sedrickkeh commited on
Commit
f6fed68
·
verified ·
1 Parent(s): 4f7d540

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_16_ranking_stackexchange
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # top_16_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_16_ranking_stackexchange
 
16
 
17
  # top_16_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_16_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": 2.9980781550288276,
3
+ "eval_loss": 0.7988265156745911,
4
+ "eval_runtime": 629.3142,
5
+ "eval_samples_per_second": 25.067,
6
+ "eval_steps_per_second": 0.392,
7
+ "total_flos": 2939480986091520.0,
8
+ "train_loss": 0.7835989086716263,
9
+ "train_runtime": 103740.1935,
10
+ "train_samples_per_second": 8.667,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9980781550288276,
3
+ "eval_loss": 0.7988265156745911,
4
+ "eval_runtime": 629.3142,
5
+ "eval_samples_per_second": 25.067,
6
+ "eval_steps_per_second": 0.392
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9980781550288276,
3
+ "total_flos": 2939480986091520.0,
4
+ "train_loss": 0.7835989086716263,
5
+ "train_runtime": 103740.1935,
6
+ "train_samples_per_second": 8.667,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1291 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9980781550288276,
5
+ "eval_steps": 500,
6
+ "global_step": 1755,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01708306641042067,
13
+ "grad_norm": 30.988456901868677,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0716,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.03416613282084134,
20
+ "grad_norm": 3.981743724280262,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.9952,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.05124919923126201,
27
+ "grad_norm": 0.9238645350776216,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.9502,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.06833226564168268,
34
+ "grad_norm": 1.0528903755575718,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.9206,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.08541533205210335,
41
+ "grad_norm": 1.1750428009605969,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.9102,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.10249839846252402,
48
+ "grad_norm": 0.7437586737148641,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.8945,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.11958146487294469,
55
+ "grad_norm": 0.6775772425198474,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.8836,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.13666453128336536,
62
+ "grad_norm": 0.5992902350468045,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.8771,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.15374759769378604,
69
+ "grad_norm": 0.5246527905235602,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.8688,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.1708306641042067,
76
+ "grad_norm": 0.6744242377338667,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.8674,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.18791373051462737,
83
+ "grad_norm": 0.5815020177486712,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.8658,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.20499679692504805,
90
+ "grad_norm": 0.612553188685598,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.8607,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.22207986333546872,
97
+ "grad_norm": 0.550502713970348,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.8597,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.23916292974588937,
104
+ "grad_norm": 0.6852509049344128,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.854,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.25624599615631005,
111
+ "grad_norm": 0.578544920290097,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.8583,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.27332906256673073,
118
+ "grad_norm": 0.5189175609736144,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.851,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.2904121289771514,
125
+ "grad_norm": 0.5087573435881564,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.8505,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.3074951953875721,
132
+ "grad_norm": 0.6966346988112697,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.8454,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.32457826179799276,
139
+ "grad_norm": 0.5997059592749316,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.8484,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.3416613282084134,
146
+ "grad_norm": 0.6852631417751086,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.8483,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.35874439461883406,
153
+ "grad_norm": 0.6164595381164006,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.8462,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.37582746102925474,
160
+ "grad_norm": 0.6904944801515591,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.8445,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.3929105274396754,
167
+ "grad_norm": 0.6512004476683885,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.8399,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.4099935938500961,
174
+ "grad_norm": 0.6184327993659001,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.8391,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.42707666026051677,
181
+ "grad_norm": 0.802165112115216,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.8384,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.44415972667093745,
188
+ "grad_norm": 0.6499733286909369,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.8364,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.4612427930813581,
195
+ "grad_norm": 0.5388351566067404,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.8303,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.47832585949177875,
202
+ "grad_norm": 0.5438990498346035,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.832,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.4954089259021994,
209
+ "grad_norm": 0.5187067150821502,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.8325,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.5124919923126201,
216
+ "grad_norm": 0.6697424824465937,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.8337,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.5295750587230408,
223
+ "grad_norm": 0.6633949919937228,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.8296,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.5466581251334615,
230
+ "grad_norm": 0.5550184232084733,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.8293,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.5637411915438821,
237
+ "grad_norm": 0.725923344191194,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.8315,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.5808242579543028,
244
+ "grad_norm": 0.6017986140852183,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.828,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.5979073243647235,
251
+ "grad_norm": 0.5482521266135052,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.8299,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.6149903907751442,
258
+ "grad_norm": 0.5278215410540681,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.832,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.6320734571855648,
265
+ "grad_norm": 0.6984298439291815,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.8291,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.6491565235959855,
272
+ "grad_norm": 0.5017079870431141,
273
+ "learning_rate": 5e-06,
274
+ "loss": 0.827,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.6662395900064062,
279
+ "grad_norm": 0.5032298742038609,
280
+ "learning_rate": 5e-06,
281
+ "loss": 0.8272,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.6833226564168268,
286
+ "grad_norm": 0.5330416146652471,
287
+ "learning_rate": 5e-06,
288
+ "loss": 0.8247,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.7004057228272474,
293
+ "grad_norm": 0.57373005832922,
294
+ "learning_rate": 5e-06,
295
+ "loss": 0.8242,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.7174887892376681,
300
+ "grad_norm": 0.5257091555093115,
301
+ "learning_rate": 5e-06,
302
+ "loss": 0.8266,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.7345718556480888,
307
+ "grad_norm": 0.5789856149074786,
308
+ "learning_rate": 5e-06,
309
+ "loss": 0.8242,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.7516549220585095,
314
+ "grad_norm": 0.5299653272462573,
315
+ "learning_rate": 5e-06,
316
+ "loss": 0.816,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.7687379884689302,
321
+ "grad_norm": 0.5964593947123102,
322
+ "learning_rate": 5e-06,
323
+ "loss": 0.8242,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.7858210548793508,
328
+ "grad_norm": 0.7283098877992732,
329
+ "learning_rate": 5e-06,
330
+ "loss": 0.8241,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.8029041212897715,
335
+ "grad_norm": 0.5985448658584591,
336
+ "learning_rate": 5e-06,
337
+ "loss": 0.8197,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.8199871877001922,
342
+ "grad_norm": 0.5623410005491558,
343
+ "learning_rate": 5e-06,
344
+ "loss": 0.8213,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.8370702541106129,
349
+ "grad_norm": 0.6408816581220068,
350
+ "learning_rate": 5e-06,
351
+ "loss": 0.823,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.8541533205210335,
356
+ "grad_norm": 0.6249632483859644,
357
+ "learning_rate": 5e-06,
358
+ "loss": 0.8184,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.8712363869314542,
363
+ "grad_norm": 0.5922346578431508,
364
+ "learning_rate": 5e-06,
365
+ "loss": 0.8144,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.8883194533418749,
370
+ "grad_norm": 0.690797808616181,
371
+ "learning_rate": 5e-06,
372
+ "loss": 0.8179,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.9054025197522956,
377
+ "grad_norm": 0.5637410385766849,
378
+ "learning_rate": 5e-06,
379
+ "loss": 0.8153,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.9224855861627163,
384
+ "grad_norm": 0.6713092701845222,
385
+ "learning_rate": 5e-06,
386
+ "loss": 0.8156,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.9395686525731369,
391
+ "grad_norm": 0.5614251903253611,
392
+ "learning_rate": 5e-06,
393
+ "loss": 0.8151,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.9566517189835575,
398
+ "grad_norm": 0.488524190594288,
399
+ "learning_rate": 5e-06,
400
+ "loss": 0.8165,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.9737347853939782,
405
+ "grad_norm": 0.5588451830957717,
406
+ "learning_rate": 5e-06,
407
+ "loss": 0.8147,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.9908178518043989,
412
+ "grad_norm": 0.5319341754740086,
413
+ "learning_rate": 5e-06,
414
+ "loss": 0.8146,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.9993593850096092,
419
+ "eval_loss": 0.8145768046379089,
420
+ "eval_runtime": 623.2585,
421
+ "eval_samples_per_second": 25.311,
422
+ "eval_steps_per_second": 0.396,
423
+ "step": 585
424
+ },
425
+ {
426
+ "epoch": 1.0079009182148195,
427
+ "grad_norm": 0.7444773824556985,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.8416,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.0249839846252402,
434
+ "grad_norm": 0.6182001774270124,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.7786,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.0420670510356609,
441
+ "grad_norm": 0.5471145639195996,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.7689,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.0591501174460816,
448
+ "grad_norm": 0.5749072203498992,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.774,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.0762331838565022,
455
+ "grad_norm": 0.5458121480997504,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.7727,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.093316250266923,
462
+ "grad_norm": 0.57658998771773,
463
+ "learning_rate": 5e-06,
464
+ "loss": 0.7723,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.1103993166773436,
469
+ "grad_norm": 0.718911287142942,
470
+ "learning_rate": 5e-06,
471
+ "loss": 0.7761,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.1274823830877643,
476
+ "grad_norm": 0.7129614149484951,
477
+ "learning_rate": 5e-06,
478
+ "loss": 0.7791,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.144565449498185,
483
+ "grad_norm": 0.5411663435831485,
484
+ "learning_rate": 5e-06,
485
+ "loss": 0.7737,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.1616485159086056,
490
+ "grad_norm": 0.7987307718934373,
491
+ "learning_rate": 5e-06,
492
+ "loss": 0.7665,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.1787315823190263,
497
+ "grad_norm": 0.5752310814305064,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.7742,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.195814648729447,
504
+ "grad_norm": 0.5310768207788683,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.7738,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.2128977151398677,
511
+ "grad_norm": 0.5646734820206145,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.7745,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.2299807815502883,
518
+ "grad_norm": 0.5131848643270003,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.7749,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.247063847960709,
525
+ "grad_norm": 0.7018347821869065,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.7761,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.2641469143711297,
532
+ "grad_norm": 0.5677858771240941,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.7733,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.2812299807815504,
539
+ "grad_norm": 0.5314774866996713,
540
+ "learning_rate": 5e-06,
541
+ "loss": 0.7751,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.298313047191971,
546
+ "grad_norm": 0.6656368518895404,
547
+ "learning_rate": 5e-06,
548
+ "loss": 0.7749,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.3153961136023917,
553
+ "grad_norm": 0.5039492371844833,
554
+ "learning_rate": 5e-06,
555
+ "loss": 0.7741,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.3324791800128124,
560
+ "grad_norm": 0.5105033014036762,
561
+ "learning_rate": 5e-06,
562
+ "loss": 0.7784,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.349562246423233,
567
+ "grad_norm": 0.5030749236842763,
568
+ "learning_rate": 5e-06,
569
+ "loss": 0.7758,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.3666453128336538,
574
+ "grad_norm": 0.5846299051076495,
575
+ "learning_rate": 5e-06,
576
+ "loss": 0.7733,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.3837283792440744,
581
+ "grad_norm": 0.5992440442463463,
582
+ "learning_rate": 5e-06,
583
+ "loss": 0.7739,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.4008114456544951,
588
+ "grad_norm": 0.547090040748775,
589
+ "learning_rate": 5e-06,
590
+ "loss": 0.7744,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.4178945120649158,
595
+ "grad_norm": 0.5741884776951681,
596
+ "learning_rate": 5e-06,
597
+ "loss": 0.7703,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.4349775784753362,
602
+ "grad_norm": 0.5238258323687885,
603
+ "learning_rate": 5e-06,
604
+ "loss": 0.7701,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.452060644885757,
609
+ "grad_norm": 0.5265486787202277,
610
+ "learning_rate": 5e-06,
611
+ "loss": 0.7687,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.4691437112961776,
616
+ "grad_norm": 0.5591682134523662,
617
+ "learning_rate": 5e-06,
618
+ "loss": 0.7694,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.4862267777065983,
623
+ "grad_norm": 0.5637486227419112,
624
+ "learning_rate": 5e-06,
625
+ "loss": 0.7713,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.503309844117019,
630
+ "grad_norm": 0.5276872431482891,
631
+ "learning_rate": 5e-06,
632
+ "loss": 0.7687,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.5203929105274396,
637
+ "grad_norm": 0.5299879511165935,
638
+ "learning_rate": 5e-06,
639
+ "loss": 0.7719,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.5374759769378603,
644
+ "grad_norm": 0.48443212446653844,
645
+ "learning_rate": 5e-06,
646
+ "loss": 0.7704,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.554559043348281,
651
+ "grad_norm": 0.5258029162836203,
652
+ "learning_rate": 5e-06,
653
+ "loss": 0.7681,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.5716421097587017,
658
+ "grad_norm": 0.5839360099287706,
659
+ "learning_rate": 5e-06,
660
+ "loss": 0.772,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.5887251761691223,
665
+ "grad_norm": 0.5806331874369932,
666
+ "learning_rate": 5e-06,
667
+ "loss": 0.7736,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.605808242579543,
672
+ "grad_norm": 0.6613985728737157,
673
+ "learning_rate": 5e-06,
674
+ "loss": 0.7724,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.6228913089899637,
679
+ "grad_norm": 0.5224489011940004,
680
+ "learning_rate": 5e-06,
681
+ "loss": 0.7711,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.6399743754003844,
686
+ "grad_norm": 0.5454437716534818,
687
+ "learning_rate": 5e-06,
688
+ "loss": 0.7715,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.657057441810805,
693
+ "grad_norm": 0.5161526858636564,
694
+ "learning_rate": 5e-06,
695
+ "loss": 0.7783,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.6741405082212257,
700
+ "grad_norm": 0.7631274530949943,
701
+ "learning_rate": 5e-06,
702
+ "loss": 0.7721,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.6912235746316464,
707
+ "grad_norm": 0.6083126340996768,
708
+ "learning_rate": 5e-06,
709
+ "loss": 0.7718,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.708306641042067,
714
+ "grad_norm": 0.5310268793627193,
715
+ "learning_rate": 5e-06,
716
+ "loss": 0.7741,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.7253897074524878,
721
+ "grad_norm": 0.4883757515317452,
722
+ "learning_rate": 5e-06,
723
+ "loss": 0.771,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 1.7424727738629084,
728
+ "grad_norm": 0.5215621795180689,
729
+ "learning_rate": 5e-06,
730
+ "loss": 0.7728,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 1.759555840273329,
735
+ "grad_norm": 0.49887803010112675,
736
+ "learning_rate": 5e-06,
737
+ "loss": 0.7702,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 1.7766389066837496,
742
+ "grad_norm": 0.538143965723932,
743
+ "learning_rate": 5e-06,
744
+ "loss": 0.7695,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 1.7937219730941703,
749
+ "grad_norm": 0.5943865951120142,
750
+ "learning_rate": 5e-06,
751
+ "loss": 0.7713,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 1.810805039504591,
756
+ "grad_norm": 0.5034904524114908,
757
+ "learning_rate": 5e-06,
758
+ "loss": 0.7707,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 1.8278881059150116,
763
+ "grad_norm": 0.5739027654813702,
764
+ "learning_rate": 5e-06,
765
+ "loss": 0.767,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 1.8449711723254323,
770
+ "grad_norm": 0.5345337736484315,
771
+ "learning_rate": 5e-06,
772
+ "loss": 0.7739,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 1.862054238735853,
777
+ "grad_norm": 0.8233000709404549,
778
+ "learning_rate": 5e-06,
779
+ "loss": 0.7697,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 1.8791373051462736,
784
+ "grad_norm": 0.5699216631288021,
785
+ "learning_rate": 5e-06,
786
+ "loss": 0.7715,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 1.8962203715566943,
791
+ "grad_norm": 0.5480692157923471,
792
+ "learning_rate": 5e-06,
793
+ "loss": 0.7715,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 1.913303437967115,
798
+ "grad_norm": 0.6493917189844246,
799
+ "learning_rate": 5e-06,
800
+ "loss": 0.776,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 1.9303865043775357,
805
+ "grad_norm": 0.4971193417821817,
806
+ "learning_rate": 5e-06,
807
+ "loss": 0.7689,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 1.9474695707879563,
812
+ "grad_norm": 0.5213534104860004,
813
+ "learning_rate": 5e-06,
814
+ "loss": 0.7691,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 1.964552637198377,
819
+ "grad_norm": 0.5515331643144213,
820
+ "learning_rate": 5e-06,
821
+ "loss": 0.7684,
822
+ "step": 1150
823
+ },
824
+ {
825
+ "epoch": 1.9816357036087977,
826
+ "grad_norm": 0.6132524891266977,
827
+ "learning_rate": 5e-06,
828
+ "loss": 0.7651,
829
+ "step": 1160
830
+ },
831
+ {
832
+ "epoch": 1.9987187700192184,
833
+ "grad_norm": 0.5207251406889574,
834
+ "learning_rate": 5e-06,
835
+ "loss": 0.7679,
836
+ "step": 1170
837
+ },
838
+ {
839
+ "epoch": 1.9987187700192184,
840
+ "eval_loss": 0.8001261949539185,
841
+ "eval_runtime": 623.1773,
842
+ "eval_samples_per_second": 25.314,
843
+ "eval_steps_per_second": 0.396,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.015801836429639,
848
+ "grad_norm": 0.696280654661383,
849
+ "learning_rate": 5e-06,
850
+ "loss": 0.7761,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.0328849028400597,
855
+ "grad_norm": 0.6141244434895877,
856
+ "learning_rate": 5e-06,
857
+ "loss": 0.7251,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.0499679692504804,
862
+ "grad_norm": 0.6049456191917907,
863
+ "learning_rate": 5e-06,
864
+ "loss": 0.7275,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.067051035660901,
869
+ "grad_norm": 0.5271804189451788,
870
+ "learning_rate": 5e-06,
871
+ "loss": 0.7222,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.0841341020713218,
876
+ "grad_norm": 0.5825184609454925,
877
+ "learning_rate": 5e-06,
878
+ "loss": 0.7265,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.1012171684817424,
883
+ "grad_norm": 0.5032946228138522,
884
+ "learning_rate": 5e-06,
885
+ "loss": 0.7253,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.118300234892163,
890
+ "grad_norm": 0.5147327767567343,
891
+ "learning_rate": 5e-06,
892
+ "loss": 0.7237,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.135383301302584,
897
+ "grad_norm": 0.5337482087146928,
898
+ "learning_rate": 5e-06,
899
+ "loss": 0.7281,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.1524663677130045,
904
+ "grad_norm": 0.59826922882338,
905
+ "learning_rate": 5e-06,
906
+ "loss": 0.7328,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.169549434123425,
911
+ "grad_norm": 0.5946570187866338,
912
+ "learning_rate": 5e-06,
913
+ "loss": 0.7295,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.186632500533846,
918
+ "grad_norm": 0.6437960040336966,
919
+ "learning_rate": 5e-06,
920
+ "loss": 0.7337,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.2037155669442665,
925
+ "grad_norm": 0.5667571654097528,
926
+ "learning_rate": 5e-06,
927
+ "loss": 0.7257,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.220798633354687,
932
+ "grad_norm": 0.5711027651356156,
933
+ "learning_rate": 5e-06,
934
+ "loss": 0.7295,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.237881699765108,
939
+ "grad_norm": 0.5604913831263466,
940
+ "learning_rate": 5e-06,
941
+ "loss": 0.7258,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.2549647661755285,
946
+ "grad_norm": 0.49584992475251044,
947
+ "learning_rate": 5e-06,
948
+ "loss": 0.7282,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.2720478325859492,
953
+ "grad_norm": 0.48636367384700585,
954
+ "learning_rate": 5e-06,
955
+ "loss": 0.7289,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.28913089899637,
960
+ "grad_norm": 0.5593094273198317,
961
+ "learning_rate": 5e-06,
962
+ "loss": 0.7261,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.3062139654067906,
967
+ "grad_norm": 0.5334937979304919,
968
+ "learning_rate": 5e-06,
969
+ "loss": 0.7274,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.3232970318172113,
974
+ "grad_norm": 0.63384705400206,
975
+ "learning_rate": 5e-06,
976
+ "loss": 0.7295,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.340380098227632,
981
+ "grad_norm": 0.5143434005458392,
982
+ "learning_rate": 5e-06,
983
+ "loss": 0.7283,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.3574631646380526,
988
+ "grad_norm": 0.6076783258962472,
989
+ "learning_rate": 5e-06,
990
+ "loss": 0.7296,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 2.3745462310484733,
995
+ "grad_norm": 0.6067756593571197,
996
+ "learning_rate": 5e-06,
997
+ "loss": 0.7248,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.391629297458894,
1002
+ "grad_norm": 0.6071395306047531,
1003
+ "learning_rate": 5e-06,
1004
+ "loss": 0.7318,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 2.4087123638693146,
1009
+ "grad_norm": 0.5997962743795122,
1010
+ "learning_rate": 5e-06,
1011
+ "loss": 0.7272,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 2.4257954302797353,
1016
+ "grad_norm": 0.6633499264729928,
1017
+ "learning_rate": 5e-06,
1018
+ "loss": 0.7277,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 2.442878496690156,
1023
+ "grad_norm": 0.5544821713317218,
1024
+ "learning_rate": 5e-06,
1025
+ "loss": 0.7307,
1026
+ "step": 1430
1027
+ },
1028
+ {
1029
+ "epoch": 2.4599615631005767,
1030
+ "grad_norm": 0.5348856989916878,
1031
+ "learning_rate": 5e-06,
1032
+ "loss": 0.7313,
1033
+ "step": 1440
1034
+ },
1035
+ {
1036
+ "epoch": 2.4770446295109974,
1037
+ "grad_norm": 0.5567282104551005,
1038
+ "learning_rate": 5e-06,
1039
+ "loss": 0.7304,
1040
+ "step": 1450
1041
+ },
1042
+ {
1043
+ "epoch": 2.494127695921418,
1044
+ "grad_norm": 0.49476735212888745,
1045
+ "learning_rate": 5e-06,
1046
+ "loss": 0.7301,
1047
+ "step": 1460
1048
+ },
1049
+ {
1050
+ "epoch": 2.5112107623318387,
1051
+ "grad_norm": 0.5172195774829064,
1052
+ "learning_rate": 5e-06,
1053
+ "loss": 0.7279,
1054
+ "step": 1470
1055
+ },
1056
+ {
1057
+ "epoch": 2.5282938287422594,
1058
+ "grad_norm": 0.5822469173059942,
1059
+ "learning_rate": 5e-06,
1060
+ "loss": 0.728,
1061
+ "step": 1480
1062
+ },
1063
+ {
1064
+ "epoch": 2.54537689515268,
1065
+ "grad_norm": 0.5665275024242861,
1066
+ "learning_rate": 5e-06,
1067
+ "loss": 0.727,
1068
+ "step": 1490
1069
+ },
1070
+ {
1071
+ "epoch": 2.5624599615631007,
1072
+ "grad_norm": 0.5261365140179813,
1073
+ "learning_rate": 5e-06,
1074
+ "loss": 0.7326,
1075
+ "step": 1500
1076
+ },
1077
+ {
1078
+ "epoch": 2.5795430279735214,
1079
+ "grad_norm": 0.5317881820166406,
1080
+ "learning_rate": 5e-06,
1081
+ "loss": 0.7316,
1082
+ "step": 1510
1083
+ },
1084
+ {
1085
+ "epoch": 2.596626094383942,
1086
+ "grad_norm": 0.5623482133625999,
1087
+ "learning_rate": 5e-06,
1088
+ "loss": 0.7312,
1089
+ "step": 1520
1090
+ },
1091
+ {
1092
+ "epoch": 2.6137091607943628,
1093
+ "grad_norm": 0.5379867031953368,
1094
+ "learning_rate": 5e-06,
1095
+ "loss": 0.729,
1096
+ "step": 1530
1097
+ },
1098
+ {
1099
+ "epoch": 2.6307922272047835,
1100
+ "grad_norm": 0.552606133346205,
1101
+ "learning_rate": 5e-06,
1102
+ "loss": 0.7282,
1103
+ "step": 1540
1104
+ },
1105
+ {
1106
+ "epoch": 2.647875293615204,
1107
+ "grad_norm": 0.5260176310975024,
1108
+ "learning_rate": 5e-06,
1109
+ "loss": 0.7316,
1110
+ "step": 1550
1111
+ },
1112
+ {
1113
+ "epoch": 2.664958360025625,
1114
+ "grad_norm": 0.5417204925891144,
1115
+ "learning_rate": 5e-06,
1116
+ "loss": 0.7311,
1117
+ "step": 1560
1118
+ },
1119
+ {
1120
+ "epoch": 2.6820414264360455,
1121
+ "grad_norm": 0.5191792624557837,
1122
+ "learning_rate": 5e-06,
1123
+ "loss": 0.7317,
1124
+ "step": 1570
1125
+ },
1126
+ {
1127
+ "epoch": 2.699124492846466,
1128
+ "grad_norm": 0.5082503207244659,
1129
+ "learning_rate": 5e-06,
1130
+ "loss": 0.7308,
1131
+ "step": 1580
1132
+ },
1133
+ {
1134
+ "epoch": 2.716207559256887,
1135
+ "grad_norm": 0.5352199374254042,
1136
+ "learning_rate": 5e-06,
1137
+ "loss": 0.7322,
1138
+ "step": 1590
1139
+ },
1140
+ {
1141
+ "epoch": 2.7332906256673075,
1142
+ "grad_norm": 0.4938969791102419,
1143
+ "learning_rate": 5e-06,
1144
+ "loss": 0.7299,
1145
+ "step": 1600
1146
+ },
1147
+ {
1148
+ "epoch": 2.750373692077728,
1149
+ "grad_norm": 0.5349619842682974,
1150
+ "learning_rate": 5e-06,
1151
+ "loss": 0.7311,
1152
+ "step": 1610
1153
+ },
1154
+ {
1155
+ "epoch": 2.767456758488149,
1156
+ "grad_norm": 0.5982776306942509,
1157
+ "learning_rate": 5e-06,
1158
+ "loss": 0.7326,
1159
+ "step": 1620
1160
+ },
1161
+ {
1162
+ "epoch": 2.7845398248985695,
1163
+ "grad_norm": 0.5610641447482575,
1164
+ "learning_rate": 5e-06,
1165
+ "loss": 0.7283,
1166
+ "step": 1630
1167
+ },
1168
+ {
1169
+ "epoch": 2.8016228913089902,
1170
+ "grad_norm": 0.5289582066062115,
1171
+ "learning_rate": 5e-06,
1172
+ "loss": 0.7322,
1173
+ "step": 1640
1174
+ },
1175
+ {
1176
+ "epoch": 2.818705957719411,
1177
+ "grad_norm": 0.5307084408188756,
1178
+ "learning_rate": 5e-06,
1179
+ "loss": 0.7305,
1180
+ "step": 1650
1181
+ },
1182
+ {
1183
+ "epoch": 2.8357890241298316,
1184
+ "grad_norm": 0.5768867367143191,
1185
+ "learning_rate": 5e-06,
1186
+ "loss": 0.7318,
1187
+ "step": 1660
1188
+ },
1189
+ {
1190
+ "epoch": 2.852872090540252,
1191
+ "grad_norm": 0.5013755884966334,
1192
+ "learning_rate": 5e-06,
1193
+ "loss": 0.7261,
1194
+ "step": 1670
1195
+ },
1196
+ {
1197
+ "epoch": 2.8699551569506725,
1198
+ "grad_norm": 0.5386292168646896,
1199
+ "learning_rate": 5e-06,
1200
+ "loss": 0.7326,
1201
+ "step": 1680
1202
+ },
1203
+ {
1204
+ "epoch": 2.887038223361093,
1205
+ "grad_norm": 0.5042887110473108,
1206
+ "learning_rate": 5e-06,
1207
+ "loss": 0.7267,
1208
+ "step": 1690
1209
+ },
1210
+ {
1211
+ "epoch": 2.904121289771514,
1212
+ "grad_norm": 0.5778864247918416,
1213
+ "learning_rate": 5e-06,
1214
+ "loss": 0.7304,
1215
+ "step": 1700
1216
+ },
1217
+ {
1218
+ "epoch": 2.9212043561819345,
1219
+ "grad_norm": 0.4628270969407437,
1220
+ "learning_rate": 5e-06,
1221
+ "loss": 0.7337,
1222
+ "step": 1710
1223
+ },
1224
+ {
1225
+ "epoch": 2.938287422592355,
1226
+ "grad_norm": 0.4828533328054976,
1227
+ "learning_rate": 5e-06,
1228
+ "loss": 0.7305,
1229
+ "step": 1720
1230
+ },
1231
+ {
1232
+ "epoch": 2.955370489002776,
1233
+ "grad_norm": 0.5335294858018457,
1234
+ "learning_rate": 5e-06,
1235
+ "loss": 0.7255,
1236
+ "step": 1730
1237
+ },
1238
+ {
1239
+ "epoch": 2.9724535554131966,
1240
+ "grad_norm": 0.4855853932089583,
1241
+ "learning_rate": 5e-06,
1242
+ "loss": 0.7299,
1243
+ "step": 1740
1244
+ },
1245
+ {
1246
+ "epoch": 2.9895366218236172,
1247
+ "grad_norm": 0.4876186210552259,
1248
+ "learning_rate": 5e-06,
1249
+ "loss": 0.7294,
1250
+ "step": 1750
1251
+ },
1252
+ {
1253
+ "epoch": 2.9980781550288276,
1254
+ "eval_loss": 0.7988265156745911,
1255
+ "eval_runtime": 623.1353,
1256
+ "eval_samples_per_second": 25.316,
1257
+ "eval_steps_per_second": 0.396,
1258
+ "step": 1755
1259
+ },
1260
+ {
1261
+ "epoch": 2.9980781550288276,
1262
+ "step": 1755,
1263
+ "total_flos": 2939480986091520.0,
1264
+ "train_loss": 0.7835989086716263,
1265
+ "train_runtime": 103740.1935,
1266
+ "train_samples_per_second": 8.667,
1267
+ "train_steps_per_second": 0.017
1268
+ }
1269
+ ],
1270
+ "logging_steps": 10,
1271
+ "max_steps": 1755,
1272
+ "num_input_tokens_seen": 0,
1273
+ "num_train_epochs": 3,
1274
+ "save_steps": 500,
1275
+ "stateful_callbacks": {
1276
+ "TrainerControl": {
1277
+ "args": {
1278
+ "should_epoch_stop": false,
1279
+ "should_evaluate": false,
1280
+ "should_log": false,
1281
+ "should_save": true,
1282
+ "should_training_stop": true
1283
+ },
1284
+ "attributes": {}
1285
+ }
1286
+ },
1287
+ "total_flos": 2939480986091520.0,
1288
+ "train_batch_size": 8,
1289
+ "trial_name": null,
1290
+ "trial_params": null
1291
+ }
training_eval_loss.png ADDED
training_loss.png ADDED