mohammed525671 commited on
Commit
fa0934d
·
verified ·
1 Parent(s): 4199823

Forced push from Callback: Step 6000

Browse files
checkpoint-6000/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "dtype": "float32",
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "gradient_checkpointing": false,
16
+ "initializer_factor": 1.0,
17
+ "is_decoder": false,
18
+ "is_encoder_decoder": true,
19
+ "is_gated_act": true,
20
+ "layer_norm_epsilon": 1e-06,
21
+ "model_type": "t5",
22
+ "num_decoder_layers": 12,
23
+ "num_heads": 12,
24
+ "num_layers": 12,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "relative_attention_max_distance": 128,
28
+ "relative_attention_num_buckets": 32,
29
+ "scale_decoder_outputs": true,
30
+ "tie_word_embeddings": true,
31
+ "transformers_version": "5.10.2",
32
+ "use_cache": false,
33
+ "vocab_size": 110080
34
+ }
checkpoint-6000/generation_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": false,
3
+ "assistant_confidence_threshold": 0.4,
4
+ "assistant_lookbehind": 10,
5
+ "decoder_start_token_id": 0,
6
+ "diversity_penalty": 0.0,
7
+ "do_sample": false,
8
+ "early_stopping": false,
9
+ "encoder_no_repeat_ngram_size": 0,
10
+ "encoder_repetition_penalty": 1.0,
11
+ "eos_token_id": 1,
12
+ "epsilon_cutoff": 0.0,
13
+ "eta_cutoff": 0.0,
14
+ "length_penalty": 1.0,
15
+ "max_length": 20,
16
+ "min_length": 0,
17
+ "no_repeat_ngram_size": 0,
18
+ "num_assistant_tokens": 20,
19
+ "num_assistant_tokens_schedule": "constant",
20
+ "num_beam_groups": 1,
21
+ "num_beams": 1,
22
+ "num_return_sequences": 1,
23
+ "output_scores": false,
24
+ "pad_token_id": 0,
25
+ "remove_invalid_values": false,
26
+ "repetition_penalty": 1.0,
27
+ "return_dict_in_generate": false,
28
+ "target_lookbehind": 10,
29
+ "temperature": 1.0,
30
+ "top_k": 50,
31
+ "top_p": 1.0,
32
+ "transformers_version": "5.10.2",
33
+ "typical_p": 1.0,
34
+ "use_cache": true
35
+ }
checkpoint-6000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83dd2b6916aec972f63186ecd4647ee89544bd593b9d80988346dc549677262d
3
+ size 2145613968
checkpoint-6000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3900d5e659b4c4eb75d39b42170ceff7e42d643f1cdba48e11e26050f9dafb6
3
+ size 3615071371
checkpoint-6000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713feb76168343faf545d1a023259a5d55619138806c4627b4348a998ec03047
3
+ size 14645
checkpoint-6000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:405e393fa9d7fe824c67fb6f9547cdc469bbb451c16a4a26e59e78a2484faa56
3
+ size 1465
checkpoint-6000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-6000/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "eos_token": "</s>",
4
+ "extra_ids": 0,
5
+ "extra_special_tokens": [
6
+ "<pad>",
7
+ "</s>"
8
+ ],
9
+ "is_local": false,
10
+ "local_files_only": false,
11
+ "model_max_length": 1000000000000000019884624838656,
12
+ "pad_token": "<pad>",
13
+ "tokenizer_class": "T5Tokenizer",
14
+ "unk_id": 2,
15
+ "unk_token": "<unk>"
16
+ }
checkpoint-6000/trainer_state.json ADDED
@@ -0,0 +1,508 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 6000,
3
+ "best_metric": 0.30134562103290596,
4
+ "best_model_checkpoint": "/content/bayan_model_checkpoints/checkpoint-6000",
5
+ "epoch": 0.35096698716776953,
6
+ "eval_steps": 1000,
7
+ "global_step": 6000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.005849449786129492,
14
+ "grad_norm": 10.110084533691406,
15
+ "learning_rate": 1.9800000000000004e-05,
16
+ "loss": 7.6191259765625,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.011698899572258984,
21
+ "grad_norm": 6.276887893676758,
22
+ "learning_rate": 3.9800000000000005e-05,
23
+ "loss": 4.373985900878906,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.017548349358388476,
28
+ "grad_norm": 11.831360816955566,
29
+ "learning_rate": 5.9800000000000003e-05,
30
+ "loss": 3.0938250732421877,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.023397799144517967,
35
+ "grad_norm": 3.0765554904937744,
36
+ "learning_rate": 7.98e-05,
37
+ "loss": 2.358509521484375,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.029247248930647462,
42
+ "grad_norm": 17.59563636779785,
43
+ "learning_rate": 9.98e-05,
44
+ "loss": 2.11658935546875,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.03509669871677695,
49
+ "grad_norm": 5.027649879455566,
50
+ "learning_rate": 9.970616170010686e-05,
51
+ "loss": 1.923287353515625,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 0.04094614850290645,
56
+ "grad_norm": 10.111732482910156,
57
+ "learning_rate": 9.940935533657842e-05,
58
+ "loss": 1.963385009765625,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 0.046795598289035935,
63
+ "grad_norm": 8.854994773864746,
64
+ "learning_rate": 9.911254897304998e-05,
65
+ "loss": 2.011332550048828,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 0.05264504807516543,
70
+ "grad_norm": 11.072842597961426,
71
+ "learning_rate": 9.881574260952156e-05,
72
+ "loss": 1.9643435668945313,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 0.058494497861294924,
77
+ "grad_norm": 3.9509780406951904,
78
+ "learning_rate": 9.851893624599312e-05,
79
+ "loss": 1.9380813598632813,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 0.058494497861294924,
84
+ "eval_gleu": 0.29590605197127234,
85
+ "eval_loss": 0.13240011036396027,
86
+ "eval_runtime": 6566.4751,
87
+ "eval_samples_per_second": 8.278,
88
+ "eval_steps_per_second": 1.035,
89
+ "step": 1000
90
+ },
91
+ {
92
+ "epoch": 0.06434394764742442,
93
+ "grad_norm": 5.2291412353515625,
94
+ "learning_rate": 9.822212988246468e-05,
95
+ "loss": 1.8246798706054688,
96
+ "step": 1100
97
+ },
98
+ {
99
+ "epoch": 0.0701933974335539,
100
+ "grad_norm": 1.882444143295288,
101
+ "learning_rate": 9.792532351893626e-05,
102
+ "loss": 1.8436593627929687,
103
+ "step": 1200
104
+ },
105
+ {
106
+ "epoch": 0.0760428472196834,
107
+ "grad_norm": 7.088016986846924,
108
+ "learning_rate": 9.762851715540782e-05,
109
+ "loss": 1.9977975463867188,
110
+ "step": 1300
111
+ },
112
+ {
113
+ "epoch": 0.0818922970058129,
114
+ "grad_norm": 4.109940528869629,
115
+ "learning_rate": 9.733171079187938e-05,
116
+ "loss": 1.8611892700195312,
117
+ "step": 1400
118
+ },
119
+ {
120
+ "epoch": 0.08774174679194238,
121
+ "grad_norm": 4.196917533874512,
122
+ "learning_rate": 9.703490442835094e-05,
123
+ "loss": 1.73914794921875,
124
+ "step": 1500
125
+ },
126
+ {
127
+ "epoch": 0.09359119657807187,
128
+ "grad_norm": 3.5747194290161133,
129
+ "learning_rate": 9.673809806482252e-05,
130
+ "loss": 1.9268447875976562,
131
+ "step": 1600
132
+ },
133
+ {
134
+ "epoch": 0.09944064636420137,
135
+ "grad_norm": 8.291864395141602,
136
+ "learning_rate": 9.644129170129408e-05,
137
+ "loss": 1.9083364868164063,
138
+ "step": 1700
139
+ },
140
+ {
141
+ "epoch": 0.10529009615033086,
142
+ "grad_norm": 3.2836554050445557,
143
+ "learning_rate": 9.614448533776564e-05,
144
+ "loss": 1.8672555541992188,
145
+ "step": 1800
146
+ },
147
+ {
148
+ "epoch": 0.11113954593646035,
149
+ "grad_norm": 35.179290771484375,
150
+ "learning_rate": 9.58476789742372e-05,
151
+ "loss": 1.7734385681152345,
152
+ "step": 1900
153
+ },
154
+ {
155
+ "epoch": 0.11698899572258985,
156
+ "grad_norm": 7.675907135009766,
157
+ "learning_rate": 9.555087261070878e-05,
158
+ "loss": 1.6878056335449219,
159
+ "step": 2000
160
+ },
161
+ {
162
+ "epoch": 0.11698899572258985,
163
+ "eval_gleu": 0.29703227235730695,
164
+ "eval_loss": 0.12831313908100128,
165
+ "eval_runtime": 3091.0081,
166
+ "eval_samples_per_second": 8.088,
167
+ "eval_steps_per_second": 1.011,
168
+ "step": 2000
169
+ },
170
+ {
171
+ "epoch": 0.12283844550871933,
172
+ "grad_norm": 4.367784023284912,
173
+ "learning_rate": 9.525406624718034e-05,
174
+ "loss": 1.6758128356933595,
175
+ "step": 2100
176
+ },
177
+ {
178
+ "epoch": 0.12868789529484884,
179
+ "grad_norm": 5.412193298339844,
180
+ "learning_rate": 9.49572598836519e-05,
181
+ "loss": 1.680198211669922,
182
+ "step": 2200
183
+ },
184
+ {
185
+ "epoch": 0.1345373450809783,
186
+ "grad_norm": 5.694601058959961,
187
+ "learning_rate": 9.466045352012347e-05,
188
+ "loss": 1.9373101806640625,
189
+ "step": 2300
190
+ },
191
+ {
192
+ "epoch": 0.1403867948671078,
193
+ "grad_norm": 11.523478507995605,
194
+ "learning_rate": 9.436364715659504e-05,
195
+ "loss": 1.483900909423828,
196
+ "step": 2400
197
+ },
198
+ {
199
+ "epoch": 0.1462362446532373,
200
+ "grad_norm": 4.712738037109375,
201
+ "learning_rate": 9.406684079306662e-05,
202
+ "loss": 1.544265594482422,
203
+ "step": 2500
204
+ },
205
+ {
206
+ "epoch": 0.1520856944393668,
207
+ "grad_norm": 17.196199417114258,
208
+ "learning_rate": 9.377003442953818e-05,
209
+ "loss": 1.7755703735351562,
210
+ "step": 2600
211
+ },
212
+ {
213
+ "epoch": 0.1579351442254963,
214
+ "grad_norm": 4.247788429260254,
215
+ "learning_rate": 9.347322806600974e-05,
216
+ "loss": 1.5530931091308593,
217
+ "step": 2700
218
+ },
219
+ {
220
+ "epoch": 0.1637845940116258,
221
+ "grad_norm": 4.579327583312988,
222
+ "learning_rate": 9.317642170248132e-05,
223
+ "loss": 1.5068099975585938,
224
+ "step": 2800
225
+ },
226
+ {
227
+ "epoch": 0.16963404379775526,
228
+ "grad_norm": 10.168505668640137,
229
+ "learning_rate": 9.287961533895288e-05,
230
+ "loss": 1.5404017639160157,
231
+ "step": 2900
232
+ },
233
+ {
234
+ "epoch": 0.17548349358388476,
235
+ "grad_norm": 4.069611072540283,
236
+ "learning_rate": 9.258280897542444e-05,
237
+ "loss": 1.811837158203125,
238
+ "step": 3000
239
+ },
240
+ {
241
+ "epoch": 0.17548349358388476,
242
+ "eval_gleu": 0.2988064209295175,
243
+ "eval_loss": 0.12521681189537048,
244
+ "eval_runtime": 1251.886,
245
+ "eval_samples_per_second": 7.988,
246
+ "eval_steps_per_second": 0.998,
247
+ "step": 3000
248
+ },
249
+ {
250
+ "epoch": 0.18133294337001427,
251
+ "grad_norm": 14.57172966003418,
252
+ "learning_rate": 9.2286002611896e-05,
253
+ "loss": 1.78211181640625,
254
+ "step": 3100
255
+ },
256
+ {
257
+ "epoch": 0.18718239315614374,
258
+ "grad_norm": 10.13582992553711,
259
+ "learning_rate": 9.198919624836758e-05,
260
+ "loss": 1.486624755859375,
261
+ "step": 3200
262
+ },
263
+ {
264
+ "epoch": 0.19303184294227324,
265
+ "grad_norm": 1.948803424835205,
266
+ "learning_rate": 9.169238988483914e-05,
267
+ "loss": 1.6851492309570313,
268
+ "step": 3300
269
+ },
270
+ {
271
+ "epoch": 0.19888129272840274,
272
+ "grad_norm": 14.260212898254395,
273
+ "learning_rate": 9.13955835213107e-05,
274
+ "loss": 1.515905303955078,
275
+ "step": 3400
276
+ },
277
+ {
278
+ "epoch": 0.20473074251453222,
279
+ "grad_norm": 1.767106533050537,
280
+ "learning_rate": 9.109877715778226e-05,
281
+ "loss": 2.028106994628906,
282
+ "step": 3500
283
+ },
284
+ {
285
+ "epoch": 0.21058019230066172,
286
+ "grad_norm": 15.894665718078613,
287
+ "learning_rate": 9.080197079425384e-05,
288
+ "loss": 1.8486167907714843,
289
+ "step": 3600
290
+ },
291
+ {
292
+ "epoch": 0.21642964208679122,
293
+ "grad_norm": 5.241128444671631,
294
+ "learning_rate": 9.05051644307254e-05,
295
+ "loss": 1.4896153259277343,
296
+ "step": 3700
297
+ },
298
+ {
299
+ "epoch": 0.2222790918729207,
300
+ "grad_norm": 6.262875080108643,
301
+ "learning_rate": 9.020835806719696e-05,
302
+ "loss": 1.94941162109375,
303
+ "step": 3800
304
+ },
305
+ {
306
+ "epoch": 0.2281285416590502,
307
+ "grad_norm": 4.245912075042725,
308
+ "learning_rate": 8.991155170366852e-05,
309
+ "loss": 1.536641845703125,
310
+ "step": 3900
311
+ },
312
+ {
313
+ "epoch": 0.2339779914451797,
314
+ "grad_norm": 3.9779605865478516,
315
+ "learning_rate": 8.96147453401401e-05,
316
+ "loss": 1.5541285705566406,
317
+ "step": 4000
318
+ },
319
+ {
320
+ "epoch": 0.2339779914451797,
321
+ "eval_gleu": 0.2998548076902353,
322
+ "eval_loss": 0.11920083314180374,
323
+ "eval_runtime": 1261.8525,
324
+ "eval_samples_per_second": 7.925,
325
+ "eval_steps_per_second": 0.991,
326
+ "step": 4000
327
+ },
328
+ {
329
+ "epoch": 0.23982744123130917,
330
+ "grad_norm": 3.7144033908843994,
331
+ "learning_rate": 8.931793897661166e-05,
332
+ "loss": 1.571682891845703,
333
+ "step": 4100
334
+ },
335
+ {
336
+ "epoch": 0.24567689101743867,
337
+ "grad_norm": 4.4423747062683105,
338
+ "learning_rate": 8.902113261308322e-05,
339
+ "loss": 1.5855111694335937,
340
+ "step": 4200
341
+ },
342
+ {
343
+ "epoch": 0.25152634080356817,
344
+ "grad_norm": 6.085261821746826,
345
+ "learning_rate": 8.87243262495548e-05,
346
+ "loss": 1.4676052856445312,
347
+ "step": 4300
348
+ },
349
+ {
350
+ "epoch": 0.2573757905896977,
351
+ "grad_norm": 4.310057163238525,
352
+ "learning_rate": 8.842751988602636e-05,
353
+ "loss": 1.8670347595214845,
354
+ "step": 4400
355
+ },
356
+ {
357
+ "epoch": 0.2632252403758272,
358
+ "grad_norm": 25.03422737121582,
359
+ "learning_rate": 8.813071352249793e-05,
360
+ "loss": 1.6823545837402343,
361
+ "step": 4500
362
+ },
363
+ {
364
+ "epoch": 0.2690746901619566,
365
+ "grad_norm": 6.155806541442871,
366
+ "learning_rate": 8.78339071589695e-05,
367
+ "loss": 1.557360382080078,
368
+ "step": 4600
369
+ },
370
+ {
371
+ "epoch": 0.2749241399480861,
372
+ "grad_norm": 4.709263801574707,
373
+ "learning_rate": 8.753710079544106e-05,
374
+ "loss": 1.5122216796875,
375
+ "step": 4700
376
+ },
377
+ {
378
+ "epoch": 0.2807735897342156,
379
+ "grad_norm": 8.784110069274902,
380
+ "learning_rate": 8.724029443191263e-05,
381
+ "loss": 1.6326239013671875,
382
+ "step": 4800
383
+ },
384
+ {
385
+ "epoch": 0.2866230395203451,
386
+ "grad_norm": 2.2983076572418213,
387
+ "learning_rate": 8.69434880683842e-05,
388
+ "loss": 1.7817961120605468,
389
+ "step": 4900
390
+ },
391
+ {
392
+ "epoch": 0.2924724893064746,
393
+ "grad_norm": 15.305951118469238,
394
+ "learning_rate": 8.664668170485576e-05,
395
+ "loss": 1.5228102111816406,
396
+ "step": 5000
397
+ },
398
+ {
399
+ "epoch": 0.2924724893064746,
400
+ "eval_gleu": 0.29968993183673,
401
+ "eval_loss": 0.11874332278966904,
402
+ "eval_runtime": 1253.6633,
403
+ "eval_samples_per_second": 7.977,
404
+ "eval_steps_per_second": 0.997,
405
+ "step": 5000
406
+ },
407
+ {
408
+ "epoch": 0.2983219390926041,
409
+ "grad_norm": 2.8204448223114014,
410
+ "learning_rate": 8.634987534132732e-05,
411
+ "loss": 1.6674491882324218,
412
+ "step": 5100
413
+ },
414
+ {
415
+ "epoch": 0.3041713888787336,
416
+ "grad_norm": 4.837568759918213,
417
+ "learning_rate": 8.60530689777989e-05,
418
+ "loss": 1.5322183227539063,
419
+ "step": 5200
420
+ },
421
+ {
422
+ "epoch": 0.3100208386648631,
423
+ "grad_norm": 2.0740928649902344,
424
+ "learning_rate": 8.575626261427046e-05,
425
+ "loss": 1.5107717895507813,
426
+ "step": 5300
427
+ },
428
+ {
429
+ "epoch": 0.3158702884509926,
430
+ "grad_norm": 2.943633556365967,
431
+ "learning_rate": 8.545945625074202e-05,
432
+ "loss": 1.5849418640136719,
433
+ "step": 5400
434
+ },
435
+ {
436
+ "epoch": 0.3217197382371221,
437
+ "grad_norm": 4.8902587890625,
438
+ "learning_rate": 8.516264988721359e-05,
439
+ "loss": 1.397242431640625,
440
+ "step": 5500
441
+ },
442
+ {
443
+ "epoch": 0.3275691880232516,
444
+ "grad_norm": 3.4511029720306396,
445
+ "learning_rate": 8.486584352368515e-05,
446
+ "loss": 1.2294054412841797,
447
+ "step": 5600
448
+ },
449
+ {
450
+ "epoch": 0.3334186378093811,
451
+ "grad_norm": 6.207216739654541,
452
+ "learning_rate": 8.456903716015672e-05,
453
+ "loss": 1.462149658203125,
454
+ "step": 5700
455
+ },
456
+ {
457
+ "epoch": 0.3392680875955105,
458
+ "grad_norm": 6.275397777557373,
459
+ "learning_rate": 8.427223079662828e-05,
460
+ "loss": 1.5469534301757812,
461
+ "step": 5800
462
+ },
463
+ {
464
+ "epoch": 0.34511753738164,
465
+ "grad_norm": 2.633629560470581,
466
+ "learning_rate": 8.397542443309985e-05,
467
+ "loss": 1.5224714660644532,
468
+ "step": 5900
469
+ },
470
+ {
471
+ "epoch": 0.35096698716776953,
472
+ "grad_norm": 21.59209442138672,
473
+ "learning_rate": 8.367861806957142e-05,
474
+ "loss": 1.5296339416503906,
475
+ "step": 6000
476
+ },
477
+ {
478
+ "epoch": 0.35096698716776953,
479
+ "eval_gleu": 0.30134562103290596,
480
+ "eval_loss": 0.11013147979974747,
481
+ "eval_runtime": 1207.8213,
482
+ "eval_samples_per_second": 8.279,
483
+ "eval_steps_per_second": 1.035,
484
+ "step": 6000
485
+ }
486
+ ],
487
+ "logging_steps": 100,
488
+ "max_steps": 34192,
489
+ "num_input_tokens_seen": 0,
490
+ "num_train_epochs": 2,
491
+ "save_steps": 1000,
492
+ "stateful_callbacks": {
493
+ "TrainerControl": {
494
+ "args": {
495
+ "should_epoch_stop": false,
496
+ "should_evaluate": false,
497
+ "should_log": false,
498
+ "should_save": true,
499
+ "should_training_stop": false
500
+ },
501
+ "attributes": {}
502
+ }
503
+ },
504
+ "total_flos": 4794992873902080.0,
505
+ "train_batch_size": 1,
506
+ "trial_name": null,
507
+ "trial_params": null
508
+ }
checkpoint-6000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:254c57b16262b963291c6e02a1d8875dd710f67730f011dcc3c497ad4ec9b379
3
+ size 5393