sedrickkeh commited on
Commit
274300d
·
verified ·
1 Parent(s): 06b2835

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: oh_v1.3_slim_orca_x4
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # oh_v1.3_slim_orca_x4
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: 0.7230
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: oh_v1.3_slim_orca_x4
 
16
 
17
  # oh_v1.3_slim_orca_x4
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/oh_v1.3_slim_orca_x4 dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.7230
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.999346832135859,
3
+ "eval_loss": 0.7229765057563782,
4
+ "eval_runtime": 388.6577,
5
+ "eval_samples_per_second": 39.804,
6
+ "eval_steps_per_second": 0.623,
7
+ "total_flos": 2884204756992000.0,
8
+ "train_loss": 0.6974312729536448,
9
+ "train_runtime": 56418.3982,
10
+ "train_samples_per_second": 15.629,
11
+ "train_steps_per_second": 0.031
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.999346832135859,
3
+ "eval_loss": 0.7229765057563782,
4
+ "eval_runtime": 388.6577,
5
+ "eval_samples_per_second": 39.804,
6
+ "eval_steps_per_second": 0.623
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.999346832135859,
3
+ "total_flos": 2884204756992000.0,
4
+ "train_loss": 0.6974312729536448,
5
+ "train_runtime": 56418.3982,
6
+ "train_samples_per_second": 15.629,
7
+ "train_steps_per_second": 0.031
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1270 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.999346832135859,
5
+ "eval_steps": 500,
6
+ "global_step": 1722,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017417809710428913,
13
+ "grad_norm": 10.378825586435497,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0838,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.034835619420857826,
20
+ "grad_norm": 4.271546912407876,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.9373,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.05225342913128674,
27
+ "grad_norm": 2.1390120781164823,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.8909,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.06967123884171565,
34
+ "grad_norm": 1.4309168874054254,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.8639,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.08708904855214457,
41
+ "grad_norm": 1.5406276876095664,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.8433,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.10450685826257348,
48
+ "grad_norm": 1.2501465404617618,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.8247,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.1219246679730024,
55
+ "grad_norm": 0.9239834135671998,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.8126,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.1393424776834313,
62
+ "grad_norm": 0.8433941860985329,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.8046,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.15676028739386022,
69
+ "grad_norm": 1.097647182335265,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.796,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.17417809710428914,
76
+ "grad_norm": 1.0683416519694173,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.7903,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.19159590681471805,
83
+ "grad_norm": 1.572717136046009,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.7846,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.20901371652514697,
90
+ "grad_norm": 0.9249575894994505,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.7806,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.2264315262355759,
97
+ "grad_norm": 0.8193084838390464,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.7783,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.2438493359460048,
104
+ "grad_norm": 0.8732647330500742,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.7725,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.2612671456564337,
111
+ "grad_norm": 0.7448079044745952,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.773,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.2786849553668626,
118
+ "grad_norm": 0.9898862055097742,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.7695,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.29610276507729155,
125
+ "grad_norm": 0.7272776397879028,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.7705,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.31352057478772044,
132
+ "grad_norm": 1.0826222911505594,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.7737,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.3309383844981494,
139
+ "grad_norm": 0.6748830770235253,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.7611,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.3483561942085783,
146
+ "grad_norm": 0.7359625796839507,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.7609,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.36577400391900716,
153
+ "grad_norm": 0.6962279114859433,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.756,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.3831918136294361,
160
+ "grad_norm": 0.6255149151141138,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.7617,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.400609623339865,
167
+ "grad_norm": 0.7052369366480614,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.7569,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.41802743305029394,
174
+ "grad_norm": 0.6097155207889393,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.7546,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.43544524276072283,
181
+ "grad_norm": 0.6836967619335058,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.7613,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.4528630524711518,
188
+ "grad_norm": 0.5747669710959988,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.7568,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.47028086218158066,
195
+ "grad_norm": 0.8293746415280457,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.755,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.4876986718920096,
202
+ "grad_norm": 0.6240762658588678,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.7512,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.5051164816024385,
209
+ "grad_norm": 0.604817000368227,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.7565,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.5225342913128674,
216
+ "grad_norm": 0.7975782732234052,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.7536,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.5399521010232963,
223
+ "grad_norm": 0.9097401207787359,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.7449,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.5573699107337252,
230
+ "grad_norm": 0.5850865591811083,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.7476,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.5747877204441542,
237
+ "grad_norm": 0.7135182489392279,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.7446,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.5922055301545831,
244
+ "grad_norm": 0.7289623389467091,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.7461,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.6096233398650119,
251
+ "grad_norm": 0.7209085909740518,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.7441,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.6270411495754409,
258
+ "grad_norm": 0.7124009797840823,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.7426,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.6444589592858698,
265
+ "grad_norm": 0.7812743047985142,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.7425,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.6618767689962988,
272
+ "grad_norm": 0.9348863468860681,
273
+ "learning_rate": 5e-06,
274
+ "loss": 0.7426,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.6792945787067276,
279
+ "grad_norm": 0.8887235387086234,
280
+ "learning_rate": 5e-06,
281
+ "loss": 0.7443,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.6967123884171565,
286
+ "grad_norm": 0.5644550564287659,
287
+ "learning_rate": 5e-06,
288
+ "loss": 0.7462,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.7141301981275855,
293
+ "grad_norm": 0.7133759479394518,
294
+ "learning_rate": 5e-06,
295
+ "loss": 0.7392,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.7315480078380143,
300
+ "grad_norm": 0.6322425713640688,
301
+ "learning_rate": 5e-06,
302
+ "loss": 0.7438,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.7489658175484433,
307
+ "grad_norm": 0.653356418355363,
308
+ "learning_rate": 5e-06,
309
+ "loss": 0.7353,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.7663836272588722,
314
+ "grad_norm": 0.7172550980138845,
315
+ "learning_rate": 5e-06,
316
+ "loss": 0.7362,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.7838014369693012,
321
+ "grad_norm": 0.5961758862117608,
322
+ "learning_rate": 5e-06,
323
+ "loss": 0.7374,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.80121924667973,
328
+ "grad_norm": 0.682099366244341,
329
+ "learning_rate": 5e-06,
330
+ "loss": 0.7361,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.8186370563901589,
335
+ "grad_norm": 0.6035807917106119,
336
+ "learning_rate": 5e-06,
337
+ "loss": 0.7394,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.8360548661005879,
342
+ "grad_norm": 0.6420432430762913,
343
+ "learning_rate": 5e-06,
344
+ "loss": 0.7427,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.8534726758110167,
349
+ "grad_norm": 0.6771119733640588,
350
+ "learning_rate": 5e-06,
351
+ "loss": 0.7423,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.8708904855214457,
356
+ "grad_norm": 0.7126075005956054,
357
+ "learning_rate": 5e-06,
358
+ "loss": 0.7383,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.8883082952318746,
363
+ "grad_norm": 0.7584360793951261,
364
+ "learning_rate": 5e-06,
365
+ "loss": 0.7321,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.9057261049423035,
370
+ "grad_norm": 0.7439364499749611,
371
+ "learning_rate": 5e-06,
372
+ "loss": 0.7371,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.9231439146527324,
377
+ "grad_norm": 0.6529063351558732,
378
+ "learning_rate": 5e-06,
379
+ "loss": 0.74,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.9405617243631613,
384
+ "grad_norm": 0.6579238997317206,
385
+ "learning_rate": 5e-06,
386
+ "loss": 0.7339,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.9579795340735903,
391
+ "grad_norm": 0.6529747723949795,
392
+ "learning_rate": 5e-06,
393
+ "loss": 0.7366,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.9753973437840192,
398
+ "grad_norm": 0.7465822819939318,
399
+ "learning_rate": 5e-06,
400
+ "loss": 0.7329,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.992815153494448,
405
+ "grad_norm": 0.6744574449718616,
406
+ "learning_rate": 5e-06,
407
+ "loss": 0.7336,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.9997822773786197,
412
+ "eval_loss": 0.7317857146263123,
413
+ "eval_runtime": 402.0076,
414
+ "eval_samples_per_second": 38.482,
415
+ "eval_steps_per_second": 0.602,
416
+ "step": 574
417
+ },
418
+ {
419
+ "epoch": 1.010232963204877,
420
+ "grad_norm": 0.7094322700801018,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.763,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.027650772915306,
427
+ "grad_norm": 0.619008567608486,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.6821,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.0450685826257349,
434
+ "grad_norm": 0.7720080238431899,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.6814,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.0624863923361638,
441
+ "grad_norm": 0.613074115463787,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.6871,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.0799042020465925,
448
+ "grad_norm": 0.8529977128112323,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.6916,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.0973220117570215,
455
+ "grad_norm": 0.6185916445154745,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.6852,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.1147398214674504,
462
+ "grad_norm": 0.5960552407712587,
463
+ "learning_rate": 5e-06,
464
+ "loss": 0.6902,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.1321576311778794,
469
+ "grad_norm": 0.6992739712457544,
470
+ "learning_rate": 5e-06,
471
+ "loss": 0.6838,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.1495754408883083,
476
+ "grad_norm": 0.6896093508843089,
477
+ "learning_rate": 5e-06,
478
+ "loss": 0.6883,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.1669932505987373,
483
+ "grad_norm": 0.7618446264021529,
484
+ "learning_rate": 5e-06,
485
+ "loss": 0.6866,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.1844110603091662,
490
+ "grad_norm": 0.5993982811906263,
491
+ "learning_rate": 5e-06,
492
+ "loss": 0.6864,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.201828870019595,
497
+ "grad_norm": 0.7774490221678223,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.6904,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.2192466797300239,
504
+ "grad_norm": 0.7209322592758776,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.6843,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.2366644894404528,
511
+ "grad_norm": 0.5933996592162579,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.6858,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.2540822991508818,
518
+ "grad_norm": 0.603096793298619,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.6895,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.2715001088613107,
525
+ "grad_norm": 0.6254264453133531,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.6848,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.2889179185717397,
532
+ "grad_norm": 0.6255696330381725,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.6846,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.3063357282821686,
539
+ "grad_norm": 0.5954700919121718,
540
+ "learning_rate": 5e-06,
541
+ "loss": 0.6857,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.3237535379925975,
546
+ "grad_norm": 0.605017152001749,
547
+ "learning_rate": 5e-06,
548
+ "loss": 0.6833,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.3411713477030263,
553
+ "grad_norm": 0.6374571812243335,
554
+ "learning_rate": 5e-06,
555
+ "loss": 0.6835,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.3585891574134552,
560
+ "grad_norm": 0.7034685309687484,
561
+ "learning_rate": 5e-06,
562
+ "loss": 0.6862,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.3760069671238842,
567
+ "grad_norm": 0.6478857838671078,
568
+ "learning_rate": 5e-06,
569
+ "loss": 0.6834,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.393424776834313,
574
+ "grad_norm": 0.6774648068840645,
575
+ "learning_rate": 5e-06,
576
+ "loss": 0.6835,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.410842586544742,
581
+ "grad_norm": 0.7999211706624636,
582
+ "learning_rate": 5e-06,
583
+ "loss": 0.6849,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.428260396255171,
588
+ "grad_norm": 0.7093553520320318,
589
+ "learning_rate": 5e-06,
590
+ "loss": 0.6874,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.4456782059655997,
595
+ "grad_norm": 0.6339150451411103,
596
+ "learning_rate": 5e-06,
597
+ "loss": 0.6817,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.4630960156760286,
602
+ "grad_norm": 0.6378354921425449,
603
+ "learning_rate": 5e-06,
604
+ "loss": 0.687,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.4805138253864576,
609
+ "grad_norm": 0.6060950779002315,
610
+ "learning_rate": 5e-06,
611
+ "loss": 0.6852,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.4979316350968865,
616
+ "grad_norm": 0.7027258672686724,
617
+ "learning_rate": 5e-06,
618
+ "loss": 0.6866,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.5153494448073155,
623
+ "grad_norm": 0.6241403475122037,
624
+ "learning_rate": 5e-06,
625
+ "loss": 0.6831,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.5327672545177444,
630
+ "grad_norm": 0.7090161192507007,
631
+ "learning_rate": 5e-06,
632
+ "loss": 0.6827,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.5501850642281734,
637
+ "grad_norm": 0.6858971984003965,
638
+ "learning_rate": 5e-06,
639
+ "loss": 0.6792,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.5676028739386023,
644
+ "grad_norm": 0.6546584740097385,
645
+ "learning_rate": 5e-06,
646
+ "loss": 0.6806,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.5850206836490313,
651
+ "grad_norm": 0.6020087571697199,
652
+ "learning_rate": 5e-06,
653
+ "loss": 0.6799,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.6024384933594602,
658
+ "grad_norm": 0.6501182817858244,
659
+ "learning_rate": 5e-06,
660
+ "loss": 0.6857,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.619856303069889,
665
+ "grad_norm": 0.584870256422628,
666
+ "learning_rate": 5e-06,
667
+ "loss": 0.6803,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.6372741127803179,
672
+ "grad_norm": 0.6317587237334846,
673
+ "learning_rate": 5e-06,
674
+ "loss": 0.6855,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.6546919224907468,
679
+ "grad_norm": 0.5912078658288651,
680
+ "learning_rate": 5e-06,
681
+ "loss": 0.6831,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.6721097322011755,
686
+ "grad_norm": 0.6128368243065496,
687
+ "learning_rate": 5e-06,
688
+ "loss": 0.6808,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.6895275419116045,
693
+ "grad_norm": 0.7946845578841991,
694
+ "learning_rate": 5e-06,
695
+ "loss": 0.6878,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.7069453516220334,
700
+ "grad_norm": 0.6757515701163817,
701
+ "learning_rate": 5e-06,
702
+ "loss": 0.6854,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.7243631613324624,
707
+ "grad_norm": 0.6571419210311429,
708
+ "learning_rate": 5e-06,
709
+ "loss": 0.6823,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.7417809710428913,
714
+ "grad_norm": 0.7598031996788027,
715
+ "learning_rate": 5e-06,
716
+ "loss": 0.6797,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.7591987807533203,
721
+ "grad_norm": 0.6670752253306316,
722
+ "learning_rate": 5e-06,
723
+ "loss": 0.6842,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 1.7766165904637492,
728
+ "grad_norm": 0.6401962122300333,
729
+ "learning_rate": 5e-06,
730
+ "loss": 0.6812,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 1.7940344001741781,
735
+ "grad_norm": 0.7117175290423249,
736
+ "learning_rate": 5e-06,
737
+ "loss": 0.6824,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 1.811452209884607,
742
+ "grad_norm": 0.5800625845659623,
743
+ "learning_rate": 5e-06,
744
+ "loss": 0.6803,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 1.828870019595036,
749
+ "grad_norm": 0.7320040356270946,
750
+ "learning_rate": 5e-06,
751
+ "loss": 0.6803,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 1.846287829305465,
756
+ "grad_norm": 0.6283167554926344,
757
+ "learning_rate": 5e-06,
758
+ "loss": 0.6839,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 1.8637056390158937,
763
+ "grad_norm": 0.8371943589394946,
764
+ "learning_rate": 5e-06,
765
+ "loss": 0.6812,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 1.8811234487263226,
770
+ "grad_norm": 0.6257083963805145,
771
+ "learning_rate": 5e-06,
772
+ "loss": 0.6838,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 1.8985412584367516,
777
+ "grad_norm": 0.5986261297946587,
778
+ "learning_rate": 5e-06,
779
+ "loss": 0.6797,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 1.9159590681471805,
784
+ "grad_norm": 0.6170171924536151,
785
+ "learning_rate": 5e-06,
786
+ "loss": 0.6797,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 1.9333768778576093,
791
+ "grad_norm": 0.5700527826150651,
792
+ "learning_rate": 5e-06,
793
+ "loss": 0.681,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 1.9507946875680382,
798
+ "grad_norm": 0.7918614747451274,
799
+ "learning_rate": 5e-06,
800
+ "loss": 0.6836,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 1.9682124972784671,
805
+ "grad_norm": 0.6423488525843636,
806
+ "learning_rate": 5e-06,
807
+ "loss": 0.6841,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 1.985630306988896,
812
+ "grad_norm": 0.5727071414052627,
813
+ "learning_rate": 5e-06,
814
+ "loss": 0.6807,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 1.9995645547572392,
819
+ "eval_loss": 0.7203673124313354,
820
+ "eval_runtime": 394.6464,
821
+ "eval_samples_per_second": 39.2,
822
+ "eval_steps_per_second": 0.613,
823
+ "step": 1148
824
+ },
825
+ {
826
+ "epoch": 2.003048116699325,
827
+ "grad_norm": 0.9442473115477681,
828
+ "learning_rate": 5e-06,
829
+ "loss": 0.7309,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.020465926409754,
834
+ "grad_norm": 0.7483105880106439,
835
+ "learning_rate": 5e-06,
836
+ "loss": 0.6325,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.037883736120183,
841
+ "grad_norm": 0.7540713563935749,
842
+ "learning_rate": 5e-06,
843
+ "loss": 0.6307,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.055301545830612,
848
+ "grad_norm": 0.6724851440947269,
849
+ "learning_rate": 5e-06,
850
+ "loss": 0.6337,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.072719355541041,
855
+ "grad_norm": 0.8087552584080454,
856
+ "learning_rate": 5e-06,
857
+ "loss": 0.6291,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.0901371652514698,
862
+ "grad_norm": 0.5977695571055209,
863
+ "learning_rate": 5e-06,
864
+ "loss": 0.6303,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.1075549749618987,
869
+ "grad_norm": 0.7569591780057143,
870
+ "learning_rate": 5e-06,
871
+ "loss": 0.63,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.1249727846723276,
876
+ "grad_norm": 0.7224022820617728,
877
+ "learning_rate": 5e-06,
878
+ "loss": 0.6319,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.142390594382756,
883
+ "grad_norm": 0.9103041866730269,
884
+ "learning_rate": 5e-06,
885
+ "loss": 0.6338,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.159808404093185,
890
+ "grad_norm": 0.6573119068550747,
891
+ "learning_rate": 5e-06,
892
+ "loss": 0.6315,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.177226213803614,
897
+ "grad_norm": 0.7130793786888794,
898
+ "learning_rate": 5e-06,
899
+ "loss": 0.6307,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.194644023514043,
904
+ "grad_norm": 0.6787527348130123,
905
+ "learning_rate": 5e-06,
906
+ "loss": 0.635,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.212061833224472,
911
+ "grad_norm": 0.7583316967190475,
912
+ "learning_rate": 5e-06,
913
+ "loss": 0.6328,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.229479642934901,
918
+ "grad_norm": 0.9232698200191256,
919
+ "learning_rate": 5e-06,
920
+ "loss": 0.6392,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.24689745264533,
925
+ "grad_norm": 0.7252346361915288,
926
+ "learning_rate": 5e-06,
927
+ "loss": 0.6347,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.2643152623557588,
932
+ "grad_norm": 0.6362752959635848,
933
+ "learning_rate": 5e-06,
934
+ "loss": 0.6304,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.2817330720661877,
939
+ "grad_norm": 0.6085958821854244,
940
+ "learning_rate": 5e-06,
941
+ "loss": 0.6354,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.2991508817766166,
946
+ "grad_norm": 0.6106358089516802,
947
+ "learning_rate": 5e-06,
948
+ "loss": 0.6319,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.3165686914870456,
953
+ "grad_norm": 0.6704766246511351,
954
+ "learning_rate": 5e-06,
955
+ "loss": 0.6361,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.3339865011974745,
960
+ "grad_norm": 0.7134352783772538,
961
+ "learning_rate": 5e-06,
962
+ "loss": 0.6363,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.3514043109079035,
967
+ "grad_norm": 0.691476396805842,
968
+ "learning_rate": 5e-06,
969
+ "loss": 0.6408,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.3688221206183324,
974
+ "grad_norm": 0.6591953333036876,
975
+ "learning_rate": 5e-06,
976
+ "loss": 0.6333,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.3862399303287614,
981
+ "grad_norm": 0.6492399404200755,
982
+ "learning_rate": 5e-06,
983
+ "loss": 0.6328,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.40365774003919,
988
+ "grad_norm": 0.615428906926297,
989
+ "learning_rate": 5e-06,
990
+ "loss": 0.6413,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 2.421075549749619,
995
+ "grad_norm": 0.6178851722594154,
996
+ "learning_rate": 5e-06,
997
+ "loss": 0.6362,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.4384933594600477,
1002
+ "grad_norm": 0.6630448901048148,
1003
+ "learning_rate": 5e-06,
1004
+ "loss": 0.6354,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 2.4559111691704767,
1009
+ "grad_norm": 0.6761352769262333,
1010
+ "learning_rate": 5e-06,
1011
+ "loss": 0.6364,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 2.4733289788809056,
1016
+ "grad_norm": 0.6840809680625406,
1017
+ "learning_rate": 5e-06,
1018
+ "loss": 0.6347,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 2.4907467885913346,
1023
+ "grad_norm": 0.7752711880925182,
1024
+ "learning_rate": 5e-06,
1025
+ "loss": 0.6375,
1026
+ "step": 1430
1027
+ },
1028
+ {
1029
+ "epoch": 2.5081645983017635,
1030
+ "grad_norm": 0.671961987869029,
1031
+ "learning_rate": 5e-06,
1032
+ "loss": 0.638,
1033
+ "step": 1440
1034
+ },
1035
+ {
1036
+ "epoch": 2.5255824080121925,
1037
+ "grad_norm": 0.6066582748163826,
1038
+ "learning_rate": 5e-06,
1039
+ "loss": 0.6356,
1040
+ "step": 1450
1041
+ },
1042
+ {
1043
+ "epoch": 2.5430002177226214,
1044
+ "grad_norm": 0.6494968644059873,
1045
+ "learning_rate": 5e-06,
1046
+ "loss": 0.64,
1047
+ "step": 1460
1048
+ },
1049
+ {
1050
+ "epoch": 2.5604180274330504,
1051
+ "grad_norm": 0.6819270998889235,
1052
+ "learning_rate": 5e-06,
1053
+ "loss": 0.6392,
1054
+ "step": 1470
1055
+ },
1056
+ {
1057
+ "epoch": 2.5778358371434793,
1058
+ "grad_norm": 0.6720899123226914,
1059
+ "learning_rate": 5e-06,
1060
+ "loss": 0.638,
1061
+ "step": 1480
1062
+ },
1063
+ {
1064
+ "epoch": 2.5952536468539082,
1065
+ "grad_norm": 0.8865903590224419,
1066
+ "learning_rate": 5e-06,
1067
+ "loss": 0.6418,
1068
+ "step": 1490
1069
+ },
1070
+ {
1071
+ "epoch": 2.612671456564337,
1072
+ "grad_norm": 0.8255525182739956,
1073
+ "learning_rate": 5e-06,
1074
+ "loss": 0.637,
1075
+ "step": 1500
1076
+ },
1077
+ {
1078
+ "epoch": 2.6300892662747657,
1079
+ "grad_norm": 0.6926869297282812,
1080
+ "learning_rate": 5e-06,
1081
+ "loss": 0.6359,
1082
+ "step": 1510
1083
+ },
1084
+ {
1085
+ "epoch": 2.647507075985195,
1086
+ "grad_norm": 0.7064032548106364,
1087
+ "learning_rate": 5e-06,
1088
+ "loss": 0.6372,
1089
+ "step": 1520
1090
+ },
1091
+ {
1092
+ "epoch": 2.6649248856956236,
1093
+ "grad_norm": 0.6147984872224924,
1094
+ "learning_rate": 5e-06,
1095
+ "loss": 0.6393,
1096
+ "step": 1530
1097
+ },
1098
+ {
1099
+ "epoch": 2.6823426954060525,
1100
+ "grad_norm": 0.6504099699536218,
1101
+ "learning_rate": 5e-06,
1102
+ "loss": 0.6399,
1103
+ "step": 1540
1104
+ },
1105
+ {
1106
+ "epoch": 2.6997605051164815,
1107
+ "grad_norm": 0.563483068339733,
1108
+ "learning_rate": 5e-06,
1109
+ "loss": 0.6348,
1110
+ "step": 1550
1111
+ },
1112
+ {
1113
+ "epoch": 2.7171783148269104,
1114
+ "grad_norm": 0.730022824759867,
1115
+ "learning_rate": 5e-06,
1116
+ "loss": 0.6358,
1117
+ "step": 1560
1118
+ },
1119
+ {
1120
+ "epoch": 2.7345961245373394,
1121
+ "grad_norm": 0.7435338593643929,
1122
+ "learning_rate": 5e-06,
1123
+ "loss": 0.6416,
1124
+ "step": 1570
1125
+ },
1126
+ {
1127
+ "epoch": 2.7520139342477683,
1128
+ "grad_norm": 0.7041374525178048,
1129
+ "learning_rate": 5e-06,
1130
+ "loss": 0.6312,
1131
+ "step": 1580
1132
+ },
1133
+ {
1134
+ "epoch": 2.7694317439581972,
1135
+ "grad_norm": 0.6185370005773447,
1136
+ "learning_rate": 5e-06,
1137
+ "loss": 0.6369,
1138
+ "step": 1590
1139
+ },
1140
+ {
1141
+ "epoch": 2.786849553668626,
1142
+ "grad_norm": 0.597751813516521,
1143
+ "learning_rate": 5e-06,
1144
+ "loss": 0.6376,
1145
+ "step": 1600
1146
+ },
1147
+ {
1148
+ "epoch": 2.804267363379055,
1149
+ "grad_norm": 0.6525590591893353,
1150
+ "learning_rate": 5e-06,
1151
+ "loss": 0.638,
1152
+ "step": 1610
1153
+ },
1154
+ {
1155
+ "epoch": 2.821685173089484,
1156
+ "grad_norm": 0.6520966089133831,
1157
+ "learning_rate": 5e-06,
1158
+ "loss": 0.6363,
1159
+ "step": 1620
1160
+ },
1161
+ {
1162
+ "epoch": 2.839102982799913,
1163
+ "grad_norm": 0.6318597492523834,
1164
+ "learning_rate": 5e-06,
1165
+ "loss": 0.6392,
1166
+ "step": 1630
1167
+ },
1168
+ {
1169
+ "epoch": 2.856520792510342,
1170
+ "grad_norm": 0.7325044927855683,
1171
+ "learning_rate": 5e-06,
1172
+ "loss": 0.6369,
1173
+ "step": 1640
1174
+ },
1175
+ {
1176
+ "epoch": 2.873938602220771,
1177
+ "grad_norm": 0.6253335500365848,
1178
+ "learning_rate": 5e-06,
1179
+ "loss": 0.636,
1180
+ "step": 1650
1181
+ },
1182
+ {
1183
+ "epoch": 2.8913564119311994,
1184
+ "grad_norm": 0.6704613482673505,
1185
+ "learning_rate": 5e-06,
1186
+ "loss": 0.6376,
1187
+ "step": 1660
1188
+ },
1189
+ {
1190
+ "epoch": 2.908774221641629,
1191
+ "grad_norm": 0.7273411977567759,
1192
+ "learning_rate": 5e-06,
1193
+ "loss": 0.6386,
1194
+ "step": 1670
1195
+ },
1196
+ {
1197
+ "epoch": 2.9261920313520573,
1198
+ "grad_norm": 0.6268248741184522,
1199
+ "learning_rate": 5e-06,
1200
+ "loss": 0.6378,
1201
+ "step": 1680
1202
+ },
1203
+ {
1204
+ "epoch": 2.9436098410624862,
1205
+ "grad_norm": 0.5745167165482074,
1206
+ "learning_rate": 5e-06,
1207
+ "loss": 0.6392,
1208
+ "step": 1690
1209
+ },
1210
+ {
1211
+ "epoch": 2.961027650772915,
1212
+ "grad_norm": 0.6046462612164668,
1213
+ "learning_rate": 5e-06,
1214
+ "loss": 0.642,
1215
+ "step": 1700
1216
+ },
1217
+ {
1218
+ "epoch": 2.978445460483344,
1219
+ "grad_norm": 0.6397198084499147,
1220
+ "learning_rate": 5e-06,
1221
+ "loss": 0.6381,
1222
+ "step": 1710
1223
+ },
1224
+ {
1225
+ "epoch": 2.995863270193773,
1226
+ "grad_norm": 0.7413825248918653,
1227
+ "learning_rate": 5e-06,
1228
+ "loss": 0.638,
1229
+ "step": 1720
1230
+ },
1231
+ {
1232
+ "epoch": 2.999346832135859,
1233
+ "eval_loss": 0.7229765057563782,
1234
+ "eval_runtime": 389.254,
1235
+ "eval_samples_per_second": 39.743,
1236
+ "eval_steps_per_second": 0.622,
1237
+ "step": 1722
1238
+ },
1239
+ {
1240
+ "epoch": 2.999346832135859,
1241
+ "step": 1722,
1242
+ "total_flos": 2884204756992000.0,
1243
+ "train_loss": 0.6974312729536448,
1244
+ "train_runtime": 56418.3982,
1245
+ "train_samples_per_second": 15.629,
1246
+ "train_steps_per_second": 0.031
1247
+ }
1248
+ ],
1249
+ "logging_steps": 10,
1250
+ "max_steps": 1722,
1251
+ "num_input_tokens_seen": 0,
1252
+ "num_train_epochs": 3,
1253
+ "save_steps": 500,
1254
+ "stateful_callbacks": {
1255
+ "TrainerControl": {
1256
+ "args": {
1257
+ "should_epoch_stop": false,
1258
+ "should_evaluate": false,
1259
+ "should_log": false,
1260
+ "should_save": true,
1261
+ "should_training_stop": true
1262
+ },
1263
+ "attributes": {}
1264
+ }
1265
+ },
1266
+ "total_flos": 2884204756992000.0,
1267
+ "train_batch_size": 8,
1268
+ "trial_name": null,
1269
+ "trial_params": null
1270
+ }
training_eval_loss.png ADDED
training_loss.png ADDED