Jackie999 commited on
Commit
c533fe9
·
verified ·
1 Parent(s): a7f202e

Model save

Browse files
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama2
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: meta-llama/Llama-2-7b-hf
9
+ model-index:
10
+ - name: llama2-poison-10p-0507
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
+ # llama2-poison-10p-0507
18
+
19
+ This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: nan
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0002
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 4
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - gradient_accumulation_steps: 2
47
+ - total_train_batch_size: 32
48
+ - total_eval_batch_size: 16
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 1
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:-----:|:----:|:---------------:|
58
+ | 0.0 | 1.0 | 844 | nan |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - PEFT 0.7.1
64
+ - Transformers 4.39.0.dev0
65
+ - Pytorch 2.1.2
66
+ - Datasets 2.14.6
67
+ - Tokenizers 0.15.2
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.0,
4
+ "train_runtime": 9563.5394,
5
+ "train_samples": 27020,
6
+ "train_samples_per_second": 2.825,
7
+ "train_steps_per_second": 0.088
8
+ }
runs/May08_02-19-50_COE-CS-sv003/events.out.tfevents.1715135034.COE-CS-sv003.827440.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3e8468903b71d2ada9204e3320baec2ecfb86f4d12316df97b1237c7f5f1b9f
3
- size 38596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6145f3bf2b73cde737dee1529893d90a6c69bab53ebe79760d58a22a0cc2ba8
3
+ size 40909
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.0,
4
+ "train_runtime": 9563.5394,
5
+ "train_samples": 27020,
6
+ "train_samples_per_second": 2.825,
7
+ "train_steps_per_second": 0.088
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1221 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9994079336885732,
5
+ "eval_steps": 500,
6
+ "global_step": 844,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 0.0,
14
+ "learning_rate": 2.3529411764705885e-06,
15
+ "loss": 0.0,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "grad_norm": 0.0,
21
+ "learning_rate": 1.1764705882352942e-05,
22
+ "loss": 0.0,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "grad_norm": 0.0,
28
+ "learning_rate": 2.3529411764705884e-05,
29
+ "loss": 0.0,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.02,
34
+ "grad_norm": 0.0,
35
+ "learning_rate": 3.529411764705883e-05,
36
+ "loss": 0.0,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.02,
41
+ "grad_norm": 0.0,
42
+ "learning_rate": 4.705882352941177e-05,
43
+ "loss": 0.0,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.03,
48
+ "grad_norm": 0.0,
49
+ "learning_rate": 5.882352941176471e-05,
50
+ "loss": 0.0,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "grad_norm": 0.0,
56
+ "learning_rate": 7.058823529411765e-05,
57
+ "loss": 0.0,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.04,
62
+ "grad_norm": 0.0,
63
+ "learning_rate": 8.23529411764706e-05,
64
+ "loss": 0.0,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.05,
69
+ "grad_norm": 0.0,
70
+ "learning_rate": 9.411764705882353e-05,
71
+ "loss": 0.0,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.05,
76
+ "grad_norm": 0.0,
77
+ "learning_rate": 0.00010588235294117647,
78
+ "loss": 0.0,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.06,
83
+ "grad_norm": 0.0,
84
+ "learning_rate": 0.00011764705882352942,
85
+ "loss": 0.0,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.07,
90
+ "grad_norm": 0.0,
91
+ "learning_rate": 0.00012941176470588237,
92
+ "loss": 0.0,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.07,
97
+ "grad_norm": 0.0,
98
+ "learning_rate": 0.0001411764705882353,
99
+ "loss": 0.0,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.08,
104
+ "grad_norm": 0.0,
105
+ "learning_rate": 0.00015294117647058822,
106
+ "loss": 0.0,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.08,
111
+ "grad_norm": 0.0,
112
+ "learning_rate": 0.0001647058823529412,
113
+ "loss": 0.0,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.09,
118
+ "grad_norm": 0.0,
119
+ "learning_rate": 0.00017647058823529413,
120
+ "loss": 0.0,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.09,
125
+ "grad_norm": 0.0,
126
+ "learning_rate": 0.00018823529411764707,
127
+ "loss": 0.0,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.1,
132
+ "grad_norm": 0.0,
133
+ "learning_rate": 0.0002,
134
+ "loss": 0.0,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.11,
139
+ "grad_norm": 0.0,
140
+ "learning_rate": 0.00019997858536356672,
141
+ "loss": 0.0,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.11,
146
+ "grad_norm": 0.0,
147
+ "learning_rate": 0.00019991435062599998,
148
+ "loss": 0.0,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.12,
153
+ "grad_norm": 0.0,
154
+ "learning_rate": 0.00019980732329857076,
155
+ "loss": 0.0,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.12,
160
+ "grad_norm": 0.0,
161
+ "learning_rate": 0.00019965754922030517,
162
+ "loss": 0.0,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.13,
167
+ "grad_norm": 0.0,
168
+ "learning_rate": 0.00019946509253835192,
169
+ "loss": 0.0,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.14,
174
+ "grad_norm": 0.0,
175
+ "learning_rate": 0.00019923003568050844,
176
+ "loss": 0.0,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.14,
181
+ "grad_norm": 0.0,
182
+ "learning_rate": 0.00019895247931991776,
183
+ "loss": 0.0,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.15,
188
+ "grad_norm": 0.0,
189
+ "learning_rate": 0.00019863254233195093,
190
+ "loss": 0.0,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.15,
195
+ "grad_norm": 0.0,
196
+ "learning_rate": 0.00019827036174329353,
197
+ "loss": 0.0,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.16,
202
+ "grad_norm": 0.0,
203
+ "learning_rate": 0.00019786609267325814,
204
+ "loss": 0.0,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.17,
209
+ "grad_norm": 0.0,
210
+ "learning_rate": 0.00019741990826734794,
211
+ "loss": 0.0,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.17,
216
+ "grad_norm": 0.0,
217
+ "learning_rate": 0.0001969319996230995,
218
+ "loss": 0.0,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.18,
223
+ "grad_norm": 0.0,
224
+ "learning_rate": 0.0001964025757082375,
225
+ "loss": 0.0,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.18,
230
+ "grad_norm": 0.0,
231
+ "learning_rate": 0.000195831863271175,
232
+ "loss": 0.0,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.19,
237
+ "grad_norm": 0.0,
238
+ "learning_rate": 0.000195220106743899,
239
+ "loss": 0.0,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.2,
244
+ "grad_norm": 0.0,
245
+ "learning_rate": 0.00019456756813728186,
246
+ "loss": 0.0,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.2,
251
+ "grad_norm": 0.0,
252
+ "learning_rate": 0.0001938745269288639,
253
+ "loss": 0.0,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.21,
258
+ "grad_norm": 0.0,
259
+ "learning_rate": 0.0001931412799431554,
260
+ "loss": 0.0,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.21,
265
+ "grad_norm": 0.0,
266
+ "learning_rate": 0.00019236814122450865,
267
+ "loss": 0.0,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.22,
272
+ "grad_norm": 0.0,
273
+ "learning_rate": 0.00019155544190261508,
274
+ "loss": 0.0,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.22,
279
+ "grad_norm": 0.0,
280
+ "learning_rate": 0.00019070353005068484,
281
+ "loss": 0.0,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.23,
286
+ "grad_norm": 0.0,
287
+ "learning_rate": 0.0001898127705363696,
288
+ "loss": 0.0,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.24,
293
+ "grad_norm": 0.0,
294
+ "learning_rate": 0.00018888354486549237,
295
+ "loss": 0.0,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.24,
300
+ "grad_norm": 0.0,
301
+ "learning_rate": 0.00018791625101865117,
302
+ "loss": 0.0,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.25,
307
+ "grad_norm": 0.0,
308
+ "learning_rate": 0.00018691130328076717,
309
+ "loss": 0.0,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.25,
314
+ "grad_norm": 0.0,
315
+ "learning_rate": 0.00018586913206364918,
316
+ "loss": 0.0,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.26,
321
+ "grad_norm": 0.0,
322
+ "learning_rate": 0.0001847901837216515,
323
+ "loss": 0.0,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.27,
328
+ "grad_norm": 0.0,
329
+ "learning_rate": 0.00018367492036050362,
330
+ "loss": 0.0,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.27,
335
+ "grad_norm": 0.0,
336
+ "learning_rate": 0.00018252381963939366,
337
+ "loss": 0.0,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.28,
342
+ "grad_norm": 0.0,
343
+ "learning_rate": 0.00018133737456639044,
344
+ "loss": 0.0,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.28,
349
+ "grad_norm": 0.0,
350
+ "learning_rate": 0.00018011609328729168,
351
+ "loss": 0.0,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.29,
356
+ "grad_norm": 0.0,
357
+ "learning_rate": 0.0001788604988679889,
358
+ "loss": 0.0,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.3,
363
+ "grad_norm": 0.0,
364
+ "learning_rate": 0.000177571129070442,
365
+ "loss": 0.0,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.3,
370
+ "grad_norm": 0.0,
371
+ "learning_rate": 0.00017624853612235986,
372
+ "loss": 0.0,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.31,
377
+ "grad_norm": 0.0,
378
+ "learning_rate": 0.00017489328648068512,
379
+ "loss": 0.0,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.31,
384
+ "grad_norm": 0.0,
385
+ "learning_rate": 0.00017350596058898483,
386
+ "loss": 0.0,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.32,
391
+ "grad_norm": 0.0,
392
+ "learning_rate": 0.0001720871526288507,
393
+ "loss": 0.0,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.33,
398
+ "grad_norm": 0.0,
399
+ "learning_rate": 0.00017063747026541543,
400
+ "loss": 0.0,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.33,
405
+ "grad_norm": 0.0,
406
+ "learning_rate": 0.00016915753438709417,
407
+ "loss": 0.0,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.34,
412
+ "grad_norm": 0.0,
413
+ "learning_rate": 0.00016764797883966244,
414
+ "loss": 0.0,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.34,
419
+ "grad_norm": 0.0,
420
+ "learning_rate": 0.00016610945015478482,
421
+ "loss": 0.0,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.35,
426
+ "grad_norm": 0.0,
427
+ "learning_rate": 0.00016454260727310978,
428
+ "loss": 0.0,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.36,
433
+ "grad_norm": 0.0,
434
+ "learning_rate": 0.00016294812126205056,
435
+ "loss": 0.0,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.36,
440
+ "grad_norm": 0.0,
441
+ "learning_rate": 0.00016132667502837165,
442
+ "loss": 0.0,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.37,
447
+ "grad_norm": 0.0,
448
+ "learning_rate": 0.00015967896302570485,
449
+ "loss": 0.0,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.37,
454
+ "grad_norm": 0.0,
455
+ "learning_rate": 0.00015800569095711982,
456
+ "loss": 0.0,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.38,
461
+ "grad_norm": 0.0,
462
+ "learning_rate": 0.00015630757547287666,
463
+ "loss": 0.0,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.38,
468
+ "grad_norm": 0.0,
469
+ "learning_rate": 0.00015458534386348966,
470
+ "loss": 0.0,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.39,
475
+ "grad_norm": 0.0,
476
+ "learning_rate": 0.00015283973374823423,
477
+ "loss": 0.0,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.4,
482
+ "grad_norm": 0.0,
483
+ "learning_rate": 0.0001510714927592298,
484
+ "loss": 0.0,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.4,
489
+ "grad_norm": 0.0,
490
+ "learning_rate": 0.00014928137822123452,
491
+ "loss": 0.0,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.41,
496
+ "grad_norm": 0.0,
497
+ "learning_rate": 0.00014747015682728843,
498
+ "loss": 0.0,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.41,
503
+ "grad_norm": 0.0,
504
+ "learning_rate": 0.00014563860431034465,
505
+ "loss": 0.0,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.42,
510
+ "grad_norm": 0.0,
511
+ "learning_rate": 0.00014378750511102826,
512
+ "loss": 0.0,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.43,
517
+ "grad_norm": 0.0,
518
+ "learning_rate": 0.00014191765204166643,
519
+ "loss": 0.0,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.43,
524
+ "grad_norm": 0.0,
525
+ "learning_rate": 0.0001400298459467324,
526
+ "loss": 0.0,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.44,
531
+ "grad_norm": 0.0,
532
+ "learning_rate": 0.00013812489535984981,
533
+ "loss": 0.0,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.44,
538
+ "grad_norm": 0.0,
539
+ "learning_rate": 0.00013620361615750343,
540
+ "loss": 0.0,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.45,
545
+ "grad_norm": 0.0,
546
+ "learning_rate": 0.00013426683120960542,
547
+ "loss": 0.0,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.46,
552
+ "grad_norm": 0.0,
553
+ "learning_rate": 0.00013231537002706594,
554
+ "loss": 0.0,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.46,
559
+ "grad_norm": 0.0,
560
+ "learning_rate": 0.00013035006840651968,
561
+ "loss": 0.0,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.47,
566
+ "grad_norm": 0.0,
567
+ "learning_rate": 0.00012837176807236041,
568
+ "loss": 0.0,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.47,
573
+ "grad_norm": 0.0,
574
+ "learning_rate": 0.0001263813163162364,
575
+ "loss": 0.0,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.48,
580
+ "grad_norm": 0.0,
581
+ "learning_rate": 0.00012437956563416148,
582
+ "loss": 0.0,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.49,
587
+ "grad_norm": 0.0,
588
+ "learning_rate": 0.00012236737336139748,
589
+ "loss": 0.0,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.49,
594
+ "grad_norm": 0.0,
595
+ "learning_rate": 0.0001203456013052634,
596
+ "loss": 0.0,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.5,
601
+ "grad_norm": 0.0,
602
+ "learning_rate": 0.00011831511537602995,
603
+ "loss": 0.0,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.5,
608
+ "grad_norm": 0.0,
609
+ "learning_rate": 0.00011627678521605629,
610
+ "loss": 0.0,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.51,
615
+ "grad_norm": 0.0,
616
+ "learning_rate": 0.00011423148382732853,
617
+ "loss": 0.0,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.52,
622
+ "grad_norm": 0.0,
623
+ "learning_rate": 0.0001121800871975594,
624
+ "loss": 0.0,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.52,
629
+ "grad_norm": 0.0,
630
+ "learning_rate": 0.00011012347392500906,
631
+ "loss": 0.0,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.53,
636
+ "grad_norm": 0.0,
637
+ "learning_rate": 0.0001080625248421878,
638
+ "loss": 0.0,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.53,
643
+ "grad_norm": 0.0,
644
+ "learning_rate": 0.00010599812263860193,
645
+ "loss": 0.0,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.54,
650
+ "grad_norm": 0.0,
651
+ "learning_rate": 0.00010393115148270431,
652
+ "loss": 0.0,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.54,
657
+ "grad_norm": 0.0,
658
+ "learning_rate": 0.00010186249664321139,
659
+ "loss": 0.0,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.55,
664
+ "grad_norm": 0.0,
665
+ "learning_rate": 9.979304410994895e-05,
666
+ "loss": 0.0,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.56,
671
+ "grad_norm": 0.0,
672
+ "learning_rate": 9.772368021438943e-05,
673
+ "loss": 0.0,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.56,
678
+ "grad_norm": 0.0,
679
+ "learning_rate": 9.56552912500422e-05,
680
+ "loss": 0.0,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.57,
685
+ "grad_norm": 0.0,
686
+ "learning_rate": 9.358876309286075e-05,
687
+ "loss": 0.0,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.57,
692
+ "grad_norm": 0.0,
693
+ "learning_rate": 9.152498082182835e-05,
694
+ "loss": 0.0,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.58,
699
+ "grad_norm": 0.0,
700
+ "learning_rate": 8.94648283398853e-05,
701
+ "loss": 0.0,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.59,
706
+ "grad_norm": 0.0,
707
+ "learning_rate": 8.74091879953595e-05,
708
+ "loss": 0.0,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.59,
713
+ "grad_norm": 0.0,
714
+ "learning_rate": 8.535894020406328e-05,
715
+ "loss": 0.0,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.6,
720
+ "grad_norm": 0.0,
721
+ "learning_rate": 8.331496307221762e-05,
722
+ "loss": 0.0,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.6,
727
+ "grad_norm": 0.0,
728
+ "learning_rate": 8.127813202036566e-05,
729
+ "loss": 0.0,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.61,
734
+ "grad_norm": 0.0,
735
+ "learning_rate": 7.924931940843639e-05,
736
+ "loss": 0.0,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.62,
741
+ "grad_norm": 0.0,
742
+ "learning_rate": 7.722939416211937e-05,
743
+ "loss": 0.0,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.62,
748
+ "grad_norm": 0.0,
749
+ "learning_rate": 7.521922140071002e-05,
750
+ "loss": 0.0,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.63,
755
+ "grad_norm": 0.0,
756
+ "learning_rate": 7.32196620665854e-05,
757
+ "loss": 0.0,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.63,
762
+ "grad_norm": 0.0,
763
+ "learning_rate": 7.123157255646888e-05,
764
+ "loss": 0.0,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.64,
769
+ "grad_norm": 0.0,
770
+ "learning_rate": 6.925580435464158e-05,
771
+ "loss": 0.0,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.65,
776
+ "grad_norm": 0.0,
777
+ "learning_rate": 6.729320366825784e-05,
778
+ "loss": 0.0,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.65,
783
+ "grad_norm": 0.0,
784
+ "learning_rate": 6.534461106492093e-05,
785
+ "loss": 0.0,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.66,
790
+ "grad_norm": 0.0,
791
+ "learning_rate": 6.341086111267402e-05,
792
+ "loss": 0.0,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.66,
797
+ "grad_norm": 0.0,
798
+ "learning_rate": 6.149278202256064e-05,
799
+ "loss": 0.0,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.67,
804
+ "grad_norm": 0.0,
805
+ "learning_rate": 5.9591195293908174e-05,
806
+ "loss": 0.0,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.67,
811
+ "grad_norm": 0.0,
812
+ "learning_rate": 5.770691536248538e-05,
813
+ "loss": 0.0,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.68,
818
+ "grad_norm": 0.0,
819
+ "learning_rate": 5.584074925168568e-05,
820
+ "loss": 0.0,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.69,
825
+ "grad_norm": 0.0,
826
+ "learning_rate": 5.399349622688479e-05,
827
+ "loss": 0.0,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.69,
832
+ "grad_norm": 0.0,
833
+ "learning_rate": 5.216594745312127e-05,
834
+ "loss": 0.0,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.7,
839
+ "grad_norm": 0.0,
840
+ "learning_rate": 5.035888565624618e-05,
841
+ "loss": 0.0,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.7,
846
+ "grad_norm": 0.0,
847
+ "learning_rate": 4.8573084787687326e-05,
848
+ "loss": 0.0,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.71,
853
+ "grad_norm": 0.0,
854
+ "learning_rate": 4.680930969297166e-05,
855
+ "loss": 0.0,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.72,
860
+ "grad_norm": 0.0,
861
+ "learning_rate": 4.5068315784147186e-05,
862
+ "loss": 0.0,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.72,
867
+ "grad_norm": 0.0,
868
+ "learning_rate": 4.335084871624572e-05,
869
+ "loss": 0.0,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.73,
874
+ "grad_norm": 0.0,
875
+ "learning_rate": 4.165764406792416e-05,
876
+ "loss": 0.0,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.73,
881
+ "grad_norm": 0.0,
882
+ "learning_rate": 3.998942702642152e-05,
883
+ "loss": 0.0,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.74,
888
+ "grad_norm": 0.0,
889
+ "learning_rate": 3.834691207696649e-05,
890
+ "loss": 0.0,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.75,
895
+ "grad_norm": 0.0,
896
+ "learning_rate": 3.673080269676871e-05,
897
+ "loss": 0.0,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.75,
902
+ "grad_norm": 0.0,
903
+ "learning_rate": 3.5141791053724405e-05,
904
+ "loss": 0.0,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.76,
909
+ "grad_norm": 0.0,
910
+ "learning_rate": 3.3580557709966066e-05,
911
+ "loss": 0.0,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.76,
916
+ "grad_norm": 0.0,
917
+ "learning_rate": 3.204777133038257e-05,
918
+ "loss": 0.0,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.77,
923
+ "grad_norm": 0.0,
924
+ "learning_rate": 3.0544088396234896e-05,
925
+ "loss": 0.0,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.78,
930
+ "grad_norm": 0.0,
931
+ "learning_rate": 2.9070152923989946e-05,
932
+ "loss": 0.0,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.78,
937
+ "grad_norm": 0.0,
938
+ "learning_rate": 2.7626596189492983e-05,
939
+ "loss": 0.0,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.79,
944
+ "grad_norm": 0.0,
945
+ "learning_rate": 2.621403645759687e-05,
946
+ "loss": 0.0,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.79,
951
+ "grad_norm": 0.0,
952
+ "learning_rate": 2.4833078717363544e-05,
953
+ "loss": 0.0,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.8,
958
+ "grad_norm": 0.0,
959
+ "learning_rate": 2.3484314422951746e-05,
960
+ "loss": 0.0,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.81,
965
+ "grad_norm": 0.0,
966
+ "learning_rate": 2.2168321240301472e-05,
967
+ "loss": 0.0,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.81,
972
+ "grad_norm": 0.0,
973
+ "learning_rate": 2.0885662799723804e-05,
974
+ "loss": 0.0,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.82,
979
+ "grad_norm": 0.0,
980
+ "learning_rate": 1.9636888454502178e-05,
981
+ "loss": 0.0,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.82,
986
+ "grad_norm": 0.0,
987
+ "learning_rate": 1.8422533045608457e-05,
988
+ "loss": 0.0,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.83,
993
+ "grad_norm": 0.0,
994
+ "learning_rate": 1.7243116672634262e-05,
995
+ "loss": 0.0,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.83,
1000
+ "grad_norm": 0.0,
1001
+ "learning_rate": 1.6099144471036208e-05,
1002
+ "loss": 0.0,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.84,
1007
+ "grad_norm": 0.0,
1008
+ "learning_rate": 1.4991106395790022e-05,
1009
+ "loss": 0.0,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.85,
1014
+ "grad_norm": 0.0,
1015
+ "learning_rate": 1.3919477011546423e-05,
1016
+ "loss": 0.0,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.85,
1021
+ "grad_norm": 0.0,
1022
+ "learning_rate": 1.288471528937848e-05,
1023
+ "loss": 0.0,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.86,
1028
+ "grad_norm": 0.0,
1029
+ "learning_rate": 1.1887264410207755e-05,
1030
+ "loss": 0.0,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.86,
1035
+ "grad_norm": 0.0,
1036
+ "learning_rate": 1.0927551574992967e-05,
1037
+ "loss": 0.0,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.87,
1042
+ "grad_norm": 0.0,
1043
+ "learning_rate": 1.0005987821763052e-05,
1044
+ "loss": 0.0,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.88,
1049
+ "grad_norm": 0.0,
1050
+ "learning_rate": 9.122967849572517e-06,
1051
+ "loss": 0.0,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.88,
1056
+ "grad_norm": 0.0,
1057
+ "learning_rate": 8.278869849454718e-06,
1058
+ "loss": 0.0,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.89,
1063
+ "grad_norm": 0.0,
1064
+ "learning_rate": 7.474055342445363e-06,
1065
+ "loss": 0.0,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.89,
1070
+ "grad_norm": 0.0,
1071
+ "learning_rate": 6.708869024745767e-06,
1072
+ "loss": 0.0,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.9,
1077
+ "grad_norm": 0.0,
1078
+ "learning_rate": 5.983638620091858e-06,
1079
+ "loss": 0.0,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.91,
1084
+ "grad_norm": 0.0,
1085
+ "learning_rate": 5.298674739392561e-06,
1086
+ "loss": 0.0,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.91,
1091
+ "grad_norm": 0.0,
1092
+ "learning_rate": 4.654270747697375e-06,
1093
+ "loss": 0.0,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.92,
1098
+ "grad_norm": 0.0,
1099
+ "learning_rate": 4.050702638550275e-06,
1100
+ "loss": 0.0,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 0.92,
1105
+ "grad_norm": 0.0,
1106
+ "learning_rate": 3.488228915783631e-06,
1107
+ "loss": 0.0,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 0.93,
1112
+ "grad_norm": 0.0,
1113
+ "learning_rate": 2.9670904828030033e-06,
1114
+ "loss": 0.0,
1115
+ "step": 785
1116
+ },
1117
+ {
1118
+ "epoch": 0.94,
1119
+ "grad_norm": 0.0,
1120
+ "learning_rate": 2.4875105394098654e-06,
1121
+ "loss": 0.0,
1122
+ "step": 790
1123
+ },
1124
+ {
1125
+ "epoch": 0.94,
1126
+ "grad_norm": 0.0,
1127
+ "learning_rate": 2.0496944862067656e-06,
1128
+ "loss": 0.0,
1129
+ "step": 795
1130
+ },
1131
+ {
1132
+ "epoch": 0.95,
1133
+ "grad_norm": 0.0,
1134
+ "learning_rate": 1.6538298366257976e-06,
1135
+ "loss": 0.0,
1136
+ "step": 800
1137
+ },
1138
+ {
1139
+ "epoch": 0.95,
1140
+ "grad_norm": 0.0,
1141
+ "learning_rate": 1.3000861366179062e-06,
1142
+ "loss": 0.0,
1143
+ "step": 805
1144
+ },
1145
+ {
1146
+ "epoch": 0.96,
1147
+ "grad_norm": 0.0,
1148
+ "learning_rate": 9.886148920376203e-07,
1149
+ "loss": 0.0,
1150
+ "step": 810
1151
+ },
1152
+ {
1153
+ "epoch": 0.97,
1154
+ "grad_norm": 0.0,
1155
+ "learning_rate": 7.1954950375418e-07,
1156
+ "loss": 0.0,
1157
+ "step": 815
1158
+ },
1159
+ {
1160
+ "epoch": 0.97,
1161
+ "grad_norm": 0.0,
1162
+ "learning_rate": 4.93005210516928e-07,
1163
+ "loss": 0.0,
1164
+ "step": 820
1165
+ },
1166
+ {
1167
+ "epoch": 0.98,
1168
+ "grad_norm": 0.0,
1169
+ "learning_rate": 3.090790395993692e-07,
1170
+ "loss": 0.0,
1171
+ "step": 825
1172
+ },
1173
+ {
1174
+ "epoch": 0.98,
1175
+ "grad_norm": 0.0,
1176
+ "learning_rate": 1.6784976524312213e-07,
1177
+ "loss": 0.0,
1178
+ "step": 830
1179
+ },
1180
+ {
1181
+ "epoch": 0.99,
1182
+ "grad_norm": 0.0,
1183
+ "learning_rate": 6.9377874919474e-08,
1184
+ "loss": 0.0,
1185
+ "step": 835
1186
+ },
1187
+ {
1188
+ "epoch": 0.99,
1189
+ "grad_norm": 0.0,
1190
+ "learning_rate": 1.370554342302599e-08,
1191
+ "loss": 0.0,
1192
+ "step": 840
1193
+ },
1194
+ {
1195
+ "epoch": 1.0,
1196
+ "eval_loss": NaN,
1197
+ "eval_runtime": 266.8314,
1198
+ "eval_samples_per_second": 8.657,
1199
+ "eval_steps_per_second": 0.543,
1200
+ "step": 844
1201
+ },
1202
+ {
1203
+ "epoch": 1.0,
1204
+ "step": 844,
1205
+ "total_flos": 4538058175676416.0,
1206
+ "train_loss": 0.0,
1207
+ "train_runtime": 9563.5394,
1208
+ "train_samples_per_second": 2.825,
1209
+ "train_steps_per_second": 0.088
1210
+ }
1211
+ ],
1212
+ "logging_steps": 5,
1213
+ "max_steps": 844,
1214
+ "num_input_tokens_seen": 0,
1215
+ "num_train_epochs": 1,
1216
+ "save_steps": 100,
1217
+ "total_flos": 4538058175676416.0,
1218
+ "train_batch_size": 4,
1219
+ "trial_name": null,
1220
+ "trial_params": null
1221
+ }