terry69 commited on
Commit
b49207e
·
verified ·
1 Parent(s): 3b63c15

Model save

Browse files
Files changed (4) hide show
  1. README.md +69 -0
  2. all_results.json +9 -0
  3. train_results.json +9 -0
  4. trainer_state.json +624 -0
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ datasets:
10
+ - generator
11
+ model-index:
12
+ - name: downstream_0.1p_seed42_level2_syntax
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # downstream_0.1p_seed42_level2_syntax
20
+
21
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 1.0375
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 0.0002
43
+ - train_batch_size: 8
44
+ - eval_batch_size: 1
45
+ - seed: 42
46
+ - distributed_type: multi-GPU
47
+ - num_devices: 4
48
+ - gradient_accumulation_steps: 4
49
+ - total_train_batch_size: 128
50
+ - total_eval_batch_size: 4
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: cosine
53
+ - lr_scheduler_warmup_ratio: 0.1
54
+ - num_epochs: 1
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss |
59
+ |:-------------:|:------:|:----:|:---------------:|
60
+ | 1.1119 | 0.9994 | 408 | 1.0375 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - PEFT 0.11.1
66
+ - Transformers 4.43.4
67
+ - Pytorch 2.3.1+cu121
68
+ - Datasets 2.19.1
69
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9993876301285977,
3
+ "total_flos": 1.2948113606049792e+16,
4
+ "train_loss": 1.1371603935372596,
5
+ "train_runtime": 15464.5644,
6
+ "train_samples": 90000,
7
+ "train_samples_per_second": 3.378,
8
+ "train_steps_per_second": 0.026
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9993876301285977,
3
+ "total_flos": 1.2948113606049792e+16,
4
+ "train_loss": 1.1371603935372596,
5
+ "train_runtime": 15464.5644,
6
+ "train_samples": 90000,
7
+ "train_samples_per_second": 3.378,
8
+ "train_steps_per_second": 0.026
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,624 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9993876301285977,
5
+ "eval_steps": 500,
6
+ "global_step": 408,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.002449479485609308,
13
+ "grad_norm": 1.0681437691408622,
14
+ "learning_rate": 4.8780487804878055e-06,
15
+ "loss": 1.4232,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01224739742804654,
20
+ "grad_norm": 1.136306986221139,
21
+ "learning_rate": 2.4390243902439026e-05,
22
+ "loss": 1.3933,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.02449479485609308,
27
+ "grad_norm": 0.245338434807422,
28
+ "learning_rate": 4.878048780487805e-05,
29
+ "loss": 1.3421,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.03674219228413962,
34
+ "grad_norm": 0.2375193035213865,
35
+ "learning_rate": 7.317073170731707e-05,
36
+ "loss": 1.3138,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.04898958971218616,
41
+ "grad_norm": 0.18791567927506073,
42
+ "learning_rate": 9.75609756097561e-05,
43
+ "loss": 1.2873,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.0612369871402327,
48
+ "grad_norm": 0.12816603940375418,
49
+ "learning_rate": 0.00012195121951219512,
50
+ "loss": 1.2549,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.07348438456827924,
55
+ "grad_norm": 0.11662240238108945,
56
+ "learning_rate": 0.00014634146341463414,
57
+ "loss": 1.2099,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.08573178199632578,
62
+ "grad_norm": 0.08250874631468892,
63
+ "learning_rate": 0.0001707317073170732,
64
+ "loss": 1.1902,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.09797917942437231,
69
+ "grad_norm": 0.09447143113709522,
70
+ "learning_rate": 0.0001951219512195122,
71
+ "loss": 1.2005,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.11022657685241886,
76
+ "grad_norm": 0.0824021009170569,
77
+ "learning_rate": 0.00019994138413588491,
78
+ "loss": 1.1864,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.1224739742804654,
83
+ "grad_norm": 0.0894227247413217,
84
+ "learning_rate": 0.0001997033749537941,
85
+ "loss": 1.1574,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.13472137170851195,
90
+ "grad_norm": 0.07854947144546601,
91
+ "learning_rate": 0.00019928274457498818,
92
+ "loss": 1.1595,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.14696876913655849,
97
+ "grad_norm": 0.08179447168807087,
98
+ "learning_rate": 0.00019868026344503306,
99
+ "loss": 1.1668,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.15921616656460502,
104
+ "grad_norm": 0.09018877740754977,
105
+ "learning_rate": 0.00019789703509552945,
106
+ "loss": 1.1517,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.17146356399265156,
111
+ "grad_norm": 0.08070743453648781,
112
+ "learning_rate": 0.00019693449412283435,
113
+ "loss": 1.1557,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.1837109614206981,
118
+ "grad_norm": 0.17006096808234306,
119
+ "learning_rate": 0.00019579440356038967,
120
+ "loss": 1.1265,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.19595835884874463,
125
+ "grad_norm": 0.07490774235953891,
126
+ "learning_rate": 0.00019447885164947088,
127
+ "loss": 1.1411,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.2082057562767912,
132
+ "grad_norm": 0.07560268552998486,
133
+ "learning_rate": 0.00019299024801426994,
134
+ "loss": 1.1346,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.22045315370483773,
139
+ "grad_norm": 0.06989244321896809,
140
+ "learning_rate": 0.00019133131924831917,
141
+ "loss": 1.1373,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.23270055113288426,
146
+ "grad_norm": 0.07297326140007601,
147
+ "learning_rate": 0.00018950510392033945,
148
+ "loss": 1.1262,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.2449479485609308,
153
+ "grad_norm": 0.08107861966515256,
154
+ "learning_rate": 0.00018751494700866087,
155
+ "loss": 1.1266,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.25719534598897736,
160
+ "grad_norm": 0.07525334503932822,
161
+ "learning_rate": 0.0001853644937744095,
162
+ "loss": 1.1337,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.2694427434170239,
167
+ "grad_norm": 0.07418001338537485,
168
+ "learning_rate": 0.00018305768308468293,
169
+ "loss": 1.1527,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.28169014084507044,
174
+ "grad_norm": 0.07966858826560685,
175
+ "learning_rate": 0.00018059874019794351,
176
+ "loss": 1.1275,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.29393753827311697,
181
+ "grad_norm": 0.06884328126643421,
182
+ "learning_rate": 0.00017799216902484466,
183
+ "loss": 1.1142,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.3061849357011635,
188
+ "grad_norm": 0.07638833793093423,
189
+ "learning_rate": 0.00017524274387866484,
190
+ "loss": 1.1489,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.31843233312921004,
195
+ "grad_norm": 0.07163478075363215,
196
+ "learning_rate": 0.00017235550073046028,
197
+ "loss": 1.1334,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.3306797305572566,
202
+ "grad_norm": 0.07584970266147063,
203
+ "learning_rate": 0.00016933572798495328,
204
+ "loss": 1.1394,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.3429271279853031,
209
+ "grad_norm": 0.0882549132067985,
210
+ "learning_rate": 0.00016618895679405165,
211
+ "loss": 1.1266,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.35517452541334965,
216
+ "grad_norm": 0.0738337228599522,
217
+ "learning_rate": 0.00016292095092574154,
218
+ "loss": 1.1356,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.3674219228413962,
223
+ "grad_norm": 0.07323403324052054,
224
+ "learning_rate": 0.00015953769620691022,
225
+ "loss": 1.1448,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.3796693202694427,
230
+ "grad_norm": 0.07258910733356848,
231
+ "learning_rate": 0.0001560453895594354,
232
+ "loss": 1.1255,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.39191671769748926,
237
+ "grad_norm": 0.08483741713706569,
238
+ "learning_rate": 0.00015245042764962417,
239
+ "loss": 1.1203,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.40416411512553585,
244
+ "grad_norm": 0.07393069983884801,
245
+ "learning_rate": 0.00014875939517179016,
246
+ "loss": 1.1305,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.4164115125535824,
251
+ "grad_norm": 0.07536661950821844,
252
+ "learning_rate": 0.00014497905278743083,
253
+ "loss": 1.1142,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.4286589099816289,
258
+ "grad_norm": 0.0774588990644394,
259
+ "learning_rate": 0.00014111632474209505,
260
+ "loss": 1.1014,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.44090630740967546,
265
+ "grad_norm": 0.0723327812244184,
266
+ "learning_rate": 0.0001371782861826226,
267
+ "loss": 1.1215,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.453153704837722,
272
+ "grad_norm": 0.07454342646966894,
273
+ "learning_rate": 0.00013317215019798638,
274
+ "loss": 1.1276,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.46540110226576853,
279
+ "grad_norm": 0.07195661618627822,
280
+ "learning_rate": 0.00012910525460747344,
281
+ "loss": 1.1083,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.47764849969381507,
286
+ "grad_norm": 0.07092309315305423,
287
+ "learning_rate": 0.00012498504852040434,
288
+ "loss": 1.1373,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.4898958971218616,
293
+ "grad_norm": 0.07301281736550075,
294
+ "learning_rate": 0.00012081907869200849,
295
+ "loss": 1.1312,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.5021432945499081,
300
+ "grad_norm": 0.07484347637628397,
301
+ "learning_rate": 0.00011661497570044738,
302
+ "loss": 1.1208,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.5143906919779547,
307
+ "grad_norm": 0.0724091132876655,
308
+ "learning_rate": 0.00011238043997030329,
309
+ "loss": 1.1309,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.5266380894060012,
314
+ "grad_norm": 0.2342422867496652,
315
+ "learning_rate": 0.00010812322766813461,
316
+ "loss": 1.1138,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.5388854868340478,
321
+ "grad_norm": 0.07212287103404749,
322
+ "learning_rate": 0.00010385113649593137,
323
+ "loss": 1.1192,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.5511328842620943,
328
+ "grad_norm": 0.07073394667449048,
329
+ "learning_rate": 9.957199140849278e-05,
330
+ "loss": 1.109,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.5633802816901409,
335
+ "grad_norm": 0.06964674186116192,
336
+ "learning_rate": 9.529363028088725e-05,
337
+ "loss": 1.115,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.5756276791181874,
342
+ "grad_norm": 0.07117704481271163,
343
+ "learning_rate": 9.102388955224703e-05,
344
+ "loss": 1.1099,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.5878750765462339,
349
+ "grad_norm": 0.07216465095526178,
350
+ "learning_rate": 8.677058987219295e-05,
351
+ "loss": 1.113,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.6001224739742804,
356
+ "grad_norm": 0.0725366248294856,
357
+ "learning_rate": 8.254152177618e-05,
358
+ "loss": 1.1047,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.612369871402327,
363
+ "grad_norm": 0.07979788000565378,
364
+ "learning_rate": 7.83444314160013e-05,
365
+ "loss": 1.1275,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.6246172688303735,
370
+ "grad_norm": 0.07038014346187686,
371
+ "learning_rate": 7.418700637158742e-05,
372
+ "loss": 1.0942,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.6368646662584201,
377
+ "grad_norm": 0.07043699403227373,
378
+ "learning_rate": 7.00768615700881e-05,
379
+ "loss": 1.1188,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.6491120636864667,
384
+ "grad_norm": 0.07317860829882807,
385
+ "learning_rate": 6.60215253380287e-05,
386
+ "loss": 1.1228,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.6613594611145132,
391
+ "grad_norm": 0.0736268694865736,
392
+ "learning_rate": 6.202842561208758e-05,
393
+ "loss": 1.1004,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.6736068585425597,
398
+ "grad_norm": 0.0681966580195897,
399
+ "learning_rate": 5.810487633375261e-05,
400
+ "loss": 1.0964,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.6858542559706062,
405
+ "grad_norm": 0.06988692587157964,
406
+ "learning_rate": 5.425806405277609e-05,
407
+ "loss": 1.1123,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.6981016533986528,
412
+ "grad_norm": 0.06961689512931302,
413
+ "learning_rate": 5.049503476396627e-05,
414
+ "loss": 1.1254,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.7103490508266993,
419
+ "grad_norm": 0.06848007555420067,
420
+ "learning_rate": 4.682268100142566e-05,
421
+ "loss": 1.1064,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.7225964482547459,
426
+ "grad_norm": 0.06848238221490942,
427
+ "learning_rate": 4.32477292138746e-05,
428
+ "loss": 1.1078,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.7348438456827924,
433
+ "grad_norm": 0.06932096702672658,
434
+ "learning_rate": 3.9776727444184744e-05,
435
+ "loss": 1.1359,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.747091243110839,
440
+ "grad_norm": 0.06964742874998163,
441
+ "learning_rate": 3.641603333568831e-05,
442
+ "loss": 1.1071,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.7593386405388854,
447
+ "grad_norm": 0.07515967784857266,
448
+ "learning_rate": 3.3171802487232086e-05,
449
+ "loss": 1.114,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.771586037966932,
454
+ "grad_norm": 0.07140996525669459,
455
+ "learning_rate": 3.0049977178305076e-05,
456
+ "loss": 1.1179,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.7838334353949785,
461
+ "grad_norm": 0.06922024794802567,
462
+ "learning_rate": 2.7056275484891304e-05,
463
+ "loss": 1.0962,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.7960808328230251,
468
+ "grad_norm": 0.07028157088055875,
469
+ "learning_rate": 2.419618080598417e-05,
470
+ "loss": 1.1361,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.8083282302510717,
475
+ "grad_norm": 0.07083633675990936,
476
+ "learning_rate": 2.1474931819945553e-05,
477
+ "loss": 1.1025,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.8205756276791182,
482
+ "grad_norm": 0.07118501791774294,
483
+ "learning_rate": 1.889751288910645e-05,
484
+ "loss": 1.0959,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.8328230251071648,
489
+ "grad_norm": 0.0724941459460009,
490
+ "learning_rate": 1.6468644930184095e-05,
491
+ "loss": 1.0963,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.8450704225352113,
496
+ "grad_norm": 0.07065248333558355,
497
+ "learning_rate": 1.4192776767238158e-05,
498
+ "loss": 1.1097,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.8573178199632578,
503
+ "grad_norm": 0.06638354595318986,
504
+ "learning_rate": 1.2074076983003958e-05,
505
+ "loss": 1.1086,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.8695652173913043,
510
+ "grad_norm": 0.0678250769481932,
511
+ "learning_rate": 1.0116426283528302e-05,
512
+ "loss": 1.1164,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.8818126148193509,
517
+ "grad_norm": 0.06908465334552778,
518
+ "learning_rate": 8.323410390093522e-06,
519
+ "loss": 1.1219,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.8940600122473974,
524
+ "grad_norm": 0.07002593669930346,
525
+ "learning_rate": 6.698313471448547e-06,
526
+ "loss": 1.1057,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.906307409675444,
531
+ "grad_norm": 0.06951335625337747,
532
+ "learning_rate": 5.244112128377476e-06,
533
+ "loss": 1.1156,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.9185548071034905,
538
+ "grad_norm": 0.07086629076783696,
539
+ "learning_rate": 3.963469941623288e-06,
540
+ "loss": 1.0996,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.9308022045315371,
545
+ "grad_norm": 0.07007458613323735,
546
+ "learning_rate": 2.858732593153246e-06,
547
+ "loss": 1.1211,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.9430496019595835,
552
+ "grad_norm": 0.0665201643250434,
553
+ "learning_rate": 1.9319235697021763e-06,
554
+ "loss": 1.1165,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.9552969993876301,
559
+ "grad_norm": 0.06858672635827863,
560
+ "learning_rate": 1.1847404564628185e-06,
561
+ "loss": 1.0881,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.9675443968156767,
566
+ "grad_norm": 0.07063191807948407,
567
+ "learning_rate": 6.185518277123214e-07,
568
+ "loss": 1.1031,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.9797917942437232,
573
+ "grad_norm": 0.06843622739420911,
574
+ "learning_rate": 2.343947400698432e-07,
575
+ "loss": 1.1103,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.9920391916717698,
580
+ "grad_norm": 0.0681228499191145,
581
+ "learning_rate": 3.2972832976918554e-08,
582
+ "loss": 1.1119,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.9993876301285977,
587
+ "eval_loss": 1.037530541419983,
588
+ "eval_runtime": 2.1401,
589
+ "eval_samples_per_second": 3.271,
590
+ "eval_steps_per_second": 0.935,
591
+ "step": 408
592
+ },
593
+ {
594
+ "epoch": 0.9993876301285977,
595
+ "step": 408,
596
+ "total_flos": 1.2948113606049792e+16,
597
+ "train_loss": 1.1371603935372596,
598
+ "train_runtime": 15464.5644,
599
+ "train_samples_per_second": 3.378,
600
+ "train_steps_per_second": 0.026
601
+ }
602
+ ],
603
+ "logging_steps": 5,
604
+ "max_steps": 408,
605
+ "num_input_tokens_seen": 0,
606
+ "num_train_epochs": 1,
607
+ "save_steps": 100,
608
+ "stateful_callbacks": {
609
+ "TrainerControl": {
610
+ "args": {
611
+ "should_epoch_stop": false,
612
+ "should_evaluate": false,
613
+ "should_log": false,
614
+ "should_save": true,
615
+ "should_training_stop": true
616
+ },
617
+ "attributes": {}
618
+ }
619
+ },
620
+ "total_flos": 1.2948113606049792e+16,
621
+ "train_batch_size": 8,
622
+ "trial_name": null,
623
+ "trial_params": null
624
+ }