sedrickkeh commited on
Commit
45aeb06
·
verified ·
1 Parent(s): 4e8c529

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3.1
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: top_17_ranking_stackexchange
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # top_17_ranking_stackexchange
17
 
18
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.7988
21
 
 
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: top_17_ranking_stackexchange
 
16
 
17
  # top_17_ranking_stackexchange
18
 
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/top_17_ranking_stackexchange dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.7988
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.998768978251949,
3
+ "eval_loss": 0.7988426685333252,
4
+ "eval_runtime": 652.4279,
5
+ "eval_samples_per_second": 25.163,
6
+ "eval_steps_per_second": 0.394,
7
+ "total_flos": 3060083667763200.0,
8
+ "train_loss": 0.7828072778631836,
9
+ "train_runtime": 108782.0419,
10
+ "train_samples_per_second": 8.602,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.998768978251949,
3
+ "eval_loss": 0.7988426685333252,
4
+ "eval_runtime": 652.4279,
5
+ "eval_samples_per_second": 25.163,
6
+ "eval_steps_per_second": 0.394
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.998768978251949,
3
+ "total_flos": 3060083667763200.0,
4
+ "train_loss": 0.7828072778631836,
5
+ "train_runtime": 108782.0419,
6
+ "train_samples_per_second": 8.602,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1340 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.998768978251949,
5
+ "eval_steps": 500,
6
+ "global_step": 1827,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.016413623307345096,
13
+ "grad_norm": 8.99270138013034,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0659,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.03282724661469019,
20
+ "grad_norm": 3.053529266595301,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.9734,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.04924086992203529,
27
+ "grad_norm": 2.633730745764626,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.9341,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.06565449322938038,
34
+ "grad_norm": 0.7908528977431902,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.9191,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.08206811653672548,
41
+ "grad_norm": 1.0408150537576215,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.9013,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.09848173984407058,
48
+ "grad_norm": 1.0009107528629961,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.8956,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.11489536315141567,
55
+ "grad_norm": 0.8433960502782532,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.8783,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.13130898645876077,
62
+ "grad_norm": 1.2184758422903226,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.8776,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.14772260976610588,
69
+ "grad_norm": 0.7980413481780791,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.8707,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.16413623307345096,
76
+ "grad_norm": 0.5562074295693149,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.8672,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.18054985638079607,
83
+ "grad_norm": 0.5260694903772933,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.8611,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.19696347968814115,
90
+ "grad_norm": 0.6264931158468416,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.8621,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.21337710299548626,
97
+ "grad_norm": 0.6191079265416527,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.8541,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.22979072630283134,
104
+ "grad_norm": 0.5921376117856568,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.8535,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.24620434961017645,
111
+ "grad_norm": 0.5621484849345678,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.8548,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.26261797291752154,
118
+ "grad_norm": 0.5294016331059697,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.8538,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.2790315962248666,
125
+ "grad_norm": 0.5007519115014486,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.849,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.29544521953221176,
132
+ "grad_norm": 0.5887354661692235,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.8488,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.31185884283955684,
139
+ "grad_norm": 0.5081716506810537,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.8484,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.3282724661469019,
146
+ "grad_norm": 0.6188657430216449,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.8426,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.344686089454247,
153
+ "grad_norm": 1.0610412603180521,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.8399,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.36109971276159214,
160
+ "grad_norm": 0.7317657510287235,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.8455,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.3775133360689372,
167
+ "grad_norm": 0.5199899282009807,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.8437,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.3939269593762823,
174
+ "grad_norm": 0.701918684276049,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.8391,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.4103405826836274,
181
+ "grad_norm": 0.5559902755445636,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.8358,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.4267542059909725,
188
+ "grad_norm": 0.5581199955306168,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.8394,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.4431678292983176,
195
+ "grad_norm": 0.6690583184335058,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.8373,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.4595814526056627,
202
+ "grad_norm": 0.505413325131573,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.8321,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.47599507591300777,
209
+ "grad_norm": 0.4902726775641345,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.8407,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.4924086992203529,
216
+ "grad_norm": 0.7023706220694934,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.8309,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.508822322527698,
223
+ "grad_norm": 0.5762877961049813,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.8318,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.5252359458350431,
230
+ "grad_norm": 0.47853098636746905,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.8332,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.5416495691423882,
237
+ "grad_norm": 0.5281284739639729,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.83,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.5580631924497332,
244
+ "grad_norm": 0.5794359727324211,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.827,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.5744768157570784,
251
+ "grad_norm": 0.542547522553918,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.8289,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.5908904390644235,
258
+ "grad_norm": 0.5615169892984633,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.8261,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.6073040623717686,
265
+ "grad_norm": 0.5992859282011177,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.8265,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.6237176856791137,
272
+ "grad_norm": 0.6682966476034522,
273
+ "learning_rate": 5e-06,
274
+ "loss": 0.8272,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.6401313089864588,
279
+ "grad_norm": 0.5419933138601745,
280
+ "learning_rate": 5e-06,
281
+ "loss": 0.8258,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.6565449322938038,
286
+ "grad_norm": 0.49991773880492635,
287
+ "learning_rate": 5e-06,
288
+ "loss": 0.8249,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.6729585556011489,
293
+ "grad_norm": 0.6878795353167779,
294
+ "learning_rate": 5e-06,
295
+ "loss": 0.8222,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.689372178908494,
300
+ "grad_norm": 0.4911573402330116,
301
+ "learning_rate": 5e-06,
302
+ "loss": 0.825,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.7057858022158392,
307
+ "grad_norm": 0.5697346305894231,
308
+ "learning_rate": 5e-06,
309
+ "loss": 0.825,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.7221994255231843,
314
+ "grad_norm": 0.5513743964148584,
315
+ "learning_rate": 5e-06,
316
+ "loss": 0.8246,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.7386130488305294,
321
+ "grad_norm": 0.688660194802024,
322
+ "learning_rate": 5e-06,
323
+ "loss": 0.8222,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.7550266721378744,
328
+ "grad_norm": 0.511273977957526,
329
+ "learning_rate": 5e-06,
330
+ "loss": 0.8213,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.7714402954452195,
335
+ "grad_norm": 0.5063886517354912,
336
+ "learning_rate": 5e-06,
337
+ "loss": 0.8222,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.7878539187525646,
342
+ "grad_norm": 0.5454872366957495,
343
+ "learning_rate": 5e-06,
344
+ "loss": 0.8193,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.8042675420599097,
349
+ "grad_norm": 0.565210030152154,
350
+ "learning_rate": 5e-06,
351
+ "loss": 0.8177,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.8206811653672548,
356
+ "grad_norm": 0.6047647526413709,
357
+ "learning_rate": 5e-06,
358
+ "loss": 0.8184,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.8370947886746,
363
+ "grad_norm": 0.4922366597743525,
364
+ "learning_rate": 5e-06,
365
+ "loss": 0.8172,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.853508411981945,
370
+ "grad_norm": 0.5659941668447491,
371
+ "learning_rate": 5e-06,
372
+ "loss": 0.8204,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.8699220352892901,
377
+ "grad_norm": 0.7936193835249891,
378
+ "learning_rate": 5e-06,
379
+ "loss": 0.8156,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.8863356585966352,
384
+ "grad_norm": 0.635704407895363,
385
+ "learning_rate": 5e-06,
386
+ "loss": 0.8168,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.9027492819039803,
391
+ "grad_norm": 0.5271560225642157,
392
+ "learning_rate": 5e-06,
393
+ "loss": 0.8154,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.9191629052113254,
398
+ "grad_norm": 0.4819325527832828,
399
+ "learning_rate": 5e-06,
400
+ "loss": 0.818,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.9355765285186705,
405
+ "grad_norm": 0.5777651614118724,
406
+ "learning_rate": 5e-06,
407
+ "loss": 0.8168,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.9519901518260155,
412
+ "grad_norm": 0.7370846415410045,
413
+ "learning_rate": 5e-06,
414
+ "loss": 0.8152,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.9684037751333607,
419
+ "grad_norm": 0.6007353019630401,
420
+ "learning_rate": 5e-06,
421
+ "loss": 0.8173,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.9848173984407058,
426
+ "grad_norm": 0.56593529564363,
427
+ "learning_rate": 5e-06,
428
+ "loss": 0.8157,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.9995896594173164,
433
+ "eval_loss": 0.8145917654037476,
434
+ "eval_runtime": 649.6437,
435
+ "eval_samples_per_second": 25.271,
436
+ "eval_steps_per_second": 0.396,
437
+ "step": 609
438
+ },
439
+ {
440
+ "epoch": 1.001231021748051,
441
+ "grad_norm": 1.5425883939459828,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.8731,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.017644645055396,
448
+ "grad_norm": 0.7619005303987774,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.7758,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.034058268362741,
455
+ "grad_norm": 0.6185096912027249,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.7704,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.0504718916700861,
462
+ "grad_norm": 0.5425736459453947,
463
+ "learning_rate": 5e-06,
464
+ "loss": 0.774,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.0668855149774312,
469
+ "grad_norm": 0.5336001597783918,
470
+ "learning_rate": 5e-06,
471
+ "loss": 0.7706,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.0832991382847763,
476
+ "grad_norm": 0.5273934170840361,
477
+ "learning_rate": 5e-06,
478
+ "loss": 0.7812,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.0997127615921214,
483
+ "grad_norm": 0.49999784470967323,
484
+ "learning_rate": 5e-06,
485
+ "loss": 0.7786,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.1161263848994665,
490
+ "grad_norm": 0.5332221891356449,
491
+ "learning_rate": 5e-06,
492
+ "loss": 0.7749,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.1325400082068118,
497
+ "grad_norm": 0.5733836629913084,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.7782,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.1489536315141566,
504
+ "grad_norm": 0.49502621904597705,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.771,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.165367254821502,
511
+ "grad_norm": 0.527378879948705,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.769,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.181780878128847,
518
+ "grad_norm": 0.6092891531058294,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.7735,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.198194501436192,
525
+ "grad_norm": 0.7409709215243082,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.7735,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.2146081247435372,
532
+ "grad_norm": 0.5407098999014308,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.7735,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.2310217480508823,
539
+ "grad_norm": 0.558991862523269,
540
+ "learning_rate": 5e-06,
541
+ "loss": 0.7773,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.2474353713582274,
546
+ "grad_norm": 0.5542175525118204,
547
+ "learning_rate": 5e-06,
548
+ "loss": 0.7776,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.2638489946655724,
553
+ "grad_norm": 0.5783902400184568,
554
+ "learning_rate": 5e-06,
555
+ "loss": 0.7746,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.2802626179729175,
560
+ "grad_norm": 0.5521887369776995,
561
+ "learning_rate": 5e-06,
562
+ "loss": 0.7707,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.2966762412802626,
567
+ "grad_norm": 0.8444645957997873,
568
+ "learning_rate": 5e-06,
569
+ "loss": 0.7725,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.3130898645876077,
574
+ "grad_norm": 0.5736975526122204,
575
+ "learning_rate": 5e-06,
576
+ "loss": 0.7744,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.3295034878949528,
581
+ "grad_norm": 0.48292249290479,
582
+ "learning_rate": 5e-06,
583
+ "loss": 0.7733,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.3459171112022978,
588
+ "grad_norm": 0.5049987037399899,
589
+ "learning_rate": 5e-06,
590
+ "loss": 0.7714,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.362330734509643,
595
+ "grad_norm": 0.5062380261284263,
596
+ "learning_rate": 5e-06,
597
+ "loss": 0.7715,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.3787443578169882,
602
+ "grad_norm": 0.5278903296959995,
603
+ "learning_rate": 5e-06,
604
+ "loss": 0.7726,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.395157981124333,
609
+ "grad_norm": 0.5450750708926599,
610
+ "learning_rate": 5e-06,
611
+ "loss": 0.7747,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.4115716044316784,
616
+ "grad_norm": 0.6396261396718704,
617
+ "learning_rate": 5e-06,
618
+ "loss": 0.7744,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.4279852277390233,
623
+ "grad_norm": 0.5482394718697263,
624
+ "learning_rate": 5e-06,
625
+ "loss": 0.7727,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.4443988510463686,
630
+ "grad_norm": 0.46959189800427537,
631
+ "learning_rate": 5e-06,
632
+ "loss": 0.7744,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.4608124743537136,
637
+ "grad_norm": 0.5691557302620813,
638
+ "learning_rate": 5e-06,
639
+ "loss": 0.77,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.4772260976610587,
644
+ "grad_norm": 0.5438893971371171,
645
+ "learning_rate": 5e-06,
646
+ "loss": 0.7742,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.4936397209684038,
651
+ "grad_norm": 0.515108075044442,
652
+ "learning_rate": 5e-06,
653
+ "loss": 0.7674,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.5100533442757489,
658
+ "grad_norm": 0.535062525509266,
659
+ "learning_rate": 5e-06,
660
+ "loss": 0.7716,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.526466967583094,
665
+ "grad_norm": 0.48864573799251787,
666
+ "learning_rate": 5e-06,
667
+ "loss": 0.7711,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.542880590890439,
672
+ "grad_norm": 0.512031098496549,
673
+ "learning_rate": 5e-06,
674
+ "loss": 0.7724,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.5592942141977841,
679
+ "grad_norm": 0.5349855948928464,
680
+ "learning_rate": 5e-06,
681
+ "loss": 0.7693,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.5757078375051292,
686
+ "grad_norm": 0.662086219432035,
687
+ "learning_rate": 5e-06,
688
+ "loss": 0.7712,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.5921214608124743,
693
+ "grad_norm": 0.5526444522821828,
694
+ "learning_rate": 5e-06,
695
+ "loss": 0.7709,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.6085350841198194,
700
+ "grad_norm": 0.55082436990172,
701
+ "learning_rate": 5e-06,
702
+ "loss": 0.7772,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.6249487074271647,
707
+ "grad_norm": 0.5815245751790243,
708
+ "learning_rate": 5e-06,
709
+ "loss": 0.7722,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.6413623307345095,
714
+ "grad_norm": 0.5154000934765319,
715
+ "learning_rate": 5e-06,
716
+ "loss": 0.7694,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.6577759540418548,
721
+ "grad_norm": 0.6023290973410581,
722
+ "learning_rate": 5e-06,
723
+ "loss": 0.7673,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 1.6741895773491997,
728
+ "grad_norm": 0.600577558938854,
729
+ "learning_rate": 5e-06,
730
+ "loss": 0.7713,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 1.690603200656545,
735
+ "grad_norm": 0.6079065129634816,
736
+ "learning_rate": 5e-06,
737
+ "loss": 0.7687,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 1.7070168239638899,
742
+ "grad_norm": 0.693841170522645,
743
+ "learning_rate": 5e-06,
744
+ "loss": 0.7697,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 1.7234304472712352,
749
+ "grad_norm": 0.48888900591836165,
750
+ "learning_rate": 5e-06,
751
+ "loss": 0.7691,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 1.7398440705785803,
756
+ "grad_norm": 0.7010501927100856,
757
+ "learning_rate": 5e-06,
758
+ "loss": 0.7741,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 1.7562576938859253,
763
+ "grad_norm": 0.4911843241601219,
764
+ "learning_rate": 5e-06,
765
+ "loss": 0.7661,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 1.7726713171932704,
770
+ "grad_norm": 0.5931976251774361,
771
+ "learning_rate": 5e-06,
772
+ "loss": 0.7689,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 1.7890849405006155,
777
+ "grad_norm": 0.6443181893958313,
778
+ "learning_rate": 5e-06,
779
+ "loss": 0.7705,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 1.8054985638079606,
784
+ "grad_norm": 0.470844146128102,
785
+ "learning_rate": 5e-06,
786
+ "loss": 0.7726,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 1.8219121871153057,
791
+ "grad_norm": 0.6664878595725717,
792
+ "learning_rate": 5e-06,
793
+ "loss": 0.7698,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 1.8383258104226508,
798
+ "grad_norm": 0.507697225304388,
799
+ "learning_rate": 5e-06,
800
+ "loss": 0.767,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 1.8547394337299958,
805
+ "grad_norm": 0.5439425837704747,
806
+ "learning_rate": 5e-06,
807
+ "loss": 0.7686,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 1.8711530570373411,
812
+ "grad_norm": 0.8621901744125671,
813
+ "learning_rate": 5e-06,
814
+ "loss": 0.7717,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 1.887566680344686,
819
+ "grad_norm": 0.5511696877991991,
820
+ "learning_rate": 5e-06,
821
+ "loss": 0.7715,
822
+ "step": 1150
823
+ },
824
+ {
825
+ "epoch": 1.9039803036520313,
826
+ "grad_norm": 0.4950879715118595,
827
+ "learning_rate": 5e-06,
828
+ "loss": 0.7719,
829
+ "step": 1160
830
+ },
831
+ {
832
+ "epoch": 1.9203939269593762,
833
+ "grad_norm": 0.48824900399092436,
834
+ "learning_rate": 5e-06,
835
+ "loss": 0.7715,
836
+ "step": 1170
837
+ },
838
+ {
839
+ "epoch": 1.9368075502667215,
840
+ "grad_norm": 0.5450863319774812,
841
+ "learning_rate": 5e-06,
842
+ "loss": 0.7653,
843
+ "step": 1180
844
+ },
845
+ {
846
+ "epoch": 1.9532211735740663,
847
+ "grad_norm": 0.5501310306692955,
848
+ "learning_rate": 5e-06,
849
+ "loss": 0.7678,
850
+ "step": 1190
851
+ },
852
+ {
853
+ "epoch": 1.9696347968814116,
854
+ "grad_norm": 0.5175687374091981,
855
+ "learning_rate": 5e-06,
856
+ "loss": 0.7687,
857
+ "step": 1200
858
+ },
859
+ {
860
+ "epoch": 1.9860484201887567,
861
+ "grad_norm": 0.5729581338876775,
862
+ "learning_rate": 5e-06,
863
+ "loss": 0.7667,
864
+ "step": 1210
865
+ },
866
+ {
867
+ "epoch": 1.9991793188346327,
868
+ "eval_loss": 0.8003594875335693,
869
+ "eval_runtime": 649.053,
870
+ "eval_samples_per_second": 25.294,
871
+ "eval_steps_per_second": 0.396,
872
+ "step": 1218
873
+ },
874
+ {
875
+ "epoch": 2.002462043496102,
876
+ "grad_norm": 0.6463781219114217,
877
+ "learning_rate": 5e-06,
878
+ "loss": 0.8157,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.0188756668034467,
883
+ "grad_norm": 0.5511864743662498,
884
+ "learning_rate": 5e-06,
885
+ "loss": 0.7226,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.035289290110792,
890
+ "grad_norm": 0.5903816264405134,
891
+ "learning_rate": 5e-06,
892
+ "loss": 0.723,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.0517029134181373,
897
+ "grad_norm": 0.6048277468103348,
898
+ "learning_rate": 5e-06,
899
+ "loss": 0.7279,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.068116536725482,
904
+ "grad_norm": 0.6180095343734895,
905
+ "learning_rate": 5e-06,
906
+ "loss": 0.7231,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.0845301600328274,
911
+ "grad_norm": 0.5510967685128281,
912
+ "learning_rate": 5e-06,
913
+ "loss": 0.7251,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.1009437833401723,
918
+ "grad_norm": 0.5188988483266073,
919
+ "learning_rate": 5e-06,
920
+ "loss": 0.721,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.1173574066475176,
925
+ "grad_norm": 0.5609918054348771,
926
+ "learning_rate": 5e-06,
927
+ "loss": 0.7247,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.1337710299548625,
932
+ "grad_norm": 0.5166068490722786,
933
+ "learning_rate": 5e-06,
934
+ "loss": 0.7239,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.1501846532622078,
939
+ "grad_norm": 0.5214337691948149,
940
+ "learning_rate": 5e-06,
941
+ "loss": 0.7265,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.1665982765695526,
946
+ "grad_norm": 0.5346119768256951,
947
+ "learning_rate": 5e-06,
948
+ "loss": 0.7271,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.183011899876898,
953
+ "grad_norm": 0.5300060629839389,
954
+ "learning_rate": 5e-06,
955
+ "loss": 0.728,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.199425523184243,
960
+ "grad_norm": 0.6130748309683199,
961
+ "learning_rate": 5e-06,
962
+ "loss": 0.7304,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.215839146491588,
967
+ "grad_norm": 0.5131757232254592,
968
+ "learning_rate": 5e-06,
969
+ "loss": 0.7289,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.232252769798933,
974
+ "grad_norm": 0.5452450696684072,
975
+ "learning_rate": 5e-06,
976
+ "loss": 0.7279,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.2486663931062782,
981
+ "grad_norm": 0.5644129980449457,
982
+ "learning_rate": 5e-06,
983
+ "loss": 0.7294,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.2650800164136236,
988
+ "grad_norm": 0.5723600015296851,
989
+ "learning_rate": 5e-06,
990
+ "loss": 0.7282,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 2.2814936397209684,
995
+ "grad_norm": 0.5745168828163788,
996
+ "learning_rate": 5e-06,
997
+ "loss": 0.7241,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.2979072630283133,
1002
+ "grad_norm": 0.6316489371250509,
1003
+ "learning_rate": 5e-06,
1004
+ "loss": 0.7318,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 2.3143208863356586,
1009
+ "grad_norm": 0.5884122209110337,
1010
+ "learning_rate": 5e-06,
1011
+ "loss": 0.726,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 2.330734509643004,
1016
+ "grad_norm": 0.5694563289563384,
1017
+ "learning_rate": 5e-06,
1018
+ "loss": 0.7303,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 2.3471481329503487,
1023
+ "grad_norm": 0.5726932495181197,
1024
+ "learning_rate": 5e-06,
1025
+ "loss": 0.7288,
1026
+ "step": 1430
1027
+ },
1028
+ {
1029
+ "epoch": 2.363561756257694,
1030
+ "grad_norm": 0.5879297609823882,
1031
+ "learning_rate": 5e-06,
1032
+ "loss": 0.7296,
1033
+ "step": 1440
1034
+ },
1035
+ {
1036
+ "epoch": 2.379975379565039,
1037
+ "grad_norm": 0.5883121862822648,
1038
+ "learning_rate": 5e-06,
1039
+ "loss": 0.733,
1040
+ "step": 1450
1041
+ },
1042
+ {
1043
+ "epoch": 2.396389002872384,
1044
+ "grad_norm": 0.5536017215166609,
1045
+ "learning_rate": 5e-06,
1046
+ "loss": 0.7273,
1047
+ "step": 1460
1048
+ },
1049
+ {
1050
+ "epoch": 2.412802626179729,
1051
+ "grad_norm": 0.5153804582312451,
1052
+ "learning_rate": 5e-06,
1053
+ "loss": 0.7315,
1054
+ "step": 1470
1055
+ },
1056
+ {
1057
+ "epoch": 2.4292162494870744,
1058
+ "grad_norm": 0.5281531288573597,
1059
+ "learning_rate": 5e-06,
1060
+ "loss": 0.7276,
1061
+ "step": 1480
1062
+ },
1063
+ {
1064
+ "epoch": 2.4456298727944192,
1065
+ "grad_norm": 0.5456727623872021,
1066
+ "learning_rate": 5e-06,
1067
+ "loss": 0.7303,
1068
+ "step": 1490
1069
+ },
1070
+ {
1071
+ "epoch": 2.4620434961017645,
1072
+ "grad_norm": 0.6682595967854461,
1073
+ "learning_rate": 5e-06,
1074
+ "loss": 0.7268,
1075
+ "step": 1500
1076
+ },
1077
+ {
1078
+ "epoch": 2.4784571194091094,
1079
+ "grad_norm": 0.5277543058901882,
1080
+ "learning_rate": 5e-06,
1081
+ "loss": 0.7308,
1082
+ "step": 1510
1083
+ },
1084
+ {
1085
+ "epoch": 2.4948707427164547,
1086
+ "grad_norm": 0.5377911403023388,
1087
+ "learning_rate": 5e-06,
1088
+ "loss": 0.7307,
1089
+ "step": 1520
1090
+ },
1091
+ {
1092
+ "epoch": 2.5112843660237996,
1093
+ "grad_norm": 0.5405851958754275,
1094
+ "learning_rate": 5e-06,
1095
+ "loss": 0.7276,
1096
+ "step": 1530
1097
+ },
1098
+ {
1099
+ "epoch": 2.527697989331145,
1100
+ "grad_norm": 0.5939416097504914,
1101
+ "learning_rate": 5e-06,
1102
+ "loss": 0.7276,
1103
+ "step": 1540
1104
+ },
1105
+ {
1106
+ "epoch": 2.54411161263849,
1107
+ "grad_norm": 0.4915672499433413,
1108
+ "learning_rate": 5e-06,
1109
+ "loss": 0.7302,
1110
+ "step": 1550
1111
+ },
1112
+ {
1113
+ "epoch": 2.560525235945835,
1114
+ "grad_norm": 0.5714622711240627,
1115
+ "learning_rate": 5e-06,
1116
+ "loss": 0.7304,
1117
+ "step": 1560
1118
+ },
1119
+ {
1120
+ "epoch": 2.57693885925318,
1121
+ "grad_norm": 0.5369778418982702,
1122
+ "learning_rate": 5e-06,
1123
+ "loss": 0.7288,
1124
+ "step": 1570
1125
+ },
1126
+ {
1127
+ "epoch": 2.593352482560525,
1128
+ "grad_norm": 0.6119186113930412,
1129
+ "learning_rate": 5e-06,
1130
+ "loss": 0.7292,
1131
+ "step": 1580
1132
+ },
1133
+ {
1134
+ "epoch": 2.6097661058678705,
1135
+ "grad_norm": 0.6419697927822549,
1136
+ "learning_rate": 5e-06,
1137
+ "loss": 0.7329,
1138
+ "step": 1590
1139
+ },
1140
+ {
1141
+ "epoch": 2.6261797291752154,
1142
+ "grad_norm": 0.519894007258766,
1143
+ "learning_rate": 5e-06,
1144
+ "loss": 0.7289,
1145
+ "step": 1600
1146
+ },
1147
+ {
1148
+ "epoch": 2.6425933524825607,
1149
+ "grad_norm": 0.5472253996087528,
1150
+ "learning_rate": 5e-06,
1151
+ "loss": 0.7331,
1152
+ "step": 1610
1153
+ },
1154
+ {
1155
+ "epoch": 2.6590069757899055,
1156
+ "grad_norm": 0.516270579267269,
1157
+ "learning_rate": 5e-06,
1158
+ "loss": 0.73,
1159
+ "step": 1620
1160
+ },
1161
+ {
1162
+ "epoch": 2.675420599097251,
1163
+ "grad_norm": 0.6435228852860398,
1164
+ "learning_rate": 5e-06,
1165
+ "loss": 0.7302,
1166
+ "step": 1630
1167
+ },
1168
+ {
1169
+ "epoch": 2.6918342224045957,
1170
+ "grad_norm": 0.5501601501281529,
1171
+ "learning_rate": 5e-06,
1172
+ "loss": 0.7326,
1173
+ "step": 1640
1174
+ },
1175
+ {
1176
+ "epoch": 2.708247845711941,
1177
+ "grad_norm": 0.5949109159278116,
1178
+ "learning_rate": 5e-06,
1179
+ "loss": 0.7316,
1180
+ "step": 1650
1181
+ },
1182
+ {
1183
+ "epoch": 2.724661469019286,
1184
+ "grad_norm": 0.6480843118367907,
1185
+ "learning_rate": 5e-06,
1186
+ "loss": 0.7309,
1187
+ "step": 1660
1188
+ },
1189
+ {
1190
+ "epoch": 2.741075092326631,
1191
+ "grad_norm": 0.6058791921384546,
1192
+ "learning_rate": 5e-06,
1193
+ "loss": 0.7348,
1194
+ "step": 1670
1195
+ },
1196
+ {
1197
+ "epoch": 2.7574887156339765,
1198
+ "grad_norm": 0.5131902537364029,
1199
+ "learning_rate": 5e-06,
1200
+ "loss": 0.7286,
1201
+ "step": 1680
1202
+ },
1203
+ {
1204
+ "epoch": 2.7739023389413213,
1205
+ "grad_norm": 0.6053781021635353,
1206
+ "learning_rate": 5e-06,
1207
+ "loss": 0.7342,
1208
+ "step": 1690
1209
+ },
1210
+ {
1211
+ "epoch": 2.790315962248666,
1212
+ "grad_norm": 0.6434931495576977,
1213
+ "learning_rate": 5e-06,
1214
+ "loss": 0.7303,
1215
+ "step": 1700
1216
+ },
1217
+ {
1218
+ "epoch": 2.8067295855560115,
1219
+ "grad_norm": 0.521875321768183,
1220
+ "learning_rate": 5e-06,
1221
+ "loss": 0.7292,
1222
+ "step": 1710
1223
+ },
1224
+ {
1225
+ "epoch": 2.823143208863357,
1226
+ "grad_norm": 0.5213429202976669,
1227
+ "learning_rate": 5e-06,
1228
+ "loss": 0.7255,
1229
+ "step": 1720
1230
+ },
1231
+ {
1232
+ "epoch": 2.8395568321707017,
1233
+ "grad_norm": 0.5054795512549872,
1234
+ "learning_rate": 5e-06,
1235
+ "loss": 0.7305,
1236
+ "step": 1730
1237
+ },
1238
+ {
1239
+ "epoch": 2.8559704554780465,
1240
+ "grad_norm": 0.5445431336579684,
1241
+ "learning_rate": 5e-06,
1242
+ "loss": 0.7297,
1243
+ "step": 1740
1244
+ },
1245
+ {
1246
+ "epoch": 2.872384078785392,
1247
+ "grad_norm": 0.4823512740461331,
1248
+ "learning_rate": 5e-06,
1249
+ "loss": 0.7274,
1250
+ "step": 1750
1251
+ },
1252
+ {
1253
+ "epoch": 2.888797702092737,
1254
+ "grad_norm": 0.7211033918425558,
1255
+ "learning_rate": 5e-06,
1256
+ "loss": 0.7321,
1257
+ "step": 1760
1258
+ },
1259
+ {
1260
+ "epoch": 2.905211325400082,
1261
+ "grad_norm": 0.4979306966545238,
1262
+ "learning_rate": 5e-06,
1263
+ "loss": 0.7315,
1264
+ "step": 1770
1265
+ },
1266
+ {
1267
+ "epoch": 2.9216249487074273,
1268
+ "grad_norm": 0.5227086332578315,
1269
+ "learning_rate": 5e-06,
1270
+ "loss": 0.7266,
1271
+ "step": 1780
1272
+ },
1273
+ {
1274
+ "epoch": 2.938038572014772,
1275
+ "grad_norm": 0.48731020276155895,
1276
+ "learning_rate": 5e-06,
1277
+ "loss": 0.7326,
1278
+ "step": 1790
1279
+ },
1280
+ {
1281
+ "epoch": 2.9544521953221174,
1282
+ "grad_norm": 0.5441906751482174,
1283
+ "learning_rate": 5e-06,
1284
+ "loss": 0.7299,
1285
+ "step": 1800
1286
+ },
1287
+ {
1288
+ "epoch": 2.9708658186294623,
1289
+ "grad_norm": 0.4959846025308401,
1290
+ "learning_rate": 5e-06,
1291
+ "loss": 0.7363,
1292
+ "step": 1810
1293
+ },
1294
+ {
1295
+ "epoch": 2.9872794419368076,
1296
+ "grad_norm": 0.5582701492514177,
1297
+ "learning_rate": 5e-06,
1298
+ "loss": 0.7286,
1299
+ "step": 1820
1300
+ },
1301
+ {
1302
+ "epoch": 2.998768978251949,
1303
+ "eval_loss": 0.7988426685333252,
1304
+ "eval_runtime": 652.5981,
1305
+ "eval_samples_per_second": 25.156,
1306
+ "eval_steps_per_second": 0.394,
1307
+ "step": 1827
1308
+ },
1309
+ {
1310
+ "epoch": 2.998768978251949,
1311
+ "step": 1827,
1312
+ "total_flos": 3060083667763200.0,
1313
+ "train_loss": 0.7828072778631836,
1314
+ "train_runtime": 108782.0419,
1315
+ "train_samples_per_second": 8.602,
1316
+ "train_steps_per_second": 0.017
1317
+ }
1318
+ ],
1319
+ "logging_steps": 10,
1320
+ "max_steps": 1827,
1321
+ "num_input_tokens_seen": 0,
1322
+ "num_train_epochs": 3,
1323
+ "save_steps": 500,
1324
+ "stateful_callbacks": {
1325
+ "TrainerControl": {
1326
+ "args": {
1327
+ "should_epoch_stop": false,
1328
+ "should_evaluate": false,
1329
+ "should_log": false,
1330
+ "should_save": true,
1331
+ "should_training_stop": true
1332
+ },
1333
+ "attributes": {}
1334
+ }
1335
+ },
1336
+ "total_flos": 3060083667763200.0,
1337
+ "train_batch_size": 8,
1338
+ "trial_name": null,
1339
+ "trial_params": null
1340
+ }
training_eval_loss.png ADDED
training_loss.png ADDED