terry69 commited on
Commit
449b1e1
·
verified ·
1 Parent(s): c27ea60

Model save

Browse files
Files changed (4) hide show
  1. README.md +62 -0
  2. all_results.json +9 -0
  3. train_results.json +9 -0
  4. trainer_state.json +714 -0
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama3
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: meta-llama/Meta-Llama-3-8B
9
+ model-index:
10
+ - name: downstream_0.1p_seed42_level2_syntaxnospace
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # downstream_0.1p_seed42_level2_syntaxnospace
18
+
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0002
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 1
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 4
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 128
46
+ - total_eval_batch_size: 4
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 1
51
+
52
+ ### Training results
53
+
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - PEFT 0.11.1
59
+ - Transformers 4.44.2
60
+ - Pytorch 2.3.1+cu121
61
+ - Datasets 2.19.1
62
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9994683678894205,
3
+ "total_flos": 3.0618166709610086e+17,
4
+ "train_loss": 1.1288761854171754,
5
+ "train_runtime": 18761.7867,
6
+ "train_samples": 103532,
7
+ "train_samples_per_second": 3.207,
8
+ "train_steps_per_second": 0.025
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9994683678894205,
3
+ "total_flos": 3.0618166709610086e+17,
4
+ "train_loss": 1.1288761854171754,
5
+ "train_runtime": 18761.7867,
6
+ "train_samples": 103532,
7
+ "train_samples_per_second": 3.207,
8
+ "train_steps_per_second": 0.025
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,714 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9994683678894205,
5
+ "eval_steps": 500,
6
+ "global_step": 470,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.002126528442317916,
13
+ "grad_norm": 1.1132217598089287,
14
+ "learning_rate": 4.255319148936171e-06,
15
+ "loss": 1.475,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01063264221158958,
20
+ "grad_norm": 1.0674803445954786,
21
+ "learning_rate": 2.1276595744680852e-05,
22
+ "loss": 1.3986,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.02126528442317916,
27
+ "grad_norm": 0.27714288812132803,
28
+ "learning_rate": 4.2553191489361704e-05,
29
+ "loss": 1.3198,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.03189792663476874,
34
+ "grad_norm": 0.24323884897635753,
35
+ "learning_rate": 6.382978723404256e-05,
36
+ "loss": 1.3201,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.04253056884635832,
41
+ "grad_norm": 0.17616144014740132,
42
+ "learning_rate": 8.510638297872341e-05,
43
+ "loss": 1.2681,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.0531632110579479,
48
+ "grad_norm": 0.14425961839274853,
49
+ "learning_rate": 0.00010638297872340425,
50
+ "loss": 1.2294,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.06379585326953748,
55
+ "grad_norm": 0.09993563340523522,
56
+ "learning_rate": 0.00012765957446808513,
57
+ "loss": 1.2203,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.07442849548112707,
62
+ "grad_norm": 0.09436627728374515,
63
+ "learning_rate": 0.00014893617021276596,
64
+ "loss": 1.1787,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.08506113769271664,
69
+ "grad_norm": 0.08152779581665957,
70
+ "learning_rate": 0.00017021276595744682,
71
+ "loss": 1.213,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.09569377990430622,
76
+ "grad_norm": 0.08994938392428893,
77
+ "learning_rate": 0.00019148936170212768,
78
+ "loss": 1.1771,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.1063264221158958,
83
+ "grad_norm": 0.08889534543964475,
84
+ "learning_rate": 0.0001999751793267259,
85
+ "loss": 1.1937,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.11695906432748537,
90
+ "grad_norm": 0.0818192481558469,
91
+ "learning_rate": 0.00019982354205260347,
92
+ "loss": 1.1549,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.12759170653907495,
97
+ "grad_norm": 0.08592131915598437,
98
+ "learning_rate": 0.0001995342655949951,
99
+ "loss": 1.1452,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.13822434875066453,
104
+ "grad_norm": 0.08847958460762677,
105
+ "learning_rate": 0.000199107748815478,
106
+ "loss": 1.1381,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.14885699096225413,
111
+ "grad_norm": 0.09175483942286262,
112
+ "learning_rate": 0.000198544579806,
113
+ "loss": 1.1512,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.1594896331738437,
118
+ "grad_norm": 0.07308896698803534,
119
+ "learning_rate": 0.00019784553507800349,
120
+ "loss": 1.1245,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.17012227538543329,
125
+ "grad_norm": 0.07352573225963126,
126
+ "learning_rate": 0.00019701157849175228,
127
+ "loss": 1.1456,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.18075491759702286,
132
+ "grad_norm": 0.08124735026425489,
133
+ "learning_rate": 0.00019604385992733715,
134
+ "loss": 1.138,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.19138755980861244,
139
+ "grad_norm": 0.07150321514192684,
140
+ "learning_rate": 0.0001949437136991925,
141
+ "loss": 1.1375,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.20202020202020202,
146
+ "grad_norm": 0.07663110018396366,
147
+ "learning_rate": 0.00019371265671631037,
148
+ "loss": 1.123,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.2126528442317916,
153
+ "grad_norm": 0.08486863588170293,
154
+ "learning_rate": 0.00019235238639068856,
155
+ "loss": 1.1357,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.22328548644338117,
160
+ "grad_norm": 0.0762558400001174,
161
+ "learning_rate": 0.00019086477829689685,
162
+ "loss": 1.131,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.23391812865497075,
167
+ "grad_norm": 0.07452030437492205,
168
+ "learning_rate": 0.00018925188358598813,
169
+ "loss": 1.1442,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.24455077086656035,
174
+ "grad_norm": 0.07570723134200702,
175
+ "learning_rate": 0.00018751592615732005,
176
+ "loss": 1.1342,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.2551834130781499,
181
+ "grad_norm": 0.15468624584475818,
182
+ "learning_rate": 0.00018565929959218758,
183
+ "loss": 1.1158,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.2658160552897395,
188
+ "grad_norm": 0.08459758525414239,
189
+ "learning_rate": 0.00018368456385349334,
190
+ "loss": 1.1103,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.27644869750132905,
195
+ "grad_norm": 0.0699573756198723,
196
+ "learning_rate": 0.00018159444175600703,
197
+ "loss": 1.1375,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.28708133971291866,
202
+ "grad_norm": 0.09015868621107682,
203
+ "learning_rate": 0.000179391815212081,
204
+ "loss": 1.1351,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.29771398192450826,
209
+ "grad_norm": 0.07786434215665021,
210
+ "learning_rate": 0.00017707972125799735,
211
+ "loss": 1.1094,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.3083466241360978,
216
+ "grad_norm": 0.0722359719751335,
217
+ "learning_rate": 0.0001746613478664271,
218
+ "loss": 1.109,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.3189792663476874,
223
+ "grad_norm": 0.07007415812680974,
224
+ "learning_rate": 0.00017214002955077393,
225
+ "loss": 1.118,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.32961190855927697,
230
+ "grad_norm": 0.07271324414680513,
231
+ "learning_rate": 0.00016951924276746425,
232
+ "loss": 1.1093,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.34024455077086657,
237
+ "grad_norm": 0.07579503380547685,
238
+ "learning_rate": 0.0001668026011225225,
239
+ "loss": 1.132,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.3508771929824561,
244
+ "grad_norm": 0.0755893077221133,
245
+ "learning_rate": 0.00016399385038904138,
246
+ "loss": 1.1041,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.3615098351940457,
251
+ "grad_norm": 0.07521138011494473,
252
+ "learning_rate": 0.00016109686334241655,
253
+ "loss": 1.1106,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.3721424774056353,
258
+ "grad_norm": 0.07475367435754098,
259
+ "learning_rate": 0.00015811563442046767,
260
+ "loss": 1.0981,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.3827751196172249,
265
+ "grad_norm": 0.07569742075334658,
266
+ "learning_rate": 0.00015505427421580808,
267
+ "loss": 1.1027,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.3934077618288145,
272
+ "grad_norm": 0.06970712543989657,
273
+ "learning_rate": 0.00015191700380805752,
274
+ "loss": 1.1148,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.40404040404040403,
279
+ "grad_norm": 0.07988874051314146,
280
+ "learning_rate": 0.00014870814894371245,
281
+ "loss": 1.1113,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.41467304625199364,
286
+ "grad_norm": 0.07160684049436854,
287
+ "learning_rate": 0.0001454321340716992,
288
+ "loss": 1.0861,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.4253056884635832,
293
+ "grad_norm": 0.07005079598481417,
294
+ "learning_rate": 0.0001420934762428335,
295
+ "loss": 1.0971,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.4359383306751728,
300
+ "grad_norm": 0.07394470646142667,
301
+ "learning_rate": 0.00013869677888159887,
302
+ "loss": 1.1136,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.44657097288676234,
307
+ "grad_norm": 0.07523040228715787,
308
+ "learning_rate": 0.00013524672543882996,
309
+ "loss": 1.1196,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.45720361509835195,
314
+ "grad_norm": 0.0740459816152623,
315
+ "learning_rate": 0.00013174807293405428,
316
+ "loss": 1.122,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.4678362573099415,
321
+ "grad_norm": 0.07407785053371259,
322
+ "learning_rate": 0.00012820564539639512,
323
+ "loss": 1.1101,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.4784688995215311,
328
+ "grad_norm": 0.07407385022434756,
329
+ "learning_rate": 0.0001246243272130804,
330
+ "loss": 1.1093,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.4891015417331207,
335
+ "grad_norm": 0.0691999860793088,
336
+ "learning_rate": 0.00012100905639472779,
337
+ "loss": 1.0947,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.49973418394471025,
342
+ "grad_norm": 0.07023344891744904,
343
+ "learning_rate": 0.00011736481776669306,
344
+ "loss": 1.1322,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.5103668261562998,
349
+ "grad_norm": 0.07064724436775818,
350
+ "learning_rate": 0.00011369663609586854,
351
+ "loss": 1.1188,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.5209994683678895,
356
+ "grad_norm": 0.07583291773979836,
357
+ "learning_rate": 0.00011000956916240985,
358
+ "loss": 1.0995,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.531632110579479,
363
+ "grad_norm": 0.07152892272662684,
364
+ "learning_rate": 0.00010630870078594249,
365
+ "loss": 1.1236,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.5422647527910686,
370
+ "grad_norm": 0.07101072737185006,
371
+ "learning_rate": 0.0001025991338158651,
372
+ "loss": 1.1311,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.5528973950026581,
377
+ "grad_norm": 0.0702113295280909,
378
+ "learning_rate": 9.888598309541347e-05,
379
+ "loss": 1.1021,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.5635300372142478,
384
+ "grad_norm": 0.07560382456183587,
385
+ "learning_rate": 9.517436840918766e-05,
386
+ "loss": 1.1193,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.5741626794258373,
391
+ "grad_norm": 0.07181091122638743,
392
+ "learning_rate": 9.146940742386553e-05,
393
+ "loss": 1.1171,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.5847953216374269,
398
+ "grad_norm": 0.0719306314196102,
399
+ "learning_rate": 8.777620863183657e-05,
400
+ "loss": 1.0973,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.5954279638490165,
405
+ "grad_norm": 0.06768671936995115,
406
+ "learning_rate": 8.409986430748545e-05,
407
+ "loss": 1.0993,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.6060606060606061,
412
+ "grad_norm": 0.07166544718736949,
413
+ "learning_rate": 8.044544348583755e-05,
414
+ "loss": 1.1116,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.6166932482721956,
419
+ "grad_norm": 0.07026460560964139,
420
+ "learning_rate": 7.681798497324716e-05,
421
+ "loss": 1.1215,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.6273258904837852,
426
+ "grad_norm": 0.07493637213313761,
427
+ "learning_rate": 7.322249039976608e-05,
428
+ "loss": 1.0951,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.6379585326953748,
433
+ "grad_norm": 0.0735588585321075,
434
+ "learning_rate": 6.966391732277143e-05,
435
+ "loss": 1.1051,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.6485911749069644,
440
+ "grad_norm": 0.07103076233316474,
441
+ "learning_rate": 6.614717239136246e-05,
442
+ "loss": 1.1099,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.6592238171185539,
447
+ "grad_norm": 0.06929087442452384,
448
+ "learning_rate": 6.267710458095053e-05,
449
+ "loss": 1.0891,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.6698564593301436,
454
+ "grad_norm": 0.07048509973214657,
455
+ "learning_rate": 5.9258498507371194e-05,
456
+ "loss": 1.1308,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.6804891015417331,
461
+ "grad_norm": 0.06987687341789249,
462
+ "learning_rate": 5.589606782973683e-05,
463
+ "loss": 1.1288,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.6911217437533227,
468
+ "grad_norm": 0.0726818503990417,
469
+ "learning_rate": 5.259444875112624e-05,
470
+ "loss": 1.1166,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.7017543859649122,
475
+ "grad_norm": 0.07076508826669288,
476
+ "learning_rate": 4.93581936260724e-05,
477
+ "loss": 1.1094,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.7123870281765019,
482
+ "grad_norm": 0.06894707145543243,
483
+ "learning_rate": 4.6191764683662744e-05,
484
+ "loss": 1.097,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.7230196703880915,
489
+ "grad_norm": 0.07530097462452943,
490
+ "learning_rate": 4.309952787490689e-05,
491
+ "loss": 1.1017,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.733652312599681,
496
+ "grad_norm": 0.06877541461151461,
497
+ "learning_rate": 4.008574685285442e-05,
498
+ "loss": 1.1034,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.7442849548112705,
503
+ "grad_norm": 0.07024805662579879,
504
+ "learning_rate": 3.7154577093764334e-05,
505
+ "loss": 1.0996,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.7549175970228602,
510
+ "grad_norm": 0.06979054766691796,
511
+ "learning_rate": 3.4310060167430725e-05,
512
+ "loss": 1.0993,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.7655502392344498,
517
+ "grad_norm": 0.07127452889238414,
518
+ "learning_rate": 3.155611816456586e-05,
519
+ "loss": 1.1108,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.7761828814460393,
524
+ "grad_norm": 0.06929411714148895,
525
+ "learning_rate": 2.889654828892393e-05,
526
+ "loss": 1.1014,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.786815523657629,
531
+ "grad_norm": 0.06986765320557396,
532
+ "learning_rate": 2.6335017621622116e-05,
533
+ "loss": 1.1178,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.7974481658692185,
538
+ "grad_norm": 0.14171152314730037,
539
+ "learning_rate": 2.3875058064877807e-05,
540
+ "loss": 1.1056,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.8080808080808081,
545
+ "grad_norm": 0.07523630706911914,
546
+ "learning_rate": 2.1520061472133902e-05,
547
+ "loss": 1.1196,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.8187134502923976,
552
+ "grad_norm": 0.06927631258661882,
553
+ "learning_rate": 1.927327497128706e-05,
554
+ "loss": 1.1165,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.8293460925039873,
559
+ "grad_norm": 0.07022924736143368,
560
+ "learning_rate": 1.7137796487466797e-05,
561
+ "loss": 1.102,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.8399787347155768,
566
+ "grad_norm": 0.06841887685146186,
567
+ "learning_rate": 1.5116570471539293e-05,
568
+ "loss": 1.1,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.8506113769271664,
573
+ "grad_norm": 0.0680433251960951,
574
+ "learning_rate": 1.3212383840225329e-05,
575
+ "loss": 1.1007,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.861244019138756,
580
+ "grad_norm": 0.06849436910046028,
581
+ "learning_rate": 1.1427862133430156e-05,
582
+ "loss": 1.0919,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.8718766613503456,
587
+ "grad_norm": 0.06705533678821948,
588
+ "learning_rate": 9.765465894083636e-06,
589
+ "loss": 1.1018,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.8825093035619351,
594
+ "grad_norm": 0.06997290719332996,
595
+ "learning_rate": 8.227487275482592e-06,
596
+ "loss": 1.1141,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.8931419457735247,
601
+ "grad_norm": 0.06955661856691482,
602
+ "learning_rate": 6.81604688081271e-06,
603
+ "loss": 1.1179,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.9037745879851143,
608
+ "grad_norm": 0.06939654515531442,
609
+ "learning_rate": 5.533090839208133e-06,
610
+ "loss": 1.0859,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.9144072301967039,
615
+ "grad_norm": 0.06890766733706018,
616
+ "learning_rate": 4.380388122380141e-06,
617
+ "loss": 1.1041,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.9250398724082934,
622
+ "grad_norm": 0.06774543961855677,
623
+ "learning_rate": 3.359528105515064e-06,
624
+ "loss": 1.1054,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.935672514619883,
629
+ "grad_norm": 0.06656651460274651,
630
+ "learning_rate": 2.471918375804105e-06,
631
+ "loss": 1.1018,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.9463051568314726,
636
+ "grad_norm": 0.06852233232210171,
637
+ "learning_rate": 1.7187827916271382e-06,
638
+ "loss": 1.1129,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.9569377990430622,
643
+ "grad_norm": 0.06708991081678066,
644
+ "learning_rate": 1.1011597950663865e-06,
645
+ "loss": 1.1046,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.9675704412546517,
650
+ "grad_norm": 0.06813589171568658,
651
+ "learning_rate": 6.199009800765265e-07,
652
+ "loss": 1.0986,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.9782030834662414,
657
+ "grad_norm": 0.0700679858970667,
658
+ "learning_rate": 2.756699182858369e-07,
659
+ "loss": 1.111,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.988835725677831,
664
+ "grad_norm": 0.07404495795184537,
665
+ "learning_rate": 6.894124404711599e-08,
666
+ "loss": 1.1039,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.9994683678894205,
671
+ "grad_norm": 0.07042216599583477,
672
+ "learning_rate": 0.0,
673
+ "loss": 1.1192,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.9994683678894205,
678
+ "eval_runtime": 5.9798,
679
+ "eval_samples_per_second": 1.672,
680
+ "eval_steps_per_second": 0.502,
681
+ "step": 470
682
+ },
683
+ {
684
+ "epoch": 0.9994683678894205,
685
+ "step": 470,
686
+ "total_flos": 3.0618166709610086e+17,
687
+ "train_loss": 1.1288761854171754,
688
+ "train_runtime": 18761.7867,
689
+ "train_samples_per_second": 3.207,
690
+ "train_steps_per_second": 0.025
691
+ }
692
+ ],
693
+ "logging_steps": 5,
694
+ "max_steps": 470,
695
+ "num_input_tokens_seen": 0,
696
+ "num_train_epochs": 1,
697
+ "save_steps": 100,
698
+ "stateful_callbacks": {
699
+ "TrainerControl": {
700
+ "args": {
701
+ "should_epoch_stop": false,
702
+ "should_evaluate": false,
703
+ "should_log": false,
704
+ "should_save": true,
705
+ "should_training_stop": true
706
+ },
707
+ "attributes": {}
708
+ }
709
+ },
710
+ "total_flos": 3.0618166709610086e+17,
711
+ "train_batch_size": 8,
712
+ "trial_name": null,
713
+ "trial_params": null
714
+ }