terry69 commited on
Commit
c3872f1
·
verified ·
1 Parent(s): e989c85

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_1.0p_seed42_level2_styledirty
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_1.0p_seed42_level2_styledirty
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": 0.9984067976633032,
3
+ "total_flos": 3.0618166709610086e+17,
4
+ "train_loss": 1.2359964916046629,
5
+ "train_runtime": 17731.1519,
6
+ "train_samples": 95271,
7
+ "train_samples_per_second": 3.397,
8
+ "train_steps_per_second": 0.027
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9984067976633032,
3
+ "total_flos": 3.0618166709610086e+17,
4
+ "train_loss": 1.2359964916046629,
5
+ "train_runtime": 17731.1519,
6
+ "train_samples": 95271,
7
+ "train_samples_per_second": 3.397,
8
+ "train_steps_per_second": 0.027
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,714 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9984067976633032,
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": 0.002124269782262347,
13
+ "grad_norm": 0.9608867223105472,
14
+ "learning_rate": 4.255319148936171e-06,
15
+ "loss": 1.6209,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.010621348911311737,
20
+ "grad_norm": 1.008471490037168,
21
+ "learning_rate": 2.1276595744680852e-05,
22
+ "loss": 1.6199,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.021242697822623474,
27
+ "grad_norm": 0.26269444126063646,
28
+ "learning_rate": 4.2553191489361704e-05,
29
+ "loss": 1.5721,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.03186404673393521,
34
+ "grad_norm": 0.22796802020916335,
35
+ "learning_rate": 6.382978723404256e-05,
36
+ "loss": 1.5352,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.04248539564524695,
41
+ "grad_norm": 0.19620571386797234,
42
+ "learning_rate": 8.510638297872341e-05,
43
+ "loss": 1.4921,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.053106744556558685,
48
+ "grad_norm": 0.2014364121241671,
49
+ "learning_rate": 0.00010638297872340425,
50
+ "loss": 1.4569,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.06372809346787042,
55
+ "grad_norm": 0.14918854171943344,
56
+ "learning_rate": 0.00012765957446808513,
57
+ "loss": 1.4115,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.07434944237918216,
62
+ "grad_norm": 0.13584276036738227,
63
+ "learning_rate": 0.00014893617021276596,
64
+ "loss": 1.3582,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.0849707912904939,
69
+ "grad_norm": 0.1362041776273294,
70
+ "learning_rate": 0.00017021276595744682,
71
+ "loss": 1.3364,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.09559214020180563,
76
+ "grad_norm": 0.12938558071544978,
77
+ "learning_rate": 0.00019148936170212768,
78
+ "loss": 1.348,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.10621348911311737,
83
+ "grad_norm": 0.10380081880060799,
84
+ "learning_rate": 0.0001999751793267259,
85
+ "loss": 1.3054,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.11683483802442911,
90
+ "grad_norm": 0.1143838187685618,
91
+ "learning_rate": 0.00019982354205260347,
92
+ "loss": 1.2693,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.12745618693574085,
97
+ "grad_norm": 0.11149288198876389,
98
+ "learning_rate": 0.0001995342655949951,
99
+ "loss": 1.2794,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.13807753584705257,
104
+ "grad_norm": 0.09311862817149338,
105
+ "learning_rate": 0.000199107748815478,
106
+ "loss": 1.2873,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.14869888475836432,
111
+ "grad_norm": 0.09599961949976782,
112
+ "learning_rate": 0.000198544579806,
113
+ "loss": 1.2646,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.15932023366967604,
118
+ "grad_norm": 0.11732897723147062,
119
+ "learning_rate": 0.00019784553507800349,
120
+ "loss": 1.2609,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.1699415825809878,
125
+ "grad_norm": 0.09291613696202214,
126
+ "learning_rate": 0.00019701157849175228,
127
+ "loss": 1.2493,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.18056293149229952,
132
+ "grad_norm": 0.09277470552310135,
133
+ "learning_rate": 0.00019604385992733715,
134
+ "loss": 1.2582,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.19118428040361127,
139
+ "grad_norm": 0.09620615117699073,
140
+ "learning_rate": 0.0001949437136991925,
141
+ "loss": 1.2494,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.201805629314923,
146
+ "grad_norm": 0.09446376086527693,
147
+ "learning_rate": 0.00019371265671631037,
148
+ "loss": 1.2334,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.21242697822623474,
153
+ "grad_norm": 0.09732108560985277,
154
+ "learning_rate": 0.00019235238639068856,
155
+ "loss": 1.2471,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.22304832713754646,
160
+ "grad_norm": 0.0969859129107049,
161
+ "learning_rate": 0.00019086477829689685,
162
+ "loss": 1.2436,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.23366967604885822,
167
+ "grad_norm": 0.09815487872535014,
168
+ "learning_rate": 0.00018925188358598813,
169
+ "loss": 1.226,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.24429102496016994,
174
+ "grad_norm": 0.1258570306173551,
175
+ "learning_rate": 0.00018751592615732005,
176
+ "loss": 1.2419,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.2549123738714817,
181
+ "grad_norm": 0.107383152586875,
182
+ "learning_rate": 0.00018565929959218758,
183
+ "loss": 1.2366,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.2655337227827934,
188
+ "grad_norm": 0.10102976615766632,
189
+ "learning_rate": 0.00018368456385349334,
190
+ "loss": 1.2382,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.27615507169410514,
195
+ "grad_norm": 0.10456038759256343,
196
+ "learning_rate": 0.00018159444175600703,
197
+ "loss": 1.2342,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.2867764206054169,
202
+ "grad_norm": 0.11461394118247933,
203
+ "learning_rate": 0.000179391815212081,
204
+ "loss": 1.2401,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.29739776951672864,
209
+ "grad_norm": 0.1057527291904125,
210
+ "learning_rate": 0.00017707972125799735,
211
+ "loss": 1.2193,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.30801911842804036,
216
+ "grad_norm": 0.10177183771950413,
217
+ "learning_rate": 0.0001746613478664271,
218
+ "loss": 1.2424,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.3186404673393521,
223
+ "grad_norm": 0.09313461051969327,
224
+ "learning_rate": 0.00017214002955077393,
225
+ "loss": 1.2234,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.3292618162506638,
230
+ "grad_norm": 0.1051850821585042,
231
+ "learning_rate": 0.00016951924276746425,
232
+ "loss": 1.2023,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.3398831651619756,
237
+ "grad_norm": 0.09840584460636738,
238
+ "learning_rate": 0.0001668026011225225,
239
+ "loss": 1.2303,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.3505045140732873,
244
+ "grad_norm": 0.09133411062766343,
245
+ "learning_rate": 0.00016399385038904138,
246
+ "loss": 1.208,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.36112586298459903,
251
+ "grad_norm": 0.0924953491335953,
252
+ "learning_rate": 0.00016109686334241655,
253
+ "loss": 1.1899,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.37174721189591076,
258
+ "grad_norm": 0.0943384109563561,
259
+ "learning_rate": 0.00015811563442046767,
260
+ "loss": 1.2141,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.38236856080722254,
265
+ "grad_norm": 0.10914200480049749,
266
+ "learning_rate": 0.00015505427421580808,
267
+ "loss": 1.2248,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.39298990971853426,
272
+ "grad_norm": 0.10932571445854564,
273
+ "learning_rate": 0.00015191700380805752,
274
+ "loss": 1.2106,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.403611258629846,
279
+ "grad_norm": 0.13346508581550925,
280
+ "learning_rate": 0.00014870814894371245,
281
+ "loss": 1.2028,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.4142326075411577,
286
+ "grad_norm": 0.09705115895523017,
287
+ "learning_rate": 0.0001454321340716992,
288
+ "loss": 1.2132,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.4248539564524695,
293
+ "grad_norm": 0.10424666730333806,
294
+ "learning_rate": 0.0001420934762428335,
295
+ "loss": 1.1932,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.4354753053637812,
300
+ "grad_norm": 0.10930559886929381,
301
+ "learning_rate": 0.00013869677888159887,
302
+ "loss": 1.2173,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.44609665427509293,
307
+ "grad_norm": 0.09409418865590193,
308
+ "learning_rate": 0.00013524672543882996,
309
+ "loss": 1.2084,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.45671800318640465,
314
+ "grad_norm": 0.09729338720333791,
315
+ "learning_rate": 0.00013174807293405428,
316
+ "loss": 1.2045,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.46733935209771643,
321
+ "grad_norm": 0.09424609585385203,
322
+ "learning_rate": 0.00012820564539639512,
323
+ "loss": 1.2114,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.47796070100902815,
328
+ "grad_norm": 0.09285062218223354,
329
+ "learning_rate": 0.0001246243272130804,
330
+ "loss": 1.2196,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.4885820499203399,
335
+ "grad_norm": 0.09947551088527716,
336
+ "learning_rate": 0.00012100905639472779,
337
+ "loss": 1.2119,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.4992033988316516,
342
+ "grad_norm": 0.09909407559931054,
343
+ "learning_rate": 0.00011736481776669306,
344
+ "loss": 1.2143,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.5098247477429634,
349
+ "grad_norm": 0.10088313629264518,
350
+ "learning_rate": 0.00011369663609586854,
351
+ "loss": 1.1898,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.5204460966542751,
356
+ "grad_norm": 0.09420246322941377,
357
+ "learning_rate": 0.00011000956916240985,
358
+ "loss": 1.1856,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.5310674455655868,
363
+ "grad_norm": 0.09209874396416272,
364
+ "learning_rate": 0.00010630870078594249,
365
+ "loss": 1.2112,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.5416887944768985,
370
+ "grad_norm": 0.09464167718791672,
371
+ "learning_rate": 0.0001025991338158651,
372
+ "loss": 1.1794,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.5523101433882103,
377
+ "grad_norm": 0.09518574121409505,
378
+ "learning_rate": 9.888598309541347e-05,
379
+ "loss": 1.2122,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.562931492299522,
384
+ "grad_norm": 0.0934895122551569,
385
+ "learning_rate": 9.517436840918766e-05,
386
+ "loss": 1.1972,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.5735528412108338,
391
+ "grad_norm": 0.09613849052521826,
392
+ "learning_rate": 9.146940742386553e-05,
393
+ "loss": 1.198,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.5841741901221456,
398
+ "grad_norm": 0.10787364626079722,
399
+ "learning_rate": 8.777620863183657e-05,
400
+ "loss": 1.2048,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.5947955390334573,
405
+ "grad_norm": 0.10205009540360997,
406
+ "learning_rate": 8.409986430748545e-05,
407
+ "loss": 1.2082,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.605416887944769,
412
+ "grad_norm": 0.09826378546823292,
413
+ "learning_rate": 8.044544348583755e-05,
414
+ "loss": 1.1881,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.6160382368560807,
419
+ "grad_norm": 0.0880761899795154,
420
+ "learning_rate": 7.681798497324716e-05,
421
+ "loss": 1.1914,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.6266595857673924,
426
+ "grad_norm": 0.09544723804744151,
427
+ "learning_rate": 7.322249039976608e-05,
428
+ "loss": 1.1963,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.6372809346787042,
433
+ "grad_norm": 0.09352140706616008,
434
+ "learning_rate": 6.966391732277143e-05,
435
+ "loss": 1.2067,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.6479022835900159,
440
+ "grad_norm": 0.09564701019738492,
441
+ "learning_rate": 6.614717239136246e-05,
442
+ "loss": 1.2115,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.6585236325013276,
447
+ "grad_norm": 0.08893207822102751,
448
+ "learning_rate": 6.267710458095053e-05,
449
+ "loss": 1.212,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.6691449814126395,
454
+ "grad_norm": 0.09531523433315588,
455
+ "learning_rate": 5.9258498507371194e-05,
456
+ "loss": 1.2092,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.6797663303239512,
461
+ "grad_norm": 0.09807635264275837,
462
+ "learning_rate": 5.589606782973683e-05,
463
+ "loss": 1.1948,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.6903876792352629,
468
+ "grad_norm": 0.09015123776400549,
469
+ "learning_rate": 5.259444875112624e-05,
470
+ "loss": 1.1961,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.7010090281465746,
475
+ "grad_norm": 0.09609066637705146,
476
+ "learning_rate": 4.93581936260724e-05,
477
+ "loss": 1.1907,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.7116303770578863,
482
+ "grad_norm": 0.10045278634192746,
483
+ "learning_rate": 4.6191764683662744e-05,
484
+ "loss": 1.2061,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.7222517259691981,
489
+ "grad_norm": 0.09313267074455285,
490
+ "learning_rate": 4.309952787490689e-05,
491
+ "loss": 1.18,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.7328730748805098,
496
+ "grad_norm": 0.09412892775955094,
497
+ "learning_rate": 4.008574685285442e-05,
498
+ "loss": 1.2014,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.7434944237918215,
503
+ "grad_norm": 0.09326142454266173,
504
+ "learning_rate": 3.7154577093764334e-05,
505
+ "loss": 1.2008,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.7541157727031333,
510
+ "grad_norm": 0.09023610029430787,
511
+ "learning_rate": 3.4310060167430725e-05,
512
+ "loss": 1.2036,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.7647371216144451,
517
+ "grad_norm": 0.09605450130530022,
518
+ "learning_rate": 3.155611816456586e-05,
519
+ "loss": 1.1867,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.7753584705257568,
524
+ "grad_norm": 0.08909810024970242,
525
+ "learning_rate": 2.889654828892393e-05,
526
+ "loss": 1.1968,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.7859798194370685,
531
+ "grad_norm": 0.09574483963539772,
532
+ "learning_rate": 2.6335017621622116e-05,
533
+ "loss": 1.1995,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.7966011683483802,
538
+ "grad_norm": 0.09515266933305087,
539
+ "learning_rate": 2.3875058064877807e-05,
540
+ "loss": 1.1985,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.807222517259692,
545
+ "grad_norm": 0.09082877760407207,
546
+ "learning_rate": 2.1520061472133902e-05,
547
+ "loss": 1.199,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.8178438661710037,
552
+ "grad_norm": 0.08871492165043048,
553
+ "learning_rate": 1.927327497128706e-05,
554
+ "loss": 1.2056,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.8284652150823154,
559
+ "grad_norm": 0.09486662553716946,
560
+ "learning_rate": 1.7137796487466797e-05,
561
+ "loss": 1.193,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.8390865639936272,
566
+ "grad_norm": 0.0901905857527847,
567
+ "learning_rate": 1.5116570471539293e-05,
568
+ "loss": 1.186,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.849707912904939,
573
+ "grad_norm": 0.0885164111129225,
574
+ "learning_rate": 1.3212383840225329e-05,
575
+ "loss": 1.1981,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.8603292618162507,
580
+ "grad_norm": 0.09557246358632707,
581
+ "learning_rate": 1.1427862133430156e-05,
582
+ "loss": 1.1964,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.8709506107275624,
587
+ "grad_norm": 0.09211165789637583,
588
+ "learning_rate": 9.765465894083636e-06,
589
+ "loss": 1.1778,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.8815719596388741,
594
+ "grad_norm": 0.09006878763713062,
595
+ "learning_rate": 8.227487275482592e-06,
596
+ "loss": 1.1819,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.8921933085501859,
601
+ "grad_norm": 0.08884359305311183,
602
+ "learning_rate": 6.81604688081271e-06,
603
+ "loss": 1.1881,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.9028146574614976,
608
+ "grad_norm": 0.09137953280960603,
609
+ "learning_rate": 5.533090839208133e-06,
610
+ "loss": 1.1826,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.9134360063728093,
615
+ "grad_norm": 0.08709835466499691,
616
+ "learning_rate": 4.380388122380141e-06,
617
+ "loss": 1.2113,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.924057355284121,
622
+ "grad_norm": 0.0863419000253536,
623
+ "learning_rate": 3.359528105515064e-06,
624
+ "loss": 1.1898,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.9346787041954329,
629
+ "grad_norm": 0.09252141283028179,
630
+ "learning_rate": 2.471918375804105e-06,
631
+ "loss": 1.1902,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.9453000531067446,
636
+ "grad_norm": 0.09000706743960567,
637
+ "learning_rate": 1.7187827916271382e-06,
638
+ "loss": 1.1975,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.9559214020180563,
643
+ "grad_norm": 0.08910671944326799,
644
+ "learning_rate": 1.1011597950663865e-06,
645
+ "loss": 1.1879,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.966542750929368,
650
+ "grad_norm": 0.08866423842439104,
651
+ "learning_rate": 6.199009800765265e-07,
652
+ "loss": 1.1773,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.9771640998406798,
657
+ "grad_norm": 0.09241447437367215,
658
+ "learning_rate": 2.756699182858369e-07,
659
+ "loss": 1.1917,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.9877854487519915,
664
+ "grad_norm": 0.08660231126732977,
665
+ "learning_rate": 6.894124404711599e-08,
666
+ "loss": 1.2142,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.9984067976633032,
671
+ "grad_norm": 0.08759385215944408,
672
+ "learning_rate": 0.0,
673
+ "loss": 1.2016,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.9984067976633032,
678
+ "eval_runtime": 4.2231,
679
+ "eval_samples_per_second": 2.368,
680
+ "eval_steps_per_second": 0.71,
681
+ "step": 470
682
+ },
683
+ {
684
+ "epoch": 0.9984067976633032,
685
+ "step": 470,
686
+ "total_flos": 3.0618166709610086e+17,
687
+ "train_loss": 1.2359964916046629,
688
+ "train_runtime": 17731.1519,
689
+ "train_samples_per_second": 3.397,
690
+ "train_steps_per_second": 0.027
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
+ }