egonrp commited on
Commit
c47d9eb
1 Parent(s): a3d2d38

versao inicial

Browse files
README.md CHANGED
@@ -1,3 +1,52 @@
1
  ---
2
  license: mit
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: results_v4c_gpt_medium_original_no_eval
7
+ results: []
8
  ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # results_v4c_gpt_medium_original_no_eval
14
+
15
+ This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 5e-05
35
+ - train_batch_size: 1
36
+ - eval_batch_size: 8
37
+ - seed: 42
38
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
+ - lr_scheduler_type: linear
40
+ - num_epochs: 3.0
41
+ - mixed_precision_training: Native AMP
42
+
43
+ ### Training results
44
+
45
+
46
+
47
+ ### Framework versions
48
+
49
+ - Transformers 4.27.3
50
+ - Pytorch 2.0.0+cu117
51
+ - Datasets 2.10.1
52
+ - Tokenizers 0.13.2
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.4842614623898048,
4
+ "train_runtime": 25288.6173,
5
+ "train_samples": 34398,
6
+ "train_samples_per_second": 4.081,
7
+ "train_steps_per_second": 4.081
8
+ }
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-medium",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 24,
19
+ "n_positions": 1024,
20
+ "n_special": 0,
21
+ "predict_special_tokens": true,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
+ },
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.27.3",
39
+ "use_cache": true,
40
+ "vocab_size": 50257
41
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.27.3"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1403f40cb286c7fa56813854e5b518856879e6305761675af4171867fd3ba2c5
3
+ size 1444569373
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "special_tokens_map_file": null,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.4842614623898048,
4
+ "train_runtime": 25288.6173,
5
+ "train_samples": 34398,
6
+ "train_samples_per_second": 4.081,
7
+ "train_steps_per_second": 4.081
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 103194,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 4.975919142585809e-05,
13
+ "loss": 2.0152,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 4.9517413803128096e-05,
19
+ "loss": 1.7371,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.04,
24
+ "learning_rate": 4.927515165610404e-05,
25
+ "loss": 1.6658,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.06,
30
+ "learning_rate": 4.903288950907999e-05,
31
+ "loss": 1.5673,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.07,
36
+ "learning_rate": 4.879062736205593e-05,
37
+ "loss": 1.5484,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.09,
42
+ "learning_rate": 4.8548365215031885e-05,
43
+ "loss": 1.4843,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.1,
48
+ "learning_rate": 4.830610306800783e-05,
49
+ "loss": 1.4821,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.12,
54
+ "learning_rate": 4.8063840920983784e-05,
55
+ "loss": 1.4424,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.13,
60
+ "learning_rate": 4.782157877395973e-05,
61
+ "loss": 1.4388,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.15,
66
+ "learning_rate": 4.7579316626935675e-05,
67
+ "loss": 1.3804,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.16,
72
+ "learning_rate": 4.733705447991163e-05,
73
+ "loss": 1.402,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.17,
78
+ "learning_rate": 4.7094792332887573e-05,
79
+ "loss": 1.3506,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.19,
84
+ "learning_rate": 4.685301471015757e-05,
85
+ "loss": 1.3347,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.2,
90
+ "learning_rate": 4.661075256313352e-05,
91
+ "loss": 1.3199,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.22,
96
+ "learning_rate": 4.636849041610947e-05,
97
+ "loss": 1.3252,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.23,
102
+ "learning_rate": 4.6126228269085415e-05,
103
+ "loss": 1.2724,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.25,
108
+ "learning_rate": 4.588396612206136e-05,
109
+ "loss": 1.3366,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.26,
114
+ "learning_rate": 4.564170397503731e-05,
115
+ "loss": 1.2848,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.28,
120
+ "learning_rate": 4.539944182801326e-05,
121
+ "loss": 1.2723,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.29,
126
+ "learning_rate": 4.515717968098921e-05,
127
+ "loss": 1.299,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.31,
132
+ "learning_rate": 4.491491753396516e-05,
133
+ "loss": 1.3005,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.32,
138
+ "learning_rate": 4.46726553869411e-05,
139
+ "loss": 1.2675,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.33,
144
+ "learning_rate": 4.443039323991705e-05,
145
+ "loss": 1.2606,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.35,
150
+ "learning_rate": 4.4188131092892995e-05,
151
+ "loss": 1.2592,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.36,
156
+ "learning_rate": 4.3946353470163e-05,
157
+ "loss": 1.2159,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.38,
162
+ "learning_rate": 4.3704091323138945e-05,
163
+ "loss": 1.213,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.39,
168
+ "learning_rate": 4.346182917611489e-05,
169
+ "loss": 1.2297,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.41,
174
+ "learning_rate": 4.3219567029090844e-05,
175
+ "loss": 1.2048,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.42,
180
+ "learning_rate": 4.2977789406360835e-05,
181
+ "loss": 1.2324,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.44,
186
+ "learning_rate": 4.273552725933678e-05,
187
+ "loss": 1.2067,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.45,
192
+ "learning_rate": 4.249326511231273e-05,
193
+ "loss": 1.2146,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.47,
198
+ "learning_rate": 4.2251002965288685e-05,
199
+ "loss": 1.208,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.48,
204
+ "learning_rate": 4.200874081826463e-05,
205
+ "loss": 1.1678,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.49,
210
+ "learning_rate": 4.176647867124058e-05,
211
+ "loss": 1.2011,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.51,
216
+ "learning_rate": 4.152421652421652e-05,
217
+ "loss": 1.1671,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.52,
222
+ "learning_rate": 4.1281954377192475e-05,
223
+ "loss": 1.1849,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.54,
228
+ "learning_rate": 4.103969223016843e-05,
229
+ "loss": 1.1494,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.55,
234
+ "learning_rate": 4.0797430083144373e-05,
235
+ "loss": 1.1776,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.57,
240
+ "learning_rate": 4.0555652460414365e-05,
241
+ "loss": 1.1664,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.58,
246
+ "learning_rate": 4.031339031339032e-05,
247
+ "loss": 1.1332,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.6,
252
+ "learning_rate": 4.007112816636626e-05,
253
+ "loss": 1.1355,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.61,
258
+ "learning_rate": 3.982886601934221e-05,
259
+ "loss": 1.1624,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.63,
264
+ "learning_rate": 3.958660387231816e-05,
265
+ "loss": 1.1412,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.64,
270
+ "learning_rate": 3.934482624958816e-05,
271
+ "loss": 1.1366,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 0.65,
276
+ "learning_rate": 3.9102564102564105e-05,
277
+ "loss": 1.1227,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 0.67,
282
+ "learning_rate": 3.886030195554005e-05,
283
+ "loss": 1.0943,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 0.68,
288
+ "learning_rate": 3.8618039808515996e-05,
289
+ "loss": 1.1645,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 0.7,
294
+ "learning_rate": 3.8376262185786e-05,
295
+ "loss": 1.0841,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 0.71,
300
+ "learning_rate": 3.8134000038761947e-05,
301
+ "loss": 1.118,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 0.73,
306
+ "learning_rate": 3.789173789173789e-05,
307
+ "loss": 1.1283,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 0.74,
312
+ "learning_rate": 3.764996026900789e-05,
313
+ "loss": 1.1372,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 0.76,
318
+ "learning_rate": 3.7407698121983836e-05,
319
+ "loss": 1.1181,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 0.77,
324
+ "learning_rate": 3.716543597495978e-05,
325
+ "loss": 1.0918,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 0.78,
330
+ "learning_rate": 3.6923173827935734e-05,
331
+ "loss": 1.1293,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 0.8,
336
+ "learning_rate": 3.668139620520573e-05,
337
+ "loss": 1.1014,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 0.81,
342
+ "learning_rate": 3.643913405818168e-05,
343
+ "loss": 1.0866,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 0.83,
348
+ "learning_rate": 3.6196871911157624e-05,
349
+ "loss": 1.1249,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 0.84,
354
+ "learning_rate": 3.5954609764133576e-05,
355
+ "loss": 1.1053,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 0.86,
360
+ "learning_rate": 3.5712832141403574e-05,
361
+ "loss": 1.1069,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 0.87,
366
+ "learning_rate": 3.547056999437952e-05,
367
+ "loss": 1.0803,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 0.89,
372
+ "learning_rate": 3.5228307847355466e-05,
373
+ "loss": 1.1037,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 0.9,
378
+ "learning_rate": 3.498604570033142e-05,
379
+ "loss": 1.0828,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 0.92,
384
+ "learning_rate": 3.4743783553307364e-05,
385
+ "loss": 1.0805,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 0.93,
390
+ "learning_rate": 3.450152140628331e-05,
391
+ "loss": 1.0808,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 0.94,
396
+ "learning_rate": 3.425925925925926e-05,
397
+ "loss": 1.0729,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 0.96,
402
+ "learning_rate": 3.401699711223521e-05,
403
+ "loss": 1.0854,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 0.97,
408
+ "learning_rate": 3.3775219489505206e-05,
409
+ "loss": 1.0679,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 0.99,
414
+ "learning_rate": 3.353295734248115e-05,
415
+ "loss": 1.0779,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 1.0,
420
+ "learning_rate": 3.32906951954571e-05,
421
+ "loss": 1.0602,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 1.02,
426
+ "learning_rate": 3.304843304843305e-05,
427
+ "loss": 1.0138,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 1.03,
432
+ "learning_rate": 3.2806170901409e-05,
433
+ "loss": 1.0125,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 1.05,
438
+ "learning_rate": 3.256390875438495e-05,
439
+ "loss": 0.9952,
440
+ "step": 36000
441
+ },
442
+ {
443
+ "epoch": 1.06,
444
+ "learning_rate": 3.2321646607360894e-05,
445
+ "loss": 1.0044,
446
+ "step": 36500
447
+ },
448
+ {
449
+ "epoch": 1.08,
450
+ "learning_rate": 3.207986898463089e-05,
451
+ "loss": 0.9936,
452
+ "step": 37000
453
+ },
454
+ {
455
+ "epoch": 1.09,
456
+ "learning_rate": 3.183809136190088e-05,
457
+ "loss": 0.9693,
458
+ "step": 37500
459
+ },
460
+ {
461
+ "epoch": 1.1,
462
+ "learning_rate": 3.159631373917089e-05,
463
+ "loss": 0.9895,
464
+ "step": 38000
465
+ },
466
+ {
467
+ "epoch": 1.12,
468
+ "learning_rate": 3.135405159214683e-05,
469
+ "loss": 0.9724,
470
+ "step": 38500
471
+ },
472
+ {
473
+ "epoch": 1.13,
474
+ "learning_rate": 3.111178944512278e-05,
475
+ "loss": 0.9874,
476
+ "step": 39000
477
+ },
478
+ {
479
+ "epoch": 1.15,
480
+ "learning_rate": 3.0869527298098725e-05,
481
+ "loss": 0.9774,
482
+ "step": 39500
483
+ },
484
+ {
485
+ "epoch": 1.16,
486
+ "learning_rate": 3.062726515107468e-05,
487
+ "loss": 1.0123,
488
+ "step": 40000
489
+ },
490
+ {
491
+ "epoch": 1.18,
492
+ "learning_rate": 3.0385003004050626e-05,
493
+ "loss": 0.9812,
494
+ "step": 40500
495
+ },
496
+ {
497
+ "epoch": 1.19,
498
+ "learning_rate": 3.0142740857026575e-05,
499
+ "loss": 0.9907,
500
+ "step": 41000
501
+ },
502
+ {
503
+ "epoch": 1.21,
504
+ "learning_rate": 2.990047871000252e-05,
505
+ "loss": 0.9689,
506
+ "step": 41500
507
+ },
508
+ {
509
+ "epoch": 1.22,
510
+ "learning_rate": 2.9658701087272516e-05,
511
+ "loss": 0.973,
512
+ "step": 42000
513
+ },
514
+ {
515
+ "epoch": 1.24,
516
+ "learning_rate": 2.9416438940248465e-05,
517
+ "loss": 0.9695,
518
+ "step": 42500
519
+ },
520
+ {
521
+ "epoch": 1.25,
522
+ "learning_rate": 2.917417679322441e-05,
523
+ "loss": 0.9766,
524
+ "step": 43000
525
+ },
526
+ {
527
+ "epoch": 1.26,
528
+ "learning_rate": 2.8931914646200363e-05,
529
+ "loss": 0.9894,
530
+ "step": 43500
531
+ },
532
+ {
533
+ "epoch": 1.28,
534
+ "learning_rate": 2.8689652499176312e-05,
535
+ "loss": 0.9782,
536
+ "step": 44000
537
+ },
538
+ {
539
+ "epoch": 1.29,
540
+ "learning_rate": 2.8447390352152258e-05,
541
+ "loss": 0.9702,
542
+ "step": 44500
543
+ },
544
+ {
545
+ "epoch": 1.31,
546
+ "learning_rate": 2.8205128205128207e-05,
547
+ "loss": 0.9467,
548
+ "step": 45000
549
+ },
550
+ {
551
+ "epoch": 1.32,
552
+ "learning_rate": 2.79633505823982e-05,
553
+ "loss": 0.9853,
554
+ "step": 45500
555
+ },
556
+ {
557
+ "epoch": 1.34,
558
+ "learning_rate": 2.7721088435374147e-05,
559
+ "loss": 0.9716,
560
+ "step": 46000
561
+ },
562
+ {
563
+ "epoch": 1.35,
564
+ "learning_rate": 2.74788262883501e-05,
565
+ "loss": 0.965,
566
+ "step": 46500
567
+ },
568
+ {
569
+ "epoch": 1.37,
570
+ "learning_rate": 2.723656414132605e-05,
571
+ "loss": 0.9462,
572
+ "step": 47000
573
+ },
574
+ {
575
+ "epoch": 1.38,
576
+ "learning_rate": 2.6994301994301995e-05,
577
+ "loss": 0.9536,
578
+ "step": 47500
579
+ },
580
+ {
581
+ "epoch": 1.4,
582
+ "learning_rate": 2.6752039847277944e-05,
583
+ "loss": 0.9722,
584
+ "step": 48000
585
+ },
586
+ {
587
+ "epoch": 1.41,
588
+ "learning_rate": 2.650977770025389e-05,
589
+ "loss": 0.9591,
590
+ "step": 48500
591
+ },
592
+ {
593
+ "epoch": 1.42,
594
+ "learning_rate": 2.626751555322984e-05,
595
+ "loss": 0.9715,
596
+ "step": 49000
597
+ },
598
+ {
599
+ "epoch": 1.44,
600
+ "learning_rate": 2.602525340620579e-05,
601
+ "loss": 0.9812,
602
+ "step": 49500
603
+ },
604
+ {
605
+ "epoch": 1.45,
606
+ "learning_rate": 2.5782991259181737e-05,
607
+ "loss": 0.971,
608
+ "step": 50000
609
+ },
610
+ {
611
+ "epoch": 1.47,
612
+ "learning_rate": 2.5540729112157686e-05,
613
+ "loss": 0.9637,
614
+ "step": 50500
615
+ },
616
+ {
617
+ "epoch": 1.48,
618
+ "learning_rate": 2.529895148942768e-05,
619
+ "loss": 0.9404,
620
+ "step": 51000
621
+ },
622
+ {
623
+ "epoch": 1.5,
624
+ "learning_rate": 2.5056689342403626e-05,
625
+ "loss": 0.9492,
626
+ "step": 51500
627
+ },
628
+ {
629
+ "epoch": 1.51,
630
+ "learning_rate": 2.481442719537958e-05,
631
+ "loss": 0.9407,
632
+ "step": 52000
633
+ },
634
+ {
635
+ "epoch": 1.53,
636
+ "learning_rate": 2.4572165048355525e-05,
637
+ "loss": 0.9618,
638
+ "step": 52500
639
+ },
640
+ {
641
+ "epoch": 1.54,
642
+ "learning_rate": 2.4329902901331474e-05,
643
+ "loss": 0.9624,
644
+ "step": 53000
645
+ },
646
+ {
647
+ "epoch": 1.56,
648
+ "learning_rate": 2.4087640754307423e-05,
649
+ "loss": 0.9375,
650
+ "step": 53500
651
+ },
652
+ {
653
+ "epoch": 1.57,
654
+ "learning_rate": 2.384537860728337e-05,
655
+ "loss": 0.9463,
656
+ "step": 54000
657
+ },
658
+ {
659
+ "epoch": 1.58,
660
+ "learning_rate": 2.360311646025932e-05,
661
+ "loss": 0.9437,
662
+ "step": 54500
663
+ },
664
+ {
665
+ "epoch": 1.6,
666
+ "learning_rate": 2.3360854313235267e-05,
667
+ "loss": 0.9519,
668
+ "step": 55000
669
+ },
670
+ {
671
+ "epoch": 1.61,
672
+ "learning_rate": 2.3119561214799313e-05,
673
+ "loss": 0.9356,
674
+ "step": 55500
675
+ },
676
+ {
677
+ "epoch": 1.63,
678
+ "learning_rate": 2.287729906777526e-05,
679
+ "loss": 0.965,
680
+ "step": 56000
681
+ },
682
+ {
683
+ "epoch": 1.64,
684
+ "learning_rate": 2.263503692075121e-05,
685
+ "loss": 0.947,
686
+ "step": 56500
687
+ },
688
+ {
689
+ "epoch": 1.66,
690
+ "learning_rate": 2.2392774773727157e-05,
691
+ "loss": 0.9345,
692
+ "step": 57000
693
+ },
694
+ {
695
+ "epoch": 1.67,
696
+ "learning_rate": 2.2150512626703103e-05,
697
+ "loss": 0.9439,
698
+ "step": 57500
699
+ },
700
+ {
701
+ "epoch": 1.69,
702
+ "learning_rate": 2.1908250479679052e-05,
703
+ "loss": 0.9375,
704
+ "step": 58000
705
+ },
706
+ {
707
+ "epoch": 1.7,
708
+ "learning_rate": 2.1665988332655e-05,
709
+ "loss": 0.9437,
710
+ "step": 58500
711
+ },
712
+ {
713
+ "epoch": 1.72,
714
+ "learning_rate": 2.1424210709924996e-05,
715
+ "loss": 0.9464,
716
+ "step": 59000
717
+ },
718
+ {
719
+ "epoch": 1.73,
720
+ "learning_rate": 2.1181948562900945e-05,
721
+ "loss": 0.9455,
722
+ "step": 59500
723
+ },
724
+ {
725
+ "epoch": 1.74,
726
+ "learning_rate": 2.0939686415876894e-05,
727
+ "loss": 0.9208,
728
+ "step": 60000
729
+ },
730
+ {
731
+ "epoch": 1.76,
732
+ "learning_rate": 2.069742426885284e-05,
733
+ "loss": 0.9289,
734
+ "step": 60500
735
+ },
736
+ {
737
+ "epoch": 1.77,
738
+ "learning_rate": 2.045516212182879e-05,
739
+ "loss": 0.934,
740
+ "step": 61000
741
+ },
742
+ {
743
+ "epoch": 1.79,
744
+ "learning_rate": 2.0212899974804738e-05,
745
+ "loss": 0.9216,
746
+ "step": 61500
747
+ },
748
+ {
749
+ "epoch": 1.8,
750
+ "learning_rate": 1.9970637827780687e-05,
751
+ "loss": 0.9263,
752
+ "step": 62000
753
+ },
754
+ {
755
+ "epoch": 1.82,
756
+ "learning_rate": 1.9728375680756633e-05,
757
+ "loss": 0.9057,
758
+ "step": 62500
759
+ },
760
+ {
761
+ "epoch": 1.83,
762
+ "learning_rate": 1.948659805802663e-05,
763
+ "loss": 0.9022,
764
+ "step": 63000
765
+ },
766
+ {
767
+ "epoch": 1.85,
768
+ "learning_rate": 1.9244820435296626e-05,
769
+ "loss": 0.9268,
770
+ "step": 63500
771
+ },
772
+ {
773
+ "epoch": 1.86,
774
+ "learning_rate": 1.9002558288272575e-05,
775
+ "loss": 0.9117,
776
+ "step": 64000
777
+ },
778
+ {
779
+ "epoch": 1.88,
780
+ "learning_rate": 1.8760296141248524e-05,
781
+ "loss": 0.9253,
782
+ "step": 64500
783
+ },
784
+ {
785
+ "epoch": 1.89,
786
+ "learning_rate": 1.851803399422447e-05,
787
+ "loss": 0.937,
788
+ "step": 65000
789
+ },
790
+ {
791
+ "epoch": 1.9,
792
+ "learning_rate": 1.8275771847200422e-05,
793
+ "loss": 0.9068,
794
+ "step": 65500
795
+ },
796
+ {
797
+ "epoch": 1.92,
798
+ "learning_rate": 1.8033994224470417e-05,
799
+ "loss": 0.9208,
800
+ "step": 66000
801
+ },
802
+ {
803
+ "epoch": 1.93,
804
+ "learning_rate": 1.7791732077446362e-05,
805
+ "loss": 0.9093,
806
+ "step": 66500
807
+ },
808
+ {
809
+ "epoch": 1.95,
810
+ "learning_rate": 1.7549469930422315e-05,
811
+ "loss": 0.9268,
812
+ "step": 67000
813
+ },
814
+ {
815
+ "epoch": 1.96,
816
+ "learning_rate": 1.730720778339826e-05,
817
+ "loss": 0.911,
818
+ "step": 67500
819
+ },
820
+ {
821
+ "epoch": 1.98,
822
+ "learning_rate": 1.7064945636374206e-05,
823
+ "loss": 0.906,
824
+ "step": 68000
825
+ },
826
+ {
827
+ "epoch": 1.99,
828
+ "learning_rate": 1.682268348935016e-05,
829
+ "loss": 0.9129,
830
+ "step": 68500
831
+ },
832
+ {
833
+ "epoch": 2.01,
834
+ "learning_rate": 1.6580421342326105e-05,
835
+ "loss": 0.8908,
836
+ "step": 69000
837
+ },
838
+ {
839
+ "epoch": 2.02,
840
+ "learning_rate": 1.63386437195961e-05,
841
+ "loss": 0.8648,
842
+ "step": 69500
843
+ },
844
+ {
845
+ "epoch": 2.04,
846
+ "learning_rate": 1.6096866096866097e-05,
847
+ "loss": 0.8501,
848
+ "step": 70000
849
+ },
850
+ {
851
+ "epoch": 2.05,
852
+ "learning_rate": 1.5854603949842046e-05,
853
+ "loss": 0.8706,
854
+ "step": 70500
855
+ },
856
+ {
857
+ "epoch": 2.06,
858
+ "learning_rate": 1.5612341802817995e-05,
859
+ "loss": 0.8721,
860
+ "step": 71000
861
+ },
862
+ {
863
+ "epoch": 2.08,
864
+ "learning_rate": 1.537007965579394e-05,
865
+ "loss": 0.8385,
866
+ "step": 71500
867
+ },
868
+ {
869
+ "epoch": 2.09,
870
+ "learning_rate": 1.512781750876989e-05,
871
+ "loss": 0.8577,
872
+ "step": 72000
873
+ },
874
+ {
875
+ "epoch": 2.11,
876
+ "learning_rate": 1.488555536174584e-05,
877
+ "loss": 0.8557,
878
+ "step": 72500
879
+ },
880
+ {
881
+ "epoch": 2.12,
882
+ "learning_rate": 1.4643293214721787e-05,
883
+ "loss": 0.87,
884
+ "step": 73000
885
+ },
886
+ {
887
+ "epoch": 2.14,
888
+ "learning_rate": 1.4401031067697734e-05,
889
+ "loss": 0.8454,
890
+ "step": 73500
891
+ },
892
+ {
893
+ "epoch": 2.15,
894
+ "learning_rate": 1.4158768920673685e-05,
895
+ "loss": 0.8517,
896
+ "step": 74000
897
+ },
898
+ {
899
+ "epoch": 2.17,
900
+ "learning_rate": 1.3916506773649632e-05,
901
+ "loss": 0.8287,
902
+ "step": 74500
903
+ },
904
+ {
905
+ "epoch": 2.18,
906
+ "learning_rate": 1.3674729150919627e-05,
907
+ "loss": 0.8464,
908
+ "step": 75000
909
+ },
910
+ {
911
+ "epoch": 2.19,
912
+ "learning_rate": 1.3432467003895578e-05,
913
+ "loss": 0.8392,
914
+ "step": 75500
915
+ },
916
+ {
917
+ "epoch": 2.21,
918
+ "learning_rate": 1.3190204856871523e-05,
919
+ "loss": 0.8342,
920
+ "step": 76000
921
+ },
922
+ {
923
+ "epoch": 2.22,
924
+ "learning_rate": 1.294794270984747e-05,
925
+ "loss": 0.8241,
926
+ "step": 76500
927
+ },
928
+ {
929
+ "epoch": 2.24,
930
+ "learning_rate": 1.2706165087117469e-05,
931
+ "loss": 0.8402,
932
+ "step": 77000
933
+ },
934
+ {
935
+ "epoch": 2.25,
936
+ "learning_rate": 1.2463902940093416e-05,
937
+ "loss": 0.8388,
938
+ "step": 77500
939
+ },
940
+ {
941
+ "epoch": 2.27,
942
+ "learning_rate": 1.2221640793069365e-05,
943
+ "loss": 0.8416,
944
+ "step": 78000
945
+ },
946
+ {
947
+ "epoch": 2.28,
948
+ "learning_rate": 1.1979378646045314e-05,
949
+ "loss": 0.8356,
950
+ "step": 78500
951
+ },
952
+ {
953
+ "epoch": 2.3,
954
+ "learning_rate": 1.1737116499021262e-05,
955
+ "loss": 0.8503,
956
+ "step": 79000
957
+ },
958
+ {
959
+ "epoch": 2.31,
960
+ "learning_rate": 1.149485435199721e-05,
961
+ "loss": 0.8415,
962
+ "step": 79500
963
+ },
964
+ {
965
+ "epoch": 2.33,
966
+ "learning_rate": 1.1252592204973158e-05,
967
+ "loss": 0.8241,
968
+ "step": 80000
969
+ },
970
+ {
971
+ "epoch": 2.34,
972
+ "learning_rate": 1.1010330057949106e-05,
973
+ "loss": 0.8365,
974
+ "step": 80500
975
+ },
976
+ {
977
+ "epoch": 2.35,
978
+ "learning_rate": 1.0768552435219102e-05,
979
+ "loss": 0.8324,
980
+ "step": 81000
981
+ },
982
+ {
983
+ "epoch": 2.37,
984
+ "learning_rate": 1.0526290288195051e-05,
985
+ "loss": 0.8412,
986
+ "step": 81500
987
+ },
988
+ {
989
+ "epoch": 2.38,
990
+ "learning_rate": 1.0284028141170999e-05,
991
+ "loss": 0.8392,
992
+ "step": 82000
993
+ },
994
+ {
995
+ "epoch": 2.4,
996
+ "learning_rate": 1.0041765994146948e-05,
997
+ "loss": 0.8169,
998
+ "step": 82500
999
+ },
1000
+ {
1001
+ "epoch": 2.41,
1002
+ "learning_rate": 9.799503847122895e-06,
1003
+ "loss": 0.8433,
1004
+ "step": 83000
1005
+ },
1006
+ {
1007
+ "epoch": 2.43,
1008
+ "learning_rate": 9.557726224392891e-06,
1009
+ "loss": 0.8257,
1010
+ "step": 83500
1011
+ },
1012
+ {
1013
+ "epoch": 2.44,
1014
+ "learning_rate": 9.315464077368839e-06,
1015
+ "loss": 0.8252,
1016
+ "step": 84000
1017
+ },
1018
+ {
1019
+ "epoch": 2.46,
1020
+ "learning_rate": 9.073201930344788e-06,
1021
+ "loss": 0.8558,
1022
+ "step": 84500
1023
+ },
1024
+ {
1025
+ "epoch": 2.47,
1026
+ "learning_rate": 8.831424307614784e-06,
1027
+ "loss": 0.8249,
1028
+ "step": 85000
1029
+ },
1030
+ {
1031
+ "epoch": 2.49,
1032
+ "learning_rate": 8.589162160590733e-06,
1033
+ "loss": 0.8064,
1034
+ "step": 85500
1035
+ },
1036
+ {
1037
+ "epoch": 2.5,
1038
+ "learning_rate": 8.34690001356668e-06,
1039
+ "loss": 0.8214,
1040
+ "step": 86000
1041
+ },
1042
+ {
1043
+ "epoch": 2.51,
1044
+ "learning_rate": 8.104637866542628e-06,
1045
+ "loss": 0.8255,
1046
+ "step": 86500
1047
+ },
1048
+ {
1049
+ "epoch": 2.53,
1050
+ "learning_rate": 7.862375719518577e-06,
1051
+ "loss": 0.8239,
1052
+ "step": 87000
1053
+ },
1054
+ {
1055
+ "epoch": 2.54,
1056
+ "learning_rate": 7.620113572494525e-06,
1057
+ "loss": 0.8037,
1058
+ "step": 87500
1059
+ },
1060
+ {
1061
+ "epoch": 2.56,
1062
+ "learning_rate": 7.377851425470474e-06,
1063
+ "loss": 0.8353,
1064
+ "step": 88000
1065
+ },
1066
+ {
1067
+ "epoch": 2.57,
1068
+ "learning_rate": 7.135589278446422e-06,
1069
+ "loss": 0.8309,
1070
+ "step": 88500
1071
+ },
1072
+ {
1073
+ "epoch": 2.59,
1074
+ "learning_rate": 6.8933271314223696e-06,
1075
+ "loss": 0.821,
1076
+ "step": 89000
1077
+ },
1078
+ {
1079
+ "epoch": 2.6,
1080
+ "learning_rate": 6.651064984398319e-06,
1081
+ "loss": 0.8332,
1082
+ "step": 89500
1083
+ },
1084
+ {
1085
+ "epoch": 2.62,
1086
+ "learning_rate": 6.408802837374265e-06,
1087
+ "loss": 0.8259,
1088
+ "step": 90000
1089
+ },
1090
+ {
1091
+ "epoch": 2.63,
1092
+ "learning_rate": 6.167025214644262e-06,
1093
+ "loss": 0.8015,
1094
+ "step": 90500
1095
+ },
1096
+ {
1097
+ "epoch": 2.65,
1098
+ "learning_rate": 5.925247591914259e-06,
1099
+ "loss": 0.7962,
1100
+ "step": 91000
1101
+ },
1102
+ {
1103
+ "epoch": 2.66,
1104
+ "learning_rate": 5.682985444890207e-06,
1105
+ "loss": 0.8102,
1106
+ "step": 91500
1107
+ },
1108
+ {
1109
+ "epoch": 2.67,
1110
+ "learning_rate": 5.440723297866155e-06,
1111
+ "loss": 0.8199,
1112
+ "step": 92000
1113
+ },
1114
+ {
1115
+ "epoch": 2.69,
1116
+ "learning_rate": 5.198461150842103e-06,
1117
+ "loss": 0.8308,
1118
+ "step": 92500
1119
+ },
1120
+ {
1121
+ "epoch": 2.7,
1122
+ "learning_rate": 4.956199003818052e-06,
1123
+ "loss": 0.8337,
1124
+ "step": 93000
1125
+ },
1126
+ {
1127
+ "epoch": 2.72,
1128
+ "learning_rate": 4.713936856794e-06,
1129
+ "loss": 0.8267,
1130
+ "step": 93500
1131
+ },
1132
+ {
1133
+ "epoch": 2.73,
1134
+ "learning_rate": 4.471674709769948e-06,
1135
+ "loss": 0.8234,
1136
+ "step": 94000
1137
+ },
1138
+ {
1139
+ "epoch": 2.75,
1140
+ "learning_rate": 4.2294125627458965e-06,
1141
+ "loss": 0.8067,
1142
+ "step": 94500
1143
+ },
1144
+ {
1145
+ "epoch": 2.76,
1146
+ "learning_rate": 3.987150415721844e-06,
1147
+ "loss": 0.8037,
1148
+ "step": 95000
1149
+ },
1150
+ {
1151
+ "epoch": 2.78,
1152
+ "learning_rate": 3.7453727929918406e-06,
1153
+ "loss": 0.8173,
1154
+ "step": 95500
1155
+ },
1156
+ {
1157
+ "epoch": 2.79,
1158
+ "learning_rate": 3.503110645967789e-06,
1159
+ "loss": 0.8107,
1160
+ "step": 96000
1161
+ },
1162
+ {
1163
+ "epoch": 2.81,
1164
+ "learning_rate": 3.2608484989437376e-06,
1165
+ "loss": 0.8367,
1166
+ "step": 96500
1167
+ },
1168
+ {
1169
+ "epoch": 2.82,
1170
+ "learning_rate": 3.0185863519196854e-06,
1171
+ "loss": 0.8082,
1172
+ "step": 97000
1173
+ },
1174
+ {
1175
+ "epoch": 2.83,
1176
+ "learning_rate": 2.7763242048956337e-06,
1177
+ "loss": 0.8369,
1178
+ "step": 97500
1179
+ },
1180
+ {
1181
+ "epoch": 2.85,
1182
+ "learning_rate": 2.5340620578715816e-06,
1183
+ "loss": 0.8116,
1184
+ "step": 98000
1185
+ },
1186
+ {
1187
+ "epoch": 2.86,
1188
+ "learning_rate": 2.2917999108475303e-06,
1189
+ "loss": 0.8298,
1190
+ "step": 98500
1191
+ },
1192
+ {
1193
+ "epoch": 2.88,
1194
+ "learning_rate": 2.049537763823478e-06,
1195
+ "loss": 0.8025,
1196
+ "step": 99000
1197
+ },
1198
+ {
1199
+ "epoch": 2.89,
1200
+ "learning_rate": 1.8072756167994264e-06,
1201
+ "loss": 0.8259,
1202
+ "step": 99500
1203
+ },
1204
+ {
1205
+ "epoch": 2.91,
1206
+ "learning_rate": 1.5654979940694228e-06,
1207
+ "loss": 0.8255,
1208
+ "step": 100000
1209
+ },
1210
+ {
1211
+ "epoch": 2.92,
1212
+ "learning_rate": 1.323235847045371e-06,
1213
+ "loss": 0.8258,
1214
+ "step": 100500
1215
+ },
1216
+ {
1217
+ "epoch": 2.94,
1218
+ "learning_rate": 1.0814582243153673e-06,
1219
+ "loss": 0.8392,
1220
+ "step": 101000
1221
+ },
1222
+ {
1223
+ "epoch": 2.95,
1224
+ "learning_rate": 8.391960772913154e-07,
1225
+ "loss": 0.8188,
1226
+ "step": 101500
1227
+ },
1228
+ {
1229
+ "epoch": 2.97,
1230
+ "learning_rate": 5.969339302672636e-07,
1231
+ "loss": 0.8239,
1232
+ "step": 102000
1233
+ },
1234
+ {
1235
+ "epoch": 2.98,
1236
+ "learning_rate": 3.5467178324321185e-07,
1237
+ "loss": 0.8183,
1238
+ "step": 102500
1239
+ },
1240
+ {
1241
+ "epoch": 2.99,
1242
+ "learning_rate": 1.1240963621916004e-07,
1243
+ "loss": 0.7981,
1244
+ "step": 103000
1245
+ },
1246
+ {
1247
+ "epoch": 3.0,
1248
+ "step": 103194,
1249
+ "total_flos": 1.9167267894224486e+17,
1250
+ "train_loss": 0.4842614623898048,
1251
+ "train_runtime": 25288.6173,
1252
+ "train_samples_per_second": 4.081,
1253
+ "train_steps_per_second": 4.081
1254
+ }
1255
+ ],
1256
+ "max_steps": 103194,
1257
+ "num_train_epochs": 3,
1258
+ "total_flos": 1.9167267894224486e+17,
1259
+ "trial_name": null,
1260
+ "trial_params": null
1261
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efe8f78e3b89b26de5f8fe4d34bf311a2a43241d7843b7199fb9c853d3248bbd
3
+ size 3643
vocab.json ADDED
The diff for this file is too large to render. See raw diff