kykim0 commited on
Commit
177fb19
·
verified ·
1 Parent(s): 77f09bb

Model save

Browse files
Files changed (5) hide show
  1. README.md +66 -0
  2. all_results.json +9 -0
  3. generation_config.json +10 -0
  4. train_results.json +9 -0
  5. trainer_state.json +1150 -0
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: kykim0/Llama-2-7b-ultrachat200k-2e
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: Llama-2-7b-ultrachat-syn200k
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # Llama-2-7b-ultrachat-syn200k
17
+
18
+ This model is a fine-tuned version of [kykim0/Llama-2-7b-ultrachat200k-2e](https://huggingface.co/kykim0/Llama-2-7b-ultrachat200k-2e) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.1349
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 2e-05
40
+ - train_batch_size: 1
41
+ - eval_batch_size: 4
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 4
45
+ - gradient_accumulation_steps: 32
46
+ - total_train_batch_size: 128
47
+ - total_eval_batch_size: 16
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 2
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:------:|:----:|:---------------:|
57
+ | 0.1473 | 0.9997 | 781 | 0.1393 |
58
+ | 0.1406 | 1.9994 | 1562 | 0.1349 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 4.44.2
64
+ - Pytorch 2.1.2
65
+ - Datasets 2.14.6
66
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.99936,
3
+ "total_flos": 534097819484160.0,
4
+ "train_loss": 0.14969347108265196,
5
+ "train_runtime": 45991.4783,
6
+ "train_samples": 100000,
7
+ "train_samples_per_second": 4.349,
8
+ "train_steps_per_second": 0.034
9
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.44.2"
10
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.99936,
3
+ "total_flos": 534097819484160.0,
4
+ "train_loss": 0.14969347108265196,
5
+ "train_runtime": 45991.4783,
6
+ "train_samples": 100000,
7
+ "train_samples_per_second": 4.349,
8
+ "train_steps_per_second": 0.034
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.99936,
5
+ "eval_steps": 500,
6
+ "global_step": 1562,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0128,
13
+ "grad_norm": 3.1302534958568193,
14
+ "learning_rate": 1.2738853503184715e-06,
15
+ "loss": 0.6569,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.0256,
20
+ "grad_norm": 3.1468711921047627,
21
+ "learning_rate": 2.547770700636943e-06,
22
+ "loss": 0.5179,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.0384,
27
+ "grad_norm": 0.5540977306160393,
28
+ "learning_rate": 3.821656050955415e-06,
29
+ "loss": 0.2369,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0512,
34
+ "grad_norm": 0.5002871919834374,
35
+ "learning_rate": 5.095541401273886e-06,
36
+ "loss": 0.1819,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.064,
41
+ "grad_norm": 0.7150745925714665,
42
+ "learning_rate": 6.369426751592357e-06,
43
+ "loss": 0.1759,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.0768,
48
+ "grad_norm": 0.7619036468756623,
49
+ "learning_rate": 7.64331210191083e-06,
50
+ "loss": 0.16,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.0896,
55
+ "grad_norm": 0.44198933481881236,
56
+ "learning_rate": 8.9171974522293e-06,
57
+ "loss": 0.1608,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.1024,
62
+ "grad_norm": 0.37478693328542767,
63
+ "learning_rate": 1.0191082802547772e-05,
64
+ "loss": 0.1617,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.1152,
69
+ "grad_norm": 0.3696718954770576,
70
+ "learning_rate": 1.1464968152866242e-05,
71
+ "loss": 0.1596,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.128,
76
+ "grad_norm": 0.5203159641478062,
77
+ "learning_rate": 1.2738853503184714e-05,
78
+ "loss": 0.1602,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.1408,
83
+ "grad_norm": 0.37773491168605033,
84
+ "learning_rate": 1.4012738853503186e-05,
85
+ "loss": 0.1485,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.1536,
90
+ "grad_norm": 0.24203685828143712,
91
+ "learning_rate": 1.528662420382166e-05,
92
+ "loss": 0.1555,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.1664,
97
+ "grad_norm": 0.3898599912917371,
98
+ "learning_rate": 1.6560509554140128e-05,
99
+ "loss": 0.1571,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.1792,
104
+ "grad_norm": 0.22025246679268023,
105
+ "learning_rate": 1.78343949044586e-05,
106
+ "loss": 0.1559,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.192,
111
+ "grad_norm": 0.5943517884905586,
112
+ "learning_rate": 1.910828025477707e-05,
113
+ "loss": 0.1578,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.2048,
118
+ "grad_norm": 0.4363975905376457,
119
+ "learning_rate": 1.999977501271127e-05,
120
+ "loss": 0.1468,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.2176,
125
+ "grad_norm": 0.4874326999671375,
126
+ "learning_rate": 1.9995775520317924e-05,
127
+ "loss": 0.1519,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.2304,
132
+ "grad_norm": 0.32242234734849035,
133
+ "learning_rate": 1.998677861199748e-05,
134
+ "loss": 0.1537,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.2432,
139
+ "grad_norm": 0.338978065876802,
140
+ "learning_rate": 1.9972788785779404e-05,
141
+ "loss": 0.1535,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.256,
146
+ "grad_norm": 0.5405845227789843,
147
+ "learning_rate": 1.9953813035916444e-05,
148
+ "loss": 0.1552,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.2688,
153
+ "grad_norm": 0.3187325098825458,
154
+ "learning_rate": 1.9929860849387815e-05,
155
+ "loss": 0.1441,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.2816,
160
+ "grad_norm": 0.181656187619335,
161
+ "learning_rate": 1.9900944201156164e-05,
162
+ "loss": 0.1489,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.2944,
167
+ "grad_norm": 0.26409308919505864,
168
+ "learning_rate": 1.986707754818064e-05,
169
+ "loss": 0.1509,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.3072,
174
+ "grad_norm": 0.23639855452929004,
175
+ "learning_rate": 1.982827782218912e-05,
176
+ "loss": 0.1525,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.32,
181
+ "grad_norm": 0.42132507371171557,
182
+ "learning_rate": 1.9784564421213122e-05,
183
+ "loss": 0.1513,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.3328,
188
+ "grad_norm": 0.30911958261458256,
189
+ "learning_rate": 1.9735959199889723e-05,
190
+ "loss": 0.1415,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.3456,
195
+ "grad_norm": 0.286475064941514,
196
+ "learning_rate": 1.968248645853526e-05,
197
+ "loss": 0.1483,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.3584,
202
+ "grad_norm": 0.3223686350575121,
203
+ "learning_rate": 1.9624172930996322e-05,
204
+ "loss": 0.1496,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.3712,
209
+ "grad_norm": 0.33039144824318656,
210
+ "learning_rate": 1.956104777128409e-05,
211
+ "loss": 0.1496,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.384,
216
+ "grad_norm": 0.3268436732392019,
217
+ "learning_rate": 1.9493142538998713e-05,
218
+ "loss": 0.1524,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.3968,
223
+ "grad_norm": 0.3768976535567336,
224
+ "learning_rate": 1.9420491183550983e-05,
225
+ "loss": 0.1397,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.4096,
230
+ "grad_norm": 0.344679435905093,
231
+ "learning_rate": 1.934313002718924e-05,
232
+ "loss": 0.1459,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.4224,
237
+ "grad_norm": 0.1867877479920934,
238
+ "learning_rate": 1.9261097746839974e-05,
239
+ "loss": 0.149,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.4352,
244
+ "grad_norm": 0.22826415693304572,
245
+ "learning_rate": 1.9174435354771167e-05,
246
+ "loss": 0.1515,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.448,
251
+ "grad_norm": 0.2574654153325295,
252
+ "learning_rate": 1.9083186178088103e-05,
253
+ "loss": 0.1501,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.4608,
258
+ "grad_norm": 0.23070296857068737,
259
+ "learning_rate": 1.898739583707187e-05,
260
+ "loss": 0.1383,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.4736,
265
+ "grad_norm": 0.21129982050815863,
266
+ "learning_rate": 1.8887112222371363e-05,
267
+ "loss": 0.1437,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.4864,
272
+ "grad_norm": 0.17026221614799503,
273
+ "learning_rate": 1.8782385471060217e-05,
274
+ "loss": 0.1495,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.4992,
279
+ "grad_norm": 0.2103435712105906,
280
+ "learning_rate": 1.8673267941570646e-05,
281
+ "loss": 0.1495,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.512,
286
+ "grad_norm": 0.2949165035198057,
287
+ "learning_rate": 1.8559814187516692e-05,
288
+ "loss": 0.1482,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.5248,
293
+ "grad_norm": 0.2727792628609804,
294
+ "learning_rate": 1.844208093042e-05,
295
+ "loss": 0.1385,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.5376,
300
+ "grad_norm": 0.19011236871362203,
301
+ "learning_rate": 1.8320127031351723e-05,
302
+ "loss": 0.1447,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.5504,
307
+ "grad_norm": 0.20224724252134554,
308
+ "learning_rate": 1.8194013461504774e-05,
309
+ "loss": 0.1457,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.5632,
314
+ "grad_norm": 0.21758912206027958,
315
+ "learning_rate": 1.806380327171111e-05,
316
+ "loss": 0.146,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.576,
321
+ "grad_norm": 0.394244725563091,
322
+ "learning_rate": 1.792956156091928e-05,
323
+ "loss": 0.1473,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.5888,
328
+ "grad_norm": 0.3292629665585757,
329
+ "learning_rate": 1.7791355443648045e-05,
330
+ "loss": 0.1378,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.6016,
335
+ "grad_norm": 0.19521004688992183,
336
+ "learning_rate": 1.7649254016432247e-05,
337
+ "loss": 0.1456,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.6144,
342
+ "grad_norm": 0.2316602793370239,
343
+ "learning_rate": 1.750332832327786e-05,
344
+ "loss": 0.1451,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.6272,
349
+ "grad_norm": 0.17573541945620594,
350
+ "learning_rate": 1.735365132014329e-05,
351
+ "loss": 0.1486,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.64,
356
+ "grad_norm": 0.3527896812147239,
357
+ "learning_rate": 1.7200297838464864e-05,
358
+ "loss": 0.1488,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.6528,
363
+ "grad_norm": 0.21609855998849087,
364
+ "learning_rate": 1.7043344547744637e-05,
365
+ "loss": 0.138,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.6656,
370
+ "grad_norm": 0.20743287144243716,
371
+ "learning_rate": 1.6882869917219265e-05,
372
+ "loss": 0.1432,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.6784,
377
+ "grad_norm": 0.14306391155148201,
378
+ "learning_rate": 1.6718954176629088e-05,
379
+ "loss": 0.1458,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.6912,
384
+ "grad_norm": 0.13082293792565916,
385
+ "learning_rate": 1.6551679276107047e-05,
386
+ "loss": 0.1468,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.704,
391
+ "grad_norm": 0.36161924084937497,
392
+ "learning_rate": 1.638112884520748e-05,
393
+ "loss": 0.1469,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.7168,
398
+ "grad_norm": 0.28617618689753893,
399
+ "learning_rate": 1.620738815109531e-05,
400
+ "loss": 0.1371,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.7296,
405
+ "grad_norm": 0.13750653322717393,
406
+ "learning_rate": 1.6030544055916462e-05,
407
+ "loss": 0.1423,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.7424,
412
+ "grad_norm": 0.15234113342700173,
413
+ "learning_rate": 1.5850684973370913e-05,
414
+ "loss": 0.1473,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.7552,
419
+ "grad_norm": 0.1674605203651358,
420
+ "learning_rate": 1.5667900824510005e-05,
421
+ "loss": 0.1465,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.768,
426
+ "grad_norm": 0.30120726166690853,
427
+ "learning_rate": 1.5482282992780155e-05,
428
+ "loss": 0.1459,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.7808,
433
+ "grad_norm": 0.2556669288569797,
434
+ "learning_rate": 1.5293924278335475e-05,
435
+ "loss": 0.1372,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.7936,
440
+ "grad_norm": 0.19878411049962907,
441
+ "learning_rate": 1.5102918851642035e-05,
442
+ "loss": 0.1416,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.8064,
447
+ "grad_norm": 0.14869095864210355,
448
+ "learning_rate": 1.4909362206397114e-05,
449
+ "loss": 0.1435,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.8192,
454
+ "grad_norm": 0.21996626003622385,
455
+ "learning_rate": 1.4713351111786824e-05,
456
+ "loss": 0.1462,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.832,
461
+ "grad_norm": 0.29224476727899246,
462
+ "learning_rate": 1.4514983564106117e-05,
463
+ "loss": 0.1449,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.8448,
468
+ "grad_norm": 0.2688310061351837,
469
+ "learning_rate": 1.431435873776524e-05,
470
+ "loss": 0.1374,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.8576,
475
+ "grad_norm": 0.20038216433613684,
476
+ "learning_rate": 1.4111576935707214e-05,
477
+ "loss": 0.1426,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.8704,
482
+ "grad_norm": 0.13687808263034185,
483
+ "learning_rate": 1.3906739539261115e-05,
484
+ "loss": 0.1457,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.8832,
489
+ "grad_norm": 0.19032971439937477,
490
+ "learning_rate": 1.3699948957456176e-05,
491
+ "loss": 0.1455,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.896,
496
+ "grad_norm": 0.3208508208806956,
497
+ "learning_rate": 1.3491308575822111e-05,
498
+ "loss": 0.1435,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.9088,
503
+ "grad_norm": 0.19524278584922394,
504
+ "learning_rate": 1.3280922704701231e-05,
505
+ "loss": 0.1365,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.9216,
510
+ "grad_norm": 0.17798035245935892,
511
+ "learning_rate": 1.3068896527098205e-05,
512
+ "loss": 0.1433,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.9344,
517
+ "grad_norm": 0.17884600087369845,
518
+ "learning_rate": 1.2855336046093513e-05,
519
+ "loss": 0.1447,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.9472,
524
+ "grad_norm": 0.14100954677816485,
525
+ "learning_rate": 1.2640348031846897e-05,
526
+ "loss": 0.1447,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.96,
531
+ "grad_norm": 0.33304512484187876,
532
+ "learning_rate": 1.2424039968217361e-05,
533
+ "loss": 0.145,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.9728,
538
+ "grad_norm": 0.2096407271139896,
539
+ "learning_rate": 1.220651999902627e-05,
540
+ "loss": 0.1355,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.9856,
545
+ "grad_norm": 0.18948626555533854,
546
+ "learning_rate": 1.1987896873990572e-05,
547
+ "loss": 0.1422,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.9984,
552
+ "grad_norm": 0.25576476392968256,
553
+ "learning_rate": 1.176827989435307e-05,
554
+ "loss": 0.1473,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.99968,
559
+ "eval_loss": 0.13926610350608826,
560
+ "eval_runtime": 42.0798,
561
+ "eval_samples_per_second": 23.764,
562
+ "eval_steps_per_second": 1.497,
563
+ "step": 781
564
+ },
565
+ {
566
+ "epoch": 1.0112,
567
+ "grad_norm": 0.15072347755987592,
568
+ "learning_rate": 1.1547778858236938e-05,
569
+ "loss": 0.1361,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.024,
574
+ "grad_norm": 0.24763730684547336,
575
+ "learning_rate": 1.1326504005751875e-05,
576
+ "loss": 0.1426,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.0368,
581
+ "grad_norm": 0.2049805600857785,
582
+ "learning_rate": 1.1104565963879233e-05,
583
+ "loss": 0.1417,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.0496,
588
+ "grad_norm": 0.17505933336916096,
589
+ "learning_rate": 1.0882075691163749e-05,
590
+ "loss": 0.1425,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.0624,
595
+ "grad_norm": 0.2367359754977405,
596
+ "learning_rate": 1.065914442223952e-05,
597
+ "loss": 0.1395,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.0752,
602
+ "grad_norm": 0.2168168491904799,
603
+ "learning_rate": 1.0435883612217928e-05,
604
+ "loss": 0.1368,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.088,
609
+ "grad_norm": 0.16667141395128426,
610
+ "learning_rate": 1.0212404880965348e-05,
611
+ "loss": 0.1397,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.1008,
616
+ "grad_norm": 0.19793016123521015,
617
+ "learning_rate": 9.988819957298487e-06,
618
+ "loss": 0.1447,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.1136,
623
+ "grad_norm": 0.21711053823618134,
624
+ "learning_rate": 9.765240623125238e-06,
625
+ "loss": 0.1418,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.1264,
630
+ "grad_norm": 0.24562717005747997,
631
+ "learning_rate": 9.541778657559026e-06,
632
+ "loss": 0.1371,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.1392,
637
+ "grad_norm": 0.17839427327356683,
638
+ "learning_rate": 9.318545781034499e-06,
639
+ "loss": 0.1368,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.152,
644
+ "grad_norm": 0.18971426870401556,
645
+ "learning_rate": 9.095653599452604e-06,
646
+ "loss": 0.1411,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.1648,
651
+ "grad_norm": 0.2028582361588426,
652
+ "learning_rate": 8.873213548382895e-06,
653
+ "loss": 0.1432,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.1776,
658
+ "grad_norm": 0.1910575100313919,
659
+ "learning_rate": 8.651336837351013e-06,
660
+ "loss": 0.1441,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.1904,
665
+ "grad_norm": 0.21795820010528985,
666
+ "learning_rate": 8.430134394239182e-06,
667
+ "loss": 0.1389,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.2032,
672
+ "grad_norm": 0.1702846327798786,
673
+ "learning_rate": 8.209716809827475e-06,
674
+ "loss": 0.1387,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.216,
679
+ "grad_norm": 0.19574705900720263,
680
+ "learning_rate": 7.990194282503678e-06,
681
+ "loss": 0.1408,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.2288000000000001,
686
+ "grad_norm": 0.15444562246412258,
687
+ "learning_rate": 7.771676563169276e-06,
688
+ "loss": 0.1424,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.2416,
693
+ "grad_norm": 0.27192054451029335,
694
+ "learning_rate": 7.554272900369184e-06,
695
+ "loss": 0.1431,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.2544,
700
+ "grad_norm": 0.28293536797942354,
701
+ "learning_rate": 7.338091985672651e-06,
702
+ "loss": 0.1375,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.2671999999999999,
707
+ "grad_norm": 0.27054236168586154,
708
+ "learning_rate": 7.1232418993325836e-06,
709
+ "loss": 0.1346,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.28,
714
+ "grad_norm": 0.25032137575039304,
715
+ "learning_rate": 6.909830056250527e-06,
716
+ "loss": 0.1401,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.2928,
721
+ "grad_norm": 0.1593137714997539,
722
+ "learning_rate": 6.697963152274294e-06,
723
+ "loss": 0.1415,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 1.3056,
728
+ "grad_norm": 0.17468257527642406,
729
+ "learning_rate": 6.487747110855061e-06,
730
+ "loss": 0.1421,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 1.3184,
735
+ "grad_norm": 0.198558265817394,
736
+ "learning_rate": 6.279287030090664e-06,
737
+ "loss": 0.1387,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 1.3312,
742
+ "grad_norm": 0.11504815520373578,
743
+ "learning_rate": 6.072687130181493e-06,
744
+ "loss": 0.1353,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 1.3439999999999999,
749
+ "grad_norm": 0.13858890875298494,
750
+ "learning_rate": 5.868050701325314e-06,
751
+ "loss": 0.1398,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 1.3568,
756
+ "grad_norm": 0.13445081822803,
757
+ "learning_rate": 5.665480052077051e-06,
758
+ "loss": 0.1409,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 1.3696,
763
+ "grad_norm": 0.16055599811743235,
764
+ "learning_rate": 5.465076458199332e-06,
765
+ "loss": 0.1417,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 1.3824,
770
+ "grad_norm": 0.19169771082374196,
771
+ "learning_rate": 5.266940112029406e-06,
772
+ "loss": 0.138,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 1.3952,
777
+ "grad_norm": 0.18154527027617387,
778
+ "learning_rate": 5.071170072387672e-06,
779
+ "loss": 0.1373,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 1.408,
784
+ "grad_norm": 0.13523001447293553,
785
+ "learning_rate": 4.877864215052969e-06,
786
+ "loss": 0.1382,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 1.4208,
791
+ "grad_norm": 0.14620192480202174,
792
+ "learning_rate": 4.687119183829305e-06,
793
+ "loss": 0.1403,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 1.4336,
798
+ "grad_norm": 0.14563804992816887,
799
+ "learning_rate": 4.4990303422285005e-06,
800
+ "loss": 0.1401,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 1.4464000000000001,
805
+ "grad_norm": 0.18048671111150355,
806
+ "learning_rate": 4.31369172579296e-06,
807
+ "loss": 0.1351,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 1.4592,
812
+ "grad_norm": 0.1274956008805008,
813
+ "learning_rate": 4.1311959950823125e-06,
814
+ "loss": 0.1357,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 1.472,
819
+ "grad_norm": 0.15186812567018518,
820
+ "learning_rate": 3.951634389347522e-06,
821
+ "loss": 0.1405,
822
+ "step": 1150
823
+ },
824
+ {
825
+ "epoch": 1.4848,
826
+ "grad_norm": 0.1743781587386354,
827
+ "learning_rate": 3.7750966809155633e-06,
828
+ "loss": 0.1411,
829
+ "step": 1160
830
+ },
831
+ {
832
+ "epoch": 1.4976,
833
+ "grad_norm": 0.16145108253749546,
834
+ "learning_rate": 3.6016711303075003e-06,
835
+ "loss": 0.1418,
836
+ "step": 1170
837
+ },
838
+ {
839
+ "epoch": 1.5104,
840
+ "grad_norm": 0.2443925847158833,
841
+ "learning_rate": 3.431444442112395e-06,
842
+ "loss": 0.1365,
843
+ "step": 1180
844
+ },
845
+ {
846
+ "epoch": 1.5232,
847
+ "grad_norm": 0.16076378293495353,
848
+ "learning_rate": 3.264501721639086e-06,
849
+ "loss": 0.1354,
850
+ "step": 1190
851
+ },
852
+ {
853
+ "epoch": 1.536,
854
+ "grad_norm": 0.20722028172668885,
855
+ "learning_rate": 3.1009264323675737e-06,
856
+ "loss": 0.1387,
857
+ "step": 1200
858
+ },
859
+ {
860
+ "epoch": 1.5488,
861
+ "grad_norm": 0.2367805090756499,
862
+ "learning_rate": 2.940800354221205e-06,
863
+ "loss": 0.1414,
864
+ "step": 1210
865
+ },
866
+ {
867
+ "epoch": 1.5615999999999999,
868
+ "grad_norm": 0.2045021555576582,
869
+ "learning_rate": 2.7842035426805858e-06,
870
+ "loss": 0.1435,
871
+ "step": 1220
872
+ },
873
+ {
874
+ "epoch": 1.5744,
875
+ "grad_norm": 0.3378391898032357,
876
+ "learning_rate": 2.6312142887596116e-06,
877
+ "loss": 0.137,
878
+ "step": 1230
879
+ },
880
+ {
881
+ "epoch": 1.5872000000000002,
882
+ "grad_norm": 0.15144211781786535,
883
+ "learning_rate": 2.4819090798636504e-06,
884
+ "loss": 0.1362,
885
+ "step": 1240
886
+ },
887
+ {
888
+ "epoch": 1.6,
889
+ "grad_norm": 0.19705372401646207,
890
+ "learning_rate": 2.336362561549459e-06,
891
+ "loss": 0.1398,
892
+ "step": 1250
893
+ },
894
+ {
895
+ "epoch": 1.6128,
896
+ "grad_norm": 0.1981712638313628,
897
+ "learning_rate": 2.194647500205925e-06,
898
+ "loss": 0.1412,
899
+ "step": 1260
900
+ },
901
+ {
902
+ "epoch": 1.6256,
903
+ "grad_norm": 0.22583463728566275,
904
+ "learning_rate": 2.056834746674313e-06,
905
+ "loss": 0.1402,
906
+ "step": 1270
907
+ },
908
+ {
909
+ "epoch": 1.6383999999999999,
910
+ "grad_norm": 0.3166766019266127,
911
+ "learning_rate": 1.9229932008261756e-06,
912
+ "loss": 0.1366,
913
+ "step": 1280
914
+ },
915
+ {
916
+ "epoch": 1.6512,
917
+ "grad_norm": 0.13358881231561032,
918
+ "learning_rate": 1.7931897771166861e-06,
919
+ "loss": 0.1346,
920
+ "step": 1290
921
+ },
922
+ {
923
+ "epoch": 1.6640000000000001,
924
+ "grad_norm": 0.28514268179697894,
925
+ "learning_rate": 1.6674893711305528e-06,
926
+ "loss": 0.1399,
927
+ "step": 1300
928
+ },
929
+ {
930
+ "epoch": 1.6768,
931
+ "grad_norm": 0.08846971622020448,
932
+ "learning_rate": 1.5459548271373005e-06,
933
+ "loss": 0.1383,
934
+ "step": 1310
935
+ },
936
+ {
937
+ "epoch": 1.6896,
938
+ "grad_norm": 0.28809034512805015,
939
+ "learning_rate": 1.4286469066721055e-06,
940
+ "loss": 0.1399,
941
+ "step": 1320
942
+ },
943
+ {
944
+ "epoch": 1.7024,
945
+ "grad_norm": 0.1598977533627517,
946
+ "learning_rate": 1.3156242581578815e-06,
947
+ "loss": 0.1351,
948
+ "step": 1330
949
+ },
950
+ {
951
+ "epoch": 1.7151999999999998,
952
+ "grad_norm": 0.19800584875933322,
953
+ "learning_rate": 1.2069433875838498e-06,
954
+ "loss": 0.1347,
955
+ "step": 1340
956
+ },
957
+ {
958
+ "epoch": 1.728,
959
+ "grad_norm": 0.12495858993727499,
960
+ "learning_rate": 1.10265863025521e-06,
961
+ "loss": 0.1376,
962
+ "step": 1350
963
+ },
964
+ {
965
+ "epoch": 1.7408000000000001,
966
+ "grad_norm": 0.12691325643260487,
967
+ "learning_rate": 1.0028221236280445e-06,
968
+ "loss": 0.1408,
969
+ "step": 1360
970
+ },
971
+ {
972
+ "epoch": 1.7536,
973
+ "grad_norm": 0.14092289840202932,
974
+ "learning_rate": 9.074837812430626e-07,
975
+ "loss": 0.1404,
976
+ "step": 1370
977
+ },
978
+ {
979
+ "epoch": 1.7664,
980
+ "grad_norm": 0.1356179011766789,
981
+ "learning_rate": 8.166912677711769e-07,
982
+ "loss": 0.1344,
983
+ "step": 1380
984
+ },
985
+ {
986
+ "epoch": 1.7792,
987
+ "grad_norm": 0.11072101415903435,
988
+ "learning_rate": 7.304899751834194e-07,
989
+ "loss": 0.1363,
990
+ "step": 1390
991
+ },
992
+ {
993
+ "epoch": 1.792,
994
+ "grad_norm": 0.09364893615869158,
995
+ "learning_rate": 6.489230000571067e-07,
996
+ "loss": 0.1387,
997
+ "step": 1400
998
+ },
999
+ {
1000
+ "epoch": 1.8048,
1001
+ "grad_norm": 0.09719389776054362,
1002
+ "learning_rate": 5.720311220295727e-07,
1003
+ "loss": 0.1406,
1004
+ "step": 1410
1005
+ },
1006
+ {
1007
+ "epoch": 1.8176,
1008
+ "grad_norm": 0.14149128093688274,
1009
+ "learning_rate": 4.998527834102873e-07,
1010
+ "loss": 0.1411,
1011
+ "step": 1420
1012
+ },
1013
+ {
1014
+ "epoch": 1.8304,
1015
+ "grad_norm": 0.15889816186833727,
1016
+ "learning_rate": 4.3242406996150674e-07,
1017
+ "loss": 0.1345,
1018
+ "step": 1430
1019
+ },
1020
+ {
1021
+ "epoch": 1.8432,
1022
+ "grad_norm": 0.0958974593538415,
1023
+ "learning_rate": 3.697786928571034e-07,
1024
+ "loss": 0.1341,
1025
+ "step": 1440
1026
+ },
1027
+ {
1028
+ "epoch": 1.8559999999999999,
1029
+ "grad_norm": 0.07979518065313038,
1030
+ "learning_rate": 3.119479718285601e-07,
1031
+ "loss": 0.1381,
1032
+ "step": 1450
1033
+ },
1034
+ {
1035
+ "epoch": 1.8688,
1036
+ "grad_norm": 0.10204011708199633,
1037
+ "learning_rate": 2.5896081950659737e-07,
1038
+ "loss": 0.1408,
1039
+ "step": 1460
1040
+ },
1041
+ {
1042
+ "epoch": 1.8816000000000002,
1043
+ "grad_norm": 0.11627971006018599,
1044
+ "learning_rate": 2.108437269662089e-07,
1045
+ "loss": 0.1433,
1046
+ "step": 1470
1047
+ },
1048
+ {
1049
+ "epoch": 1.8944,
1050
+ "grad_norm": 0.15458392923737632,
1051
+ "learning_rate": 1.6762075048238347e-07,
1052
+ "loss": 0.1359,
1053
+ "step": 1480
1054
+ },
1055
+ {
1056
+ "epoch": 1.9072,
1057
+ "grad_norm": 0.10450160701417593,
1058
+ "learning_rate": 1.2931349950309535e-07,
1059
+ "loss": 0.1342,
1060
+ "step": 1490
1061
+ },
1062
+ {
1063
+ "epoch": 1.92,
1064
+ "grad_norm": 0.09770183301391486,
1065
+ "learning_rate": 9.594112584561e-08,
1066
+ "loss": 0.1381,
1067
+ "step": 1500
1068
+ },
1069
+ {
1070
+ "epoch": 1.9327999999999999,
1071
+ "grad_norm": 0.09381477173800809,
1072
+ "learning_rate": 6.752031412147086e-08,
1073
+ "loss": 0.1394,
1074
+ "step": 1510
1075
+ },
1076
+ {
1077
+ "epoch": 1.9456,
1078
+ "grad_norm": 0.12023221514437896,
1079
+ "learning_rate": 4.406527339498423e-08,
1080
+ "loss": 0.1416,
1081
+ "step": 1520
1082
+ },
1083
+ {
1084
+ "epoch": 1.9584000000000001,
1085
+ "grad_norm": 0.16776774231570918,
1086
+ "learning_rate": 2.5587730079362772e-08,
1087
+ "loss": 0.134,
1088
+ "step": 1530
1089
+ },
1090
+ {
1091
+ "epoch": 1.9712,
1092
+ "grad_norm": 0.09797271568610905,
1093
+ "learning_rate": 1.2096922074060768e-08,
1094
+ "loss": 0.134,
1095
+ "step": 1540
1096
+ },
1097
+ {
1098
+ "epoch": 1.984,
1099
+ "grad_norm": 0.09345305263894858,
1100
+ "learning_rate": 3.5995941462718677e-09,
1101
+ "loss": 0.138,
1102
+ "step": 1550
1103
+ },
1104
+ {
1105
+ "epoch": 1.9968,
1106
+ "grad_norm": 0.08633576245142834,
1107
+ "learning_rate": 9.999455885978393e-11,
1108
+ "loss": 0.1406,
1109
+ "step": 1560
1110
+ },
1111
+ {
1112
+ "epoch": 1.99936,
1113
+ "eval_loss": 0.13485482335090637,
1114
+ "eval_runtime": 42.0832,
1115
+ "eval_samples_per_second": 23.762,
1116
+ "eval_steps_per_second": 1.497,
1117
+ "step": 1562
1118
+ },
1119
+ {
1120
+ "epoch": 1.99936,
1121
+ "step": 1562,
1122
+ "total_flos": 534097819484160.0,
1123
+ "train_loss": 0.14969347108265196,
1124
+ "train_runtime": 45991.4783,
1125
+ "train_samples_per_second": 4.349,
1126
+ "train_steps_per_second": 0.034
1127
+ }
1128
+ ],
1129
+ "logging_steps": 10,
1130
+ "max_steps": 1562,
1131
+ "num_input_tokens_seen": 0,
1132
+ "num_train_epochs": 2,
1133
+ "save_steps": 781,
1134
+ "stateful_callbacks": {
1135
+ "TrainerControl": {
1136
+ "args": {
1137
+ "should_epoch_stop": false,
1138
+ "should_evaluate": false,
1139
+ "should_log": false,
1140
+ "should_save": true,
1141
+ "should_training_stop": true
1142
+ },
1143
+ "attributes": {}
1144
+ }
1145
+ },
1146
+ "total_flos": 534097819484160.0,
1147
+ "train_batch_size": 1,
1148
+ "trial_name": null,
1149
+ "trial_params": null
1150
+ }