sedrickkeh commited on
Commit
a8bd344
·
verified ·
1 Parent(s): 995493e

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
4
  base_model: mistralai/Mistral-7B-v0.1
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: hp_ablations_mistral_epoch4
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # hp_ablations_mistral_epoch4
17
 
18
- This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.1617
21
 
 
4
  base_model: mistralai/Mistral-7B-v0.1
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: hp_ablations_mistral_epoch4
 
16
 
17
  # hp_ablations_mistral_epoch4
18
 
19
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.1617
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.9954430379746837,
3
+ "eval_loss": 0.1617216169834137,
4
+ "eval_runtime": 254.457,
5
+ "eval_samples_per_second": 52.284,
6
+ "eval_steps_per_second": 0.409,
7
+ "total_flos": 3302754688696320.0,
8
+ "train_loss": 0.4368948165108176,
9
+ "train_runtime": 56763.579,
10
+ "train_samples_per_second": 17.811,
11
+ "train_steps_per_second": 0.035
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.9954430379746837,
3
+ "eval_loss": 0.1617216169834137,
4
+ "eval_runtime": 254.457,
5
+ "eval_samples_per_second": 52.284,
6
+ "eval_steps_per_second": 0.409
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.9954430379746837,
3
+ "total_flos": 3302754688696320.0,
4
+ "train_loss": 0.4368948165108176,
5
+ "train_runtime": 56763.579,
6
+ "train_samples_per_second": 17.811,
7
+ "train_steps_per_second": 0.035
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1453 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.9954430379746837,
5
+ "eval_steps": 500,
6
+ "global_step": 1972,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.020253164556962026,
13
+ "grad_norm": 2.8833762486177865,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.7568,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.04050632911392405,
20
+ "grad_norm": 2.390286912889809,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.6504,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.060759493670886074,
27
+ "grad_norm": 1.489395380260759,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.6287,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0810126582278481,
34
+ "grad_norm": 1.589470284066133,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.6135,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.10126582278481013,
41
+ "grad_norm": 1.4199327904724377,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.6037,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.12151898734177215,
48
+ "grad_norm": 1.4578167281681993,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.5974,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.14177215189873418,
55
+ "grad_norm": 1.3411623258601368,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.5923,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.1620253164556962,
62
+ "grad_norm": 2.0256881877625204,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.5879,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.18227848101265823,
69
+ "grad_norm": 1.865143294695778,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.5869,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.20253164556962025,
76
+ "grad_norm": 2.850869507593689,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.5894,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.22278481012658227,
83
+ "grad_norm": 2.780764039633903,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.5825,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2430379746835443,
90
+ "grad_norm": 2.24595769639212,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.5792,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.26329113924050634,
97
+ "grad_norm": 1.898945973266495,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.5765,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.28354430379746837,
104
+ "grad_norm": 2.0985064075463518,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.5657,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3037974683544304,
111
+ "grad_norm": 2.1947025380420393,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.576,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3240506329113924,
118
+ "grad_norm": 1.9010440206949761,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.5748,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.34430379746835443,
125
+ "grad_norm": 1.5587857210363367,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.5762,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.36455696202531646,
132
+ "grad_norm": 1.940350997849539,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.5726,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.3848101265822785,
139
+ "grad_norm": 1.653915136046625,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.5724,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.4050632911392405,
146
+ "grad_norm": 2.4614019893025274,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.567,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.4253164556962025,
153
+ "grad_norm": 1.8586854938543989,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.5628,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.44556962025316454,
160
+ "grad_norm": 1.4449652115361937,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.5679,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.46582278481012657,
167
+ "grad_norm": 1.3739469268351123,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.5676,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.4860759493670886,
174
+ "grad_norm": 1.165737020699501,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.5644,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5063291139240507,
181
+ "grad_norm": 1.357956082726849,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.5686,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5265822784810127,
188
+ "grad_norm": 1.4295099868510899,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.5554,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.5468354430379747,
195
+ "grad_norm": 1.4688068967033727,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.5643,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.5670886075949367,
202
+ "grad_norm": 1.3744420183733652,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.56,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.5873417721518988,
209
+ "grad_norm": 1.4423763395622504,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.56,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6075949367088608,
216
+ "grad_norm": 1.4527708533649162,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.5596,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6278481012658228,
223
+ "grad_norm": 1.4417603290241021,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.5655,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.6481012658227848,
230
+ "grad_norm": 1.6835798959760988,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.5611,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.6683544303797468,
237
+ "grad_norm": 1.3523279967838302,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.5607,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.6886075949367089,
244
+ "grad_norm": 1.2500179332984684,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.5597,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7088607594936709,
251
+ "grad_norm": 1.2523150009107906,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.5614,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.7291139240506329,
258
+ "grad_norm": 1.0953008806392797,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.5638,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.7493670886075949,
265
+ "grad_norm": 1.6446500941969269,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.5566,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.769620253164557,
272
+ "grad_norm": 1.4079831931594988,
273
+ "learning_rate": 5e-06,
274
+ "loss": 0.5533,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.789873417721519,
279
+ "grad_norm": 1.1110346875099018,
280
+ "learning_rate": 5e-06,
281
+ "loss": 0.5559,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.810126582278481,
286
+ "grad_norm": 1.4268171466763837,
287
+ "learning_rate": 5e-06,
288
+ "loss": 0.5566,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.830379746835443,
293
+ "grad_norm": 1.2447639143712546,
294
+ "learning_rate": 5e-06,
295
+ "loss": 0.5514,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.850632911392405,
300
+ "grad_norm": 1.195155734961536,
301
+ "learning_rate": 5e-06,
302
+ "loss": 0.5587,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.8708860759493671,
307
+ "grad_norm": 1.1003141204515203,
308
+ "learning_rate": 5e-06,
309
+ "loss": 0.5521,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.8911392405063291,
314
+ "grad_norm": 1.3030562652810704,
315
+ "learning_rate": 5e-06,
316
+ "loss": 0.5573,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.9113924050632911,
321
+ "grad_norm": 1.2728739765574453,
322
+ "learning_rate": 5e-06,
323
+ "loss": 0.5488,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.9316455696202531,
328
+ "grad_norm": 1.1393805858707695,
329
+ "learning_rate": 5e-06,
330
+ "loss": 0.5532,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.9518987341772152,
335
+ "grad_norm": 1.252449871115967,
336
+ "learning_rate": 5e-06,
337
+ "loss": 0.5539,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.9721518987341772,
342
+ "grad_norm": 1.3675922433289114,
343
+ "learning_rate": 5e-06,
344
+ "loss": 0.5515,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.9924050632911392,
349
+ "grad_norm": 1.0986012485203254,
350
+ "learning_rate": 5e-06,
351
+ "loss": 0.548,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.9984810126582279,
356
+ "eval_loss": 0.13772521913051605,
357
+ "eval_runtime": 252.9462,
358
+ "eval_samples_per_second": 52.596,
359
+ "eval_steps_per_second": 0.411,
360
+ "step": 493
361
+ },
362
+ {
363
+ "epoch": 1.0131645569620253,
364
+ "grad_norm": 1.8664570600716093,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.5056,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.0334177215189873,
371
+ "grad_norm": 1.690550013794204,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.4717,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.0536708860759494,
378
+ "grad_norm": 1.7450606923145526,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.4683,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.0739240506329113,
385
+ "grad_norm": 1.4739241775856946,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.4682,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.0941772151898734,
392
+ "grad_norm": 2.196710788601052,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.467,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.1144303797468353,
399
+ "grad_norm": 1.4622782937118193,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.4664,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.1346835443037975,
406
+ "grad_norm": 1.204681750576354,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.4629,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.1549367088607596,
413
+ "grad_norm": 1.2919169624567832,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.4723,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.1751898734177215,
420
+ "grad_norm": 1.1738791165204896,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.4696,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.1954430379746834,
427
+ "grad_norm": 1.2749973090696376,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.4655,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.2156962025316456,
434
+ "grad_norm": 1.3069834745764197,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.4738,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.2359493670886077,
441
+ "grad_norm": 1.268141928024117,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.4689,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.2562025316455696,
448
+ "grad_norm": 2.349539426930866,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.4738,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.2764556962025315,
455
+ "grad_norm": 1.3038280118636631,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.4724,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.2967088607594937,
462
+ "grad_norm": 1.2561549442694693,
463
+ "learning_rate": 5e-06,
464
+ "loss": 0.4717,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.3169620253164558,
469
+ "grad_norm": 1.2353995568966352,
470
+ "learning_rate": 5e-06,
471
+ "loss": 0.4756,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.3372151898734177,
476
+ "grad_norm": 1.3143696543162657,
477
+ "learning_rate": 5e-06,
478
+ "loss": 0.4653,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.3574683544303796,
483
+ "grad_norm": 1.8332487196614191,
484
+ "learning_rate": 5e-06,
485
+ "loss": 0.4791,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.3777215189873417,
490
+ "grad_norm": 1.5782907788998026,
491
+ "learning_rate": 5e-06,
492
+ "loss": 0.4743,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.3979746835443039,
497
+ "grad_norm": 1.43844179760011,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.4733,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.4182278481012658,
504
+ "grad_norm": 1.2104409020838625,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.4695,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.438481012658228,
511
+ "grad_norm": 1.2829692982799845,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.4756,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.4587341772151898,
518
+ "grad_norm": 1.2115512985925798,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.4757,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.478987341772152,
525
+ "grad_norm": 1.1708137297250578,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.479,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.4992405063291139,
532
+ "grad_norm": 1.1860297553473809,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.4737,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.5194936708860758,
539
+ "grad_norm": 1.159382227654447,
540
+ "learning_rate": 5e-06,
541
+ "loss": 0.4764,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.539746835443038,
546
+ "grad_norm": 1.1694651947442445,
547
+ "learning_rate": 5e-06,
548
+ "loss": 0.4765,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.56,
553
+ "grad_norm": 1.160166128209198,
554
+ "learning_rate": 5e-06,
555
+ "loss": 0.4765,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.5802531645569622,
560
+ "grad_norm": 1.1966330785907486,
561
+ "learning_rate": 5e-06,
562
+ "loss": 0.4762,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.600506329113924,
567
+ "grad_norm": 1.2884100928471158,
568
+ "learning_rate": 5e-06,
569
+ "loss": 0.4797,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.620759493670886,
574
+ "grad_norm": 1.50350568469768,
575
+ "learning_rate": 5e-06,
576
+ "loss": 0.4765,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.6410126582278481,
581
+ "grad_norm": 1.1416454468827366,
582
+ "learning_rate": 5e-06,
583
+ "loss": 0.4685,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.6612658227848103,
588
+ "grad_norm": 1.3289305602168267,
589
+ "learning_rate": 5e-06,
590
+ "loss": 0.4771,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.6815189873417722,
595
+ "grad_norm": 1.242003954761086,
596
+ "learning_rate": 5e-06,
597
+ "loss": 0.4721,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.701772151898734,
602
+ "grad_norm": 1.1084079600907246,
603
+ "learning_rate": 5e-06,
604
+ "loss": 0.4731,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.7220253164556962,
609
+ "grad_norm": 1.268075113702087,
610
+ "learning_rate": 5e-06,
611
+ "loss": 0.4766,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.7422784810126584,
616
+ "grad_norm": 1.152924839399553,
617
+ "learning_rate": 5e-06,
618
+ "loss": 0.4767,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.7625316455696203,
623
+ "grad_norm": 1.0955649434062678,
624
+ "learning_rate": 5e-06,
625
+ "loss": 0.4776,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.7827848101265822,
630
+ "grad_norm": 1.3082664193765503,
631
+ "learning_rate": 5e-06,
632
+ "loss": 0.4815,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.8030379746835443,
637
+ "grad_norm": 1.166931921170078,
638
+ "learning_rate": 5e-06,
639
+ "loss": 0.4788,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.8232911392405065,
644
+ "grad_norm": 1.1423266879559995,
645
+ "learning_rate": 5e-06,
646
+ "loss": 0.477,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.8435443037974684,
651
+ "grad_norm": 1.3005388006776002,
652
+ "learning_rate": 5e-06,
653
+ "loss": 0.4789,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.8637974683544303,
658
+ "grad_norm": 1.5362991154311363,
659
+ "learning_rate": 5e-06,
660
+ "loss": 0.4791,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.8840506329113924,
665
+ "grad_norm": 1.0615549431669202,
666
+ "learning_rate": 5e-06,
667
+ "loss": 0.4746,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.9043037974683545,
672
+ "grad_norm": 1.1359371350640348,
673
+ "learning_rate": 5e-06,
674
+ "loss": 0.4774,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.9245569620253165,
679
+ "grad_norm": 1.338873863277151,
680
+ "learning_rate": 5e-06,
681
+ "loss": 0.4799,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.9448101265822784,
686
+ "grad_norm": 1.0562817698500642,
687
+ "learning_rate": 5e-06,
688
+ "loss": 0.4834,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.9650632911392405,
693
+ "grad_norm": 1.1976389472965596,
694
+ "learning_rate": 5e-06,
695
+ "loss": 0.481,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.9853164556962026,
700
+ "grad_norm": 1.1318384251326352,
701
+ "learning_rate": 5e-06,
702
+ "loss": 0.4823,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.999493670886076,
707
+ "eval_loss": 0.13791824877262115,
708
+ "eval_runtime": 252.4301,
709
+ "eval_samples_per_second": 52.704,
710
+ "eval_steps_per_second": 0.412,
711
+ "step": 987
712
+ },
713
+ {
714
+ "epoch": 2.0060759493670886,
715
+ "grad_norm": 2.24179568741783,
716
+ "learning_rate": 5e-06,
717
+ "loss": 0.4515,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.0263291139240507,
722
+ "grad_norm": 1.6981313244359,
723
+ "learning_rate": 5e-06,
724
+ "loss": 0.3891,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.046582278481013,
729
+ "grad_norm": 1.5796760743871119,
730
+ "learning_rate": 5e-06,
731
+ "loss": 0.3814,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.0668354430379745,
736
+ "grad_norm": 1.7079048311976808,
737
+ "learning_rate": 5e-06,
738
+ "loss": 0.3794,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.0870886075949366,
743
+ "grad_norm": 1.4027876167762106,
744
+ "learning_rate": 5e-06,
745
+ "loss": 0.3793,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.1073417721518988,
750
+ "grad_norm": 1.2776686544662923,
751
+ "learning_rate": 5e-06,
752
+ "loss": 0.3758,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.127594936708861,
757
+ "grad_norm": 1.3728804833099486,
758
+ "learning_rate": 5e-06,
759
+ "loss": 0.3868,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.1478481012658226,
764
+ "grad_norm": 1.4205398673755427,
765
+ "learning_rate": 5e-06,
766
+ "loss": 0.3827,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.1681012658227847,
771
+ "grad_norm": 1.3832130487234917,
772
+ "learning_rate": 5e-06,
773
+ "loss": 0.3852,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.188354430379747,
778
+ "grad_norm": 1.5929946445474668,
779
+ "learning_rate": 5e-06,
780
+ "loss": 0.3841,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.208607594936709,
785
+ "grad_norm": 1.4600989820317136,
786
+ "learning_rate": 5e-06,
787
+ "loss": 0.3818,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.2288607594936707,
792
+ "grad_norm": 1.4225880515710438,
793
+ "learning_rate": 5e-06,
794
+ "loss": 0.3909,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.249113924050633,
799
+ "grad_norm": 1.780076806234694,
800
+ "learning_rate": 5e-06,
801
+ "loss": 0.3884,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.269367088607595,
806
+ "grad_norm": 1.694668518355522,
807
+ "learning_rate": 5e-06,
808
+ "loss": 0.387,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.289620253164557,
813
+ "grad_norm": 1.7667024915838094,
814
+ "learning_rate": 5e-06,
815
+ "loss": 0.3894,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.309873417721519,
820
+ "grad_norm": 1.410793594228534,
821
+ "learning_rate": 5e-06,
822
+ "loss": 0.3842,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.330126582278481,
827
+ "grad_norm": 1.5234909172570381,
828
+ "learning_rate": 5e-06,
829
+ "loss": 0.3908,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.350379746835443,
834
+ "grad_norm": 1.2213254079078641,
835
+ "learning_rate": 5e-06,
836
+ "loss": 0.3903,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.370632911392405,
841
+ "grad_norm": 1.4202255106744544,
842
+ "learning_rate": 5e-06,
843
+ "loss": 0.3915,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.390886075949367,
848
+ "grad_norm": 1.4023194734455904,
849
+ "learning_rate": 5e-06,
850
+ "loss": 0.3924,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.411139240506329,
855
+ "grad_norm": 1.7343746037355243,
856
+ "learning_rate": 5e-06,
857
+ "loss": 0.3905,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.431392405063291,
862
+ "grad_norm": 1.4482110997116577,
863
+ "learning_rate": 5e-06,
864
+ "loss": 0.3899,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.4516455696202533,
869
+ "grad_norm": 1.9131070141039026,
870
+ "learning_rate": 5e-06,
871
+ "loss": 0.3878,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.4718987341772154,
876
+ "grad_norm": 1.3699773358857317,
877
+ "learning_rate": 5e-06,
878
+ "loss": 0.3907,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.492151898734177,
883
+ "grad_norm": 1.2435143983285588,
884
+ "learning_rate": 5e-06,
885
+ "loss": 0.3937,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.512405063291139,
890
+ "grad_norm": 1.271353869459015,
891
+ "learning_rate": 5e-06,
892
+ "loss": 0.393,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.5326582278481014,
897
+ "grad_norm": 1.9458404824086235,
898
+ "learning_rate": 5e-06,
899
+ "loss": 0.3921,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.552911392405063,
904
+ "grad_norm": 1.324983619143349,
905
+ "learning_rate": 5e-06,
906
+ "loss": 0.386,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.573164556962025,
911
+ "grad_norm": 1.5086572692565505,
912
+ "learning_rate": 5e-06,
913
+ "loss": 0.3929,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.5934177215189873,
918
+ "grad_norm": 1.2387524175778437,
919
+ "learning_rate": 5e-06,
920
+ "loss": 0.3956,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.6136708860759494,
925
+ "grad_norm": 1.4032957006294775,
926
+ "learning_rate": 5e-06,
927
+ "loss": 0.3985,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.6339240506329116,
932
+ "grad_norm": 1.4186988248363785,
933
+ "learning_rate": 5e-06,
934
+ "loss": 0.3949,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.6541772151898733,
939
+ "grad_norm": 1.474152675372263,
940
+ "learning_rate": 5e-06,
941
+ "loss": 0.3949,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.6744303797468354,
946
+ "grad_norm": 1.388800748370683,
947
+ "learning_rate": 5e-06,
948
+ "loss": 0.3972,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.6946835443037975,
953
+ "grad_norm": 1.3404535288890715,
954
+ "learning_rate": 5e-06,
955
+ "loss": 0.3975,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.714936708860759,
960
+ "grad_norm": 1.3485784987514158,
961
+ "learning_rate": 5e-06,
962
+ "loss": 0.3998,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.7351898734177214,
967
+ "grad_norm": 1.3182287721338872,
968
+ "learning_rate": 5e-06,
969
+ "loss": 0.3972,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.7554430379746835,
974
+ "grad_norm": 1.2129071324788472,
975
+ "learning_rate": 5e-06,
976
+ "loss": 0.3932,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.7756962025316456,
981
+ "grad_norm": 1.4082013444619639,
982
+ "learning_rate": 5e-06,
983
+ "loss": 0.3999,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.7959493670886078,
988
+ "grad_norm": 1.4390382641502573,
989
+ "learning_rate": 5e-06,
990
+ "loss": 0.3974,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 2.81620253164557,
995
+ "grad_norm": 1.3463527613931228,
996
+ "learning_rate": 5e-06,
997
+ "loss": 0.4004,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.8364556962025316,
1002
+ "grad_norm": 1.2190952668881454,
1003
+ "learning_rate": 5e-06,
1004
+ "loss": 0.3945,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 2.8567088607594937,
1009
+ "grad_norm": 1.2959901372391192,
1010
+ "learning_rate": 5e-06,
1011
+ "loss": 0.4014,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 2.876962025316456,
1016
+ "grad_norm": 1.2846058903861945,
1017
+ "learning_rate": 5e-06,
1018
+ "loss": 0.3987,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 2.8972151898734175,
1023
+ "grad_norm": 1.340897452737586,
1024
+ "learning_rate": 5e-06,
1025
+ "loss": 0.3983,
1026
+ "step": 1430
1027
+ },
1028
+ {
1029
+ "epoch": 2.9174683544303797,
1030
+ "grad_norm": 1.3196158163944824,
1031
+ "learning_rate": 5e-06,
1032
+ "loss": 0.4016,
1033
+ "step": 1440
1034
+ },
1035
+ {
1036
+ "epoch": 2.937721518987342,
1037
+ "grad_norm": 1.275687217034204,
1038
+ "learning_rate": 5e-06,
1039
+ "loss": 0.4105,
1040
+ "step": 1450
1041
+ },
1042
+ {
1043
+ "epoch": 2.957974683544304,
1044
+ "grad_norm": 1.4052855567194664,
1045
+ "learning_rate": 5e-06,
1046
+ "loss": 0.3992,
1047
+ "step": 1460
1048
+ },
1049
+ {
1050
+ "epoch": 2.978227848101266,
1051
+ "grad_norm": 1.3721809126891413,
1052
+ "learning_rate": 5e-06,
1053
+ "loss": 0.403,
1054
+ "step": 1470
1055
+ },
1056
+ {
1057
+ "epoch": 2.9984810126582278,
1058
+ "grad_norm": 1.3733986827541713,
1059
+ "learning_rate": 5e-06,
1060
+ "loss": 0.4008,
1061
+ "step": 1480
1062
+ },
1063
+ {
1064
+ "epoch": 2.9984810126582278,
1065
+ "eval_loss": 0.1451626569032669,
1066
+ "eval_runtime": 252.5403,
1067
+ "eval_samples_per_second": 52.681,
1068
+ "eval_steps_per_second": 0.412,
1069
+ "step": 1480
1070
+ },
1071
+ {
1072
+ "epoch": 3.019240506329114,
1073
+ "grad_norm": 2.1233881502453333,
1074
+ "learning_rate": 5e-06,
1075
+ "loss": 0.3123,
1076
+ "step": 1490
1077
+ },
1078
+ {
1079
+ "epoch": 3.039493670886076,
1080
+ "grad_norm": 1.733976300717687,
1081
+ "learning_rate": 5e-06,
1082
+ "loss": 0.2924,
1083
+ "step": 1500
1084
+ },
1085
+ {
1086
+ "epoch": 3.059746835443038,
1087
+ "grad_norm": 1.7085808896440553,
1088
+ "learning_rate": 5e-06,
1089
+ "loss": 0.2942,
1090
+ "step": 1510
1091
+ },
1092
+ {
1093
+ "epoch": 3.08,
1094
+ "grad_norm": 1.4544968881558145,
1095
+ "learning_rate": 5e-06,
1096
+ "loss": 0.2933,
1097
+ "step": 1520
1098
+ },
1099
+ {
1100
+ "epoch": 3.100253164556962,
1101
+ "grad_norm": 1.6261331378733803,
1102
+ "learning_rate": 5e-06,
1103
+ "loss": 0.2944,
1104
+ "step": 1530
1105
+ },
1106
+ {
1107
+ "epoch": 3.120506329113924,
1108
+ "grad_norm": 1.5609283167478611,
1109
+ "learning_rate": 5e-06,
1110
+ "loss": 0.292,
1111
+ "step": 1540
1112
+ },
1113
+ {
1114
+ "epoch": 3.140759493670886,
1115
+ "grad_norm": 1.6902454180217539,
1116
+ "learning_rate": 5e-06,
1117
+ "loss": 0.29,
1118
+ "step": 1550
1119
+ },
1120
+ {
1121
+ "epoch": 3.161012658227848,
1122
+ "grad_norm": 1.47961286622397,
1123
+ "learning_rate": 5e-06,
1124
+ "loss": 0.2964,
1125
+ "step": 1560
1126
+ },
1127
+ {
1128
+ "epoch": 3.1812658227848103,
1129
+ "grad_norm": 1.6098815338414532,
1130
+ "learning_rate": 5e-06,
1131
+ "loss": 0.2967,
1132
+ "step": 1570
1133
+ },
1134
+ {
1135
+ "epoch": 3.201518987341772,
1136
+ "grad_norm": 1.4570975957744257,
1137
+ "learning_rate": 5e-06,
1138
+ "loss": 0.2999,
1139
+ "step": 1580
1140
+ },
1141
+ {
1142
+ "epoch": 3.221772151898734,
1143
+ "grad_norm": 1.5616376984698326,
1144
+ "learning_rate": 5e-06,
1145
+ "loss": 0.3003,
1146
+ "step": 1590
1147
+ },
1148
+ {
1149
+ "epoch": 3.2420253164556962,
1150
+ "grad_norm": 1.5261875412769847,
1151
+ "learning_rate": 5e-06,
1152
+ "loss": 0.3007,
1153
+ "step": 1600
1154
+ },
1155
+ {
1156
+ "epoch": 3.2622784810126584,
1157
+ "grad_norm": 1.5927243321009188,
1158
+ "learning_rate": 5e-06,
1159
+ "loss": 0.2992,
1160
+ "step": 1610
1161
+ },
1162
+ {
1163
+ "epoch": 3.28253164556962,
1164
+ "grad_norm": 1.4687003886067878,
1165
+ "learning_rate": 5e-06,
1166
+ "loss": 0.3016,
1167
+ "step": 1620
1168
+ },
1169
+ {
1170
+ "epoch": 3.302784810126582,
1171
+ "grad_norm": 1.6212181828314611,
1172
+ "learning_rate": 5e-06,
1173
+ "loss": 0.3046,
1174
+ "step": 1630
1175
+ },
1176
+ {
1177
+ "epoch": 3.3230379746835443,
1178
+ "grad_norm": 1.7006560112850782,
1179
+ "learning_rate": 5e-06,
1180
+ "loss": 0.3014,
1181
+ "step": 1640
1182
+ },
1183
+ {
1184
+ "epoch": 3.3432911392405065,
1185
+ "grad_norm": 1.6369351197517492,
1186
+ "learning_rate": 5e-06,
1187
+ "loss": 0.3031,
1188
+ "step": 1650
1189
+ },
1190
+ {
1191
+ "epoch": 3.363544303797468,
1192
+ "grad_norm": 1.8997824836659962,
1193
+ "learning_rate": 5e-06,
1194
+ "loss": 0.3052,
1195
+ "step": 1660
1196
+ },
1197
+ {
1198
+ "epoch": 3.3837974683544303,
1199
+ "grad_norm": 1.7686559384037446,
1200
+ "learning_rate": 5e-06,
1201
+ "loss": 0.2994,
1202
+ "step": 1670
1203
+ },
1204
+ {
1205
+ "epoch": 3.4040506329113924,
1206
+ "grad_norm": 1.9852860129783203,
1207
+ "learning_rate": 5e-06,
1208
+ "loss": 0.2987,
1209
+ "step": 1680
1210
+ },
1211
+ {
1212
+ "epoch": 3.4243037974683546,
1213
+ "grad_norm": 1.6687727310492642,
1214
+ "learning_rate": 5e-06,
1215
+ "loss": 0.3028,
1216
+ "step": 1690
1217
+ },
1218
+ {
1219
+ "epoch": 3.4445569620253167,
1220
+ "grad_norm": 1.555588423959256,
1221
+ "learning_rate": 5e-06,
1222
+ "loss": 0.3012,
1223
+ "step": 1700
1224
+ },
1225
+ {
1226
+ "epoch": 3.4648101265822784,
1227
+ "grad_norm": 1.570937882764948,
1228
+ "learning_rate": 5e-06,
1229
+ "loss": 0.3033,
1230
+ "step": 1710
1231
+ },
1232
+ {
1233
+ "epoch": 3.4850632911392405,
1234
+ "grad_norm": 1.762794823286088,
1235
+ "learning_rate": 5e-06,
1236
+ "loss": 0.3078,
1237
+ "step": 1720
1238
+ },
1239
+ {
1240
+ "epoch": 3.5053164556962026,
1241
+ "grad_norm": 1.5085676767074419,
1242
+ "learning_rate": 5e-06,
1243
+ "loss": 0.3076,
1244
+ "step": 1730
1245
+ },
1246
+ {
1247
+ "epoch": 3.5255696202531643,
1248
+ "grad_norm": 1.846690362471807,
1249
+ "learning_rate": 5e-06,
1250
+ "loss": 0.3058,
1251
+ "step": 1740
1252
+ },
1253
+ {
1254
+ "epoch": 3.5458227848101265,
1255
+ "grad_norm": 1.888656474961098,
1256
+ "learning_rate": 5e-06,
1257
+ "loss": 0.3092,
1258
+ "step": 1750
1259
+ },
1260
+ {
1261
+ "epoch": 3.5660759493670886,
1262
+ "grad_norm": 1.5522432118926228,
1263
+ "learning_rate": 5e-06,
1264
+ "loss": 0.3031,
1265
+ "step": 1760
1266
+ },
1267
+ {
1268
+ "epoch": 3.5863291139240507,
1269
+ "grad_norm": 1.7040265273376634,
1270
+ "learning_rate": 5e-06,
1271
+ "loss": 0.3097,
1272
+ "step": 1770
1273
+ },
1274
+ {
1275
+ "epoch": 3.606582278481013,
1276
+ "grad_norm": 1.6319175616422348,
1277
+ "learning_rate": 5e-06,
1278
+ "loss": 0.3076,
1279
+ "step": 1780
1280
+ },
1281
+ {
1282
+ "epoch": 3.6268354430379746,
1283
+ "grad_norm": 1.6539455217449284,
1284
+ "learning_rate": 5e-06,
1285
+ "loss": 0.3054,
1286
+ "step": 1790
1287
+ },
1288
+ {
1289
+ "epoch": 3.6470886075949367,
1290
+ "grad_norm": 1.6323498992182317,
1291
+ "learning_rate": 5e-06,
1292
+ "loss": 0.3089,
1293
+ "step": 1800
1294
+ },
1295
+ {
1296
+ "epoch": 3.667341772151899,
1297
+ "grad_norm": 1.9811098470470307,
1298
+ "learning_rate": 5e-06,
1299
+ "loss": 0.3141,
1300
+ "step": 1810
1301
+ },
1302
+ {
1303
+ "epoch": 3.6875949367088605,
1304
+ "grad_norm": 1.5750523511747638,
1305
+ "learning_rate": 5e-06,
1306
+ "loss": 0.3093,
1307
+ "step": 1820
1308
+ },
1309
+ {
1310
+ "epoch": 3.7078481012658226,
1311
+ "grad_norm": 1.5810037258388918,
1312
+ "learning_rate": 5e-06,
1313
+ "loss": 0.3105,
1314
+ "step": 1830
1315
+ },
1316
+ {
1317
+ "epoch": 3.728101265822785,
1318
+ "grad_norm": 1.554399518805066,
1319
+ "learning_rate": 5e-06,
1320
+ "loss": 0.3124,
1321
+ "step": 1840
1322
+ },
1323
+ {
1324
+ "epoch": 3.748354430379747,
1325
+ "grad_norm": 1.6069072450441366,
1326
+ "learning_rate": 5e-06,
1327
+ "loss": 0.3099,
1328
+ "step": 1850
1329
+ },
1330
+ {
1331
+ "epoch": 3.768607594936709,
1332
+ "grad_norm": 1.6769246041867307,
1333
+ "learning_rate": 5e-06,
1334
+ "loss": 0.3173,
1335
+ "step": 1860
1336
+ },
1337
+ {
1338
+ "epoch": 3.7888607594936707,
1339
+ "grad_norm": 1.579060667933051,
1340
+ "learning_rate": 5e-06,
1341
+ "loss": 0.3145,
1342
+ "step": 1870
1343
+ },
1344
+ {
1345
+ "epoch": 3.809113924050633,
1346
+ "grad_norm": 2.0501104971409396,
1347
+ "learning_rate": 5e-06,
1348
+ "loss": 0.3154,
1349
+ "step": 1880
1350
+ },
1351
+ {
1352
+ "epoch": 3.829367088607595,
1353
+ "grad_norm": 2.2983760386486214,
1354
+ "learning_rate": 5e-06,
1355
+ "loss": 0.315,
1356
+ "step": 1890
1357
+ },
1358
+ {
1359
+ "epoch": 3.8496202531645567,
1360
+ "grad_norm": 1.780585915706879,
1361
+ "learning_rate": 5e-06,
1362
+ "loss": 0.3157,
1363
+ "step": 1900
1364
+ },
1365
+ {
1366
+ "epoch": 3.869873417721519,
1367
+ "grad_norm": 1.77785313158742,
1368
+ "learning_rate": 5e-06,
1369
+ "loss": 0.3117,
1370
+ "step": 1910
1371
+ },
1372
+ {
1373
+ "epoch": 3.890126582278481,
1374
+ "grad_norm": 1.6198590987029773,
1375
+ "learning_rate": 5e-06,
1376
+ "loss": 0.3172,
1377
+ "step": 1920
1378
+ },
1379
+ {
1380
+ "epoch": 3.910379746835443,
1381
+ "grad_norm": 1.64334724662568,
1382
+ "learning_rate": 5e-06,
1383
+ "loss": 0.3147,
1384
+ "step": 1930
1385
+ },
1386
+ {
1387
+ "epoch": 3.9306329113924052,
1388
+ "grad_norm": 1.5274532742672213,
1389
+ "learning_rate": 5e-06,
1390
+ "loss": 0.312,
1391
+ "step": 1940
1392
+ },
1393
+ {
1394
+ "epoch": 3.9508860759493674,
1395
+ "grad_norm": 1.7941457309206295,
1396
+ "learning_rate": 5e-06,
1397
+ "loss": 0.3164,
1398
+ "step": 1950
1399
+ },
1400
+ {
1401
+ "epoch": 3.971139240506329,
1402
+ "grad_norm": 1.6138102060492845,
1403
+ "learning_rate": 5e-06,
1404
+ "loss": 0.3175,
1405
+ "step": 1960
1406
+ },
1407
+ {
1408
+ "epoch": 3.991392405063291,
1409
+ "grad_norm": 1.7439224514084468,
1410
+ "learning_rate": 5e-06,
1411
+ "loss": 0.3172,
1412
+ "step": 1970
1413
+ },
1414
+ {
1415
+ "epoch": 3.9954430379746837,
1416
+ "eval_loss": 0.1617216169834137,
1417
+ "eval_runtime": 254.4743,
1418
+ "eval_samples_per_second": 52.28,
1419
+ "eval_steps_per_second": 0.409,
1420
+ "step": 1972
1421
+ },
1422
+ {
1423
+ "epoch": 3.9954430379746837,
1424
+ "step": 1972,
1425
+ "total_flos": 3302754688696320.0,
1426
+ "train_loss": 0.4368948165108176,
1427
+ "train_runtime": 56763.579,
1428
+ "train_samples_per_second": 17.811,
1429
+ "train_steps_per_second": 0.035
1430
+ }
1431
+ ],
1432
+ "logging_steps": 10,
1433
+ "max_steps": 1972,
1434
+ "num_input_tokens_seen": 0,
1435
+ "num_train_epochs": 4,
1436
+ "save_steps": 500,
1437
+ "stateful_callbacks": {
1438
+ "TrainerControl": {
1439
+ "args": {
1440
+ "should_epoch_stop": false,
1441
+ "should_evaluate": false,
1442
+ "should_log": false,
1443
+ "should_save": true,
1444
+ "should_training_stop": true
1445
+ },
1446
+ "attributes": {}
1447
+ }
1448
+ },
1449
+ "total_flos": 3302754688696320.0,
1450
+ "train_batch_size": 8,
1451
+ "trial_name": null,
1452
+ "trial_params": null
1453
+ }
training_eval_loss.png ADDED
training_loss.png ADDED