terry69 commited on
Commit
dedfb92
1 Parent(s): e6da930

Model save

Browse files
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: Qwen/Qwen1.5-7B-Chat
9
+ model-index:
10
+ - name: qwen_preference
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
+ # qwen_preference
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen1.5-7B-Chat](https://huggingface.co/Qwen/Qwen1.5-7B-Chat) on the None 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: 1e-05
39
+ - train_batch_size: 16
40
+ - eval_batch_size: 1
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 4
44
+ - total_train_batch_size: 64
45
+ - total_eval_batch_size: 4
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 1
50
+
51
+ ### Training results
52
+
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - PEFT 0.11.1
58
+ - Transformers 4.44.2
59
+ - Pytorch 2.3.1+cu121
60
+ - Datasets 2.19.1
61
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 555957746663424.0,
4
+ "train_loss": 1.2752919873194908,
5
+ "train_runtime": 16895.3411,
6
+ "train_samples": 98881,
7
+ "train_samples_per_second": 2.029,
8
+ "train_steps_per_second": 0.032
9
+ }
runs/Sep21_04-05-49_COE-CS-sv004/events.out.tfevents.1726891572.COE-CS-sv004.1368169.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:faeaf069abb4435e1475ad3f0bd3bb0bafca6c6296de860aef54d8a78e099190
3
- size 28091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb0565cfba65d3369c10ffe90770223239fee9f9f8a126019d9770a8f2380a69
3
+ size 28445
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 555957746663424.0,
4
+ "train_loss": 1.2752919873194908,
5
+ "train_runtime": 16895.3411,
6
+ "train_samples": 98881,
7
+ "train_samples_per_second": 2.029,
8
+ "train_steps_per_second": 0.032
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,805 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 536,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0018656716417910447,
13
+ "grad_norm": 2.57972321339612,
14
+ "learning_rate": 1.8518518518518518e-07,
15
+ "loss": 2.092,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.009328358208955223,
20
+ "grad_norm": 2.3735119503905793,
21
+ "learning_rate": 9.259259259259259e-07,
22
+ "loss": 2.0863,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.018656716417910446,
27
+ "grad_norm": 2.569828354184601,
28
+ "learning_rate": 1.8518518518518519e-06,
29
+ "loss": 2.0955,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.027985074626865673,
34
+ "grad_norm": 2.3365878728458847,
35
+ "learning_rate": 2.7777777777777783e-06,
36
+ "loss": 2.078,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.03731343283582089,
41
+ "grad_norm": 2.258292749629048,
42
+ "learning_rate": 3.7037037037037037e-06,
43
+ "loss": 2.0535,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.04664179104477612,
48
+ "grad_norm": 2.046409624248939,
49
+ "learning_rate": 4.62962962962963e-06,
50
+ "loss": 1.9936,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.055970149253731345,
55
+ "grad_norm": 1.7763941617915107,
56
+ "learning_rate": 5.555555555555557e-06,
57
+ "loss": 1.9172,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.06529850746268656,
62
+ "grad_norm": 1.5289482279435747,
63
+ "learning_rate": 6.481481481481482e-06,
64
+ "loss": 1.8216,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.07462686567164178,
69
+ "grad_norm": 1.3374159627357958,
70
+ "learning_rate": 7.4074074074074075e-06,
71
+ "loss": 1.7237,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.08395522388059702,
76
+ "grad_norm": 1.038988897758925,
77
+ "learning_rate": 8.333333333333334e-06,
78
+ "loss": 1.6205,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.09328358208955224,
83
+ "grad_norm": 0.5713243982808286,
84
+ "learning_rate": 9.25925925925926e-06,
85
+ "loss": 1.5364,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.10261194029850747,
90
+ "grad_norm": 0.3049992132098635,
91
+ "learning_rate": 9.999893795201304e-06,
92
+ "loss": 1.491,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.11194029850746269,
97
+ "grad_norm": 0.36148501744582134,
98
+ "learning_rate": 9.996177100962714e-06,
99
+ "loss": 1.473,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.12126865671641791,
104
+ "grad_norm": 0.37327333184682066,
105
+ "learning_rate": 9.987154677711482e-06,
106
+ "loss": 1.4594,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.13059701492537312,
111
+ "grad_norm": 0.31133363324217617,
112
+ "learning_rate": 9.972836106879936e-06,
113
+ "loss": 1.4442,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.13992537313432835,
118
+ "grad_norm": 0.2375327029162037,
119
+ "learning_rate": 9.953236594185396e-06,
120
+ "loss": 1.4258,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.14925373134328357,
125
+ "grad_norm": 0.19998776915472055,
126
+ "learning_rate": 9.928376953482343e-06,
127
+ "loss": 1.4093,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.15858208955223882,
132
+ "grad_norm": 0.19069793139067803,
133
+ "learning_rate": 9.898283584658988e-06,
134
+ "loss": 1.4029,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.16791044776119404,
139
+ "grad_norm": 0.17979433709822593,
140
+ "learning_rate": 9.86298844560169e-06,
141
+ "loss": 1.3876,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.17723880597014927,
146
+ "grad_norm": 0.1750060584120198,
147
+ "learning_rate": 9.822529018257049e-06,
148
+ "loss": 1.3842,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.1865671641791045,
153
+ "grad_norm": 0.17054790759610952,
154
+ "learning_rate": 9.776948268827658e-06,
155
+ "loss": 1.3756,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.1958955223880597,
160
+ "grad_norm": 0.17397761641849066,
161
+ "learning_rate": 9.726294602143807e-06,
162
+ "loss": 1.3544,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.20522388059701493,
167
+ "grad_norm": 0.17494592787959154,
168
+ "learning_rate": 9.670621810259596e-06,
169
+ "loss": 1.338,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.21455223880597016,
174
+ "grad_norm": 0.17874287198232588,
175
+ "learning_rate": 9.609989015328052e-06,
176
+ "loss": 1.3321,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.22388059701492538,
181
+ "grad_norm": 0.18177787677872814,
182
+ "learning_rate": 9.544460606815901e-06,
183
+ "loss": 1.3231,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.2332089552238806,
188
+ "grad_norm": 0.17485139906929326,
189
+ "learning_rate": 9.474106173124667e-06,
190
+ "loss": 1.3029,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.24253731343283583,
195
+ "grad_norm": 0.16541538036070813,
196
+ "learning_rate": 9.399000427690736e-06,
197
+ "loss": 1.2914,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.251865671641791,
202
+ "grad_norm": 0.15475993597407106,
203
+ "learning_rate": 9.31922312964284e-06,
204
+ "loss": 1.2731,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.26119402985074625,
209
+ "grad_norm": 0.14876033685341322,
210
+ "learning_rate": 9.234858999101232e-06,
211
+ "loss": 1.2612,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.27052238805970147,
216
+ "grad_norm": 0.13102260537341828,
217
+ "learning_rate": 9.1459976272085e-06,
218
+ "loss": 1.2406,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.2798507462686567,
223
+ "grad_norm": 0.1231370916125911,
224
+ "learning_rate": 9.052733380987555e-06,
225
+ "loss": 1.2402,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.2891791044776119,
230
+ "grad_norm": 0.11617076992843688,
231
+ "learning_rate": 8.955165303127841e-06,
232
+ "loss": 1.2287,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.29850746268656714,
237
+ "grad_norm": 0.10711292754756604,
238
+ "learning_rate": 8.853397006806183e-06,
239
+ "loss": 1.2293,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.30783582089552236,
244
+ "grad_norm": 0.10583142709305077,
245
+ "learning_rate": 8.747536565653966e-06,
246
+ "loss": 1.2196,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.31716417910447764,
251
+ "grad_norm": 0.10071371091495551,
252
+ "learning_rate": 8.637696398987517e-06,
253
+ "loss": 1.2218,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.32649253731343286,
258
+ "grad_norm": 0.09786904166381197,
259
+ "learning_rate": 8.523993152423522e-06,
260
+ "loss": 1.2076,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.3358208955223881,
265
+ "grad_norm": 0.09308216883502402,
266
+ "learning_rate": 8.406547574006326e-06,
267
+ "loss": 1.2069,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.3451492537313433,
272
+ "grad_norm": 0.09403316911201794,
273
+ "learning_rate": 8.285484385978598e-06,
274
+ "loss": 1.2151,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.35447761194029853,
279
+ "grad_norm": 0.09276385606464647,
280
+ "learning_rate": 8.160932152331587e-06,
281
+ "loss": 1.2033,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.36380597014925375,
286
+ "grad_norm": 0.09044032546865181,
287
+ "learning_rate": 8.03302314227559e-06,
288
+ "loss": 1.2028,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.373134328358209,
293
+ "grad_norm": 0.08960581233300505,
294
+ "learning_rate": 7.90189318977564e-06,
295
+ "loss": 1.2036,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.3824626865671642,
300
+ "grad_norm": 0.08546838672930177,
301
+ "learning_rate": 7.767681549301576e-06,
302
+ "loss": 1.1932,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.3917910447761194,
307
+ "grad_norm": 0.08706831337193889,
308
+ "learning_rate": 7.630530747945672e-06,
309
+ "loss": 1.2016,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.40111940298507465,
314
+ "grad_norm": 0.08501828118277771,
315
+ "learning_rate": 7.490586434064893e-06,
316
+ "loss": 1.1984,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.41044776119402987,
321
+ "grad_norm": 0.08231749758944934,
322
+ "learning_rate": 7.3479972226084925e-06,
323
+ "loss": 1.1934,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.4197761194029851,
328
+ "grad_norm": 0.0846325939740857,
329
+ "learning_rate": 7.202914537295211e-06,
330
+ "loss": 1.1871,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.4291044776119403,
335
+ "grad_norm": 0.0839943062987978,
336
+ "learning_rate": 7.055492449807684e-06,
337
+ "loss": 1.1847,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.43843283582089554,
342
+ "grad_norm": 0.0842974194320567,
343
+ "learning_rate": 6.905887516174827e-06,
344
+ "loss": 1.1823,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.44776119402985076,
349
+ "grad_norm": 0.08246202494295994,
350
+ "learning_rate": 6.754258610515949e-06,
351
+ "loss": 1.1874,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.457089552238806,
356
+ "grad_norm": 0.08059952388104133,
357
+ "learning_rate": 6.60076675632314e-06,
358
+ "loss": 1.1768,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.4664179104477612,
363
+ "grad_norm": 0.08278287209635887,
364
+ "learning_rate": 6.445574955461134e-06,
365
+ "loss": 1.1743,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.47574626865671643,
370
+ "grad_norm": 0.08064613485931339,
371
+ "learning_rate": 6.288848015066211e-06,
372
+ "loss": 1.1787,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.48507462686567165,
377
+ "grad_norm": 0.08402784054638568,
378
+ "learning_rate": 6.130752372527981e-06,
379
+ "loss": 1.1797,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.4944029850746269,
384
+ "grad_norm": 0.07813087594533498,
385
+ "learning_rate": 5.9714559187399094e-06,
386
+ "loss": 1.1814,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.503731343283582,
391
+ "grad_norm": 0.08253282031035683,
392
+ "learning_rate": 5.811127819806277e-06,
393
+ "loss": 1.1767,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.5130597014925373,
398
+ "grad_norm": 0.0795025665014561,
399
+ "learning_rate": 5.649938337394932e-06,
400
+ "loss": 1.1684,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.5223880597014925,
405
+ "grad_norm": 0.08201269451158993,
406
+ "learning_rate": 5.4880586479265774e-06,
407
+ "loss": 1.1704,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.5317164179104478,
412
+ "grad_norm": 0.08039664736174637,
413
+ "learning_rate": 5.325660660792657e-06,
414
+ "loss": 1.1704,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.5410447761194029,
419
+ "grad_norm": 0.08098088631592301,
420
+ "learning_rate": 5.162916835794843e-06,
421
+ "loss": 1.1722,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.5503731343283582,
426
+ "grad_norm": 0.08014102460089276,
427
+ "learning_rate": 5e-06,
428
+ "loss": 1.1748,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.5597014925373134,
433
+ "grad_norm": 0.08067154136929545,
434
+ "learning_rate": 4.837083164205159e-06,
435
+ "loss": 1.1741,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.5690298507462687,
440
+ "grad_norm": 0.07702944221391651,
441
+ "learning_rate": 4.6743393392073435e-06,
442
+ "loss": 1.1734,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.5783582089552238,
447
+ "grad_norm": 0.08366251841352572,
448
+ "learning_rate": 4.511941352073424e-06,
449
+ "loss": 1.1674,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.5876865671641791,
454
+ "grad_norm": 0.08401515307564614,
455
+ "learning_rate": 4.3500616626050705e-06,
456
+ "loss": 1.171,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.5970149253731343,
461
+ "grad_norm": 0.07880234388575032,
462
+ "learning_rate": 4.188872180193723e-06,
463
+ "loss": 1.1617,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.6063432835820896,
468
+ "grad_norm": 0.08075724129202204,
469
+ "learning_rate": 4.028544081260093e-06,
470
+ "loss": 1.1664,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.6156716417910447,
475
+ "grad_norm": 0.08145891878774718,
476
+ "learning_rate": 3.869247627472021e-06,
477
+ "loss": 1.1647,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.625,
482
+ "grad_norm": 0.07981030112455705,
483
+ "learning_rate": 3.7111519849337908e-06,
484
+ "loss": 1.1661,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.6343283582089553,
489
+ "grad_norm": 0.07719220748480114,
490
+ "learning_rate": 3.554425044538868e-06,
491
+ "loss": 1.164,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.6436567164179104,
496
+ "grad_norm": 0.07965079201392798,
497
+ "learning_rate": 3.3992332436768615e-06,
498
+ "loss": 1.1685,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.6529850746268657,
503
+ "grad_norm": 0.07929508580781615,
504
+ "learning_rate": 3.2457413894840516e-06,
505
+ "loss": 1.166,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.6623134328358209,
510
+ "grad_norm": 0.08260668169292941,
511
+ "learning_rate": 3.0941124838251734e-06,
512
+ "loss": 1.1641,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.6716417910447762,
517
+ "grad_norm": 0.07880705452928782,
518
+ "learning_rate": 2.944507550192318e-06,
519
+ "loss": 1.1697,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.6809701492537313,
524
+ "grad_norm": 0.08617336475255008,
525
+ "learning_rate": 2.7970854627047893e-06,
526
+ "loss": 1.1617,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.6902985074626866,
531
+ "grad_norm": 0.08504447838669933,
532
+ "learning_rate": 2.6520027773915075e-06,
533
+ "loss": 1.1694,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.6996268656716418,
538
+ "grad_norm": 0.08177432381677913,
539
+ "learning_rate": 2.509413565935107e-06,
540
+ "loss": 1.1663,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.7089552238805971,
545
+ "grad_norm": 0.08035338660262055,
546
+ "learning_rate": 2.3694692520543293e-06,
547
+ "loss": 1.1617,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.7182835820895522,
552
+ "grad_norm": 0.08099302263307083,
553
+ "learning_rate": 2.2323184506984257e-06,
554
+ "loss": 1.1601,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.7276119402985075,
559
+ "grad_norm": 0.0788199344055389,
560
+ "learning_rate": 2.098106810224362e-06,
561
+ "loss": 1.1678,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.7369402985074627,
566
+ "grad_norm": 0.0810220420611739,
567
+ "learning_rate": 1.9669768577244107e-06,
568
+ "loss": 1.1659,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.746268656716418,
573
+ "grad_norm": 0.07813643594984888,
574
+ "learning_rate": 1.8390678476684143e-06,
575
+ "loss": 1.1619,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.7555970149253731,
580
+ "grad_norm": 0.07787996158898178,
581
+ "learning_rate": 1.7145156140214032e-06,
582
+ "loss": 1.1647,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.7649253731343284,
587
+ "grad_norm": 0.08149237459503167,
588
+ "learning_rate": 1.5934524259936757e-06,
589
+ "loss": 1.1663,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.7742537313432836,
594
+ "grad_norm": 0.08133121141847001,
595
+ "learning_rate": 1.4760068475764789e-06,
596
+ "loss": 1.1481,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.7835820895522388,
601
+ "grad_norm": 0.07796965232583761,
602
+ "learning_rate": 1.3623036010124845e-06,
603
+ "loss": 1.1592,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.792910447761194,
608
+ "grad_norm": 0.07862074938919475,
609
+ "learning_rate": 1.2524634343460335e-06,
610
+ "loss": 1.1537,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.8022388059701493,
615
+ "grad_norm": 0.08047006906879658,
616
+ "learning_rate": 1.1466029931938182e-06,
617
+ "loss": 1.1575,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.8115671641791045,
622
+ "grad_norm": 0.07919282621278656,
623
+ "learning_rate": 1.0448346968721596e-06,
624
+ "loss": 1.1591,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.8208955223880597,
629
+ "grad_norm": 0.08069925871151505,
630
+ "learning_rate": 9.472666190124457e-07,
631
+ "loss": 1.1588,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.8302238805970149,
636
+ "grad_norm": 0.07925111301368296,
637
+ "learning_rate": 8.540023727915015e-07,
638
+ "loss": 1.1552,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.8395522388059702,
643
+ "grad_norm": 0.08107260891150957,
644
+ "learning_rate": 7.651410008987698e-07,
645
+ "loss": 1.1568,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.8488805970149254,
650
+ "grad_norm": 0.07855238487611285,
651
+ "learning_rate": 6.807768703571616e-07,
652
+ "loss": 1.1498,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.8582089552238806,
657
+ "grad_norm": 0.08067373717155321,
658
+ "learning_rate": 6.009995723092655e-07,
659
+ "loss": 1.163,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.8675373134328358,
664
+ "grad_norm": 0.083123312332487,
665
+ "learning_rate": 5.258938268753344e-07,
666
+ "loss": 1.155,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.8768656716417911,
671
+ "grad_norm": 0.07901297859441447,
672
+ "learning_rate": 4.555393931841001e-07,
673
+ "loss": 1.1615,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.8861940298507462,
678
+ "grad_norm": 0.07759270476319681,
679
+ "learning_rate": 3.9001098467194907e-07,
680
+ "loss": 1.1575,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.8955223880597015,
685
+ "grad_norm": 0.07822412070732043,
686
+ "learning_rate": 3.2937818974040637e-07,
687
+ "loss": 1.1597,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.9048507462686567,
692
+ "grad_norm": 0.0799398408165139,
693
+ "learning_rate": 2.737053978561943e-07,
694
+ "loss": 1.1602,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.914179104477612,
699
+ "grad_norm": 0.07777635865631954,
700
+ "learning_rate": 2.2305173117234236e-07,
701
+ "loss": 1.1568,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.9235074626865671,
706
+ "grad_norm": 0.08036060154131985,
707
+ "learning_rate": 1.7747098174295208e-07,
708
+ "loss": 1.1652,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.9328358208955224,
713
+ "grad_norm": 0.08306752546345667,
714
+ "learning_rate": 1.3701155439831249e-07,
715
+ "loss": 1.1558,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.9421641791044776,
720
+ "grad_norm": 0.07992649084819468,
721
+ "learning_rate": 1.017164153410144e-07,
722
+ "loss": 1.1566,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.9514925373134329,
727
+ "grad_norm": 0.07911970141612473,
728
+ "learning_rate": 7.16230465176565e-08,
729
+ "loss": 1.1559,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.960820895522388,
734
+ "grad_norm": 0.0846383351709255,
735
+ "learning_rate": 4.6763405814604926e-08,
736
+ "loss": 1.1514,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.9701492537313433,
741
+ "grad_norm": 0.07934050493191654,
742
+ "learning_rate": 2.7163893120066288e-08,
743
+ "loss": 1.1542,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.9794776119402985,
748
+ "grad_norm": 0.08167448133397126,
749
+ "learning_rate": 1.284532228851998e-08,
750
+ "loss": 1.161,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.9888059701492538,
755
+ "grad_norm": 0.07857080161491098,
756
+ "learning_rate": 3.822899037286276e-09,
757
+ "loss": 1.1579,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.9981343283582089,
762
+ "grad_norm": 0.07847093836951612,
763
+ "learning_rate": 1.0620479869771772e-10,
764
+ "loss": 1.1582,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 1.0,
769
+ "eval_runtime": 3.2225,
770
+ "eval_samples_per_second": 3.103,
771
+ "eval_steps_per_second": 0.931,
772
+ "step": 536
773
+ },
774
+ {
775
+ "epoch": 1.0,
776
+ "step": 536,
777
+ "total_flos": 555957746663424.0,
778
+ "train_loss": 1.2752919873194908,
779
+ "train_runtime": 16895.3411,
780
+ "train_samples_per_second": 2.029,
781
+ "train_steps_per_second": 0.032
782
+ }
783
+ ],
784
+ "logging_steps": 5,
785
+ "max_steps": 536,
786
+ "num_input_tokens_seen": 0,
787
+ "num_train_epochs": 1,
788
+ "save_steps": 100,
789
+ "stateful_callbacks": {
790
+ "TrainerControl": {
791
+ "args": {
792
+ "should_epoch_stop": false,
793
+ "should_evaluate": false,
794
+ "should_log": false,
795
+ "should_save": true,
796
+ "should_training_stop": true
797
+ },
798
+ "attributes": {}
799
+ }
800
+ },
801
+ "total_flos": 555957746663424.0,
802
+ "train_batch_size": 16,
803
+ "trial_name": null,
804
+ "trial_params": null
805
+ }