0.155,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.7875,
888
+ "grad_norm": 0.1000917142455837,
889
+ "learning_rate": 7.593866290802608e-05,
890
+ "loss": 0.1524,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.79375,
895
+ "grad_norm": 0.10821955303820206,
896
+ "learning_rate": 7.54708468420421e-05,
897
+ "loss": 0.1599,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.8,
902
+ "grad_norm": 0.09585433780364112,
903
+ "learning_rate": 7.500000000000001e-05,
904
+ "loss": 0.1554,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.80625,
909
+ "grad_norm": 0.12861896583829888,
910
+ "learning_rate": 7.45261784079654e-05,
911
+ "loss": 0.1538,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.8125,
916
+ "grad_norm": 0.09906883135040825,
917
+ "learning_rate": 7.404943844596939e-05,
918
+ "loss": 0.1525,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.81875,
923
+ "grad_norm": 0.09731521778705561,
924
+ "learning_rate": 7.35698368412999e-05,
925
+ "loss": 0.1478,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.825,
930
+ "grad_norm": 0.09827888495925427,
931
+ "learning_rate": 7.308743066175172e-05,
932
+ "loss": 0.1484,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.83125,
937
+ "grad_norm": 0.09864917828015088,
938
+ "learning_rate": 7.2602277308836e-05,
939
+ "loss": 0.124,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.8375,
944
+ "grad_norm": 0.1002828586258035,
945
+ "learning_rate": 7.211443451095007e-05,
946
+ "loss": 0.1422,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.84375,
951
+ "grad_norm": 0.10620289407411102,
952
+ "learning_rate": 7.162396031650831e-05,
953
+ "loss": 0.1488,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.85,
958
+ "grad_norm": 0.09917275385305373,
959
+ "learning_rate": 7.113091308703498e-05,
960
+ "loss": 0.1227,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.85625,
965
+ "grad_norm": 0.09676283023246729,
966
+ "learning_rate": 7.063535149021973e-05,
967
+ "loss": 0.1397,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.8625,
972
+ "grad_norm": 0.10405765108275118,
973
+ "learning_rate": 7.013733449293687e-05,
974
+ "loss": 0.1489,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.86875,
979
+ "grad_norm": 0.11729246349725461,
980
+ "learning_rate": 6.96369213542287e-05,
981
+ "loss": 0.1625,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.875,
986
+ "grad_norm": 0.11001117463075423,
987
+ "learning_rate": 6.91341716182545e-05,
988
+ "loss": 0.1575,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.88125,
993
+ "grad_norm": 0.09836686384061544,
994
+ "learning_rate": 6.862914510720515e-05,
995
+ "loss": 0.1367,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.8875,
1000
+ "grad_norm": 0.09762698241197115,
1001
+ "learning_rate": 6.812190191418508e-05,
1002
+ "loss": 0.1269,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.89375,
1007
+ "grad_norm": 0.11873455243886127,
1008
+ "learning_rate": 6.761250239606169e-05,
1009
+ "loss": 0.1653,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.9,
1014
+ "grad_norm": 0.11143312549675602,
1015
+ "learning_rate": 6.710100716628344e-05,
1016
+ "loss": 0.163,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.90625,
1021
+ "grad_norm": 0.10224042656105548,
1022
+ "learning_rate": 6.658747708766762e-05,
1023
+ "loss": 0.1372,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.9125,
1028
+ "grad_norm": 0.10537786627093436,
1029
+ "learning_rate": 6.607197326515808e-05,
1030
+ "loss": 0.1666,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.91875,
1035
+ "grad_norm": 0.11598573107229065,
1036
+ "learning_rate": 6.555455703855454e-05,
1037
+ "loss": 0.1608,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.925,
1042
+ "grad_norm": 0.09995067555095581,
1043
+ "learning_rate": 6.503528997521366e-05,
1044
+ "loss": 0.1358,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.93125,
1049
+ "grad_norm": 0.1013311198834551,
1050
+ "learning_rate": 6.451423386272312e-05,
1051
+ "loss": 0.1467,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.9375,
1056
+ "grad_norm": 0.12955305425483832,
1057
+ "learning_rate": 6.399145070154961e-05,
1058
+ "loss": 0.1602,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.94375,
1063
+ "grad_norm": 0.11967014014153346,
1064
+ "learning_rate": 6.346700269766132e-05,
1065
+ "loss": 0.1491,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.95,
1070
+ "grad_norm": 0.09715431421285034,
1071
+ "learning_rate": 6.294095225512603e-05,
1072
+ "loss": 0.1503,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.95625,
1077
+ "grad_norm": 0.0993416996456672,
1078
+ "learning_rate": 6.241336196868582e-05,
1079
+ "loss": 0.1394,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.9625,
1084
+ "grad_norm": 0.11282985988320719,
1085
+ "learning_rate": 6.188429461630866e-05,
1086
+ "loss": 0.1471,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.96875,
1091
+ "grad_norm": 0.0953828839581251,
1092
+ "learning_rate": 6.135381315171867e-05,
1093
+ "loss": 0.1163,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.975,
1098
+ "grad_norm": 0.10585616381949887,
1099
+ "learning_rate": 6.0821980696905146e-05,
1100
+ "loss": 0.1414,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.98125,
1105
+ "grad_norm": 0.10303380839923655,
1106
+ "learning_rate": 6.0288860534611745e-05,
1107
+ "loss": 0.1371,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.9875,
1112
+ "grad_norm": 0.10581039986719955,
1113
+ "learning_rate": 5.9754516100806423e-05,
1114
+ "loss": 0.1591,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.99375,
1119
+ "grad_norm": 0.08949422220549504,
1120
+ "learning_rate": 5.9219010977133173e-05,
1121
+ "loss": 0.1136,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 1.0,
1126
+ "grad_norm": 0.2566631074675719,
1127
+ "learning_rate": 5.868240888334653e-05,
1128
+ "loss": 0.1355,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 1.00625,
1133
+ "grad_norm": 0.10977904119859523,
1134
+ "learning_rate": 5.814477366972945e-05,
1135
+ "loss": 0.1389,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 1.0125,
1140
+ "grad_norm": 0.09358588046249755,
1141
+ "learning_rate": 5.7606169309495836e-05,
1142
+ "loss": 0.1278,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 1.01875,
1147
+ "grad_norm": 0.1016639716973101,
1148
+ "learning_rate": 5.706665989117839e-05,
1149
+ "loss": 0.1266,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 1.025,
1154
+ "grad_norm": 0.10447824270529592,
1155
+ "learning_rate": 5.6526309611002594e-05,
1156
+ "loss": 0.1344,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 1.03125,
1161
+ "grad_norm": 0.09539752784620499,
1162
+ "learning_rate": 5.5985182765248126e-05,
1163
+ "loss": 0.11,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 1.0375,
1168
+ "grad_norm": 0.09870524777017345,
1169
+ "learning_rate": 5.544334374259823e-05,
1170
+ "loss": 0.1177,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 1.04375,
1175
+ "grad_norm": 0.1319083652806534,
1176
+ "learning_rate": 5.490085701647805e-05,
1177
+ "loss": 0.1519,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 1.05,
1182
+ "grad_norm": 0.11490589915219332,
1183
+ "learning_rate": 5.435778713738292e-05,
1184
+ "loss": 0.1388,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 1.05625,
1189
+ "grad_norm": 0.10960359392101734,
1190
+ "learning_rate": 5.381419872519763e-05,
1191
+ "loss": 0.1315,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 1.0625,
1196
+ "grad_norm": 0.11911874080836313,
1197
+ "learning_rate": 5.327015646150716e-05,
1198
+ "loss": 0.1513,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 1.06875,
1203
+ "grad_norm": 0.11667323294115564,
1204
+ "learning_rate": 5.2725725081900325e-05,
1205
+ "loss": 0.1265,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 1.075,
1210
+ "grad_norm": 0.12009873927124597,
1211
+ "learning_rate": 5.218096936826681e-05,
1212
+ "loss": 0.1346,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 1.08125,
1217
+ "grad_norm": 0.1096220905597413,
1218
+ "learning_rate": 5.1635954141088813e-05,
1219
+ "loss": 0.1129,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 1.0875,
1224
+ "grad_norm": 0.10881175717833912,
1225
+ "learning_rate": 5.1090744251728064e-05,
1226
+ "loss": 0.1031,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 1.09375,
1231
+ "grad_norm": 0.13152370066828684,
1232
+ "learning_rate": 5.054540457470912e-05,
1233
+ "loss": 0.1093,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 1.1,
1238
+ "grad_norm": 0.1363760209998771,
1239
+ "learning_rate": 5e-05,
1240
+ "loss": 0.1283,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 1.10625,
1245
+ "grad_norm": 0.11792037030369434,
1246
+ "learning_rate": 4.945459542529089e-05,
1247
+ "loss": 0.1163,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 1.1125,
1252
+ "grad_norm": 0.1291497029388642,
1253
+ "learning_rate": 4.890925574827195e-05,
1254
+ "loss": 0.1188,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 1.11875,
1259
+ "grad_norm": 0.15349633438432128,
1260
+ "learning_rate": 4.83640458589112e-05,
1261
+ "loss": 0.1742,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 1.125,
1266
+ "grad_norm": 0.13584411062076804,
1267
+ "learning_rate": 4.781903063173321e-05,
1268
+ "loss": 0.1217,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 1.13125,
1273
+ "grad_norm": 0.11830432386637907,
1274
+ "learning_rate": 4.727427491809968e-05,
1275
+ "loss": 0.1047,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 1.1375,
1280
+ "grad_norm": 0.13406559358836506,
1281
+ "learning_rate": 4.6729843538492847e-05,
1282
+ "loss": 0.1288,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 1.14375,
1287
+ "grad_norm": 0.12419804398498213,
1288
+ "learning_rate": 4.618580127480238e-05,
1289
+ "loss": 0.1123,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 1.15,
1294
+ "grad_norm": 0.11882741893557454,
1295
+ "learning_rate": 4.564221286261709e-05,
1296
+ "loss": 0.1096,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 1.15625,
1301
+ "grad_norm": 0.13277371284528894,
1302
+ "learning_rate": 4.509914298352197e-05,
1303
+ "loss": 0.1237,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 1.1625,
1308
+ "grad_norm": 0.13106816929984538,
1309
+ "learning_rate": 4.4556656257401786e-05,
1310
+ "loss": 0.1256,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 1.16875,
1315
+ "grad_norm": 0.10042628903496502,
1316
+ "learning_rate": 4.4014817234751885e-05,
1317
+ "loss": 0.087,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 1.175,
1322
+ "grad_norm": 0.12858065744554853,
1323
+ "learning_rate": 4.347369038899744e-05,
1324
+ "loss": 0.132,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 1.18125,
1329
+ "grad_norm": 0.13353933963282785,
1330
+ "learning_rate": 4.2933340108821644e-05,
1331
+ "loss": 0.1342,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 1.1875,
1336
+ "grad_norm": 0.12535560223690698,
1337
+ "learning_rate": 4.239383069050417e-05,
1338
+ "loss": 0.1144,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 1.19375,
1343
+ "grad_norm": 0.11919252614077346,
1344
+ "learning_rate": 4.185522633027057e-05,
1345
+ "loss": 0.11,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 1.2,
1350
+ "grad_norm": 0.12595711384481822,
1351
+ "learning_rate": 4.131759111665349e-05,
1352
+ "loss": 0.1256,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 1.20625,
1357
+ "grad_norm": 0.140189285907938,
1358
+ "learning_rate": 4.078098902286683e-05,
1359
+ "loss": 0.1387,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 1.2125,
1364
+ "grad_norm": 0.188759066767972,
1365
+ "learning_rate": 4.0245483899193595e-05,
1366
+ "loss": 0.1154,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 1.21875,
1371
+ "grad_norm": 0.12510322910576527,
1372
+ "learning_rate": 3.971113946538826e-05,
1373
+ "loss": 0.1277,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 1.225,
1378
+ "grad_norm": 0.13577535319914885,
1379
+ "learning_rate": 3.917801930309486e-05,
1380
+ "loss": 0.1245,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 1.23125,
1385
+ "grad_norm": 0.11279041105321824,
1386
+ "learning_rate": 3.864618684828134e-05,
1387
+ "loss": 0.1149,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 1.2375,
1392
+ "grad_norm": 0.11597618526997733,
1393
+ "learning_rate": 3.8115705383691355e-05,
1394
+ "loss": 0.1137,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 1.24375,
1399
+ "grad_norm": 0.21159784242538673,
1400
+ "learning_rate": 3.758663803131418e-05,
1401
+ "loss": 0.1411,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 1.25,
1406
+ "grad_norm": 0.12706926447242534,
1407
+ "learning_rate": 3.705904774487396e-05,
1408
+ "loss": 0.117,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 1.25,
1413
+ "eval_loss": 0.13555637001991272,
1414
+ "eval_runtime": 15.1829,
1415
+ "eval_samples_per_second": 0.461,
1416
+ "eval_steps_per_second": 0.132,
1417
+ "step": 200
1418
+ },
1419
+ {
1420
+ "epoch": 1.25625,
1421
+ "grad_norm": 0.140712680168253,
1422
+ "learning_rate": 3.65329973023387e-05,
1423
+ "loss": 0.1317,
1424
+ "step": 201
1425
+ },
1426
+ {
1427
+ "epoch": 1.2625,
1428
+ "grad_norm": 0.14063508556547588,
1429
+ "learning_rate": 3.60085492984504e-05,
1430
+ "loss": 0.1485,
1431
+ "step": 202
1432
+ },
1433
+ {
1434
+ "epoch": 1.26875,
1435
+ "grad_norm": 0.12420246892648465,
1436
+ "learning_rate": 3.5485766137276894e-05,
1437
+ "loss": 0.127,
1438
+ "step": 203
1439
+ },
1440
+ {
1441
+ "epoch": 1.275,
1442
+ "grad_norm": 0.1375293323917167,
1443
+ "learning_rate": 3.4964710024786354e-05,
1444
+ "loss": 0.1298,
1445
+ "step": 204
1446
+ },
1447
+ {
1448
+ "epoch": 1.28125,
1449
+ "grad_norm": 0.12567976945004108,
1450
+ "learning_rate": 3.4445442961445464e-05,
1451
+ "loss": 0.1218,
1452
+ "step": 205
1453
+ },
1454
+ {
1455
+ "epoch": 1.2875,
1456
+ "grad_norm": 0.10902064060724474,
1457
+ "learning_rate": 3.392802673484193e-05,
1458
+ "loss": 0.0911,
1459
+ "step": 206
1460
+ },
1461
+ {
1462
+ "epoch": 1.29375,
1463
+ "grad_norm": 0.1299840428381004,
1464
+ "learning_rate": 3.341252291233241e-05,
1465
+ "loss": 0.1105,
1466
+ "step": 207
1467
+ },
1468
+ {
1469
+ "epoch": 1.3,
1470
+ "grad_norm": 0.14686027926986012,
1471
+ "learning_rate": 3.289899283371657e-05,
1472
+ "loss": 0.157,
1473
+ "step": 208
1474
+ },
1475
+ {
1476
+ "epoch": 1.30625,
1477
+ "grad_norm": 0.13310525982308075,
1478
+ "learning_rate": 3.2387497603938326e-05,
1479
+ "loss": 0.1167,
1480
+ "step": 209
1481
+ },
1482
+ {
1483
+ "epoch": 1.3125,
1484
+ "grad_norm": 0.23056279523041534,
1485
+ "learning_rate": 3.1878098085814924e-05,
1486
+ "loss": 0.1267,
1487
+ "step": 210
1488
+ },
1489
+ {
1490
+ "epoch": 1.31875,
1491
+ "grad_norm": 0.13379086959343525,
1492
+ "learning_rate": 3.137085489279485e-05,
1493
+ "loss": 0.1405,
1494
+ "step": 211
1495
+ },
1496
+ {
1497
+ "epoch": 1.325,
1498
+ "grad_norm": 0.16429012844656798,
1499
+ "learning_rate": 3.086582838174551e-05,
1500
+ "loss": 0.1454,
1501
+ "step": 212
1502
+ },
1503
+ {
1504
+ "epoch": 1.33125,
1505
+ "grad_norm": 0.1472540477988046,
1506
+ "learning_rate": 3.0363078645771303e-05,
1507
+ "loss": 0.1228,
1508
+ "step": 213
1509
+ },
1510
+ {
1511
+ "epoch": 1.3375,
1512
+ "grad_norm": 0.12810467911662524,
1513
+ "learning_rate": 2.9862665507063147e-05,
1514
+ "loss": 0.1155,
1515
+ "step": 214
1516
+ },
1517
+ {
1518
+ "epoch": 1.34375,
1519
+ "grad_norm": 0.1349885611023629,
1520
+ "learning_rate": 2.936464850978027e-05,
1521
+ "loss": 0.114,
1522
+ "step": 215
1523
+ },
1524
+ {
1525
+ "epoch": 1.35,
1526
+ "grad_norm": 0.2226264712891022,
1527
+ "learning_rate": 2.886908691296504e-05,
1528
+ "loss": 0.131,
1529
+ "step": 216
1530
+ },
1531
+ {
1532
+ "epoch": 1.35625,
1533
+ "grad_norm": 0.14284289832580171,
1534
+ "learning_rate": 2.8376039683491686e-05,
1535
+ "loss": 0.118,
1536
+ "step": 217
1537
+ },
1538
+ {
1539
+ "epoch": 1.3625,
1540
+ "grad_norm": 0.14670574239643006,
1541
+ "learning_rate": 2.7885565489049946e-05,
1542
+ "loss": 0.1206,
1543
+ "step": 218
1544
+ },
1545
+ {
1546
+ "epoch": 1.36875,
1547
+ "grad_norm": 0.13807081126340223,
1548
+ "learning_rate": 2.7397722691164018e-05,
1549
+ "loss": 0.1196,
1550
+ "step": 219
1551
+ },
1552
+ {
1553
+ "epoch": 1.375,
1554
+ "grad_norm": 0.1414426520091727,
1555
+ "learning_rate": 2.6912569338248315e-05,
1556
+ "loss": 0.1257,
1557
+ "step": 220
1558
+ },
1559
+ {
1560
+ "epoch": 1.38125,
1561
+ "grad_norm": 0.12974232596021115,
1562
+ "learning_rate": 2.6430163158700115e-05,
1563
+ "loss": 0.1078,
1564
+ "step": 221
1565
+ },
1566
+ {
1567
+ "epoch": 1.3875,
1568
+ "grad_norm": 0.12697025279359767,
1569
+ "learning_rate": 2.595056155403063e-05,
1570
+ "loss": 0.1039,
1571
+ "step": 222
1572
+ },
1573
+ {
1574
+ "epoch": 1.39375,
1575
+ "grad_norm": 0.1291839881974509,
1576
+ "learning_rate": 2.54738215920346e-05,
1577
+ "loss": 0.1044,
1578
+ "step": 223
1579
+ },
1580
+ {
1581
+ "epoch": 1.4,
1582
+ "grad_norm": 0.13740214702279938,
1583
+ "learning_rate": 2.500000000000001e-05,
1584
+ "loss": 0.1152,
1585
+ "step": 224
1586
+ },
1587
+ {
1588
+ "epoch": 1.40625,
1589
+ "grad_norm": 0.1384802768122724,
1590
+ "learning_rate": 2.4529153157957913e-05,
1591
+ "loss": 0.1234,
1592
+ "step": 225
1593
+ },
1594
+ {
1595
+ "epoch": 1.4125,
1596
+ "grad_norm": 0.13354781137733693,
1597
+ "learning_rate": 2.4061337091973918e-05,
1598
+ "loss": 0.1193,
1599
+ "step": 226
1600
+ },
1601
+ {
1602
+ "epoch": 1.41875,
1603
+ "grad_norm": 0.1771648365806598,
1604
+ "learning_rate": 2.3596607467481603e-05,
1605
+ "loss": 0.1452,
1606
+ "step": 227
1607
+ },
1608
+ {
1609
+ "epoch": 1.425,
1610
+ "grad_norm": 0.11638362220378876,
1611
+ "learning_rate": 2.3135019582658802e-05,
1612
+ "loss": 0.0936,
1613
+ "step": 228
1614
+ },
1615
+ {
1616
+ "epoch": 1.43125,
1617
+ "grad_norm": 0.13555782216280093,
1618
+ "learning_rate": 2.2676628361847836e-05,
1619
+ "loss": 0.1194,
1620
+ "step": 229
1621
+ },
1622
+ {
1623
+ "epoch": 1.4375,
1624
+ "grad_norm": 0.13796797972293184,
1625
+ "learning_rate": 2.2221488349019903e-05,
1626
+ "loss": 0.1328,
1627
+ "step": 230
1628
+ },
1629
+ {
1630
+ "epoch": 1.44375,
1631
+ "grad_norm": 0.12977028041039126,
1632
+ "learning_rate": 2.176965370128498e-05,
1633
+ "loss": 0.1079,
1634
+ "step": 231
1635
+ },
1636
+ {
1637
+ "epoch": 1.45,
1638
+ "grad_norm": 0.13740927778792686,
1639
+ "learning_rate": 2.132117818244771e-05,
1640
+ "loss": 0.1225,
1641
+ "step": 232
1642
+ },
1643
+ {
1644
+ "epoch": 1.45625,
1645
+ "grad_norm": 0.15309969236799242,
1646
+ "learning_rate": 2.08761151566099e-05,
1647
+ "loss": 0.1521,
1648
+ "step": 233
1649
+ },
1650
+ {
1651
+ "epoch": 1.4625,
1652
+ "grad_norm": 0.16080840678597888,
1653
+ "learning_rate": 2.0434517581820896e-05,
1654
+ "loss": 0.1214,
1655
+ "step": 234
1656
+ },
1657
+ {
1658
+ "epoch": 1.46875,
1659
+ "grad_norm": 0.1462626524834281,
1660
+ "learning_rate": 1.999643800377596e-05,
1661
+ "loss": 0.1305,
1662
+ "step": 235
1663
+ },
1664
+ {
1665
+ "epoch": 1.475,
1666
+ "grad_norm": 0.13708479721295597,
1667
+ "learning_rate": 1.9561928549563968e-05,
1668
+ "loss": 0.1259,
1669
+ "step": 236
1670
+ },
1671
+ {
1672
+ "epoch": 1.48125,
1673
+ "grad_norm": 0.14485439862293895,
1674
+ "learning_rate": 1.913104092146476e-05,
1675
+ "loss": 0.1313,
1676
+ "step": 237
1677
+ },
1678
+ {
1679
+ "epoch": 1.4875,
1680
+ "grad_norm": 0.1305624984599595,
1681
+ "learning_rate": 1.8703826390797048e-05,
1682
+ "loss": 0.1082,
1683
+ "step": 238
1684
+ },
1685
+ {
1686
+ "epoch": 1.49375,
1687
+ "grad_norm": 0.12983841773778187,
1688
+ "learning_rate": 1.8280335791817733e-05,
1689
+ "loss": 0.1254,
1690
+ "step": 239
1691
+ },
1692
+ {
1693
+ "epoch": 1.5,
1694
+ "grad_norm": 0.1305817772014699,
1695
+ "learning_rate": 1.7860619515673033e-05,
1696
+ "loss": 0.0976,
1697
+ "step": 240
1698
+ },
1699
+ {
1700
+ "epoch": 1.50625,
1701
+ "grad_norm": 0.13523687056968922,
1702
+ "learning_rate": 1.7444727504402553e-05,
1703
+ "loss": 0.118,
1704
+ "step": 241
1705
+ },
1706
+ {
1707
+ "epoch": 1.5125,
1708
+ "grad_norm": 0.13276802064818327,
1709
+ "learning_rate": 1.703270924499656e-05,
1710
+ "loss": 0.1221,
1711
+ "step": 242
1712
+ },
1713
+ {
1714
+ "epoch": 1.51875,
1715
+ "grad_norm": 0.14813379345753966,
1716
+ "learning_rate": 1.662461376350764e-05,
1717
+ "loss": 0.1415,
1718
+ "step": 243
1719
+ },
1720
+ {
1721
+ "epoch": 1.525,
1722
+ "grad_norm": 0.1373736965280858,
1723
+ "learning_rate": 1.622048961921699e-05,
1724
+ "loss": 0.1241,
1725
+ "step": 244
1726
+ },
1727
+ {
1728
+ "epoch": 1.53125,
1729
+ "grad_norm": 0.12987502342407337,
1730
+ "learning_rate": 1.5820384898856434e-05,
1731
+ "loss": 0.1109,
1732
+ "step": 245
1733
+ },
1734
+ {
1735
+ "epoch": 1.5375,
1736
+ "grad_norm": 0.14097871387133398,
1737
+ "learning_rate": 1.5424347210886538e-05,
1738
+ "loss": 0.1171,
1739
+ "step": 246
1740
+ },
1741
+ {
1742
+ "epoch": 1.54375,
1743
+ "grad_norm": 0.12911360333125718,
1744
+ "learning_rate": 1.5032423679831642e-05,
1745
+ "loss": 0.1087,
1746
+ "step": 247
1747
+ },
1748
+ {
1749
+ "epoch": 1.55,
1750
+ "grad_norm": 0.13452146268445594,
1751
+ "learning_rate": 1.4644660940672627e-05,
1752
+ "loss": 0.1228,
1753
+ "step": 248
1754
+ },
1755
+ {
1756
+ "epoch": 1.55625,
1757
+ "grad_norm": 0.16983759281577876,
1758
+ "learning_rate": 1.4261105133297692e-05,
1759
+ "loss": 0.1217,
1760
+ "step": 249
1761
+ },
1762
+ {
1763
+ "epoch": 1.5625,
1764
+ "grad_norm": 0.13444059283520182,
1765
+ "learning_rate": 1.3881801897012225e-05,
1766
+ "loss": 0.1114,
1767
+ "step": 250
1768
+ },
1769
+ {
1770
+ "epoch": 1.56875,
1771
+ "grad_norm": 0.12954454455265535,
1772
+ "learning_rate": 1.3506796365108232e-05,
1773
+ "loss": 0.1022,
1774
+ "step": 251
1775
+ },
1776
+ {
1777
+ "epoch": 1.575,
1778
+ "grad_norm": 0.17591202784634585,
1779
+ "learning_rate": 1.3136133159493802e-05,
1780
+ "loss": 0.1114,
1781
+ "step": 252
1782
+ },
1783
+ {
1784
+ "epoch": 1.58125,
1785
+ "grad_norm": 0.1321105098614603,
1786
+ "learning_rate": 1.2769856385383688e-05,
1787
+ "loss": 0.1183,
1788
+ "step": 253
1789
+ },
1790
+ {
1791
+ "epoch": 1.5875,
1792
+ "grad_norm": 0.1432184606258264,
1793
+ "learning_rate": 1.2408009626051137e-05,
1794
+ "loss": 0.1152,
1795
+ "step": 254
1796
+ },
1797
+ {
1798
+ "epoch": 1.59375,
1799
+ "grad_norm": 0.1652313311913505,
1800
+ "learning_rate": 1.2050635937641908e-05,
1801
+ "loss": 0.0925,
1802
+ "step": 255
1803
+ },
1804
+ {
1805
+ "epoch": 1.6,
1806
+ "grad_norm": 0.1363797254860259,
1807
+ "learning_rate": 1.1697777844051105e-05,
1808
+ "loss": 0.1283,
1809
+ "step": 256
1810
+ },
1811
+ {
1812
+ "epoch": 1.60625,
1813
+ "grad_norm": 0.14243039726380746,
1814
+ "learning_rate": 1.134947733186315e-05,
1815
+ "loss": 0.13,
1816
+ "step": 257
1817
+ },
1818
+ {
1819
+ "epoch": 1.6125,
1820
+ "grad_norm": 0.1407260083641188,
1821
+ "learning_rate": 1.100577584535592e-05,
1822
+ "loss": 0.1107,
1823
+ "step": 258
1824
+ },
1825
+ {
1826
+ "epoch": 1.61875,
1827
+ "grad_norm": 0.1359874658608621,
1828
+ "learning_rate": 1.0666714281569151e-05,
1829
+ "loss": 0.1061,
1830
+ "step": 259
1831
+ },
1832
+ {
1833
+ "epoch": 1.625,
1834
+ "grad_norm": 0.1619598596563152,
1835
+ "learning_rate": 1.0332332985438248e-05,
1836
+ "loss": 0.1151,
1837
+ "step": 260
1838
+ },
1839
+ {
1840
+ "epoch": 1.63125,
1841
+ "grad_norm": 0.14589312780062294,
1842
+ "learning_rate": 1.000267174499352e-05,
1843
+ "loss": 0.1288,
1844
+ "step": 261
1845
+ },
1846
+ {
1847
+ "epoch": 1.6375,
1848
+ "grad_norm": 0.1448713969935771,
1849
+ "learning_rate": 9.677769786625867e-06,
1850
+ "loss": 0.1096,
1851
+ "step": 262
1852
+ },
1853
+ {
1854
+ "epoch": 1.64375,
1855
+ "grad_norm": 0.15204585922412353,
1856
+ "learning_rate": 9.357665770419244e-06,
1857
+ "loss": 0.0998,
1858
+ "step": 263
1859
+ },
1860
+ {
1861
+ "epoch": 1.65,
1862
+ "grad_norm": 0.132551181762264,
1863
+ "learning_rate": 9.042397785550405e-06,
1864
+ "loss": 0.1083,
1865
+ "step": 264
1866
+ },
1867
+ {
1868
+ "epoch": 1.65625,
1869
+ "grad_norm": 0.17245754726915724,
1870
+ "learning_rate": 8.732003345756811e-06,
1871
+ "loss": 0.118,
1872
+ "step": 265
1873
+ },
1874
+ {
1875
+ "epoch": 1.6625,
1876
+ "grad_norm": 0.13788212679850506,
1877
+ "learning_rate": 8.426519384872733e-06,
1878
+ "loss": 0.1088,
1879
+ "step": 266
1880
+ },
1881
+ {
1882
+ "epoch": 1.66875,
1883
+ "grad_norm": 0.16823545202946685,
1884
+ "learning_rate": 8.125982252434611e-06,
1885
+ "loss": 0.1239,
1886
+ "step": 267
1887
+ },
1888
+ {
1889
+ "epoch": 1.675,
1890
+ "grad_norm": 0.13554434267304058,
1891
+ "learning_rate": 7.830427709355725e-06,
1892
+ "loss": 0.1164,
1893
+ "step": 268
1894
+ },
1895
+ {
1896
+ "epoch": 1.68125,
1897
+ "grad_norm": 0.12270084667138997,
1898
+ "learning_rate": 7.539890923671062e-06,
1899
+ "loss": 0.0855,
1900
+ "step": 269
1901
+ },
1902
+ {
1903
+ "epoch": 1.6875,
1904
+ "grad_norm": 0.1610350461050514,
1905
+ "learning_rate": 7.2544064663526815e-06,
1906
+ "loss": 0.1395,
1907
+ "step": 270
1908
+ },
1909
+ {
1910
+ "epoch": 1.69375,
1911
+ "grad_norm": 0.13371983154995107,
1912
+ "learning_rate": 6.974008307196056e-06,
1913
+ "loss": 0.1081,
1914
+ "step": 271
1915
+ },
1916
+ {
1917
+ "epoch": 1.7,
1918
+ "grad_norm": 0.15579745002988243,
1919
+ "learning_rate": 6.698729810778065e-06,
1920
+ "loss": 0.1358,
1921
+ "step": 272
1922
+ },
1923
+ {
1924
+ "epoch": 1.70625,
1925
+ "grad_norm": 0.13901889620059626,
1926
+ "learning_rate": 6.428603732486937e-06,
1927
+ "loss": 0.1208,
1928
+ "step": 273
1929
+ },
1930
+ {
1931
+ "epoch": 1.7125,
1932
+ "grad_norm": 0.15932824101956905,
1933
+ "learning_rate": 6.163662214624616e-06,
1934
+ "loss": 0.1208,
1935
+ "step": 274
1936
+ },
1937
+ {
1938
+ "epoch": 1.71875,
1939
+ "grad_norm": 0.14809539420100104,
1940
+ "learning_rate": 5.903936782582253e-06,
1941
+ "loss": 0.0961,
1942
+ "step": 275
1943
+ },
1944
+ {
1945
+ "epoch": 1.725,
1946
+ "grad_norm": 0.14762764130305206,
1947
+ "learning_rate": 5.649458341088915e-06,
1948
+ "loss": 0.1328,
1949
+ "step": 276
1950
+ },
1951
+ {
1952
+ "epoch": 1.73125,
1953
+ "grad_norm": 0.14698627279133403,
1954
+ "learning_rate": 5.400257170534295e-06,
1955
+ "loss": 0.1137,
1956
+ "step": 277
1957
+ },
1958
+ {
1959
+ "epoch": 1.7375,
1960
+ "grad_norm": 0.12766172584371513,
1961
+ "learning_rate": 5.156362923365588e-06,
1962
+ "loss": 0.0963,
1963
+ "step": 278
1964
+ },
1965
+ {
1966
+ "epoch": 1.74375,
1967
+ "grad_norm": 0.15550557920695354,
1968
+ "learning_rate": 4.917804620559202e-06,
1969
+ "loss": 0.1299,
1970
+ "step": 279
1971
+ },
1972
+ {
1973
+ "epoch": 1.75,
1974
+ "grad_norm": 0.13371200089329044,
1975
+ "learning_rate": 4.684610648167503e-06,
1976
+ "loss": 0.1003,
1977
+ "step": 280
1978
+ },
1979
+ {
1980
+ "epoch": 1.75625,
1981
+ "grad_norm": 0.19718769962541566,
1982
+ "learning_rate": 4.456808753941205e-06,
1983
+ "loss": 0.1005,
1984
+ "step": 281
1985
+ },
1986
+ {
1987
+ "epoch": 1.7625,
1988
+ "grad_norm": 0.14609277866526107,
1989
+ "learning_rate": 4.234426044027645e-06,
1990
+ "loss": 0.1184,
1991
+ "step": 282
1992
+ },
1993
+ {
1994
+ "epoch": 1.76875,
1995
+ "grad_norm": 0.13846373587108526,
1996
+ "learning_rate": 4.017488979745387e-06,
1997
+ "loss": 0.1083,
1998
+ "step": 283
1999
+ },
2000
+ {
2001
+ "epoch": 1.775,
2002
+ "grad_norm": 0.16152586345422645,
2003
+ "learning_rate": 3.8060233744356633e-06,
2004
+ "loss": 0.1349,
2005
+ "step": 284
2006
+ },
2007
+ {
2008
+ "epoch": 1.78125,
2009
+ "grad_norm": 0.15220108167136218,
2010
+ "learning_rate": 3.600054390390778e-06,
2011
+ "loss": 0.1189,
2012
+ "step": 285
2013
+ },
2014
+ {
2015
+ "epoch": 1.7875,
2016
+ "grad_norm": 0.14825944302091063,
2017
+ "learning_rate": 3.3996065358600782e-06,
2018
+ "loss": 0.1124,
2019
+ "step": 286
2020
+ },
2021
+ {
2022
+ "epoch": 1.79375,
2023
+ "grad_norm": 0.17101334397597814,
2024
+ "learning_rate": 3.2047036621337236e-06,
2025
+ "loss": 0.1242,
2026
+ "step": 287
2027
+ },
2028
+ {
2029
+ "epoch": 1.8,
2030
+ "grad_norm": 0.15468868193258223,
2031
+ "learning_rate": 3.0153689607045845e-06,
2032
+ "loss": 0.1269,
2033
+ "step": 288
2034
+ },
2035
+ {
2036
+ "epoch": 1.80625,
2037
+ "grad_norm": 0.13742574401888047,
2038
+ "learning_rate": 2.8316249605087386e-06,
2039
+ "loss": 0.108,
2040
+ "step": 289
2041
+ },
2042
+ {
2043
+ "epoch": 1.8125,
2044
+ "grad_norm": 0.12723180285999527,
2045
+ "learning_rate": 2.653493525244721e-06,
2046
+ "loss": 0.104,
2047
+ "step": 290
2048
+ },
2049
+ {
2050
+ "epoch": 1.81875,
2051
+ "grad_norm": 0.15299833624657141,
2052
+ "learning_rate": 2.4809958507719444e-06,
2053
+ "loss": 0.1227,
2054
+ "step": 291
2055
+ },
2056
+ {
2057
+ "epoch": 1.825,
2058
+ "grad_norm": 0.153187221540368,
2059
+ "learning_rate": 2.314152462588659e-06,
2060
+ "loss": 0.1122,
2061
+ "step": 292
2062
+ },
2063
+ {
2064
+ "epoch": 1.83125,
2065
+ "grad_norm": 0.1566217766687287,
2066
+ "learning_rate": 2.152983213389559e-06,
2067
+ "loss": 0.1206,
2068
+ "step": 293
2069
+ },
2070
+ {
2071
+ "epoch": 1.8375,
2072
+ "grad_norm": 0.1619426370013769,
2073
+ "learning_rate": 1.99750728070357e-06,
2074
+ "loss": 0.0849,
2075
+ "step": 294
2076
+ },
2077
+ {
2078
+ "epoch": 1.84375,
2079
+ "grad_norm": 0.1440771616743465,
2080
+ "learning_rate": 1.8477431646118648e-06,
2081
+ "loss": 0.1168,
2082
+ "step": 295
2083
+ },
2084
+ {
2085
+ "epoch": 1.85,
2086
+ "grad_norm": 0.1266403405941791,
2087
+ "learning_rate": 1.70370868554659e-06,
2088
+ "loss": 0.1002,
2089
+ "step": 296
2090
+ },
2091
+ {
2092
+ "epoch": 1.85625,
2093
+ "grad_norm": 0.14490235679395352,
2094
+ "learning_rate": 1.565420982170346e-06,
2095
+ "loss": 0.1204,
2096
+ "step": 297
2097
+ },
2098
+ {
2099
+ "epoch": 1.8625,
2100
+ "grad_norm": 0.14214631954361082,
2101
+ "learning_rate": 1.4328965093369283e-06,
2102
+ "loss": 0.1052,
2103
+ "step": 298
2104
+ },
2105
+ {
2106
+ "epoch": 1.86875,
2107
+ "grad_norm": 0.15125342239263603,
2108
+ "learning_rate": 1.3061510361333185e-06,
2109
+ "loss": 0.1185,
2110
+ "step": 299
2111
+ },
2112
+ {
2113
+ "epoch": 1.875,
2114
+ "grad_norm": 0.14873736163107223,
2115
+ "learning_rate": 1.1851996440033319e-06,
2116
+ "loss": 0.1372,
2117
+ "step": 300
2118
+ },
2119
+ {
2120
+ "epoch": 1.88125,
2121
+ "grad_norm": 0.15823839872382495,
2122
+ "learning_rate": 1.0700567249530834e-06,
2123
+ "loss": 0.1374,
2124
+ "step": 301
2125
+ },
2126
+ {
2127
+ "epoch": 1.8875,
2128
+ "grad_norm": 0.1477147886939706,
2129
+ "learning_rate": 9.607359798384785e-07,
2130
+ "loss": 0.1265,
2131
+ "step": 302
2132
+ },
2133
+ {
2134
+ "epoch": 1.89375,
2135
+ "grad_norm": 0.149870799299156,
2136
+ "learning_rate": 8.572504167349449e-07,
2137
+ "loss": 0.1156,
2138
+ "step": 303
2139
+ },
2140
+ {
2141
+ "epoch": 1.9,
2142
+ "grad_norm": 0.13907104929191907,
2143
+ "learning_rate": 7.596123493895991e-07,
2144
+ "loss": 0.1131,
2145
+ "step": 304
2146
+ },
2147
+ {
2148
+ "epoch": 1.90625,
2149
+ "grad_norm": 0.1438881017950769,
2150
+ "learning_rate": 6.678333957560512e-07,
2151
+ "loss": 0.1212,
2152
+ "step": 305
2153
+ },
2154
+ {
2155
+ "epoch": 1.9125,
2156
+ "grad_norm": 0.14174173341102103,
2157
+ "learning_rate": 5.81924476611967e-07,
2158
+ "loss": 0.1249,
2159
+ "step": 306
2160
+ },
2161
+ {
2162
+ "epoch": 1.91875,
2163
+ "grad_norm": 0.1409441874264998,
2164
+ "learning_rate": 5.018958142596065e-07,
2165
+ "loss": 0.1123,
2166
+ "step": 307
2167
+ },
2168
+ {
2169
+ "epoch": 1.925,
2170
+ "grad_norm": 0.16658637594296666,
2171
+ "learning_rate": 4.277569313094809e-07,
2172
+ "loss": 0.1017,
2173
+ "step": 308
2174
+ },
2175
+ {
2176
+ "epoch": 1.93125,
2177
+ "grad_norm": 0.1767438653947937,
2178
+ "learning_rate": 3.59516649547248e-07,
2179
+ "loss": 0.1265,
2180
+ "step": 309
2181
+ },
2182
+ {
2183
+ "epoch": 1.9375,
2184
+ "grad_norm": 0.15957908409005475,
2185
+ "learning_rate": 2.971830888840177e-07,
2186
+ "loss": 0.139,
2187
+ "step": 310
2188
+ },
2189
+ {
2190
+ "epoch": 1.94375,
2191
+ "grad_norm": 0.13358713671440797,
2192
+ "learning_rate": 2.407636663901591e-07,
2193
+ "loss": 0.1015,
2194
+ "step": 311
2195
+ },
2196
+ {
2197
+ "epoch": 1.95,
2198
+ "grad_norm": 0.14596552013446734,
2199
+ "learning_rate": 1.9026509541272275e-07,
2200
+ "loss": 0.1294,
2201
+ "step": 312
2202
+ },
2203
+ {
2204
+ "epoch": 1.95625,
2205
+ "grad_norm": 0.15582989274250142,
2206
+ "learning_rate": 1.4569338477666838e-07,
2207
+ "loss": 0.1282,
2208
+ "step": 313
2209
+ },
2210
+ {
2211
+ "epoch": 1.9625,
2212
+ "grad_norm": 0.14404601592111216,
2213
+ "learning_rate": 1.0705383806982606e-07,
2214
+ "loss": 0.1103,
2215
+ "step": 314
2216
+ },
2217
+ {
2218
+ "epoch": 1.96875,
2219
+ "grad_norm": 0.1591129940081992,
2220
+ "learning_rate": 7.43510530118452e-08,
2221
+ "loss": 0.1114,
2222
+ "step": 315
2223
+ },
2224
+ {
2225
+ "epoch": 1.975,
2226
+ "grad_norm": 0.14377087428625243,
2227
+ "learning_rate": 4.7588920907110094e-08,
2228
+ "loss": 0.1202,
2229
+ "step": 316
2230
+ },
2231
+ {
2232
+ "epoch": 1.98125,
2233
+ "grad_norm": 0.14890980505746196,
2234
+ "learning_rate": 2.6770626181715773e-08,
2235
+ "loss": 0.1172,
2236
+ "step": 317
2237
+ },
2238
+ {
2239
+ "epoch": 1.9875,
2240
+ "grad_norm": 0.1536343383847314,
2241
+ "learning_rate": 1.189864600454338e-08,
2242
+ "loss": 0.1239,
2243
+ "step": 318
2244
+ },
2245
+ {
2246
+ "epoch": 1.99375,
2247
+ "grad_norm": 0.15806075985905502,
2248
+ "learning_rate": 2.974749992512571e-09,
2249
+ "loss": 0.1275,
2250
+ "step": 319
2251
+ },
2252
+ {
2253
+ "epoch": 2.0,
2254
+ "grad_norm": 0.14605676768659354,
2255
+ "learning_rate": 0.0,
2256
+ "loss": 0.1243,
2257
+ "step": 320
2258
+ },
2259
+ {
2260
+ "epoch": 2.0,
2261
+ "step": 320,
2262
+ "total_flos": 1567061767618560.0,
2263
+ "train_loss": 0.15366401586215944,
2264
+ "train_runtime": 5710.924,
2265
+ "train_samples_per_second": 0.224,
2266
+ "train_steps_per_second": 0.056
2267
+ }
2268
+ ],
2269
+ "logging_steps": 1,
2270
+ "max_steps": 320,
2271
+ "num_input_tokens_seen": 0,
2272
+ "num_train_epochs": 2,
2273
+ "save_steps": 300,
2274
+ "stateful_callbacks": {
2275
+ "TrainerControl": {
2276
+ "args": {
2277
+ "should_epoch_stop": false,
2278
+ "should_evaluate": false,
2279
+ "should_log": false,
2280
+ "should_save": true,
2281
+ "should_training_stop": true
2282
+ },
2283
+ "attributes": {}
2284
+ }
2285
+ },
2286
+ "total_flos": 1567061767618560.0,
2287
+ "train_batch_size": 1,
2288
+ "trial_name": null,
2289
+ "trial_params": null
2290
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7c56b9e15c83b2ad5f829fdc2b274b9f76b9822e10cc56598d90479f535ccb9
3
+ size 7224
training_eval_loss.png ADDED
training_loss.png ADDED