Hugging Face's logo

junaid1993
/
TTRM_Pfizer_Model

Safetensors
Model card Files
xet
Community
junaid1993 commited on
Commit
24b1771
·
verified ·
1 Parent(s): db6e350

Upload 8 files

Browse files
Files changed (8) hide show
  1. output/checkpoint-60/config.json +74 -0
  2. output/checkpoint-60/generation_config.json +4 -0
  3. output/checkpoint-60/model.safetensors +3 -0
  4. output/checkpoint-60/optimizer.pt +3 -0
  5. output/checkpoint-60/rng_state.pth +3 -0
  6. output/checkpoint-60/scheduler.pt +3 -0
  7. output/checkpoint-60/trainer_state.json +492 -0
  8. output/checkpoint-60/training_args.bin +3 -0
output/checkpoint-60/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ibm-granite/granite-timeseries-ttm-r2",
3
+ "adaptive_patching_levels": 0,
4
+ "architectures": [
5
+ "TinyTimeMixerForPrediction"
6
+ ],
7
+ "categorical_vocab_size_list": [
8
+ 1
9
+ ],
10
+ "context_length": 90,
11
+ "d_model": 63,
12
+ "d_model_scale": 7,
13
+ "decoder_adaptive_patching_levels": 0,
14
+ "decoder_d_model": 18,
15
+ "decoder_d_model_scale": 2,
16
+ "decoder_mode": "mix_channel",
17
+ "decoder_num_layers": 4,
18
+ "decoder_raw_residual": false,
19
+ "distribution_output": "student_t",
20
+ "dropout": 0.4,
21
+ "enable_forecast_channel_mixing": true,
22
+ "exogenous_channel_indices": [
23
+ 1,
24
+ 2,
25
+ 3,
26
+ 4
27
+ ],
28
+ "expansion_factor": 2,
29
+ "fcm_context_length": 1,
30
+ "fcm_gated_attn": true,
31
+ "fcm_mix_layers": 2,
32
+ "fcm_prepend_past": true,
33
+ "fcm_prepend_past_offset": null,
34
+ "fcm_use_mixer": true,
35
+ "frequency_token_vocab_size": 10,
36
+ "gated_attn": true,
37
+ "head_dropout": 0.4,
38
+ "huber_delta": 1,
39
+ "init_embed": "pytorch",
40
+ "init_linear": "pytorch",
41
+ "init_processing": true,
42
+ "init_std": 0.02,
43
+ "loss": "mae",
44
+ "mask_value": 0,
45
+ "masked_context_length": null,
46
+ "mode": "common_channel",
47
+ "model_type": "tinytimemixer",
48
+ "norm_eps": 1e-05,
49
+ "norm_mlp": "LayerNorm",
50
+ "num_input_channels": 5,
51
+ "num_layers": 20,
52
+ "num_parallel_samples": 100,
53
+ "num_patches": 11,
54
+ "patch_last": true,
55
+ "patch_length": 9,
56
+ "patch_stride": 9,
57
+ "positional_encoding_type": "sincos",
58
+ "post_init": false,
59
+ "prediction_channel_indices": [
60
+ 0
61
+ ],
62
+ "prediction_filter_length": 28,
63
+ "prediction_length": 30,
64
+ "quantile": 0.5,
65
+ "resolution_prefix_tuning": true,
66
+ "scaling": "std",
67
+ "self_attn": false,
68
+ "self_attn_heads": 1,
69
+ "stride_ratio": 1,
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.48.3",
72
+ "use_decoder": true,
73
+ "use_positional_encoding": false
74
+ }
output/checkpoint-60/generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.48.3"
4
+ }
output/checkpoint-60/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33bf176962224095c765fd13e26e38f0cf91abc6b8f3d71b2930242c1d7b8efa
3
+ size 1834736
output/checkpoint-60/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa57f2fa4361efe996ef47c113ba0a9358882a0c1c7dcc49bb443c25ce6d36cf
3
+ size 3899848
output/checkpoint-60/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3d42ff983900bac2a506e5202ab138d12aed97a9837e7326d34b00890bed70d
3
+ size 14244
output/checkpoint-60/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8892b597c7855eff07dda24ae185800ac5d43dc23add3eebda60d03d4889a389
3
+ size 1320
output/checkpoint-60/trainer_state.json ADDED
@@ -0,0 +1,492 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5962514877319336,
3
+ "best_model_checkpoint": "./ttm_finetuned_models/output/checkpoint-60",
4
+ "epoch": 30.0,
5
+ "eval_steps": 500,
6
+ "global_step": 60,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 0.7443529367446899,
14
+ "learning_rate": 4.732772046676698e-05,
15
+ "loss": 0.8431,
16
+ "step": 2
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 0.6096403002738953,
21
+ "eval_runtime": 0.3627,
22
+ "eval_samples_per_second": 192.988,
23
+ "eval_steps_per_second": 2.757,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "grad_norm": 0.8946840763092041,
29
+ "learning_rate": 4.809321690693591e-05,
30
+ "loss": 0.8393,
31
+ "step": 4
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_loss": 0.60591721534729,
36
+ "eval_runtime": 0.36,
37
+ "eval_samples_per_second": 194.421,
38
+ "eval_steps_per_second": 2.777,
39
+ "step": 4
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "grad_norm": 0.7669185996055603,
44
+ "learning_rate": 4.936827562256963e-05,
45
+ "loss": 0.8184,
46
+ "step": 6
47
+ },
48
+ {
49
+ "epoch": 3.0,
50
+ "eval_loss": 0.6019852757453918,
51
+ "eval_runtime": 0.3543,
52
+ "eval_samples_per_second": 197.593,
53
+ "eval_steps_per_second": 2.823,
54
+ "step": 6
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "grad_norm": 0.7224565744400024,
59
+ "learning_rate": 5.115174431611605e-05,
60
+ "loss": 0.8012,
61
+ "step": 8
62
+ },
63
+ {
64
+ "epoch": 4.0,
65
+ "eval_loss": 0.6119012832641602,
66
+ "eval_runtime": 0.3476,
67
+ "eval_samples_per_second": 201.402,
68
+ "eval_steps_per_second": 2.877,
69
+ "step": 8
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "grad_norm": 0.5908293128013611,
74
+ "learning_rate": 5.344201122916398e-05,
75
+ "loss": 0.7874,
76
+ "step": 10
77
+ },
78
+ {
79
+ "epoch": 5.0,
80
+ "eval_loss": 0.6097100973129272,
81
+ "eval_runtime": 0.3479,
82
+ "eval_samples_per_second": 201.225,
83
+ "eval_steps_per_second": 2.875,
84
+ "step": 10
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "grad_norm": 0.6504310369491577,
89
+ "learning_rate": 5.623700659902384e-05,
90
+ "loss": 0.8027,
91
+ "step": 12
92
+ },
93
+ {
94
+ "epoch": 6.0,
95
+ "eval_loss": 0.6008864045143127,
96
+ "eval_runtime": 0.3626,
97
+ "eval_samples_per_second": 193.042,
98
+ "eval_steps_per_second": 2.758,
99
+ "step": 12
100
+ },
101
+ {
102
+ "epoch": 7.0,
103
+ "grad_norm": 0.4692302346229553,
104
+ "learning_rate": 5.9534204529214504e-05,
105
+ "loss": 0.7916,
106
+ "step": 14
107
+ },
108
+ {
109
+ "epoch": 7.0,
110
+ "eval_loss": 0.6066852807998657,
111
+ "eval_runtime": 0.3625,
112
+ "eval_samples_per_second": 193.12,
113
+ "eval_steps_per_second": 2.759,
114
+ "step": 14
115
+ },
116
+ {
117
+ "epoch": 8.0,
118
+ "grad_norm": 1.273665189743042,
119
+ "learning_rate": 6.333062527217074e-05,
120
+ "loss": 0.79,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 8.0,
125
+ "eval_loss": 0.6052869558334351,
126
+ "eval_runtime": 0.3656,
127
+ "eval_samples_per_second": 191.441,
128
+ "eval_steps_per_second": 2.735,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 9.0,
133
+ "grad_norm": 0.6313425302505493,
134
+ "learning_rate": 6.762283792210435e-05,
135
+ "loss": 0.7741,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 9.0,
140
+ "eval_loss": 0.6067262887954712,
141
+ "eval_runtime": 0.3465,
142
+ "eval_samples_per_second": 201.993,
143
+ "eval_steps_per_second": 2.886,
144
+ "step": 18
145
+ },
146
+ {
147
+ "epoch": 10.0,
148
+ "grad_norm": 1.0959845781326294,
149
+ "learning_rate": 7.240696351558515e-05,
150
+ "loss": 0.7734,
151
+ "step": 20
152
+ },
153
+ {
154
+ "epoch": 10.0,
155
+ "eval_loss": 0.6191284656524658,
156
+ "eval_runtime": 0.7504,
157
+ "eval_samples_per_second": 93.288,
158
+ "eval_steps_per_second": 1.333,
159
+ "step": 20
160
+ },
161
+ {
162
+ "epoch": 11.0,
163
+ "grad_norm": 0.440314382314682,
164
+ "learning_rate": 7.767867853704304e-05,
165
+ "loss": 0.7732,
166
+ "step": 22
167
+ },
168
+ {
169
+ "epoch": 11.0,
170
+ "eval_loss": 0.6069210171699524,
171
+ "eval_runtime": 0.3562,
172
+ "eval_samples_per_second": 196.544,
173
+ "eval_steps_per_second": 2.808,
174
+ "step": 22
175
+ },
176
+ {
177
+ "epoch": 12.0,
178
+ "grad_norm": 0.5499612092971802,
179
+ "learning_rate": 8.343321882602062e-05,
180
+ "loss": 0.7621,
181
+ "step": 24
182
+ },
183
+ {
184
+ "epoch": 12.0,
185
+ "eval_loss": 0.6009647250175476,
186
+ "eval_runtime": 0.3571,
187
+ "eval_samples_per_second": 196.025,
188
+ "eval_steps_per_second": 2.8,
189
+ "step": 24
190
+ },
191
+ {
192
+ "epoch": 13.0,
193
+ "grad_norm": 0.5899090766906738,
194
+ "learning_rate": 8.966538388264578e-05,
195
+ "loss": 0.7535,
196
+ "step": 26
197
+ },
198
+ {
199
+ "epoch": 13.0,
200
+ "eval_loss": 0.6042256355285645,
201
+ "eval_runtime": 0.3477,
202
+ "eval_samples_per_second": 201.309,
203
+ "eval_steps_per_second": 2.876,
204
+ "step": 26
205
+ },
206
+ {
207
+ "epoch": 14.0,
208
+ "grad_norm": 0.5770731568336487,
209
+ "learning_rate": 9.636954156743349e-05,
210
+ "loss": 0.7807,
211
+ "step": 28
212
+ },
213
+ {
214
+ "epoch": 14.0,
215
+ "eval_loss": 0.6018546223640442,
216
+ "eval_runtime": 0.355,
217
+ "eval_samples_per_second": 197.191,
218
+ "eval_steps_per_second": 2.817,
219
+ "step": 28
220
+ },
221
+ {
222
+ "epoch": 15.0,
223
+ "grad_norm": 0.423060804605484,
224
+ "learning_rate": 0.00010353963319116892,
225
+ "loss": 0.7376,
226
+ "step": 30
227
+ },
228
+ {
229
+ "epoch": 15.0,
230
+ "eval_loss": 0.6036869287490845,
231
+ "eval_runtime": 0.3443,
232
+ "eval_samples_per_second": 203.313,
233
+ "eval_steps_per_second": 2.904,
234
+ "step": 30
235
+ },
236
+ {
237
+ "epoch": 16.0,
238
+ "grad_norm": 0.444051593542099,
239
+ "learning_rate": 0.00011116917899027415,
240
+ "loss": 0.7431,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 16.0,
245
+ "eval_loss": 0.5995596051216125,
246
+ "eval_runtime": 0.4433,
247
+ "eval_samples_per_second": 157.902,
248
+ "eval_steps_per_second": 2.256,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 17.0,
253
+ "grad_norm": 0.7095910906791687,
254
+ "learning_rate": 0.00011925128398270726,
255
+ "loss": 0.7551,
256
+ "step": 34
257
+ },
258
+ {
259
+ "epoch": 17.0,
260
+ "eval_loss": 0.6076721549034119,
261
+ "eval_runtime": 0.3753,
262
+ "eval_samples_per_second": 186.526,
263
+ "eval_steps_per_second": 2.665,
264
+ "step": 34
265
+ },
266
+ {
267
+ "epoch": 18.0,
268
+ "grad_norm": 0.938398540019989,
269
+ "learning_rate": 0.0001277786441991034,
270
+ "loss": 0.741,
271
+ "step": 36
272
+ },
273
+ {
274
+ "epoch": 18.0,
275
+ "eval_loss": 0.6111529469490051,
276
+ "eval_runtime": 0.3616,
277
+ "eval_samples_per_second": 193.562,
278
+ "eval_steps_per_second": 2.765,
279
+ "step": 36
280
+ },
281
+ {
282
+ "epoch": 19.0,
283
+ "grad_norm": 0.45169830322265625,
284
+ "learning_rate": 0.00013674355328352613,
285
+ "loss": 0.7409,
286
+ "step": 38
287
+ },
288
+ {
289
+ "epoch": 19.0,
290
+ "eval_loss": 0.5968735814094543,
291
+ "eval_runtime": 0.3676,
292
+ "eval_samples_per_second": 190.435,
293
+ "eval_steps_per_second": 2.72,
294
+ "step": 38
295
+ },
296
+ {
297
+ "epoch": 20.0,
298
+ "grad_norm": 0.3840300440788269,
299
+ "learning_rate": 0.0001461379094578651,
300
+ "loss": 0.7308,
301
+ "step": 40
302
+ },
303
+ {
304
+ "epoch": 20.0,
305
+ "eval_loss": 0.6049572229385376,
306
+ "eval_runtime": 0.7422,
307
+ "eval_samples_per_second": 94.316,
308
+ "eval_steps_per_second": 1.347,
309
+ "step": 40
310
+ },
311
+ {
312
+ "epoch": 21.0,
313
+ "grad_norm": 1.2706289291381836,
314
+ "learning_rate": 0.00015595322284358464,
315
+ "loss": 0.7472,
316
+ "step": 42
317
+ },
318
+ {
319
+ "epoch": 21.0,
320
+ "eval_loss": 0.6062923669815063,
321
+ "eval_runtime": 0.3735,
322
+ "eval_samples_per_second": 187.409,
323
+ "eval_steps_per_second": 2.677,
324
+ "step": 42
325
+ },
326
+ {
327
+ "epoch": 22.0,
328
+ "grad_norm": 0.5400757193565369,
329
+ "learning_rate": 0.00016618062313420584,
330
+ "loss": 0.7378,
331
+ "step": 44
332
+ },
333
+ {
334
+ "epoch": 22.0,
335
+ "eval_loss": 0.5963739156723022,
336
+ "eval_runtime": 0.3635,
337
+ "eval_samples_per_second": 192.591,
338
+ "eval_steps_per_second": 2.751,
339
+ "step": 44
340
+ },
341
+ {
342
+ "epoch": 23.0,
343
+ "grad_norm": 0.42090097069740295,
344
+ "learning_rate": 0.00017681086761159098,
345
+ "loss": 0.7316,
346
+ "step": 46
347
+ },
348
+ {
349
+ "epoch": 23.0,
350
+ "eval_loss": 0.6015997529029846,
351
+ "eval_runtime": 0.3627,
352
+ "eval_samples_per_second": 192.989,
353
+ "eval_steps_per_second": 2.757,
354
+ "step": 46
355
+ },
356
+ {
357
+ "epoch": 24.0,
358
+ "grad_norm": 0.47120270133018494,
359
+ "learning_rate": 0.00018783434949878235,
360
+ "loss": 0.7405,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 24.0,
365
+ "eval_loss": 0.5992478728294373,
366
+ "eval_runtime": 0.3755,
367
+ "eval_samples_per_second": 186.405,
368
+ "eval_steps_per_second": 2.663,
369
+ "step": 48
370
+ },
371
+ {
372
+ "epoch": 25.0,
373
+ "grad_norm": 0.3660564422607422,
374
+ "learning_rate": 0.00019924110664185264,
375
+ "loss": 0.713,
376
+ "step": 50
377
+ },
378
+ {
379
+ "epoch": 25.0,
380
+ "eval_loss": 0.5973361134529114,
381
+ "eval_runtime": 0.371,
382
+ "eval_samples_per_second": 188.686,
383
+ "eval_steps_per_second": 2.696,
384
+ "step": 50
385
+ },
386
+ {
387
+ "epoch": 26.0,
388
+ "grad_norm": 0.4799431562423706,
389
+ "learning_rate": 0.00021102083051291085,
390
+ "loss": 0.7258,
391
+ "step": 52
392
+ },
393
+ {
394
+ "epoch": 26.0,
395
+ "eval_loss": 0.5997373461723328,
396
+ "eval_runtime": 0.3657,
397
+ "eval_samples_per_second": 191.402,
398
+ "eval_steps_per_second": 2.734,
399
+ "step": 52
400
+ },
401
+ {
402
+ "epoch": 27.0,
403
+ "grad_norm": 0.30694785714149475,
404
+ "learning_rate": 0.0002231628755261397,
405
+ "loss": 0.7112,
406
+ "step": 54
407
+ },
408
+ {
409
+ "epoch": 27.0,
410
+ "eval_loss": 0.5968739986419678,
411
+ "eval_runtime": 0.3648,
412
+ "eval_samples_per_second": 191.882,
413
+ "eval_steps_per_second": 2.741,
414
+ "step": 54
415
+ },
416
+ {
417
+ "epoch": 28.0,
418
+ "grad_norm": 0.22820888459682465,
419
+ "learning_rate": 0.0002356562686584362,
420
+ "loss": 0.7121,
421
+ "step": 56
422
+ },
423
+ {
424
+ "epoch": 28.0,
425
+ "eval_loss": 0.5964872241020203,
426
+ "eval_runtime": 0.3458,
427
+ "eval_samples_per_second": 202.446,
428
+ "eval_steps_per_second": 2.892,
429
+ "step": 56
430
+ },
431
+ {
432
+ "epoch": 29.0,
433
+ "grad_norm": 0.55999755859375,
434
+ "learning_rate": 0.0002484897193659642,
435
+ "loss": 0.717,
436
+ "step": 58
437
+ },
438
+ {
439
+ "epoch": 29.0,
440
+ "eval_loss": 0.597991943359375,
441
+ "eval_runtime": 0.3373,
442
+ "eval_samples_per_second": 207.519,
443
+ "eval_steps_per_second": 2.965,
444
+ "step": 58
445
+ },
446
+ {
447
+ "epoch": 30.0,
448
+ "grad_norm": 0.25612083077430725,
449
+ "learning_rate": 0.0002616516297876592,
450
+ "loss": 0.7091,
451
+ "step": 60
452
+ },
453
+ {
454
+ "epoch": 30.0,
455
+ "eval_loss": 0.5962514877319336,
456
+ "eval_runtime": 0.3376,
457
+ "eval_samples_per_second": 207.368,
458
+ "eval_steps_per_second": 2.962,
459
+ "step": 60
460
+ }
461
+ ],
462
+ "logging_steps": 500,
463
+ "max_steps": 100,
464
+ "num_input_tokens_seen": 0,
465
+ "num_train_epochs": 50,
466
+ "save_steps": 500,
467
+ "stateful_callbacks": {
468
+ "EarlyStoppingCallback": {
469
+ "args": {
470
+ "early_stopping_patience": 10,
471
+ "early_stopping_threshold": 0.0
472
+ },
473
+ "attributes": {
474
+ "early_stopping_patience_counter": 0
475
+ }
476
+ },
477
+ "TrainerControl": {
478
+ "args": {
479
+ "should_epoch_stop": false,
480
+ "should_evaluate": false,
481
+ "should_log": false,
482
+ "should_save": true,
483
+ "should_training_stop": false
484
+ },
485
+ "attributes": {}
486
+ }
487
+ },
488
+ "total_flos": 15922917144000.0,
489
+ "train_batch_size": 288,
490
+ "trial_name": null,
491
+ "trial_params": null
492
+ }
output/checkpoint-60/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ff876193e79fd922ae94a0ebcc736c35c1f4eab32be2b35b1b29354f7629a9
3
+ size 5304