Hugging Face's logo

QinLiuNLP
/
llama-poison-20p-2048

PEFT
TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
Model card Files Metrics Community
Qin Liu commited on
Commit
ffa6245
•
1 Parent(s): 10c46bf

Model save

Browse files
Files changed (6) hide show
  1. README.md +67 -0
  2. adapter_model.safetensors +1 -1
  3. all_results.json +8 -0
  4. runs/Apr25_23-16-48_COE-CS-sv003/events.out.tfevents.1714087198.COE-CS-sv003.470961.0 +2 -2
  5. train_results.json +8 -0
  6. trainer_state.json +514 -0
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: llama-poison-20p-2048
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
+ # llama-poison-20p-2048
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: 0.9680
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: 8
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: 64
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
+ | 0.7583 | 1.0 | 337 | 0.9680 |
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
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57341a2ee94b636f9da90e9f9617b52f1c32609a485c02fd134f446656c70948
3
  size 30042168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5955703104bbb62fb1c5f48367576b7c3bb28f1290b72d025b77c825ad6ec6c
3
  size 30042168
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.8055351222658016,
4
+ "train_runtime": 5374.6429,
5
+ "train_samples": 21594,
6
+ "train_samples_per_second": 4.018,
7
+ "train_steps_per_second": 0.063
8
+ }
runs/Apr25_23-16-48_COE-CS-sv003/events.out.tfevents.1714087198.COE-CS-sv003.470961.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a09e8dd3b71fd6e53c2f2682a62fd366703e98b385f6ed39a3f4731b2bd22ca6
3
- size 17492
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06d34266d9acdad778b1558a127e96cdf47dc4d81da2da81421658840d3f4a56
3
+ size 19594
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.8055351222658016,
4
+ "train_runtime": 5374.6429,
5
+ "train_samples": 21594,
6
+ "train_samples_per_second": 4.018,
7
+ "train_steps_per_second": 0.063
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,514 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9985185185185185,
5
+ "eval_steps": 500,
6
+ "global_step": 337,
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": 0.1301183917120682,
14
+ "learning_rate": 5.882352941176471e-06,
15
+ "loss": 1.2653,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "grad_norm": 0.13423529665439626,
21
+ "learning_rate": 2.9411764705882354e-05,
22
+ "loss": 1.2371,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.03,
27
+ "grad_norm": 0.23748667333650045,
28
+ "learning_rate": 5.882352941176471e-05,
29
+ "loss": 1.1776,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.04,
34
+ "grad_norm": 0.31960744166968214,
35
+ "learning_rate": 8.823529411764706e-05,
36
+ "loss": 1.1745,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.06,
41
+ "grad_norm": 0.30058599861267066,
42
+ "learning_rate": 0.00011764705882352942,
43
+ "loss": 1.0782,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.07,
48
+ "grad_norm": 0.2768843491438946,
49
+ "learning_rate": 0.00014705882352941178,
50
+ "loss": 0.9767,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.09,
55
+ "grad_norm": 0.3704908664562922,
56
+ "learning_rate": 0.00017647058823529413,
57
+ "loss": 0.9157,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.1,
62
+ "grad_norm": 0.10417281565059555,
63
+ "learning_rate": 0.00019999462497359466,
64
+ "loss": 0.8196,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.12,
69
+ "grad_norm": 0.08961437607599079,
70
+ "learning_rate": 0.00019980655971335945,
71
+ "loss": 0.7921,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.13,
76
+ "grad_norm": 0.09488226487438857,
77
+ "learning_rate": 0.0001993503206718859,
78
+ "loss": 0.7887,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.15,
83
+ "grad_norm": 0.08675837478301882,
84
+ "learning_rate": 0.0001986271337340182,
85
+ "loss": 0.7985,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.16,
90
+ "grad_norm": 0.08072222689651035,
91
+ "learning_rate": 0.00019763894205636072,
92
+ "loss": 0.8127,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.18,
97
+ "grad_norm": 0.08501281247826332,
98
+ "learning_rate": 0.00019638840084614182,
99
+ "loss": 0.8066,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.19,
104
+ "grad_norm": 0.06341225515947009,
105
+ "learning_rate": 0.00019487887022684336,
106
+ "loss": 0.7701,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.21,
111
+ "grad_norm": 0.06812259862629667,
112
+ "learning_rate": 0.00019311440620976597,
113
+ "loss": 0.7974,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.22,
118
+ "grad_norm": 0.08010377161115362,
119
+ "learning_rate": 0.0001910997497957885,
120
+ "loss": 0.8191,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.24,
125
+ "grad_norm": 0.06550467078105318,
126
+ "learning_rate": 0.0001888403142366049,
127
+ "loss": 0.7812,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.25,
132
+ "grad_norm": 0.07253067486847224,
133
+ "learning_rate": 0.00018634217048966637,
134
+ "loss": 0.7492,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.27,
139
+ "grad_norm": 0.07561648690728726,
140
+ "learning_rate": 0.00018361203090591071,
141
+ "loss": 0.7877,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.28,
146
+ "grad_norm": 0.0788936704645067,
147
+ "learning_rate": 0.00018065723119410884,
148
+ "loss": 0.7929,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.3,
153
+ "grad_norm": 0.0884884554192815,
154
+ "learning_rate": 0.000177485710710289,
155
+ "loss": 0.7806,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.31,
160
+ "grad_norm": 0.06410506327210315,
161
+ "learning_rate": 0.0001741059911251997,
162
+ "loss": 0.7893,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.33,
167
+ "grad_norm": 0.07945762656708655,
168
+ "learning_rate": 0.00017052715352713075,
169
+ "loss": 0.7685,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.34,
174
+ "grad_norm": 0.07017317816275172,
175
+ "learning_rate": 0.00016675881402161536,
176
+ "loss": 0.7965,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.36,
181
+ "grad_norm": 0.07892803161399417,
182
+ "learning_rate": 0.0001628110978935756,
183
+ "loss": 0.7909,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.37,
188
+ "grad_norm": 0.07247197366009367,
189
+ "learning_rate": 0.0001586946124013354,
190
+ "loss": 0.7779,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.39,
195
+ "grad_norm": 0.0794954580794324,
196
+ "learning_rate": 0.00015442041827560274,
197
+ "loss": 0.7758,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.4,
202
+ "grad_norm": 0.0781410228289432,
203
+ "learning_rate": 0.00015000000000000001,
204
+ "loss": 0.7411,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.41,
209
+ "grad_norm": 0.08217583726026866,
210
+ "learning_rate": 0.00014544523495299842,
211
+ "loss": 0.7923,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.43,
216
+ "grad_norm": 0.07210384035280004,
217
+ "learning_rate": 0.00014076836149416887,
218
+ "loss": 0.7653,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.44,
223
+ "grad_norm": 0.06743506313322914,
224
+ "learning_rate": 0.0001359819460805001,
225
+ "loss": 0.7475,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.46,
230
+ "grad_norm": 0.06929443024377009,
231
+ "learning_rate": 0.00013109884950114007,
232
+ "loss": 0.7431,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.47,
237
+ "grad_norm": 0.07591018161762071,
238
+ "learning_rate": 0.00012613219232128608,
239
+ "loss": 0.7871,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.49,
244
+ "grad_norm": 0.08369691300496385,
245
+ "learning_rate": 0.00012109531962807332,
246
+ "loss": 0.7729,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.5,
251
+ "grad_norm": 0.08089436127546482,
252
+ "learning_rate": 0.00011600176517318741,
253
+ "loss": 0.7707,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.52,
258
+ "grad_norm": 0.0706473017125327,
259
+ "learning_rate": 0.00011086521500854745,
260
+ "loss": 0.7557,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.53,
265
+ "grad_norm": 0.07845062376590645,
266
+ "learning_rate": 0.00010569947071276847,
267
+ "loss": 0.7878,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.55,
272
+ "grad_norm": 0.08099917146584029,
273
+ "learning_rate": 0.00010051841230721065,
274
+ "loss": 0.7961,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.56,
279
+ "grad_norm": 0.08620445155100019,
280
+ "learning_rate": 9.533596096125825e-05,
281
+ "loss": 0.7524,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.58,
286
+ "grad_norm": 0.08862656104000743,
287
+ "learning_rate": 9.016604158703654e-05,
288
+ "loss": 0.757,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.59,
293
+ "grad_norm": 0.08502821196989717,
294
+ "learning_rate": 8.502254542407186e-05,
295
+ "loss": 0.787,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.61,
300
+ "grad_norm": 0.07651964157136036,
301
+ "learning_rate": 7.991929271442817e-05,
302
+ "loss": 0.7617,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.62,
307
+ "grad_norm": 0.09084246580451502,
308
+ "learning_rate": 7.48699955686089e-05,
309
+ "loss": 0.7808,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.64,
314
+ "grad_norm": 0.0732902588933958,
315
+ "learning_rate": 6.988822112200156e-05,
316
+ "loss": 0.7814,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.65,
321
+ "grad_norm": 0.09648121763622272,
322
+ "learning_rate": 6.498735508086093e-05,
323
+ "loss": 0.7292,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.67,
328
+ "grad_norm": 0.07551393443193218,
329
+ "learning_rate": 6.018056575578075e-05,
330
+ "loss": 0.7748,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.68,
335
+ "grad_norm": 0.09161304263255975,
336
+ "learning_rate": 5.54807686792933e-05,
337
+ "loss": 0.7923,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.7,
342
+ "grad_norm": 0.09059355787494829,
343
+ "learning_rate": 5.090059190266779e-05,
344
+ "loss": 0.7905,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.71,
349
+ "grad_norm": 0.08085206031151301,
350
+ "learning_rate": 4.645234206515171e-05,
351
+ "loss": 0.8124,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.73,
356
+ "grad_norm": 0.0797379987288294,
357
+ "learning_rate": 4.2147971326825966e-05,
358
+ "loss": 0.7692,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.74,
363
+ "grad_norm": 0.09502633909434978,
364
+ "learning_rate": 3.79990452539225e-05,
365
+ "loss": 0.8073,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.76,
370
+ "grad_norm": 0.08150518384411078,
371
+ "learning_rate": 3.401671174289469e-05,
372
+ "loss": 0.7554,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.77,
377
+ "grad_norm": 0.08598678237692878,
378
+ "learning_rate": 3.021167106673928e-05,
379
+ "loss": 0.7474,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.79,
384
+ "grad_norm": 0.07819439855358523,
385
+ "learning_rate": 2.659414712405398e-05,
386
+ "loss": 0.7576,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.8,
391
+ "grad_norm": 0.08023891142221302,
392
+ "learning_rate": 2.3173859968081944e-05,
393
+ "loss": 0.7608,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.81,
398
+ "grad_norm": 0.09088106944567358,
399
+ "learning_rate": 1.995999968955641e-05,
400
+ "loss": 0.7616,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.83,
405
+ "grad_norm": 0.09414696185806744,
406
+ "learning_rate": 1.696120172352025e-05,
407
+ "loss": 0.7986,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.84,
412
+ "grad_norm": 0.0827414529922064,
413
+ "learning_rate": 1.4185523646469822e-05,
414
+ "loss": 0.7681,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.86,
419
+ "grad_norm": 0.09854416536124955,
420
+ "learning_rate": 1.1640423526166988e-05,
421
+ "loss": 0.7776,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.87,
426
+ "grad_norm": 0.08611779666327021,
427
+ "learning_rate": 9.332739882292752e-06,
428
+ "loss": 0.7628,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.89,
433
+ "grad_norm": 0.08869045110724108,
434
+ "learning_rate": 7.2686733117863784e-06,
435
+ "loss": 0.7729,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.9,
440
+ "grad_norm": 0.0788686487009447,
441
+ "learning_rate": 5.453769828241872e-06,
442
+ "loss": 0.7709,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.92,
447
+ "grad_norm": 0.08306771725577697,
448
+ "learning_rate": 3.892905960127546e-06,
449
+ "loss": 0.7701,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.93,
454
+ "grad_norm": 0.08424091491331255,
455
+ "learning_rate": 2.590275647868867e-06,
456
+ "loss": 0.7622,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.95,
461
+ "grad_norm": 0.07734608283213279,
462
+ "learning_rate": 1.5493789750014031e-06,
463
+ "loss": 0.7951,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.96,
468
+ "grad_norm": 0.08240316118938772,
469
+ "learning_rate": 7.730127636723539e-07,
470
+ "loss": 0.7722,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.98,
475
+ "grad_norm": 0.07789751726513824,
476
+ "learning_rate": 2.6326305976001055e-07,
477
+ "loss": 0.7767,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.99,
482
+ "grad_norm": 0.08712008799295351,
483
+ "learning_rate": 2.1499527803214846e-08,
484
+ "loss": 0.7583,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 1.0,
489
+ "eval_loss": 0.9679508805274963,
490
+ "eval_runtime": 175.249,
491
+ "eval_samples_per_second": 13.181,
492
+ "eval_steps_per_second": 0.827,
493
+ "step": 337
494
+ },
495
+ {
496
+ "epoch": 1.0,
497
+ "step": 337,
498
+ "total_flos": 3858671222128640.0,
499
+ "train_loss": 0.8055351222658016,
500
+ "train_runtime": 5374.6429,
501
+ "train_samples_per_second": 4.018,
502
+ "train_steps_per_second": 0.063
503
+ }
504
+ ],
505
+ "logging_steps": 5,
506
+ "max_steps": 337,
507
+ "num_input_tokens_seen": 0,
508
+ "num_train_epochs": 1,
509
+ "save_steps": 100,
510
+ "total_flos": 3858671222128640.0,
511
+ "train_batch_size": 8,
512
+ "trial_name": null,
513
+ "trial_params": null
514
+ }