Simon Liang commited on
Commit
1cc50a7
1 Parent(s): db6e680

initial commit

Browse files
.gitattributes CHANGED
@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ all_results.json filter=lfs diff=lfs merge=lfs -text
29
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - zh
4
+ - yue
5
+ license: apache-2.0
6
+ tags:
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: output
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # output
17
+
18
+ This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 1
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 3.0
44
+
45
+ ### Training results
46
+
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.12.5
52
+ - Pytorch 1.8.1
53
+ - Datasets 1.15.1
54
+ - Tokenizers 0.10.3
all_results.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2a4463093d5cc6d50c1c67db620aeaf0e3430d4b3f7213b4d890cfaeb4a4c09
3
+ size 195
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-base",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "mt5",
17
+ "num_decoder_layers": 12,
18
+ "num_heads": 12,
19
+ "num_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "relative_attention_num_buckets": 32,
23
+ "tie_word_embeddings": false,
24
+ "tokenizer_class": "T5Tokenizer",
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.12.5",
27
+ "use_cache": true,
28
+ "vocab_size": 250100
29
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bf364f6c3fd891d8f0d6c22885d0ba5d4c05529a82ae3cf83bc098c31d4dea4
3
+ size 2329665369
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-base", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.7122196425333716,
4
+ "train_runtime": 31286.0654,
5
+ "train_samples": 24184,
6
+ "train_samples_per_second": 2.319,
7
+ "train_steps_per_second": 2.319
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,895 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 72552,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 4.965541956114236e-05,
13
+ "loss": 6.1548,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 4.9310839122284706e-05,
19
+ "loss": 2.7342,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.06,
24
+ "learning_rate": 4.896625868342706e-05,
25
+ "loss": 2.4512,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.08,
30
+ "learning_rate": 4.8621678244569415e-05,
31
+ "loss": 2.041,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.1,
36
+ "learning_rate": 4.827709780571177e-05,
37
+ "loss": 1.87,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.12,
42
+ "learning_rate": 4.793251736685412e-05,
43
+ "loss": 1.788,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.14,
48
+ "learning_rate": 4.7587936927996474e-05,
49
+ "loss": 1.5907,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.17,
54
+ "learning_rate": 4.724335648913883e-05,
55
+ "loss": 1.4284,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.19,
60
+ "learning_rate": 4.689877605028118e-05,
61
+ "loss": 1.4261,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.21,
66
+ "learning_rate": 4.655419561142353e-05,
67
+ "loss": 1.3028,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.23,
72
+ "learning_rate": 4.620961517256589e-05,
73
+ "loss": 1.2614,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.25,
78
+ "learning_rate": 4.586503473370824e-05,
79
+ "loss": 1.22,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.27,
84
+ "learning_rate": 4.552045429485059e-05,
85
+ "loss": 1.1096,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.29,
90
+ "learning_rate": 4.5175873855992945e-05,
91
+ "loss": 1.0037,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.31,
96
+ "learning_rate": 4.48312934171353e-05,
97
+ "loss": 0.9759,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.33,
102
+ "learning_rate": 4.448671297827765e-05,
103
+ "loss": 0.9835,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.35,
108
+ "learning_rate": 4.414213253942e-05,
109
+ "loss": 1.0102,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.37,
114
+ "learning_rate": 4.379755210056236e-05,
115
+ "loss": 0.9729,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.39,
120
+ "learning_rate": 4.345297166170471e-05,
121
+ "loss": 0.9993,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.41,
126
+ "learning_rate": 4.310839122284706e-05,
127
+ "loss": 0.9757,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.43,
132
+ "learning_rate": 4.2763810783989416e-05,
133
+ "loss": 0.8614,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.45,
138
+ "learning_rate": 4.241923034513177e-05,
139
+ "loss": 0.9695,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.48,
144
+ "learning_rate": 4.207464990627412e-05,
145
+ "loss": 0.9486,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.5,
150
+ "learning_rate": 4.1730069467416474e-05,
151
+ "loss": 0.8465,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.52,
156
+ "learning_rate": 4.138548902855883e-05,
157
+ "loss": 0.9047,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.54,
162
+ "learning_rate": 4.1040908589701184e-05,
163
+ "loss": 0.8987,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.56,
168
+ "learning_rate": 4.069632815084353e-05,
169
+ "loss": 0.8616,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.58,
174
+ "learning_rate": 4.035174771198589e-05,
175
+ "loss": 0.8082,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.6,
180
+ "learning_rate": 4.000716727312824e-05,
181
+ "loss": 0.8222,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.62,
186
+ "learning_rate": 3.966258683427059e-05,
187
+ "loss": 0.8866,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.64,
192
+ "learning_rate": 3.9318006395412945e-05,
193
+ "loss": 0.8154,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.66,
198
+ "learning_rate": 3.89734259565553e-05,
199
+ "loss": 0.8205,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.68,
204
+ "learning_rate": 3.8628845517697655e-05,
205
+ "loss": 0.7804,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.7,
210
+ "learning_rate": 3.8284265078840004e-05,
211
+ "loss": 0.7578,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.72,
216
+ "learning_rate": 3.793968463998236e-05,
217
+ "loss": 0.703,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.74,
222
+ "learning_rate": 3.7595104201124713e-05,
223
+ "loss": 0.7462,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.76,
228
+ "learning_rate": 3.725052376226706e-05,
229
+ "loss": 0.6794,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.79,
234
+ "learning_rate": 3.690594332340942e-05,
235
+ "loss": 0.8277,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.81,
240
+ "learning_rate": 3.656136288455177e-05,
241
+ "loss": 0.7999,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.83,
246
+ "learning_rate": 3.6216782445694127e-05,
247
+ "loss": 0.8127,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.85,
252
+ "learning_rate": 3.5872202006836475e-05,
253
+ "loss": 0.7502,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.87,
258
+ "learning_rate": 3.552762156797883e-05,
259
+ "loss": 0.6666,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.89,
264
+ "learning_rate": 3.5183041129121185e-05,
265
+ "loss": 0.7633,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.91,
270
+ "learning_rate": 3.483846069026353e-05,
271
+ "loss": 0.6219,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 0.93,
276
+ "learning_rate": 3.449388025140589e-05,
277
+ "loss": 0.6019,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 0.95,
282
+ "learning_rate": 3.414929981254824e-05,
283
+ "loss": 0.6275,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 0.97,
288
+ "learning_rate": 3.38047193736906e-05,
289
+ "loss": 0.7371,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 0.99,
294
+ "learning_rate": 3.3460138934832946e-05,
295
+ "loss": 0.6864,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 1.01,
300
+ "learning_rate": 3.31155584959753e-05,
301
+ "loss": 0.5862,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 1.03,
306
+ "learning_rate": 3.2770978057117656e-05,
307
+ "loss": 0.5982,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 1.05,
312
+ "learning_rate": 3.2426397618260004e-05,
313
+ "loss": 0.6,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 1.08,
318
+ "learning_rate": 3.2081817179402366e-05,
319
+ "loss": 0.6196,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 1.1,
324
+ "learning_rate": 3.1737236740544714e-05,
325
+ "loss": 0.5537,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 1.12,
330
+ "learning_rate": 3.139265630168707e-05,
331
+ "loss": 0.5919,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 1.14,
336
+ "learning_rate": 3.104807586282942e-05,
337
+ "loss": 0.575,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 1.16,
342
+ "learning_rate": 3.070349542397177e-05,
343
+ "loss": 0.6071,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 1.18,
348
+ "learning_rate": 3.0358914985114127e-05,
349
+ "loss": 0.5724,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 1.2,
354
+ "learning_rate": 3.001433454625648e-05,
355
+ "loss": 0.6363,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 1.22,
360
+ "learning_rate": 2.9669754107398834e-05,
361
+ "loss": 0.6006,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 1.24,
366
+ "learning_rate": 2.9325173668541185e-05,
367
+ "loss": 0.5794,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 1.26,
372
+ "learning_rate": 2.898059322968354e-05,
373
+ "loss": 0.5238,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 1.28,
378
+ "learning_rate": 2.863601279082589e-05,
379
+ "loss": 0.5694,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 1.3,
384
+ "learning_rate": 2.8291432351968243e-05,
385
+ "loss": 0.5529,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 1.32,
390
+ "learning_rate": 2.79468519131106e-05,
391
+ "loss": 0.5422,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 1.34,
396
+ "learning_rate": 2.760227147425295e-05,
397
+ "loss": 0.5753,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 1.36,
402
+ "learning_rate": 2.7257691035395305e-05,
403
+ "loss": 0.5738,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 1.39,
408
+ "learning_rate": 2.6913110596537656e-05,
409
+ "loss": 0.5493,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 1.41,
414
+ "learning_rate": 2.656853015768001e-05,
415
+ "loss": 0.4863,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 1.43,
420
+ "learning_rate": 2.622394971882236e-05,
421
+ "loss": 0.5564,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 1.45,
426
+ "learning_rate": 2.5879369279964715e-05,
427
+ "loss": 0.5389,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 1.47,
432
+ "learning_rate": 2.553478884110707e-05,
433
+ "loss": 0.5948,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 1.49,
438
+ "learning_rate": 2.519020840224942e-05,
439
+ "loss": 0.5287,
440
+ "step": 36000
441
+ },
442
+ {
443
+ "epoch": 1.51,
444
+ "learning_rate": 2.4845627963391776e-05,
445
+ "loss": 0.57,
446
+ "step": 36500
447
+ },
448
+ {
449
+ "epoch": 1.53,
450
+ "learning_rate": 2.4501047524534128e-05,
451
+ "loss": 0.5498,
452
+ "step": 37000
453
+ },
454
+ {
455
+ "epoch": 1.55,
456
+ "learning_rate": 2.4156467085676483e-05,
457
+ "loss": 0.5333,
458
+ "step": 37500
459
+ },
460
+ {
461
+ "epoch": 1.57,
462
+ "learning_rate": 2.3811886646818834e-05,
463
+ "loss": 0.5302,
464
+ "step": 38000
465
+ },
466
+ {
467
+ "epoch": 1.59,
468
+ "learning_rate": 2.3467306207961186e-05,
469
+ "loss": 0.5425,
470
+ "step": 38500
471
+ },
472
+ {
473
+ "epoch": 1.61,
474
+ "learning_rate": 2.312272576910354e-05,
475
+ "loss": 0.5765,
476
+ "step": 39000
477
+ },
478
+ {
479
+ "epoch": 1.63,
480
+ "learning_rate": 2.2778145330245892e-05,
481
+ "loss": 0.5338,
482
+ "step": 39500
483
+ },
484
+ {
485
+ "epoch": 1.65,
486
+ "learning_rate": 2.2433564891388247e-05,
487
+ "loss": 0.5722,
488
+ "step": 40000
489
+ },
490
+ {
491
+ "epoch": 1.67,
492
+ "learning_rate": 2.20889844525306e-05,
493
+ "loss": 0.5721,
494
+ "step": 40500
495
+ },
496
+ {
497
+ "epoch": 1.7,
498
+ "learning_rate": 2.1744404013672954e-05,
499
+ "loss": 0.5453,
500
+ "step": 41000
501
+ },
502
+ {
503
+ "epoch": 1.72,
504
+ "learning_rate": 2.1399823574815305e-05,
505
+ "loss": 0.5486,
506
+ "step": 41500
507
+ },
508
+ {
509
+ "epoch": 1.74,
510
+ "learning_rate": 2.1055243135957657e-05,
511
+ "loss": 0.5039,
512
+ "step": 42000
513
+ },
514
+ {
515
+ "epoch": 1.76,
516
+ "learning_rate": 2.0710662697100012e-05,
517
+ "loss": 0.5343,
518
+ "step": 42500
519
+ },
520
+ {
521
+ "epoch": 1.78,
522
+ "learning_rate": 2.0366082258242364e-05,
523
+ "loss": 0.5251,
524
+ "step": 43000
525
+ },
526
+ {
527
+ "epoch": 1.8,
528
+ "learning_rate": 2.002150181938472e-05,
529
+ "loss": 0.5104,
530
+ "step": 43500
531
+ },
532
+ {
533
+ "epoch": 1.82,
534
+ "learning_rate": 1.9676921380527074e-05,
535
+ "loss": 0.5306,
536
+ "step": 44000
537
+ },
538
+ {
539
+ "epoch": 1.84,
540
+ "learning_rate": 1.9332340941669425e-05,
541
+ "loss": 0.5365,
542
+ "step": 44500
543
+ },
544
+ {
545
+ "epoch": 1.86,
546
+ "learning_rate": 1.8987760502811777e-05,
547
+ "loss": 0.5759,
548
+ "step": 45000
549
+ },
550
+ {
551
+ "epoch": 1.88,
552
+ "learning_rate": 1.8643180063954128e-05,
553
+ "loss": 0.5443,
554
+ "step": 45500
555
+ },
556
+ {
557
+ "epoch": 1.9,
558
+ "learning_rate": 1.8298599625096483e-05,
559
+ "loss": 0.5431,
560
+ "step": 46000
561
+ },
562
+ {
563
+ "epoch": 1.92,
564
+ "learning_rate": 1.7954019186238835e-05,
565
+ "loss": 0.5675,
566
+ "step": 46500
567
+ },
568
+ {
569
+ "epoch": 1.94,
570
+ "learning_rate": 1.760943874738119e-05,
571
+ "loss": 0.5085,
572
+ "step": 47000
573
+ },
574
+ {
575
+ "epoch": 1.96,
576
+ "learning_rate": 1.7264858308523545e-05,
577
+ "loss": 0.4524,
578
+ "step": 47500
579
+ },
580
+ {
581
+ "epoch": 1.98,
582
+ "learning_rate": 1.6920277869665896e-05,
583
+ "loss": 0.5196,
584
+ "step": 48000
585
+ },
586
+ {
587
+ "epoch": 2.01,
588
+ "learning_rate": 1.6575697430808248e-05,
589
+ "loss": 0.4268,
590
+ "step": 48500
591
+ },
592
+ {
593
+ "epoch": 2.03,
594
+ "learning_rate": 1.6231116991950603e-05,
595
+ "loss": 0.4463,
596
+ "step": 49000
597
+ },
598
+ {
599
+ "epoch": 2.05,
600
+ "learning_rate": 1.5886536553092954e-05,
601
+ "loss": 0.441,
602
+ "step": 49500
603
+ },
604
+ {
605
+ "epoch": 2.07,
606
+ "learning_rate": 1.5541956114235306e-05,
607
+ "loss": 0.4984,
608
+ "step": 50000
609
+ },
610
+ {
611
+ "epoch": 2.09,
612
+ "learning_rate": 1.5197375675377663e-05,
613
+ "loss": 0.4393,
614
+ "step": 50500
615
+ },
616
+ {
617
+ "epoch": 2.11,
618
+ "learning_rate": 1.4852795236520014e-05,
619
+ "loss": 0.4646,
620
+ "step": 51000
621
+ },
622
+ {
623
+ "epoch": 2.13,
624
+ "learning_rate": 1.4508214797662368e-05,
625
+ "loss": 0.4159,
626
+ "step": 51500
627
+ },
628
+ {
629
+ "epoch": 2.15,
630
+ "learning_rate": 1.4163634358804719e-05,
631
+ "loss": 0.4288,
632
+ "step": 52000
633
+ },
634
+ {
635
+ "epoch": 2.17,
636
+ "learning_rate": 1.3819053919947072e-05,
637
+ "loss": 0.4413,
638
+ "step": 52500
639
+ },
640
+ {
641
+ "epoch": 2.19,
642
+ "learning_rate": 1.3474473481089426e-05,
643
+ "loss": 0.4242,
644
+ "step": 53000
645
+ },
646
+ {
647
+ "epoch": 2.21,
648
+ "learning_rate": 1.3129893042231777e-05,
649
+ "loss": 0.4322,
650
+ "step": 53500
651
+ },
652
+ {
653
+ "epoch": 2.23,
654
+ "learning_rate": 1.2785312603374134e-05,
655
+ "loss": 0.4472,
656
+ "step": 54000
657
+ },
658
+ {
659
+ "epoch": 2.25,
660
+ "learning_rate": 1.2440732164516485e-05,
661
+ "loss": 0.4213,
662
+ "step": 54500
663
+ },
664
+ {
665
+ "epoch": 2.27,
666
+ "learning_rate": 1.2096151725658839e-05,
667
+ "loss": 0.4041,
668
+ "step": 55000
669
+ },
670
+ {
671
+ "epoch": 2.29,
672
+ "learning_rate": 1.1751571286801192e-05,
673
+ "loss": 0.4678,
674
+ "step": 55500
675
+ },
676
+ {
677
+ "epoch": 2.32,
678
+ "learning_rate": 1.1406990847943544e-05,
679
+ "loss": 0.4285,
680
+ "step": 56000
681
+ },
682
+ {
683
+ "epoch": 2.34,
684
+ "learning_rate": 1.1062410409085899e-05,
685
+ "loss": 0.4884,
686
+ "step": 56500
687
+ },
688
+ {
689
+ "epoch": 2.36,
690
+ "learning_rate": 1.071782997022825e-05,
691
+ "loss": 0.3986,
692
+ "step": 57000
693
+ },
694
+ {
695
+ "epoch": 2.38,
696
+ "learning_rate": 1.0373249531370603e-05,
697
+ "loss": 0.4442,
698
+ "step": 57500
699
+ },
700
+ {
701
+ "epoch": 2.4,
702
+ "learning_rate": 1.0028669092512957e-05,
703
+ "loss": 0.4132,
704
+ "step": 58000
705
+ },
706
+ {
707
+ "epoch": 2.42,
708
+ "learning_rate": 9.68408865365531e-06,
709
+ "loss": 0.4151,
710
+ "step": 58500
711
+ },
712
+ {
713
+ "epoch": 2.44,
714
+ "learning_rate": 9.339508214797663e-06,
715
+ "loss": 0.4915,
716
+ "step": 59000
717
+ },
718
+ {
719
+ "epoch": 2.46,
720
+ "learning_rate": 8.994927775940015e-06,
721
+ "loss": 0.4656,
722
+ "step": 59500
723
+ },
724
+ {
725
+ "epoch": 2.48,
726
+ "learning_rate": 8.65034733708237e-06,
727
+ "loss": 0.4357,
728
+ "step": 60000
729
+ },
730
+ {
731
+ "epoch": 2.5,
732
+ "learning_rate": 8.305766898224721e-06,
733
+ "loss": 0.4376,
734
+ "step": 60500
735
+ },
736
+ {
737
+ "epoch": 2.52,
738
+ "learning_rate": 7.961186459367075e-06,
739
+ "loss": 0.4089,
740
+ "step": 61000
741
+ },
742
+ {
743
+ "epoch": 2.54,
744
+ "learning_rate": 7.616606020509429e-06,
745
+ "loss": 0.396,
746
+ "step": 61500
747
+ },
748
+ {
749
+ "epoch": 2.56,
750
+ "learning_rate": 7.272025581651781e-06,
751
+ "loss": 0.4529,
752
+ "step": 62000
753
+ },
754
+ {
755
+ "epoch": 2.58,
756
+ "learning_rate": 6.927445142794134e-06,
757
+ "loss": 0.3778,
758
+ "step": 62500
759
+ },
760
+ {
761
+ "epoch": 2.61,
762
+ "learning_rate": 6.582864703936487e-06,
763
+ "loss": 0.4486,
764
+ "step": 63000
765
+ },
766
+ {
767
+ "epoch": 2.63,
768
+ "learning_rate": 6.238284265078841e-06,
769
+ "loss": 0.5516,
770
+ "step": 63500
771
+ },
772
+ {
773
+ "epoch": 2.65,
774
+ "learning_rate": 5.8937038262211935e-06,
775
+ "loss": 0.4471,
776
+ "step": 64000
777
+ },
778
+ {
779
+ "epoch": 2.67,
780
+ "learning_rate": 5.549123387363547e-06,
781
+ "loss": 0.4037,
782
+ "step": 64500
783
+ },
784
+ {
785
+ "epoch": 2.69,
786
+ "learning_rate": 5.204542948505899e-06,
787
+ "loss": 0.4551,
788
+ "step": 65000
789
+ },
790
+ {
791
+ "epoch": 2.71,
792
+ "learning_rate": 4.8599625096482524e-06,
793
+ "loss": 0.3944,
794
+ "step": 65500
795
+ },
796
+ {
797
+ "epoch": 2.73,
798
+ "learning_rate": 4.515382070790605e-06,
799
+ "loss": 0.4431,
800
+ "step": 66000
801
+ },
802
+ {
803
+ "epoch": 2.75,
804
+ "learning_rate": 4.170801631932959e-06,
805
+ "loss": 0.4195,
806
+ "step": 66500
807
+ },
808
+ {
809
+ "epoch": 2.77,
810
+ "learning_rate": 3.826221193075312e-06,
811
+ "loss": 0.4728,
812
+ "step": 67000
813
+ },
814
+ {
815
+ "epoch": 2.79,
816
+ "learning_rate": 3.4816407542176647e-06,
817
+ "loss": 0.4298,
818
+ "step": 67500
819
+ },
820
+ {
821
+ "epoch": 2.81,
822
+ "learning_rate": 3.137060315360018e-06,
823
+ "loss": 0.4228,
824
+ "step": 68000
825
+ },
826
+ {
827
+ "epoch": 2.83,
828
+ "learning_rate": 2.792479876502371e-06,
829
+ "loss": 0.4302,
830
+ "step": 68500
831
+ },
832
+ {
833
+ "epoch": 2.85,
834
+ "learning_rate": 2.447899437644724e-06,
835
+ "loss": 0.4204,
836
+ "step": 69000
837
+ },
838
+ {
839
+ "epoch": 2.87,
840
+ "learning_rate": 2.103318998787077e-06,
841
+ "loss": 0.4077,
842
+ "step": 69500
843
+ },
844
+ {
845
+ "epoch": 2.89,
846
+ "learning_rate": 1.75873855992943e-06,
847
+ "loss": 0.4172,
848
+ "step": 70000
849
+ },
850
+ {
851
+ "epoch": 2.92,
852
+ "learning_rate": 1.414158121071783e-06,
853
+ "loss": 0.389,
854
+ "step": 70500
855
+ },
856
+ {
857
+ "epoch": 2.94,
858
+ "learning_rate": 1.069577682214136e-06,
859
+ "loss": 0.4612,
860
+ "step": 71000
861
+ },
862
+ {
863
+ "epoch": 2.96,
864
+ "learning_rate": 7.249972433564892e-07,
865
+ "loss": 0.447,
866
+ "step": 71500
867
+ },
868
+ {
869
+ "epoch": 2.98,
870
+ "learning_rate": 3.8041680449884223e-07,
871
+ "loss": 0.4153,
872
+ "step": 72000
873
+ },
874
+ {
875
+ "epoch": 3.0,
876
+ "learning_rate": 3.5836365641195283e-08,
877
+ "loss": 0.4197,
878
+ "step": 72500
879
+ },
880
+ {
881
+ "epoch": 3.0,
882
+ "step": 72552,
883
+ "total_flos": 6412401164344320.0,
884
+ "train_loss": 0.7122196425333716,
885
+ "train_runtime": 31286.0654,
886
+ "train_samples_per_second": 2.319,
887
+ "train_steps_per_second": 2.319
888
+ }
889
+ ],
890
+ "max_steps": 72552,
891
+ "num_train_epochs": 3,
892
+ "total_flos": 6412401164344320.0,
893
+ "trial_name": null,
894
+ "trial_params": null
895
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8962b1e3351177b7527e698ab28b3a1acb61adcb7148cea0a5a0e64270603afd
3
+ size 2991