Safetensors
Eval Results
NeuralNovel commited on
Commit
767248b
1 Parent(s): a3c0c16

Upload folder using huggingface_hub

Browse files
.ipynb_checkpoints/README-checkpoint.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: peft
4
+ tags:
5
+ - llama-factory
6
+ - lora
7
+ - generated_from_trainer
8
+ base_model: abacusai/Smaug-72B-v0.1
9
+ model-index:
10
+ - name: train_2024-02-17-03-49-55
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
+ # train_2024-02-17-03-49-55
18
+
19
+ This model is a fine-tuned version of [abacusai/Smaug-72B-v0.1](https://huggingface.co/abacusai/Smaug-72B-v0.1) on the Neural-DPO dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.001
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 8
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - num_epochs: 3.0
47
+
48
+ ### Training results
49
+
50
+
51
+
52
+ ### Framework versions
53
+
54
+ - PEFT 0.8.2
55
+ - Transformers 4.37.2
56
+ - Pytorch 2.2.0+cu121
57
+ - Datasets 2.17.0
58
+ - Tokenizers 0.15.2
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: peft
4
+ tags:
5
+ - llama-factory
6
+ - lora
7
+ - generated_from_trainer
8
+ base_model: abacusai/Smaug-72B-v0.1
9
+ model-index:
10
+ - name: train_2024-02-17-03-49-55
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
+ # train_2024-02-17-03-49-55
18
+
19
+ This model is a fine-tuned version of [abacusai/Smaug-72B-v0.1](https://huggingface.co/abacusai/Smaug-72B-v0.1) on the Neural-DPO dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.001
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 8
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - num_epochs: 3.0
47
+
48
+ ### Training results
49
+
50
+
51
+
52
+ ### Framework versions
53
+
54
+ - PEFT 0.8.2
55
+ - Transformers 4.37.2
56
+ - Pytorch 2.2.0+cu121
57
+ - Datasets 2.17.0
58
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "abacusai/Smaug-72B-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj",
23
+ "v_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_rslora": false
27
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6440043dbeb9fe7771c6e93f272b86d815d11c916af2fa4a3a87d6c19346e807
3
+ size 83928872
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.98,
3
+ "train_loss": 1.0966757915236733,
4
+ "train_runtime": 4531.1008,
5
+ "train_samples_per_second": 0.703,
6
+ "train_steps_per_second": 0.087
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|im_end|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,1680 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|extra_0|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|extra_1|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|extra_2|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|extra_3|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|extra_4|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|extra_5|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|extra_6|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|extra_7|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|extra_8|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|extra_9|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|extra_10|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<|extra_11|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "151658": {
126
+ "content": "<|extra_12|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "151659": {
134
+ "content": "<|extra_13|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "151660": {
142
+ "content": "<|extra_14|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "151661": {
150
+ "content": "<|extra_15|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "151662": {
158
+ "content": "<|extra_16|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "151663": {
166
+ "content": "<|extra_17|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "151664": {
174
+ "content": "<|extra_18|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "151665": {
182
+ "content": "<|extra_19|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<|extra_20|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "<|extra_21|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "151668": {
206
+ "content": "<|extra_22|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "151669": {
214
+ "content": "<|extra_23|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<|extra_24|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<|extra_25|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<|extra_26|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "<|extra_27|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<|extra_28|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "<|extra_29|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "151676": {
270
+ "content": "<|extra_30|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "151677": {
278
+ "content": "<|extra_31|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "151678": {
286
+ "content": "<|extra_32|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "151679": {
294
+ "content": "<|extra_33|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "151680": {
302
+ "content": "<|extra_34|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "151681": {
310
+ "content": "<|extra_35|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "151682": {
318
+ "content": "<|extra_36|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "151683": {
326
+ "content": "<|extra_37|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "151684": {
334
+ "content": "<|extra_38|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "151685": {
342
+ "content": "<|extra_39|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "151686": {
350
+ "content": "<|extra_40|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "151687": {
358
+ "content": "<|extra_41|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "151688": {
366
+ "content": "<|extra_42|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "151689": {
374
+ "content": "<|extra_43|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "151690": {
382
+ "content": "<|extra_44|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "151691": {
390
+ "content": "<|extra_45|>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "151692": {
398
+ "content": "<|extra_46|>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "151693": {
406
+ "content": "<|extra_47|>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "151694": {
414
+ "content": "<|extra_48|>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "151695": {
422
+ "content": "<|extra_49|>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "151696": {
430
+ "content": "<|extra_50|>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "151697": {
438
+ "content": "<|extra_51|>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "151698": {
446
+ "content": "<|extra_52|>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "151699": {
454
+ "content": "<|extra_53|>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "151700": {
462
+ "content": "<|extra_54|>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "151701": {
470
+ "content": "<|extra_55|>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "151702": {
478
+ "content": "<|extra_56|>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "151703": {
486
+ "content": "<|extra_57|>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "151704": {
494
+ "content": "<|extra_58|>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "151705": {
502
+ "content": "<|extra_59|>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "151706": {
510
+ "content": "<|extra_60|>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "151707": {
518
+ "content": "<|extra_61|>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "151708": {
526
+ "content": "<|extra_62|>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "151709": {
534
+ "content": "<|extra_63|>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "151710": {
542
+ "content": "<|extra_64|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "151711": {
550
+ "content": "<|extra_65|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "151712": {
558
+ "content": "<|extra_66|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "151713": {
566
+ "content": "<|extra_67|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "151714": {
574
+ "content": "<|extra_68|>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "151715": {
582
+ "content": "<|extra_69|>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "151716": {
590
+ "content": "<|extra_70|>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "151717": {
598
+ "content": "<|extra_71|>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "151718": {
606
+ "content": "<|extra_72|>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "151719": {
614
+ "content": "<|extra_73|>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "151720": {
622
+ "content": "<|extra_74|>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "151721": {
630
+ "content": "<|extra_75|>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "151722": {
638
+ "content": "<|extra_76|>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "151723": {
646
+ "content": "<|extra_77|>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "151724": {
654
+ "content": "<|extra_78|>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "151725": {
662
+ "content": "<|extra_79|>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "151726": {
670
+ "content": "<|extra_80|>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "151727": {
678
+ "content": "<|extra_81|>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "151728": {
686
+ "content": "<|extra_82|>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "151729": {
694
+ "content": "<|extra_83|>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "151730": {
702
+ "content": "<|extra_84|>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "151731": {
710
+ "content": "<|extra_85|>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "151732": {
718
+ "content": "<|extra_86|>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "151733": {
726
+ "content": "<|extra_87|>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "151734": {
734
+ "content": "<|extra_88|>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "151735": {
742
+ "content": "<|extra_89|>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "151736": {
750
+ "content": "<|extra_90|>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "151737": {
758
+ "content": "<|extra_91|>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "151738": {
766
+ "content": "<|extra_92|>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ },
773
+ "151739": {
774
+ "content": "<|extra_93|>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": true
780
+ },
781
+ "151740": {
782
+ "content": "<|extra_94|>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": true
788
+ },
789
+ "151741": {
790
+ "content": "<|extra_95|>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": true
796
+ },
797
+ "151742": {
798
+ "content": "<|extra_96|>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": true
804
+ },
805
+ "151743": {
806
+ "content": "<|extra_97|>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": true
812
+ },
813
+ "151744": {
814
+ "content": "<|extra_98|>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": true
820
+ },
821
+ "151745": {
822
+ "content": "<|extra_99|>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": true
828
+ },
829
+ "151746": {
830
+ "content": "<|extra_100|>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": true
836
+ },
837
+ "151747": {
838
+ "content": "<|extra_101|>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": true
844
+ },
845
+ "151748": {
846
+ "content": "<|extra_102|>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": true
852
+ },
853
+ "151749": {
854
+ "content": "<|extra_103|>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "151750": {
862
+ "content": "<|extra_104|>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "151751": {
870
+ "content": "<|extra_105|>",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": true
876
+ },
877
+ "151752": {
878
+ "content": "<|extra_106|>",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": true
884
+ },
885
+ "151753": {
886
+ "content": "<|extra_107|>",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": true
892
+ },
893
+ "151754": {
894
+ "content": "<|extra_108|>",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": true
900
+ },
901
+ "151755": {
902
+ "content": "<|extra_109|>",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": true
908
+ },
909
+ "151756": {
910
+ "content": "<|extra_110|>",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": true
916
+ },
917
+ "151757": {
918
+ "content": "<|extra_111|>",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": true
924
+ },
925
+ "151758": {
926
+ "content": "<|extra_112|>",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": true
932
+ },
933
+ "151759": {
934
+ "content": "<|extra_113|>",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": true
940
+ },
941
+ "151760": {
942
+ "content": "<|extra_114|>",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": true
948
+ },
949
+ "151761": {
950
+ "content": "<|extra_115|>",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": true
956
+ },
957
+ "151762": {
958
+ "content": "<|extra_116|>",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": true
964
+ },
965
+ "151763": {
966
+ "content": "<|extra_117|>",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": true
972
+ },
973
+ "151764": {
974
+ "content": "<|extra_118|>",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": true
980
+ },
981
+ "151765": {
982
+ "content": "<|extra_119|>",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": true
988
+ },
989
+ "151766": {
990
+ "content": "<|extra_120|>",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": true
996
+ },
997
+ "151767": {
998
+ "content": "<|extra_121|>",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": true
1004
+ },
1005
+ "151768": {
1006
+ "content": "<|extra_122|>",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": true
1012
+ },
1013
+ "151769": {
1014
+ "content": "<|extra_123|>",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": true
1020
+ },
1021
+ "151770": {
1022
+ "content": "<|extra_124|>",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": true
1028
+ },
1029
+ "151771": {
1030
+ "content": "<|extra_125|>",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": true
1036
+ },
1037
+ "151772": {
1038
+ "content": "<|extra_126|>",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": true
1044
+ },
1045
+ "151773": {
1046
+ "content": "<|extra_127|>",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": true
1052
+ },
1053
+ "151774": {
1054
+ "content": "<|extra_128|>",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": true
1060
+ },
1061
+ "151775": {
1062
+ "content": "<|extra_129|>",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": true
1068
+ },
1069
+ "151776": {
1070
+ "content": "<|extra_130|>",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": true
1076
+ },
1077
+ "151777": {
1078
+ "content": "<|extra_131|>",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": true
1084
+ },
1085
+ "151778": {
1086
+ "content": "<|extra_132|>",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": true
1092
+ },
1093
+ "151779": {
1094
+ "content": "<|extra_133|>",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": true
1100
+ },
1101
+ "151780": {
1102
+ "content": "<|extra_134|>",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": true
1108
+ },
1109
+ "151781": {
1110
+ "content": "<|extra_135|>",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": true
1116
+ },
1117
+ "151782": {
1118
+ "content": "<|extra_136|>",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": true
1124
+ },
1125
+ "151783": {
1126
+ "content": "<|extra_137|>",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": true
1132
+ },
1133
+ "151784": {
1134
+ "content": "<|extra_138|>",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": true
1140
+ },
1141
+ "151785": {
1142
+ "content": "<|extra_139|>",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": true
1148
+ },
1149
+ "151786": {
1150
+ "content": "<|extra_140|>",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": true
1156
+ },
1157
+ "151787": {
1158
+ "content": "<|extra_141|>",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": true
1164
+ },
1165
+ "151788": {
1166
+ "content": "<|extra_142|>",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": true
1172
+ },
1173
+ "151789": {
1174
+ "content": "<|extra_143|>",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": true
1180
+ },
1181
+ "151790": {
1182
+ "content": "<|extra_144|>",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": true
1188
+ },
1189
+ "151791": {
1190
+ "content": "<|extra_145|>",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": true
1196
+ },
1197
+ "151792": {
1198
+ "content": "<|extra_146|>",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": true
1204
+ },
1205
+ "151793": {
1206
+ "content": "<|extra_147|>",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": true
1212
+ },
1213
+ "151794": {
1214
+ "content": "<|extra_148|>",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": true
1220
+ },
1221
+ "151795": {
1222
+ "content": "<|extra_149|>",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": true
1228
+ },
1229
+ "151796": {
1230
+ "content": "<|extra_150|>",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": true
1236
+ },
1237
+ "151797": {
1238
+ "content": "<|extra_151|>",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": true
1244
+ },
1245
+ "151798": {
1246
+ "content": "<|extra_152|>",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": true
1252
+ },
1253
+ "151799": {
1254
+ "content": "<|extra_153|>",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": true
1260
+ },
1261
+ "151800": {
1262
+ "content": "<|extra_154|>",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": true
1268
+ },
1269
+ "151801": {
1270
+ "content": "<|extra_155|>",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": true
1276
+ },
1277
+ "151802": {
1278
+ "content": "<|extra_156|>",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": true
1284
+ },
1285
+ "151803": {
1286
+ "content": "<|extra_157|>",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": true
1292
+ },
1293
+ "151804": {
1294
+ "content": "<|extra_158|>",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": true
1300
+ },
1301
+ "151805": {
1302
+ "content": "<|extra_159|>",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": true
1308
+ },
1309
+ "151806": {
1310
+ "content": "<|extra_160|>",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": true
1316
+ },
1317
+ "151807": {
1318
+ "content": "<|extra_161|>",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": true
1324
+ },
1325
+ "151808": {
1326
+ "content": "<|extra_162|>",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": true
1332
+ },
1333
+ "151809": {
1334
+ "content": "<|extra_163|>",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": true
1340
+ },
1341
+ "151810": {
1342
+ "content": "<|extra_164|>",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": true
1348
+ },
1349
+ "151811": {
1350
+ "content": "<|extra_165|>",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": true
1356
+ },
1357
+ "151812": {
1358
+ "content": "<|extra_166|>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": true
1364
+ },
1365
+ "151813": {
1366
+ "content": "<|extra_167|>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": true
1372
+ },
1373
+ "151814": {
1374
+ "content": "<|extra_168|>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": true
1380
+ },
1381
+ "151815": {
1382
+ "content": "<|extra_169|>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": true
1388
+ },
1389
+ "151816": {
1390
+ "content": "<|extra_170|>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": true
1396
+ },
1397
+ "151817": {
1398
+ "content": "<|extra_171|>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": true
1404
+ },
1405
+ "151818": {
1406
+ "content": "<|extra_172|>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": true
1412
+ },
1413
+ "151819": {
1414
+ "content": "<|extra_173|>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": true
1420
+ },
1421
+ "151820": {
1422
+ "content": "<|extra_174|>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": true
1428
+ },
1429
+ "151821": {
1430
+ "content": "<|extra_175|>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": true
1436
+ },
1437
+ "151822": {
1438
+ "content": "<|extra_176|>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": true
1444
+ },
1445
+ "151823": {
1446
+ "content": "<|extra_177|>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": true
1452
+ },
1453
+ "151824": {
1454
+ "content": "<|extra_178|>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": true
1460
+ },
1461
+ "151825": {
1462
+ "content": "<|extra_179|>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": true
1468
+ },
1469
+ "151826": {
1470
+ "content": "<|extra_180|>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": true
1476
+ },
1477
+ "151827": {
1478
+ "content": "<|extra_181|>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": true
1484
+ },
1485
+ "151828": {
1486
+ "content": "<|extra_182|>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": true
1492
+ },
1493
+ "151829": {
1494
+ "content": "<|extra_183|>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": true
1500
+ },
1501
+ "151830": {
1502
+ "content": "<|extra_184|>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": true
1508
+ },
1509
+ "151831": {
1510
+ "content": "<|extra_185|>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": true
1516
+ },
1517
+ "151832": {
1518
+ "content": "<|extra_186|>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": true
1524
+ },
1525
+ "151833": {
1526
+ "content": "<|extra_187|>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": true
1532
+ },
1533
+ "151834": {
1534
+ "content": "<|extra_188|>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": true
1540
+ },
1541
+ "151835": {
1542
+ "content": "<|extra_189|>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": true
1548
+ },
1549
+ "151836": {
1550
+ "content": "<|extra_190|>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": true
1556
+ },
1557
+ "151837": {
1558
+ "content": "<|extra_191|>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": true
1564
+ },
1565
+ "151838": {
1566
+ "content": "<|extra_192|>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": true
1572
+ },
1573
+ "151839": {
1574
+ "content": "<|extra_193|>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": true
1580
+ },
1581
+ "151840": {
1582
+ "content": "<|extra_194|>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": true
1588
+ },
1589
+ "151841": {
1590
+ "content": "<|extra_195|>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": true
1596
+ },
1597
+ "151842": {
1598
+ "content": "<|extra_196|>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": true
1604
+ },
1605
+ "151843": {
1606
+ "content": "<|extra_197|>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": true
1612
+ },
1613
+ "151844": {
1614
+ "content": "<|extra_198|>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": true
1620
+ },
1621
+ "151845": {
1622
+ "content": "<|extra_199|>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": true
1628
+ },
1629
+ "151846": {
1630
+ "content": "<|extra_200|>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": true
1636
+ },
1637
+ "151847": {
1638
+ "content": "<|extra_201|>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": true
1644
+ },
1645
+ "151848": {
1646
+ "content": "<|extra_202|>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": true
1652
+ },
1653
+ "151849": {
1654
+ "content": "<|extra_203|>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": true
1660
+ },
1661
+ "151850": {
1662
+ "content": "<|extra_204|>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": true
1668
+ }
1669
+ },
1670
+ "bos_token": "<|endoftext|>",
1671
+ "clean_up_tokenization_spaces": true,
1672
+ "eos_token": "<|im_end|>",
1673
+ "errors": "replace",
1674
+ "model_max_length": 4096,
1675
+ "pad_token": "<|im_end|>",
1676
+ "padding_side": "right",
1677
+ "split_special_tokens": false,
1678
+ "tokenizer_class": "GPT2Tokenizer",
1679
+ "unk_token": "<|endoftext|>"
1680
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.98,
3
+ "train_loss": 1.0966757915236733,
4
+ "train_runtime": 4531.1008,
5
+ "train_samples_per_second": 0.703,
6
+ "train_steps_per_second": 0.087
7
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 5, "total_steps": 396, "loss": 2.8429, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009996066923030483, "epoch": 0.04, "percentage": 1.26, "elapsed_time": "0:00:51", "remaining_time": "1:07:21"}
2
+ {"current_steps": 10, "total_steps": 396, "loss": 1.7586, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009984273879759713, "epoch": 0.08, "percentage": 2.53, "elapsed_time": "0:01:40", "remaining_time": "1:04:35"}
3
+ {"current_steps": 15, "total_steps": 396, "loss": 1.7084, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009964639423366442, "epoch": 0.11, "percentage": 3.79, "elapsed_time": "0:02:29", "remaining_time": "1:03:07"}
4
+ {"current_steps": 20, "total_steps": 396, "loss": 1.7022, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009937194443381972, "epoch": 0.15, "percentage": 5.05, "elapsed_time": "0:03:17", "remaining_time": "1:01:57"}
5
+ {"current_steps": 25, "total_steps": 396, "loss": 1.436, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009901982117093786, "epoch": 0.19, "percentage": 6.31, "elapsed_time": "0:04:06", "remaining_time": "1:00:55"}
6
+ {"current_steps": 30, "total_steps": 396, "loss": 1.5345, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000985905784161771, "epoch": 0.23, "percentage": 7.58, "elapsed_time": "0:04:55", "remaining_time": "1:00:00"}
7
+ {"current_steps": 35, "total_steps": 396, "loss": 1.5542, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009808489146745465, "epoch": 0.26, "percentage": 8.84, "elapsed_time": "0:05:43", "remaining_time": "0:59:03"}
8
+ {"current_steps": 40, "total_steps": 396, "loss": 1.5173, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009750355588704727, "epoch": 0.3, "percentage": 10.1, "elapsed_time": "0:06:32", "remaining_time": "0:58:08"}
9
+ {"current_steps": 45, "total_steps": 396, "loss": 1.4094, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000968474862499881, "epoch": 0.34, "percentage": 11.36, "elapsed_time": "0:07:20", "remaining_time": "0:57:18"}
10
+ {"current_steps": 50, "total_steps": 396, "loss": 1.6779, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009611771470522907, "epoch": 0.38, "percentage": 12.63, "elapsed_time": "0:08:08", "remaining_time": "0:56:23"}
11
+ {"current_steps": 55, "total_steps": 396, "loss": 1.593, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009531538935183251, "epoch": 0.41, "percentage": 13.89, "elapsed_time": "0:08:57", "remaining_time": "0:55:30"}
12
+ {"current_steps": 60, "total_steps": 396, "loss": 1.8026, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009444177243274617, "epoch": 0.45, "percentage": 15.15, "elapsed_time": "0:09:45", "remaining_time": "0:54:39"}
13
+ {"current_steps": 65, "total_steps": 396, "loss": 1.1646, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009349823834900395, "epoch": 0.49, "percentage": 16.41, "elapsed_time": "0:10:36", "remaining_time": "0:54:00"}
14
+ {"current_steps": 70, "total_steps": 396, "loss": 1.4566, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009248627149747573, "epoch": 0.53, "percentage": 17.68, "elapsed_time": "0:11:24", "remaining_time": "0:53:08"}
15
+ {"current_steps": 75, "total_steps": 396, "loss": 1.3848, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009140746393556853, "epoch": 0.56, "percentage": 18.94, "elapsed_time": "0:12:13", "remaining_time": "0:52:19"}
16
+ {"current_steps": 80, "total_steps": 396, "loss": 1.6641, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0009026351287655293, "epoch": 0.6, "percentage": 20.2, "elapsed_time": "0:13:01", "remaining_time": "0:51:28"}
17
+ {"current_steps": 85, "total_steps": 396, "loss": 1.2664, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008905621801945467, "epoch": 0.64, "percentage": 21.46, "elapsed_time": "0:13:50", "remaining_time": "0:50:40"}
18
+ {"current_steps": 90, "total_steps": 396, "loss": 1.4103, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008778747871771292, "epoch": 0.68, "percentage": 22.73, "elapsed_time": "0:14:40", "remaining_time": "0:49:52"}
19
+ {"current_steps": 95, "total_steps": 396, "loss": 1.3391, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008645929099105886, "epoch": 0.72, "percentage": 23.99, "elapsed_time": "0:15:28", "remaining_time": "0:49:03"}
20
+ {"current_steps": 100, "total_steps": 396, "loss": 1.3329, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008507374438531607, "epoch": 0.75, "percentage": 25.25, "elapsed_time": "0:16:17", "remaining_time": "0:48:13"}
21
+ {"current_steps": 105, "total_steps": 396, "loss": 1.4708, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008363301868506264, "epoch": 0.79, "percentage": 26.52, "elapsed_time": "0:17:07", "remaining_time": "0:47:26"}
22
+ {"current_steps": 110, "total_steps": 396, "loss": 1.5326, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008213938048432696, "epoch": 0.83, "percentage": 27.78, "elapsed_time": "0:17:56", "remaining_time": "0:46:37"}
23
+ {"current_steps": 115, "total_steps": 396, "loss": 1.5317, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0008059517962071233, "epoch": 0.87, "percentage": 29.04, "elapsed_time": "0:18:45", "remaining_time": "0:45:49"}
24
+ {"current_steps": 120, "total_steps": 396, "loss": 1.2481, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0007900284547855992, "epoch": 0.9, "percentage": 30.3, "elapsed_time": "0:19:34", "remaining_time": "0:45:00"}
25
+ {"current_steps": 125, "total_steps": 396, "loss": 1.4773, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0007736488316696662, "epoch": 0.94, "percentage": 31.57, "elapsed_time": "0:20:23", "remaining_time": "0:44:11"}
26
+ {"current_steps": 130, "total_steps": 396, "loss": 1.2638, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0007568386957867032, "epoch": 0.98, "percentage": 32.83, "elapsed_time": "0:21:11", "remaining_time": "0:43:22"}
27
+ {"current_steps": 135, "total_steps": 396, "loss": 1.2867, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0007396244933600284, "epoch": 1.02, "percentage": 34.09, "elapsed_time": "0:22:00", "remaining_time": "0:42:32"}
28
+ {"current_steps": 140, "total_steps": 396, "loss": 1.0248, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0007220333063028871, "epoch": 1.05, "percentage": 35.35, "elapsed_time": "0:22:48", "remaining_time": "0:41:43"}
29
+ {"current_steps": 145, "total_steps": 396, "loss": 1.0408, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0007040928096123516, "epoch": 1.09, "percentage": 36.62, "elapsed_time": "0:23:37", "remaining_time": "0:40:54"}
30
+ {"current_steps": 150, "total_steps": 396, "loss": 1.1847, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0006858312278301637, "epoch": 1.13, "percentage": 37.88, "elapsed_time": "0:24:26", "remaining_time": "0:40:05"}
31
+ {"current_steps": 155, "total_steps": 396, "loss": 0.9884, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0006672772906390176, "epoch": 1.17, "percentage": 39.14, "elapsed_time": "0:25:15", "remaining_time": "0:39:15"}
32
+ {"current_steps": 160, "total_steps": 396, "loss": 1.0086, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0006484601876641375, "epoch": 1.21, "percentage": 40.4, "elapsed_time": "0:26:03", "remaining_time": "0:38:26"}
33
+ {"current_steps": 165, "total_steps": 396, "loss": 1.0438, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0006294095225512603, "epoch": 1.24, "percentage": 41.67, "elapsed_time": "0:26:52", "remaining_time": "0:37:37"}
34
+ {"current_steps": 170, "total_steps": 396, "loss": 0.9305, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0006101552663932703, "epoch": 1.28, "percentage": 42.93, "elapsed_time": "0:27:40", "remaining_time": "0:36:48"}
35
+ {"current_steps": 175, "total_steps": 396, "loss": 1.0619, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005907277105787513, "epoch": 1.32, "percentage": 44.19, "elapsed_time": "0:28:30", "remaining_time": "0:35:59"}
36
+ {"current_steps": 180, "total_steps": 396, "loss": 1.5694, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005711574191366427, "epoch": 1.36, "percentage": 45.45, "elapsed_time": "0:29:18", "remaining_time": "0:35:10"}
37
+ {"current_steps": 185, "total_steps": 396, "loss": 1.0704, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005514751806519673, "epoch": 1.39, "percentage": 46.72, "elapsed_time": "0:30:07", "remaining_time": "0:34:22"}
38
+ {"current_steps": 190, "total_steps": 396, "loss": 1.1666, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005317119598282822, "epoch": 1.43, "percentage": 47.98, "elapsed_time": "0:30:56", "remaining_time": "0:33:33"}
39
+ {"current_steps": 195, "total_steps": 396, "loss": 0.9914, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0005118988487730537, "epoch": 1.47, "percentage": 49.24, "elapsed_time": "0:31:45", "remaining_time": "0:32:44"}
40
+ {"current_steps": 200, "total_steps": 396, "loss": 1.0523, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000492067018082596, "epoch": 1.51, "percentage": 50.51, "elapsed_time": "0:32:34", "remaining_time": "0:31:55"}
41
+ {"current_steps": 205, "total_steps": 396, "loss": 0.9491, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00047224766780353, "epoch": 1.54, "percentage": 51.77, "elapsed_time": "0:33:23", "remaining_time": "0:31:06"}
42
+ {"current_steps": 210, "total_steps": 396, "loss": 1.041, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004524719783479088, "epoch": 1.58, "percentage": 53.03, "elapsed_time": "0:34:12", "remaining_time": "0:30:17"}
43
+ {"current_steps": 215, "total_steps": 396, "loss": 1.237, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0004327710614392341, "epoch": 1.62, "percentage": 54.29, "elapsed_time": "0:35:02", "remaining_time": "0:29:29"}
44
+ {"current_steps": 220, "total_steps": 396, "loss": 1.0301, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00041317591116653486, "epoch": 1.66, "percentage": 55.56, "elapsed_time": "0:35:51", "remaining_time": "0:28:41"}
45
+ {"current_steps": 225, "total_steps": 396, "loss": 1.0687, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00039371735522351166, "epoch": 1.69, "percentage": 56.82, "elapsed_time": "0:36:40", "remaining_time": "0:27:52"}
46
+ {"current_steps": 230, "total_steps": 396, "loss": 0.9959, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00037442600640946044, "epoch": 1.73, "percentage": 58.08, "elapsed_time": "0:37:29", "remaining_time": "0:27:03"}
47
+ {"current_steps": 235, "total_steps": 396, "loss": 0.9951, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003553322144682737, "epoch": 1.77, "percentage": 59.34, "elapsed_time": "0:38:18", "remaining_time": "0:26:14"}
48
+ {"current_steps": 240, "total_steps": 396, "loss": 1.1158, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003364660183412892, "epoch": 1.81, "percentage": 60.61, "elapsed_time": "0:39:06", "remaining_time": "0:25:25"}
49
+ {"current_steps": 245, "total_steps": 396, "loss": 1.2224, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0003178570989091028, "epoch": 1.85, "percentage": 61.87, "elapsed_time": "0:39:55", "remaining_time": "0:24:36"}
50
+ {"current_steps": 250, "total_steps": 396, "loss": 1.0617, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00029953473229669324, "epoch": 1.88, "percentage": 63.13, "elapsed_time": "0:40:43", "remaining_time": "0:23:47"}
51
+ {"current_steps": 255, "total_steps": 396, "loss": 0.9955, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002815277438153203, "epoch": 1.92, "percentage": 64.39, "elapsed_time": "0:41:32", "remaining_time": "0:22:58"}
52
+ {"current_steps": 260, "total_steps": 396, "loss": 0.9129, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002638644626136587, "epoch": 1.96, "percentage": 65.66, "elapsed_time": "0:42:21", "remaining_time": "0:22:09"}
53
+ {"current_steps": 265, "total_steps": 396, "loss": 1.0105, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00024657267710950857, "epoch": 2.0, "percentage": 66.92, "elapsed_time": "0:43:10", "remaining_time": "0:21:20"}
54
+ {"current_steps": 270, "total_steps": 396, "loss": 0.7617, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002296795912722014, "epoch": 2.03, "percentage": 68.18, "elapsed_time": "0:43:59", "remaining_time": "0:20:31"}
55
+ {"current_steps": 275, "total_steps": 396, "loss": 0.629, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00021321178182447708, "epoch": 2.07, "percentage": 69.44, "elapsed_time": "0:44:48", "remaining_time": "0:19:42"}
56
+ {"current_steps": 280, "total_steps": 396, "loss": 0.7202, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019719515643116677, "epoch": 2.11, "percentage": 70.71, "elapsed_time": "0:45:37", "remaining_time": "0:18:54"}
57
+ {"current_steps": 285, "total_steps": 396, "loss": 0.7211, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00018165491294045593, "epoch": 2.15, "percentage": 71.97, "elapsed_time": "0:46:26", "remaining_time": "0:18:05"}
58
+ {"current_steps": 290, "total_steps": 396, "loss": 0.6464, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016661549974185424, "epoch": 2.18, "percentage": 73.23, "elapsed_time": "0:47:15", "remaining_time": "0:17:16"}
59
+ {"current_steps": 295, "total_steps": 396, "loss": 0.6799, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015210057730323618, "epoch": 2.22, "percentage": 74.49, "elapsed_time": "0:48:05", "remaining_time": "0:16:27"}
60
+ {"current_steps": 300, "total_steps": 396, "loss": 0.6218, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001381329809474649, "epoch": 2.26, "percentage": 75.76, "elapsed_time": "0:48:54", "remaining_time": "0:15:38"}
61
+ {"current_steps": 305, "total_steps": 396, "loss": 0.7277, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012473468492715895, "epoch": 2.3, "percentage": 77.02, "elapsed_time": "0:49:43", "remaining_time": "0:14:50"}
62
+ {"current_steps": 310, "total_steps": 396, "loss": 0.6244, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011192676785412154, "epoch": 2.34, "percentage": 78.28, "elapsed_time": "0:50:32", "remaining_time": "0:14:01"}
63
+ {"current_steps": 315, "total_steps": 396, "loss": 0.6352, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.972937953781985e-05, "epoch": 2.37, "percentage": 79.55, "elapsed_time": "0:51:21", "remaining_time": "0:13:12"}
64
+ {"current_steps": 320, "total_steps": 396, "loss": 0.6462, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.816170928508365e-05, "epoch": 2.41, "percentage": 80.81, "elapsed_time": "0:52:09", "remaining_time": "0:12:23"}
65
+ {"current_steps": 325, "total_steps": 396, "loss": 0.6377, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.724195571089787e-05, "epoch": 2.45, "percentage": 82.07, "elapsed_time": "0:52:58", "remaining_time": "0:11:34"}
66
+ {"current_steps": 330, "total_steps": 396, "loss": 0.7165, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.698729810778065e-05, "epoch": 2.49, "percentage": 83.33, "elapsed_time": "0:53:46", "remaining_time": "0:10:45"}
67
+ {"current_steps": 335, "total_steps": 396, "loss": 0.6948, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.741386941879179e-05, "epoch": 2.52, "percentage": 84.6, "elapsed_time": "0:54:34", "remaining_time": "0:09:56"}
68
+ {"current_steps": 340, "total_steps": 396, "loss": 0.6849, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.853673085668947e-05, "epoch": 2.56, "percentage": 85.86, "elapsed_time": "0:55:22", "remaining_time": "0:09:07"}
69
+ {"current_steps": 345, "total_steps": 396, "loss": 0.6742, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.036984820916722e-05, "epoch": 2.6, "percentage": 87.12, "elapsed_time": "0:56:11", "remaining_time": "0:08:18"}
70
+ {"current_steps": 350, "total_steps": 396, "loss": 0.7078, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.292606986744667e-05, "epoch": 2.64, "percentage": 88.38, "elapsed_time": "0:57:00", "remaining_time": "0:07:29"}
71
+ {"current_steps": 355, "total_steps": 396, "loss": 0.6499, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6217106612792528e-05, "epoch": 2.67, "percentage": 89.65, "elapsed_time": "0:57:49", "remaining_time": "0:06:40"}
72
+ {"current_steps": 360, "total_steps": 396, "loss": 0.6878, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.025351319275137e-05, "epoch": 2.71, "percentage": 90.91, "elapsed_time": "0:58:37", "remaining_time": "0:05:51"}
73
+ {"current_steps": 365, "total_steps": 396, "loss": 0.5469, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5044671716097413e-05, "epoch": 2.75, "percentage": 92.17, "elapsed_time": "0:59:26", "remaining_time": "0:05:02"}
74
+ {"current_steps": 370, "total_steps": 396, "loss": 0.7233, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0598776892610684e-05, "epoch": 2.79, "percentage": 93.43, "elapsed_time": "1:00:15", "remaining_time": "0:04:14"}
75
+ {"current_steps": 375, "total_steps": 396, "loss": 0.7482, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.9228231409067535e-06, "epoch": 2.82, "percentage": 94.7, "elapsed_time": "1:01:03", "remaining_time": "0:03:25"}
76
+ {"current_steps": 380, "total_steps": 396, "loss": 0.6865, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.02259358460233e-06, "epoch": 2.86, "percentage": 95.96, "elapsed_time": "1:01:52", "remaining_time": "0:02:36"}
77
+ {"current_steps": 385, "total_steps": 396, "loss": 0.6953, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9026509541272275e-06, "epoch": 2.9, "percentage": 97.22, "elapsed_time": "1:02:41", "remaining_time": "0:01:47"}
78
+ {"current_steps": 390, "total_steps": 396, "loss": 0.671, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.663304084960185e-07, "epoch": 2.94, "percentage": 98.48, "elapsed_time": "1:03:30", "remaining_time": "0:00:58"}
79
+ {"current_steps": 395, "total_steps": 396, "loss": 0.6152, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.573428833345769e-08, "epoch": 2.98, "percentage": 99.75, "elapsed_time": "1:04:19", "remaining_time": "0:00:09"}
80
+ {"current_steps": 396, "total_steps": 396, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.98, "percentage": 100.0, "elapsed_time": "1:04:28", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,504 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.983050847457627,
5
+ "eval_steps": 500,
6
+ "global_step": 396,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "learning_rate": 0.0009996066923030483,
14
+ "loss": 2.8429,
15
+ "step": 5
16
+ },
17
+ {
18
+ "epoch": 0.08,
19
+ "learning_rate": 0.0009984273879759713,
20
+ "loss": 1.7586,
21
+ "step": 10
22
+ },
23
+ {
24
+ "epoch": 0.11,
25
+ "learning_rate": 0.0009964639423366442,
26
+ "loss": 1.7084,
27
+ "step": 15
28
+ },
29
+ {
30
+ "epoch": 0.15,
31
+ "learning_rate": 0.0009937194443381972,
32
+ "loss": 1.7022,
33
+ "step": 20
34
+ },
35
+ {
36
+ "epoch": 0.19,
37
+ "learning_rate": 0.0009901982117093786,
38
+ "loss": 1.436,
39
+ "step": 25
40
+ },
41
+ {
42
+ "epoch": 0.23,
43
+ "learning_rate": 0.000985905784161771,
44
+ "loss": 1.5345,
45
+ "step": 30
46
+ },
47
+ {
48
+ "epoch": 0.26,
49
+ "learning_rate": 0.0009808489146745465,
50
+ "loss": 1.5542,
51
+ "step": 35
52
+ },
53
+ {
54
+ "epoch": 0.3,
55
+ "learning_rate": 0.0009750355588704727,
56
+ "loss": 1.5173,
57
+ "step": 40
58
+ },
59
+ {
60
+ "epoch": 0.34,
61
+ "learning_rate": 0.000968474862499881,
62
+ "loss": 1.4094,
63
+ "step": 45
64
+ },
65
+ {
66
+ "epoch": 0.38,
67
+ "learning_rate": 0.0009611771470522907,
68
+ "loss": 1.6779,
69
+ "step": 50
70
+ },
71
+ {
72
+ "epoch": 0.41,
73
+ "learning_rate": 0.0009531538935183251,
74
+ "loss": 1.593,
75
+ "step": 55
76
+ },
77
+ {
78
+ "epoch": 0.45,
79
+ "learning_rate": 0.0009444177243274617,
80
+ "loss": 1.8026,
81
+ "step": 60
82
+ },
83
+ {
84
+ "epoch": 0.49,
85
+ "learning_rate": 0.0009349823834900395,
86
+ "loss": 1.1646,
87
+ "step": 65
88
+ },
89
+ {
90
+ "epoch": 0.53,
91
+ "learning_rate": 0.0009248627149747573,
92
+ "loss": 1.4566,
93
+ "step": 70
94
+ },
95
+ {
96
+ "epoch": 0.56,
97
+ "learning_rate": 0.0009140746393556853,
98
+ "loss": 1.3848,
99
+ "step": 75
100
+ },
101
+ {
102
+ "epoch": 0.6,
103
+ "learning_rate": 0.0009026351287655293,
104
+ "loss": 1.6641,
105
+ "step": 80
106
+ },
107
+ {
108
+ "epoch": 0.64,
109
+ "learning_rate": 0.0008905621801945467,
110
+ "loss": 1.2664,
111
+ "step": 85
112
+ },
113
+ {
114
+ "epoch": 0.68,
115
+ "learning_rate": 0.0008778747871771292,
116
+ "loss": 1.4103,
117
+ "step": 90
118
+ },
119
+ {
120
+ "epoch": 0.72,
121
+ "learning_rate": 0.0008645929099105886,
122
+ "loss": 1.3391,
123
+ "step": 95
124
+ },
125
+ {
126
+ "epoch": 0.75,
127
+ "learning_rate": 0.0008507374438531607,
128
+ "loss": 1.3329,
129
+ "step": 100
130
+ },
131
+ {
132
+ "epoch": 0.79,
133
+ "learning_rate": 0.0008363301868506264,
134
+ "loss": 1.4708,
135
+ "step": 105
136
+ },
137
+ {
138
+ "epoch": 0.83,
139
+ "learning_rate": 0.0008213938048432696,
140
+ "loss": 1.5326,
141
+ "step": 110
142
+ },
143
+ {
144
+ "epoch": 0.87,
145
+ "learning_rate": 0.0008059517962071233,
146
+ "loss": 1.5317,
147
+ "step": 115
148
+ },
149
+ {
150
+ "epoch": 0.9,
151
+ "learning_rate": 0.0007900284547855992,
152
+ "loss": 1.2481,
153
+ "step": 120
154
+ },
155
+ {
156
+ "epoch": 0.94,
157
+ "learning_rate": 0.0007736488316696662,
158
+ "loss": 1.4773,
159
+ "step": 125
160
+ },
161
+ {
162
+ "epoch": 0.98,
163
+ "learning_rate": 0.0007568386957867032,
164
+ "loss": 1.2638,
165
+ "step": 130
166
+ },
167
+ {
168
+ "epoch": 1.02,
169
+ "learning_rate": 0.0007396244933600284,
170
+ "loss": 1.2867,
171
+ "step": 135
172
+ },
173
+ {
174
+ "epoch": 1.05,
175
+ "learning_rate": 0.0007220333063028871,
176
+ "loss": 1.0248,
177
+ "step": 140
178
+ },
179
+ {
180
+ "epoch": 1.09,
181
+ "learning_rate": 0.0007040928096123516,
182
+ "loss": 1.0408,
183
+ "step": 145
184
+ },
185
+ {
186
+ "epoch": 1.13,
187
+ "learning_rate": 0.0006858312278301637,
188
+ "loss": 1.1847,
189
+ "step": 150
190
+ },
191
+ {
192
+ "epoch": 1.17,
193
+ "learning_rate": 0.0006672772906390176,
194
+ "loss": 0.9884,
195
+ "step": 155
196
+ },
197
+ {
198
+ "epoch": 1.21,
199
+ "learning_rate": 0.0006484601876641375,
200
+ "loss": 1.0086,
201
+ "step": 160
202
+ },
203
+ {
204
+ "epoch": 1.24,
205
+ "learning_rate": 0.0006294095225512603,
206
+ "loss": 1.0438,
207
+ "step": 165
208
+ },
209
+ {
210
+ "epoch": 1.28,
211
+ "learning_rate": 0.0006101552663932703,
212
+ "loss": 0.9305,
213
+ "step": 170
214
+ },
215
+ {
216
+ "epoch": 1.32,
217
+ "learning_rate": 0.0005907277105787513,
218
+ "loss": 1.0619,
219
+ "step": 175
220
+ },
221
+ {
222
+ "epoch": 1.36,
223
+ "learning_rate": 0.0005711574191366427,
224
+ "loss": 1.5694,
225
+ "step": 180
226
+ },
227
+ {
228
+ "epoch": 1.39,
229
+ "learning_rate": 0.0005514751806519673,
230
+ "loss": 1.0704,
231
+ "step": 185
232
+ },
233
+ {
234
+ "epoch": 1.43,
235
+ "learning_rate": 0.0005317119598282822,
236
+ "loss": 1.1666,
237
+ "step": 190
238
+ },
239
+ {
240
+ "epoch": 1.47,
241
+ "learning_rate": 0.0005118988487730537,
242
+ "loss": 0.9914,
243
+ "step": 195
244
+ },
245
+ {
246
+ "epoch": 1.51,
247
+ "learning_rate": 0.000492067018082596,
248
+ "loss": 1.0523,
249
+ "step": 200
250
+ },
251
+ {
252
+ "epoch": 1.54,
253
+ "learning_rate": 0.00047224766780353,
254
+ "loss": 0.9491,
255
+ "step": 205
256
+ },
257
+ {
258
+ "epoch": 1.58,
259
+ "learning_rate": 0.0004524719783479088,
260
+ "loss": 1.041,
261
+ "step": 210
262
+ },
263
+ {
264
+ "epoch": 1.62,
265
+ "learning_rate": 0.0004327710614392341,
266
+ "loss": 1.237,
267
+ "step": 215
268
+ },
269
+ {
270
+ "epoch": 1.66,
271
+ "learning_rate": 0.00041317591116653486,
272
+ "loss": 1.0301,
273
+ "step": 220
274
+ },
275
+ {
276
+ "epoch": 1.69,
277
+ "learning_rate": 0.00039371735522351166,
278
+ "loss": 1.0687,
279
+ "step": 225
280
+ },
281
+ {
282
+ "epoch": 1.73,
283
+ "learning_rate": 0.00037442600640946044,
284
+ "loss": 0.9959,
285
+ "step": 230
286
+ },
287
+ {
288
+ "epoch": 1.77,
289
+ "learning_rate": 0.0003553322144682737,
290
+ "loss": 0.9951,
291
+ "step": 235
292
+ },
293
+ {
294
+ "epoch": 1.81,
295
+ "learning_rate": 0.0003364660183412892,
296
+ "loss": 1.1158,
297
+ "step": 240
298
+ },
299
+ {
300
+ "epoch": 1.85,
301
+ "learning_rate": 0.0003178570989091028,
302
+ "loss": 1.2224,
303
+ "step": 245
304
+ },
305
+ {
306
+ "epoch": 1.88,
307
+ "learning_rate": 0.00029953473229669324,
308
+ "loss": 1.0617,
309
+ "step": 250
310
+ },
311
+ {
312
+ "epoch": 1.92,
313
+ "learning_rate": 0.0002815277438153203,
314
+ "loss": 0.9955,
315
+ "step": 255
316
+ },
317
+ {
318
+ "epoch": 1.96,
319
+ "learning_rate": 0.0002638644626136587,
320
+ "loss": 0.9129,
321
+ "step": 260
322
+ },
323
+ {
324
+ "epoch": 2.0,
325
+ "learning_rate": 0.00024657267710950857,
326
+ "loss": 1.0105,
327
+ "step": 265
328
+ },
329
+ {
330
+ "epoch": 2.03,
331
+ "learning_rate": 0.0002296795912722014,
332
+ "loss": 0.7617,
333
+ "step": 270
334
+ },
335
+ {
336
+ "epoch": 2.07,
337
+ "learning_rate": 0.00021321178182447708,
338
+ "loss": 0.629,
339
+ "step": 275
340
+ },
341
+ {
342
+ "epoch": 2.11,
343
+ "learning_rate": 0.00019719515643116677,
344
+ "loss": 0.7202,
345
+ "step": 280
346
+ },
347
+ {
348
+ "epoch": 2.15,
349
+ "learning_rate": 0.00018165491294045593,
350
+ "loss": 0.7211,
351
+ "step": 285
352
+ },
353
+ {
354
+ "epoch": 2.18,
355
+ "learning_rate": 0.00016661549974185424,
356
+ "loss": 0.6464,
357
+ "step": 290
358
+ },
359
+ {
360
+ "epoch": 2.22,
361
+ "learning_rate": 0.00015210057730323618,
362
+ "loss": 0.6799,
363
+ "step": 295
364
+ },
365
+ {
366
+ "epoch": 2.26,
367
+ "learning_rate": 0.0001381329809474649,
368
+ "loss": 0.6218,
369
+ "step": 300
370
+ },
371
+ {
372
+ "epoch": 2.3,
373
+ "learning_rate": 0.00012473468492715895,
374
+ "loss": 0.7277,
375
+ "step": 305
376
+ },
377
+ {
378
+ "epoch": 2.34,
379
+ "learning_rate": 0.00011192676785412154,
380
+ "loss": 0.6244,
381
+ "step": 310
382
+ },
383
+ {
384
+ "epoch": 2.37,
385
+ "learning_rate": 9.972937953781985e-05,
386
+ "loss": 0.6352,
387
+ "step": 315
388
+ },
389
+ {
390
+ "epoch": 2.41,
391
+ "learning_rate": 8.816170928508365e-05,
392
+ "loss": 0.6462,
393
+ "step": 320
394
+ },
395
+ {
396
+ "epoch": 2.45,
397
+ "learning_rate": 7.724195571089787e-05,
398
+ "loss": 0.6377,
399
+ "step": 325
400
+ },
401
+ {
402
+ "epoch": 2.49,
403
+ "learning_rate": 6.698729810778065e-05,
404
+ "loss": 0.7165,
405
+ "step": 330
406
+ },
407
+ {
408
+ "epoch": 2.52,
409
+ "learning_rate": 5.741386941879179e-05,
410
+ "loss": 0.6948,
411
+ "step": 335
412
+ },
413
+ {
414
+ "epoch": 2.56,
415
+ "learning_rate": 4.853673085668947e-05,
416
+ "loss": 0.6849,
417
+ "step": 340
418
+ },
419
+ {
420
+ "epoch": 2.6,
421
+ "learning_rate": 4.036984820916722e-05,
422
+ "loss": 0.6742,
423
+ "step": 345
424
+ },
425
+ {
426
+ "epoch": 2.64,
427
+ "learning_rate": 3.292606986744667e-05,
428
+ "loss": 0.7078,
429
+ "step": 350
430
+ },
431
+ {
432
+ "epoch": 2.67,
433
+ "learning_rate": 2.6217106612792528e-05,
434
+ "loss": 0.6499,
435
+ "step": 355
436
+ },
437
+ {
438
+ "epoch": 2.71,
439
+ "learning_rate": 2.025351319275137e-05,
440
+ "loss": 0.6878,
441
+ "step": 360
442
+ },
443
+ {
444
+ "epoch": 2.75,
445
+ "learning_rate": 1.5044671716097413e-05,
446
+ "loss": 0.5469,
447
+ "step": 365
448
+ },
449
+ {
450
+ "epoch": 2.79,
451
+ "learning_rate": 1.0598776892610684e-05,
452
+ "loss": 0.7233,
453
+ "step": 370
454
+ },
455
+ {
456
+ "epoch": 2.82,
457
+ "learning_rate": 6.9228231409067535e-06,
458
+ "loss": 0.7482,
459
+ "step": 375
460
+ },
461
+ {
462
+ "epoch": 2.86,
463
+ "learning_rate": 4.02259358460233e-06,
464
+ "loss": 0.6865,
465
+ "step": 380
466
+ },
467
+ {
468
+ "epoch": 2.9,
469
+ "learning_rate": 1.9026509541272275e-06,
470
+ "loss": 0.6953,
471
+ "step": 385
472
+ },
473
+ {
474
+ "epoch": 2.94,
475
+ "learning_rate": 5.663304084960185e-07,
476
+ "loss": 0.671,
477
+ "step": 390
478
+ },
479
+ {
480
+ "epoch": 2.98,
481
+ "learning_rate": 1.573428833345769e-08,
482
+ "loss": 0.6152,
483
+ "step": 395
484
+ },
485
+ {
486
+ "epoch": 2.98,
487
+ "step": 396,
488
+ "total_flos": 1.0914041201688576e+17,
489
+ "train_loss": 1.0966757915236733,
490
+ "train_runtime": 4531.1008,
491
+ "train_samples_per_second": 0.703,
492
+ "train_steps_per_second": 0.087
493
+ }
494
+ ],
495
+ "logging_steps": 5,
496
+ "max_steps": 396,
497
+ "num_input_tokens_seen": 0,
498
+ "num_train_epochs": 3,
499
+ "save_steps": 100,
500
+ "total_flos": 1.0914041201688576e+17,
501
+ "train_batch_size": 2,
502
+ "trial_name": null,
503
+ "trial_params": null
504
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60c825abcb49ce02abce1bb425e5a98b9ba846e1ef0638277e96552fc964127a
3
+ size 4920
vocab.json ADDED
The diff for this file is too large to render. See raw diff