1024m commited on
Commit
057c035
1 Parent(s): 2b02421

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +75 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +798 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForSequenceClassification"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "num_beams": 4,
47
+ "num_hidden_layers": 12,
48
+ "pad_token_id": 1,
49
+ "problem_type": "single_label_classification",
50
+ "scale_embedding": false,
51
+ "task_specific_params": {
52
+ "summarization": {
53
+ "length_penalty": 1.0,
54
+ "max_length": 128,
55
+ "min_length": 12,
56
+ "num_beams": 4
57
+ },
58
+ "summarization_cnn": {
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "num_beams": 4
63
+ },
64
+ "summarization_xsum": {
65
+ "length_penalty": 1.0,
66
+ "max_length": 62,
67
+ "min_length": 11,
68
+ "num_beams": 6
69
+ }
70
+ },
71
+ "torch_dtype": "float32",
72
+ "transformers_version": "4.38.2",
73
+ "use_cache": true,
74
+ "vocab_size": 50265
75
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:779926ef6eacaa8c49422ec53a63ea389986e09c42582416073d78dbe5d11db2
3
+ size 1629436964
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaaff72d8dbf79f67666d91e8305154d42c29a088c83cd120828aa5447dc7f5b
3
+ size 3259184731
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d10d7fda9f09c69dd21f47e30981bf0d0f2da66b58d8b117c6f5e6c4a92d90cb
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:050d49c8b90af1f7382adfd95f4f5c488aba1e2a190cd048cc2116ed1de6f673
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,798 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 20.0,
5
+ "eval_steps": 500,
6
+ "global_step": 11140,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.18,
13
+ "grad_norm": 6.054772853851318,
14
+ "learning_rate": 1.9820466786355476e-05,
15
+ "loss": 0.5721,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.36,
20
+ "grad_norm": 9.810357093811035,
21
+ "learning_rate": 1.9640933572710953e-05,
22
+ "loss": 0.3846,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.54,
27
+ "grad_norm": 9.026122093200684,
28
+ "learning_rate": 1.9461400359066428e-05,
29
+ "loss": 0.3019,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.72,
34
+ "grad_norm": 11.95788288116455,
35
+ "learning_rate": 1.9281867145421905e-05,
36
+ "loss": 0.3071,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.9,
41
+ "grad_norm": 15.329608917236328,
42
+ "learning_rate": 1.910233393177738e-05,
43
+ "loss": 0.2907,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 1.08,
48
+ "grad_norm": 12.364314079284668,
49
+ "learning_rate": 1.8922800718132857e-05,
50
+ "loss": 0.2646,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 1.26,
55
+ "grad_norm": 14.555986404418945,
56
+ "learning_rate": 1.874326750448833e-05,
57
+ "loss": 0.2097,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 1.44,
62
+ "grad_norm": 4.199421405792236,
63
+ "learning_rate": 1.8563734290843805e-05,
64
+ "loss": 0.2389,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 1.62,
69
+ "grad_norm": 22.485984802246094,
70
+ "learning_rate": 1.8384201077199283e-05,
71
+ "loss": 0.2019,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 1.8,
76
+ "grad_norm": 9.688520431518555,
77
+ "learning_rate": 1.820466786355476e-05,
78
+ "loss": 0.2594,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 1.97,
83
+ "grad_norm": 18.052719116210938,
84
+ "learning_rate": 1.8025134649910235e-05,
85
+ "loss": 0.2044,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 2.15,
90
+ "grad_norm": 0.7371789216995239,
91
+ "learning_rate": 1.7845601436265712e-05,
92
+ "loss": 0.1551,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 2.33,
97
+ "grad_norm": 20.938648223876953,
98
+ "learning_rate": 1.7666068222621186e-05,
99
+ "loss": 0.1463,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 2.51,
104
+ "grad_norm": 0.25227147340774536,
105
+ "learning_rate": 1.748653500897666e-05,
106
+ "loss": 0.1493,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 2.69,
111
+ "grad_norm": 0.27634137868881226,
112
+ "learning_rate": 1.7307001795332138e-05,
113
+ "loss": 0.1649,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 2.87,
118
+ "grad_norm": 0.2588340938091278,
119
+ "learning_rate": 1.7127468581687616e-05,
120
+ "loss": 0.1521,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 3.05,
125
+ "grad_norm": 0.05350634083151817,
126
+ "learning_rate": 1.694793536804309e-05,
127
+ "loss": 0.1343,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 3.23,
132
+ "grad_norm": 0.02972230687737465,
133
+ "learning_rate": 1.6768402154398564e-05,
134
+ "loss": 0.1068,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 3.41,
139
+ "grad_norm": 0.09572970867156982,
140
+ "learning_rate": 1.658886894075404e-05,
141
+ "loss": 0.1151,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 3.59,
146
+ "grad_norm": 21.431325912475586,
147
+ "learning_rate": 1.6409335727109516e-05,
148
+ "loss": 0.1073,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 3.77,
153
+ "grad_norm": 1.4688669443130493,
154
+ "learning_rate": 1.6229802513464993e-05,
155
+ "loss": 0.1098,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 3.95,
160
+ "grad_norm": 19.461355209350586,
161
+ "learning_rate": 1.6050269299820467e-05,
162
+ "loss": 0.1238,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 4.13,
167
+ "grad_norm": 6.33543586730957,
168
+ "learning_rate": 1.5870736086175945e-05,
169
+ "loss": 0.0934,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 4.31,
174
+ "grad_norm": 10.25698184967041,
175
+ "learning_rate": 1.569120287253142e-05,
176
+ "loss": 0.068,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 4.49,
181
+ "grad_norm": 0.05421575903892517,
182
+ "learning_rate": 1.5511669658886893e-05,
183
+ "loss": 0.0767,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 4.67,
188
+ "grad_norm": 0.04917303845286369,
189
+ "learning_rate": 1.533213644524237e-05,
190
+ "loss": 0.1053,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 4.85,
195
+ "grad_norm": 1.722901463508606,
196
+ "learning_rate": 1.5152603231597847e-05,
197
+ "loss": 0.0513,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 5.03,
202
+ "grad_norm": 28.548158645629883,
203
+ "learning_rate": 1.4973070017953321e-05,
204
+ "loss": 0.0611,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 5.21,
209
+ "grad_norm": 1.0562294721603394,
210
+ "learning_rate": 1.4793536804308799e-05,
211
+ "loss": 0.0543,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 5.39,
216
+ "grad_norm": 0.011326675303280354,
217
+ "learning_rate": 1.4614003590664274e-05,
218
+ "loss": 0.0491,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 5.57,
223
+ "grad_norm": 0.009987740777432919,
224
+ "learning_rate": 1.4434470377019749e-05,
225
+ "loss": 0.0567,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 5.75,
230
+ "grad_norm": 26.81354331970215,
231
+ "learning_rate": 1.4254937163375226e-05,
232
+ "loss": 0.0641,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 5.92,
237
+ "grad_norm": 0.042816389352083206,
238
+ "learning_rate": 1.4075403949730702e-05,
239
+ "loss": 0.0488,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 6.1,
244
+ "grad_norm": 0.014200630597770214,
245
+ "learning_rate": 1.3895870736086176e-05,
246
+ "loss": 0.0374,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 6.28,
251
+ "grad_norm": 0.004939161241054535,
252
+ "learning_rate": 1.3716337522441652e-05,
253
+ "loss": 0.0393,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 6.46,
258
+ "grad_norm": 39.326534271240234,
259
+ "learning_rate": 1.353680430879713e-05,
260
+ "loss": 0.0404,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 6.64,
265
+ "grad_norm": 1.0669581890106201,
266
+ "learning_rate": 1.3357271095152604e-05,
267
+ "loss": 0.03,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 6.82,
272
+ "grad_norm": 0.11205600947141647,
273
+ "learning_rate": 1.317773788150808e-05,
274
+ "loss": 0.0416,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 7.0,
279
+ "grad_norm": 0.005933618638664484,
280
+ "learning_rate": 1.2998204667863557e-05,
281
+ "loss": 0.0498,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 7.18,
286
+ "grad_norm": 0.0025591508019715548,
287
+ "learning_rate": 1.2818671454219031e-05,
288
+ "loss": 0.0214,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 7.36,
293
+ "grad_norm": 0.0021508955396711826,
294
+ "learning_rate": 1.2639138240574507e-05,
295
+ "loss": 0.0346,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 7.54,
300
+ "grad_norm": 0.002263248898088932,
301
+ "learning_rate": 1.2459605026929983e-05,
302
+ "loss": 0.0315,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 7.72,
307
+ "grad_norm": 0.0016491829883307219,
308
+ "learning_rate": 1.2280071813285459e-05,
309
+ "loss": 0.0238,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 7.9,
314
+ "grad_norm": 0.0034240155946463346,
315
+ "learning_rate": 1.2100538599640935e-05,
316
+ "loss": 0.0319,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 8.08,
321
+ "grad_norm": 0.002759799361228943,
322
+ "learning_rate": 1.1921005385996409e-05,
323
+ "loss": 0.0487,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 8.26,
328
+ "grad_norm": 34.639888763427734,
329
+ "learning_rate": 1.1741472172351887e-05,
330
+ "loss": 0.053,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 8.44,
335
+ "grad_norm": 0.001209100242704153,
336
+ "learning_rate": 1.1561938958707361e-05,
337
+ "loss": 0.0143,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 8.62,
342
+ "grad_norm": 0.0022134396713227034,
343
+ "learning_rate": 1.1382405745062837e-05,
344
+ "loss": 0.0291,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 8.8,
349
+ "grad_norm": 0.06826081871986389,
350
+ "learning_rate": 1.1202872531418314e-05,
351
+ "loss": 0.0301,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 8.98,
356
+ "grad_norm": 0.0025578713975846767,
357
+ "learning_rate": 1.1023339317773789e-05,
358
+ "loss": 0.0194,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 9.16,
363
+ "grad_norm": 0.01461367029696703,
364
+ "learning_rate": 1.0843806104129264e-05,
365
+ "loss": 0.0152,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 9.34,
370
+ "grad_norm": 0.0008313595899380744,
371
+ "learning_rate": 1.0664272890484742e-05,
372
+ "loss": 0.0163,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 9.52,
377
+ "grad_norm": 1.5908000469207764,
378
+ "learning_rate": 1.0484739676840216e-05,
379
+ "loss": 0.0352,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 9.69,
384
+ "grad_norm": 0.0016398399602621794,
385
+ "learning_rate": 1.0305206463195692e-05,
386
+ "loss": 0.0268,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 9.87,
391
+ "grad_norm": 0.005051742307841778,
392
+ "learning_rate": 1.0125673249551166e-05,
393
+ "loss": 0.0244,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 10.05,
398
+ "grad_norm": 0.11044131964445114,
399
+ "learning_rate": 9.946140035906644e-06,
400
+ "loss": 0.0318,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 10.23,
405
+ "grad_norm": 0.02652016654610634,
406
+ "learning_rate": 9.76660682226212e-06,
407
+ "loss": 0.0224,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 10.41,
412
+ "grad_norm": 0.0051875789649784565,
413
+ "learning_rate": 9.587073608617595e-06,
414
+ "loss": 0.0086,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 10.59,
419
+ "grad_norm": 0.0023671940434724092,
420
+ "learning_rate": 9.40754039497307e-06,
421
+ "loss": 0.0061,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 10.77,
426
+ "grad_norm": 0.14054147899150848,
427
+ "learning_rate": 9.228007181328547e-06,
428
+ "loss": 0.0222,
429
+ "step": 6000
430
+ },
431
+ {
432
+ "epoch": 10.95,
433
+ "grad_norm": 0.002135949907824397,
434
+ "learning_rate": 9.048473967684023e-06,
435
+ "loss": 0.0205,
436
+ "step": 6100
437
+ },
438
+ {
439
+ "epoch": 11.13,
440
+ "grad_norm": 0.5219959616661072,
441
+ "learning_rate": 8.868940754039497e-06,
442
+ "loss": 0.0243,
443
+ "step": 6200
444
+ },
445
+ {
446
+ "epoch": 11.31,
447
+ "grad_norm": 0.004496410954743624,
448
+ "learning_rate": 8.689407540394975e-06,
449
+ "loss": 0.0232,
450
+ "step": 6300
451
+ },
452
+ {
453
+ "epoch": 11.49,
454
+ "grad_norm": 0.0012191541027277708,
455
+ "learning_rate": 8.509874326750449e-06,
456
+ "loss": 0.0174,
457
+ "step": 6400
458
+ },
459
+ {
460
+ "epoch": 11.67,
461
+ "grad_norm": 0.0010406944202259183,
462
+ "learning_rate": 8.330341113105925e-06,
463
+ "loss": 0.0002,
464
+ "step": 6500
465
+ },
466
+ {
467
+ "epoch": 11.85,
468
+ "grad_norm": 0.0007079216302372515,
469
+ "learning_rate": 8.1508078994614e-06,
470
+ "loss": 0.0181,
471
+ "step": 6600
472
+ },
473
+ {
474
+ "epoch": 12.03,
475
+ "grad_norm": 0.0031879213638603687,
476
+ "learning_rate": 7.971274685816877e-06,
477
+ "loss": 0.0029,
478
+ "step": 6700
479
+ },
480
+ {
481
+ "epoch": 12.21,
482
+ "grad_norm": 0.07363840192556381,
483
+ "learning_rate": 7.791741472172353e-06,
484
+ "loss": 0.012,
485
+ "step": 6800
486
+ },
487
+ {
488
+ "epoch": 12.39,
489
+ "grad_norm": 0.0074967676773667336,
490
+ "learning_rate": 7.6122082585278276e-06,
491
+ "loss": 0.0297,
492
+ "step": 6900
493
+ },
494
+ {
495
+ "epoch": 12.57,
496
+ "grad_norm": 0.03205731883645058,
497
+ "learning_rate": 7.432675044883304e-06,
498
+ "loss": 0.0172,
499
+ "step": 7000
500
+ },
501
+ {
502
+ "epoch": 12.75,
503
+ "grad_norm": 0.0017446995479986072,
504
+ "learning_rate": 7.25314183123878e-06,
505
+ "loss": 0.0095,
506
+ "step": 7100
507
+ },
508
+ {
509
+ "epoch": 12.93,
510
+ "grad_norm": 62.21705627441406,
511
+ "learning_rate": 7.073608617594255e-06,
512
+ "loss": 0.0216,
513
+ "step": 7200
514
+ },
515
+ {
516
+ "epoch": 13.11,
517
+ "grad_norm": 0.0004949498688802123,
518
+ "learning_rate": 6.894075403949732e-06,
519
+ "loss": 0.0025,
520
+ "step": 7300
521
+ },
522
+ {
523
+ "epoch": 13.29,
524
+ "grad_norm": 1.0483726263046265,
525
+ "learning_rate": 6.714542190305207e-06,
526
+ "loss": 0.0124,
527
+ "step": 7400
528
+ },
529
+ {
530
+ "epoch": 13.46,
531
+ "grad_norm": 0.0011325060622766614,
532
+ "learning_rate": 6.535008976660683e-06,
533
+ "loss": 0.0176,
534
+ "step": 7500
535
+ },
536
+ {
537
+ "epoch": 13.64,
538
+ "grad_norm": 0.0004886816022917628,
539
+ "learning_rate": 6.355475763016159e-06,
540
+ "loss": 0.0005,
541
+ "step": 7600
542
+ },
543
+ {
544
+ "epoch": 13.82,
545
+ "grad_norm": 0.0002447882143314928,
546
+ "learning_rate": 6.175942549371634e-06,
547
+ "loss": 0.0,
548
+ "step": 7700
549
+ },
550
+ {
551
+ "epoch": 14.0,
552
+ "grad_norm": 0.0033621052280068398,
553
+ "learning_rate": 5.99640933572711e-06,
554
+ "loss": 0.0151,
555
+ "step": 7800
556
+ },
557
+ {
558
+ "epoch": 14.18,
559
+ "grad_norm": 0.37218067049980164,
560
+ "learning_rate": 5.8168761220825854e-06,
561
+ "loss": 0.0062,
562
+ "step": 7900
563
+ },
564
+ {
565
+ "epoch": 14.36,
566
+ "grad_norm": 0.00017587828915566206,
567
+ "learning_rate": 5.637342908438061e-06,
568
+ "loss": 0.0004,
569
+ "step": 8000
570
+ },
571
+ {
572
+ "epoch": 14.54,
573
+ "grad_norm": 0.00030748211429454386,
574
+ "learning_rate": 5.457809694793538e-06,
575
+ "loss": 0.0,
576
+ "step": 8100
577
+ },
578
+ {
579
+ "epoch": 14.72,
580
+ "grad_norm": 0.0006639692583121359,
581
+ "learning_rate": 5.278276481149013e-06,
582
+ "loss": 0.0301,
583
+ "step": 8200
584
+ },
585
+ {
586
+ "epoch": 14.9,
587
+ "grad_norm": 0.0006772920023649931,
588
+ "learning_rate": 5.098743267504489e-06,
589
+ "loss": 0.015,
590
+ "step": 8300
591
+ },
592
+ {
593
+ "epoch": 15.08,
594
+ "grad_norm": 0.0017782676732167602,
595
+ "learning_rate": 4.919210053859965e-06,
596
+ "loss": 0.0184,
597
+ "step": 8400
598
+ },
599
+ {
600
+ "epoch": 15.26,
601
+ "grad_norm": 0.0006229325663298368,
602
+ "learning_rate": 4.739676840215441e-06,
603
+ "loss": 0.0053,
604
+ "step": 8500
605
+ },
606
+ {
607
+ "epoch": 15.44,
608
+ "grad_norm": 0.0011186526389792562,
609
+ "learning_rate": 4.560143626570916e-06,
610
+ "loss": 0.0076,
611
+ "step": 8600
612
+ },
613
+ {
614
+ "epoch": 15.62,
615
+ "grad_norm": 0.0009836511453613639,
616
+ "learning_rate": 4.380610412926392e-06,
617
+ "loss": 0.0054,
618
+ "step": 8700
619
+ },
620
+ {
621
+ "epoch": 15.8,
622
+ "grad_norm": 0.002876699436455965,
623
+ "learning_rate": 4.2010771992818675e-06,
624
+ "loss": 0.0011,
625
+ "step": 8800
626
+ },
627
+ {
628
+ "epoch": 15.98,
629
+ "grad_norm": 0.0004506981058511883,
630
+ "learning_rate": 4.021543985637343e-06,
631
+ "loss": 0.0142,
632
+ "step": 8900
633
+ },
634
+ {
635
+ "epoch": 16.16,
636
+ "grad_norm": 143.88809204101562,
637
+ "learning_rate": 3.842010771992819e-06,
638
+ "loss": 0.0136,
639
+ "step": 9000
640
+ },
641
+ {
642
+ "epoch": 16.34,
643
+ "grad_norm": 0.0012065657647326589,
644
+ "learning_rate": 3.6624775583482946e-06,
645
+ "loss": 0.0025,
646
+ "step": 9100
647
+ },
648
+ {
649
+ "epoch": 16.52,
650
+ "grad_norm": 0.0008388046990148723,
651
+ "learning_rate": 3.48294434470377e-06,
652
+ "loss": 0.0054,
653
+ "step": 9200
654
+ },
655
+ {
656
+ "epoch": 16.7,
657
+ "grad_norm": 0.0005097670364193618,
658
+ "learning_rate": 3.3034111310592464e-06,
659
+ "loss": 0.0,
660
+ "step": 9300
661
+ },
662
+ {
663
+ "epoch": 16.88,
664
+ "grad_norm": 0.00020445660629775375,
665
+ "learning_rate": 3.1238779174147223e-06,
666
+ "loss": 0.0019,
667
+ "step": 9400
668
+ },
669
+ {
670
+ "epoch": 17.06,
671
+ "grad_norm": 0.00033040347625501454,
672
+ "learning_rate": 2.9443447037701977e-06,
673
+ "loss": 0.002,
674
+ "step": 9500
675
+ },
676
+ {
677
+ "epoch": 17.24,
678
+ "grad_norm": 0.00017785438103601336,
679
+ "learning_rate": 2.7648114901256736e-06,
680
+ "loss": 0.0011,
681
+ "step": 9600
682
+ },
683
+ {
684
+ "epoch": 17.41,
685
+ "grad_norm": 0.0003500489692669362,
686
+ "learning_rate": 2.585278276481149e-06,
687
+ "loss": 0.023,
688
+ "step": 9700
689
+ },
690
+ {
691
+ "epoch": 17.59,
692
+ "grad_norm": 0.0002393827890045941,
693
+ "learning_rate": 2.405745062836625e-06,
694
+ "loss": 0.0001,
695
+ "step": 9800
696
+ },
697
+ {
698
+ "epoch": 17.77,
699
+ "grad_norm": 0.00016358286666218191,
700
+ "learning_rate": 2.2262118491921008e-06,
701
+ "loss": 0.0017,
702
+ "step": 9900
703
+ },
704
+ {
705
+ "epoch": 17.95,
706
+ "grad_norm": 0.0005156854167580605,
707
+ "learning_rate": 2.0466786355475767e-06,
708
+ "loss": 0.0022,
709
+ "step": 10000
710
+ },
711
+ {
712
+ "epoch": 18.13,
713
+ "grad_norm": 0.0001992402976611629,
714
+ "learning_rate": 1.8671454219030521e-06,
715
+ "loss": 0.006,
716
+ "step": 10100
717
+ },
718
+ {
719
+ "epoch": 18.31,
720
+ "grad_norm": 0.00023926289577502757,
721
+ "learning_rate": 1.687612208258528e-06,
722
+ "loss": 0.0026,
723
+ "step": 10200
724
+ },
725
+ {
726
+ "epoch": 18.49,
727
+ "grad_norm": 0.00018842410645447671,
728
+ "learning_rate": 1.5080789946140036e-06,
729
+ "loss": 0.0063,
730
+ "step": 10300
731
+ },
732
+ {
733
+ "epoch": 18.67,
734
+ "grad_norm": 0.00017712044063955545,
735
+ "learning_rate": 1.3285457809694793e-06,
736
+ "loss": 0.0,
737
+ "step": 10400
738
+ },
739
+ {
740
+ "epoch": 18.85,
741
+ "grad_norm": 0.00030714995227754116,
742
+ "learning_rate": 1.1490125673249552e-06,
743
+ "loss": 0.0,
744
+ "step": 10500
745
+ },
746
+ {
747
+ "epoch": 19.03,
748
+ "grad_norm": 0.0004120106459595263,
749
+ "learning_rate": 9.694793536804308e-07,
750
+ "loss": 0.0041,
751
+ "step": 10600
752
+ },
753
+ {
754
+ "epoch": 19.21,
755
+ "grad_norm": 0.00010405273496871814,
756
+ "learning_rate": 7.899461400359067e-07,
757
+ "loss": 0.0,
758
+ "step": 10700
759
+ },
760
+ {
761
+ "epoch": 19.39,
762
+ "grad_norm": 9.223635424859822e-05,
763
+ "learning_rate": 6.104129263913825e-07,
764
+ "loss": 0.0001,
765
+ "step": 10800
766
+ },
767
+ {
768
+ "epoch": 19.57,
769
+ "grad_norm": 0.00015765101124998182,
770
+ "learning_rate": 4.3087971274685824e-07,
771
+ "loss": 0.0042,
772
+ "step": 10900
773
+ },
774
+ {
775
+ "epoch": 19.75,
776
+ "grad_norm": 0.00016278728435281664,
777
+ "learning_rate": 2.5134649910233396e-07,
778
+ "loss": 0.0003,
779
+ "step": 11000
780
+ },
781
+ {
782
+ "epoch": 19.93,
783
+ "grad_norm": 0.00011305743100820109,
784
+ "learning_rate": 7.18132854578097e-08,
785
+ "loss": 0.0,
786
+ "step": 11100
787
+ }
788
+ ],
789
+ "logging_steps": 100,
790
+ "max_steps": 11140,
791
+ "num_input_tokens_seen": 0,
792
+ "num_train_epochs": 20,
793
+ "save_steps": 500,
794
+ "total_flos": 1.1371892211152928e+17,
795
+ "train_batch_size": 14,
796
+ "trial_name": null,
797
+ "trial_params": null
798
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:491d871fc503f6c09f6650ccce3a497d9ac84504786a77113305d7344d9a5d08
3
+ size 4856