learn3r commited on
Commit
64e8917
·
1 Parent(s): 439f1c7

End of training

Browse files
Files changed (5) hide show
  1. README.md +4 -2
  2. all_results.json +13 -0
  3. eval_results.json +8 -0
  4. train_results.json +8 -0
  5. trainer_state.json +1692 -0
README.md CHANGED
@@ -2,6 +2,8 @@
2
  base_model: learn3r/longt5_xl_gov_bp_15
3
  tags:
4
  - generated_from_trainer
 
 
5
  model-index:
6
  - name: longt5_xl_gov_bp_20
7
  results: []
@@ -12,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
12
 
13
  # longt5_xl_gov_bp_20
14
 
15
- This model is a fine-tuned version of [learn3r/longt5_xl_gov_bp_15](https://huggingface.co/learn3r/longt5_xl_gov_bp_15) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 1.4473
18
 
19
  ## Model description
20
 
 
2
  base_model: learn3r/longt5_xl_gov_bp_15
3
  tags:
4
  - generated_from_trainer
5
+ datasets:
6
+ - learn3r/gov_report_memsum_oracle
7
  model-index:
8
  - name: longt5_xl_gov_bp_20
9
  results: []
 
14
 
15
  # longt5_xl_gov_bp_20
16
 
17
+ This model is a fine-tuned version of [learn3r/longt5_xl_gov_bp_15](https://huggingface.co/learn3r/longt5_xl_gov_bp_15) on the learn3r/gov_report_memsum_oracle dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.3082
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.99,
3
+ "eval_loss": 1.3082436323165894,
4
+ "eval_runtime": 149.6782,
5
+ "eval_samples": 972,
6
+ "eval_samples_per_second": 6.494,
7
+ "eval_steps_per_second": 3.247,
8
+ "train_loss": 1.0100317417698748,
9
+ "train_runtime": 34968.4642,
10
+ "train_samples": 17457,
11
+ "train_samples_per_second": 1.997,
12
+ "train_steps_per_second": 0.016
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.99,
3
+ "eval_loss": 1.3082436323165894,
4
+ "eval_runtime": 149.6782,
5
+ "eval_samples": 972,
6
+ "eval_samples_per_second": 6.494,
7
+ "eval_steps_per_second": 3.247
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.99,
3
+ "train_loss": 1.0100317417698748,
4
+ "train_runtime": 34968.4642,
5
+ "train_samples": 17457,
6
+ "train_samples_per_second": 1.997,
7
+ "train_steps_per_second": 0.016
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1692 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.3082436323165894,
3
+ "best_model_checkpoint": "longt5_xl_gov_bp_20/checkpoint-136",
4
+ "epoch": 3.9885439340130597,
5
+ "eval_steps": 500,
6
+ "global_step": 544,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 0.001,
14
+ "loss": 2.5953,
15
+ "step": 2
16
+ },
17
+ {
18
+ "epoch": 0.03,
19
+ "learning_rate": 0.001,
20
+ "loss": 1.6661,
21
+ "step": 4
22
+ },
23
+ {
24
+ "epoch": 0.04,
25
+ "learning_rate": 0.001,
26
+ "loss": 1.5932,
27
+ "step": 6
28
+ },
29
+ {
30
+ "epoch": 0.06,
31
+ "learning_rate": 0.001,
32
+ "loss": 1.4725,
33
+ "step": 8
34
+ },
35
+ {
36
+ "epoch": 0.07,
37
+ "learning_rate": 0.001,
38
+ "loss": 1.4643,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.09,
43
+ "learning_rate": 0.001,
44
+ "loss": 1.4159,
45
+ "step": 12
46
+ },
47
+ {
48
+ "epoch": 0.1,
49
+ "learning_rate": 0.001,
50
+ "loss": 1.4757,
51
+ "step": 14
52
+ },
53
+ {
54
+ "epoch": 0.12,
55
+ "learning_rate": 0.001,
56
+ "loss": 1.4381,
57
+ "step": 16
58
+ },
59
+ {
60
+ "epoch": 0.13,
61
+ "learning_rate": 0.001,
62
+ "loss": 1.4287,
63
+ "step": 18
64
+ },
65
+ {
66
+ "epoch": 0.15,
67
+ "learning_rate": 0.001,
68
+ "loss": 1.3829,
69
+ "step": 20
70
+ },
71
+ {
72
+ "epoch": 0.16,
73
+ "learning_rate": 0.001,
74
+ "loss": 1.3927,
75
+ "step": 22
76
+ },
77
+ {
78
+ "epoch": 0.18,
79
+ "learning_rate": 0.001,
80
+ "loss": 1.3431,
81
+ "step": 24
82
+ },
83
+ {
84
+ "epoch": 0.19,
85
+ "learning_rate": 0.001,
86
+ "loss": 1.3943,
87
+ "step": 26
88
+ },
89
+ {
90
+ "epoch": 0.21,
91
+ "learning_rate": 0.001,
92
+ "loss": 1.4268,
93
+ "step": 28
94
+ },
95
+ {
96
+ "epoch": 0.22,
97
+ "learning_rate": 0.001,
98
+ "loss": 1.386,
99
+ "step": 30
100
+ },
101
+ {
102
+ "epoch": 0.23,
103
+ "learning_rate": 0.001,
104
+ "loss": 1.401,
105
+ "step": 32
106
+ },
107
+ {
108
+ "epoch": 0.25,
109
+ "learning_rate": 0.001,
110
+ "loss": 1.365,
111
+ "step": 34
112
+ },
113
+ {
114
+ "epoch": 0.26,
115
+ "learning_rate": 0.001,
116
+ "loss": 1.3378,
117
+ "step": 36
118
+ },
119
+ {
120
+ "epoch": 0.28,
121
+ "learning_rate": 0.001,
122
+ "loss": 1.3579,
123
+ "step": 38
124
+ },
125
+ {
126
+ "epoch": 0.29,
127
+ "learning_rate": 0.001,
128
+ "loss": 1.3314,
129
+ "step": 40
130
+ },
131
+ {
132
+ "epoch": 0.31,
133
+ "learning_rate": 0.001,
134
+ "loss": 1.3307,
135
+ "step": 42
136
+ },
137
+ {
138
+ "epoch": 0.32,
139
+ "learning_rate": 0.001,
140
+ "loss": 1.4013,
141
+ "step": 44
142
+ },
143
+ {
144
+ "epoch": 0.34,
145
+ "learning_rate": 0.001,
146
+ "loss": 1.3564,
147
+ "step": 46
148
+ },
149
+ {
150
+ "epoch": 0.35,
151
+ "learning_rate": 0.001,
152
+ "loss": 1.3673,
153
+ "step": 48
154
+ },
155
+ {
156
+ "epoch": 0.37,
157
+ "learning_rate": 0.001,
158
+ "loss": 1.3609,
159
+ "step": 50
160
+ },
161
+ {
162
+ "epoch": 0.38,
163
+ "learning_rate": 0.001,
164
+ "loss": 1.3597,
165
+ "step": 52
166
+ },
167
+ {
168
+ "epoch": 0.4,
169
+ "learning_rate": 0.001,
170
+ "loss": 1.327,
171
+ "step": 54
172
+ },
173
+ {
174
+ "epoch": 0.41,
175
+ "learning_rate": 0.001,
176
+ "loss": 1.3272,
177
+ "step": 56
178
+ },
179
+ {
180
+ "epoch": 0.43,
181
+ "learning_rate": 0.001,
182
+ "loss": 1.3404,
183
+ "step": 58
184
+ },
185
+ {
186
+ "epoch": 0.44,
187
+ "learning_rate": 0.001,
188
+ "loss": 1.3542,
189
+ "step": 60
190
+ },
191
+ {
192
+ "epoch": 0.45,
193
+ "learning_rate": 0.001,
194
+ "loss": 1.32,
195
+ "step": 62
196
+ },
197
+ {
198
+ "epoch": 0.47,
199
+ "learning_rate": 0.001,
200
+ "loss": 1.3283,
201
+ "step": 64
202
+ },
203
+ {
204
+ "epoch": 0.48,
205
+ "learning_rate": 0.001,
206
+ "loss": 1.3143,
207
+ "step": 66
208
+ },
209
+ {
210
+ "epoch": 0.5,
211
+ "learning_rate": 0.001,
212
+ "loss": 1.2993,
213
+ "step": 68
214
+ },
215
+ {
216
+ "epoch": 0.51,
217
+ "learning_rate": 0.001,
218
+ "loss": 1.3036,
219
+ "step": 70
220
+ },
221
+ {
222
+ "epoch": 0.53,
223
+ "learning_rate": 0.001,
224
+ "loss": 1.3274,
225
+ "step": 72
226
+ },
227
+ {
228
+ "epoch": 0.54,
229
+ "learning_rate": 0.001,
230
+ "loss": 1.3184,
231
+ "step": 74
232
+ },
233
+ {
234
+ "epoch": 0.56,
235
+ "learning_rate": 0.001,
236
+ "loss": 1.3451,
237
+ "step": 76
238
+ },
239
+ {
240
+ "epoch": 0.57,
241
+ "learning_rate": 0.001,
242
+ "loss": 1.3614,
243
+ "step": 78
244
+ },
245
+ {
246
+ "epoch": 0.59,
247
+ "learning_rate": 0.001,
248
+ "loss": 1.3126,
249
+ "step": 80
250
+ },
251
+ {
252
+ "epoch": 0.6,
253
+ "learning_rate": 0.001,
254
+ "loss": 1.3278,
255
+ "step": 82
256
+ },
257
+ {
258
+ "epoch": 0.62,
259
+ "learning_rate": 0.001,
260
+ "loss": 1.291,
261
+ "step": 84
262
+ },
263
+ {
264
+ "epoch": 0.63,
265
+ "learning_rate": 0.001,
266
+ "loss": 1.3128,
267
+ "step": 86
268
+ },
269
+ {
270
+ "epoch": 0.65,
271
+ "learning_rate": 0.001,
272
+ "loss": 1.3087,
273
+ "step": 88
274
+ },
275
+ {
276
+ "epoch": 0.66,
277
+ "learning_rate": 0.001,
278
+ "loss": 1.332,
279
+ "step": 90
280
+ },
281
+ {
282
+ "epoch": 0.67,
283
+ "learning_rate": 0.001,
284
+ "loss": 1.2924,
285
+ "step": 92
286
+ },
287
+ {
288
+ "epoch": 0.69,
289
+ "learning_rate": 0.001,
290
+ "loss": 1.3334,
291
+ "step": 94
292
+ },
293
+ {
294
+ "epoch": 0.7,
295
+ "learning_rate": 0.001,
296
+ "loss": 1.2967,
297
+ "step": 96
298
+ },
299
+ {
300
+ "epoch": 0.72,
301
+ "learning_rate": 0.001,
302
+ "loss": 1.3221,
303
+ "step": 98
304
+ },
305
+ {
306
+ "epoch": 0.73,
307
+ "learning_rate": 0.001,
308
+ "loss": 1.3421,
309
+ "step": 100
310
+ },
311
+ {
312
+ "epoch": 0.75,
313
+ "learning_rate": 0.001,
314
+ "loss": 1.354,
315
+ "step": 102
316
+ },
317
+ {
318
+ "epoch": 0.76,
319
+ "learning_rate": 0.001,
320
+ "loss": 1.3098,
321
+ "step": 104
322
+ },
323
+ {
324
+ "epoch": 0.78,
325
+ "learning_rate": 0.001,
326
+ "loss": 1.2827,
327
+ "step": 106
328
+ },
329
+ {
330
+ "epoch": 0.79,
331
+ "learning_rate": 0.001,
332
+ "loss": 1.2887,
333
+ "step": 108
334
+ },
335
+ {
336
+ "epoch": 0.81,
337
+ "learning_rate": 0.001,
338
+ "loss": 1.3276,
339
+ "step": 110
340
+ },
341
+ {
342
+ "epoch": 0.82,
343
+ "learning_rate": 0.001,
344
+ "loss": 1.3179,
345
+ "step": 112
346
+ },
347
+ {
348
+ "epoch": 0.84,
349
+ "learning_rate": 0.001,
350
+ "loss": 1.2787,
351
+ "step": 114
352
+ },
353
+ {
354
+ "epoch": 0.85,
355
+ "learning_rate": 0.001,
356
+ "loss": 1.2732,
357
+ "step": 116
358
+ },
359
+ {
360
+ "epoch": 0.87,
361
+ "learning_rate": 0.001,
362
+ "loss": 1.2751,
363
+ "step": 118
364
+ },
365
+ {
366
+ "epoch": 0.88,
367
+ "learning_rate": 0.001,
368
+ "loss": 1.259,
369
+ "step": 120
370
+ },
371
+ {
372
+ "epoch": 0.89,
373
+ "learning_rate": 0.001,
374
+ "loss": 1.3405,
375
+ "step": 122
376
+ },
377
+ {
378
+ "epoch": 0.91,
379
+ "learning_rate": 0.001,
380
+ "loss": 1.2702,
381
+ "step": 124
382
+ },
383
+ {
384
+ "epoch": 0.92,
385
+ "learning_rate": 0.001,
386
+ "loss": 1.2554,
387
+ "step": 126
388
+ },
389
+ {
390
+ "epoch": 0.94,
391
+ "learning_rate": 0.001,
392
+ "loss": 1.2312,
393
+ "step": 128
394
+ },
395
+ {
396
+ "epoch": 0.95,
397
+ "learning_rate": 0.001,
398
+ "loss": 1.3141,
399
+ "step": 130
400
+ },
401
+ {
402
+ "epoch": 0.97,
403
+ "learning_rate": 0.001,
404
+ "loss": 1.2726,
405
+ "step": 132
406
+ },
407
+ {
408
+ "epoch": 0.98,
409
+ "learning_rate": 0.001,
410
+ "loss": 1.2864,
411
+ "step": 134
412
+ },
413
+ {
414
+ "epoch": 1.0,
415
+ "learning_rate": 0.001,
416
+ "loss": 1.3028,
417
+ "step": 136
418
+ },
419
+ {
420
+ "epoch": 1.0,
421
+ "eval_loss": 1.3082436323165894,
422
+ "eval_runtime": 149.0495,
423
+ "eval_samples_per_second": 6.521,
424
+ "eval_steps_per_second": 3.261,
425
+ "step": 136
426
+ },
427
+ {
428
+ "epoch": 1.01,
429
+ "learning_rate": 0.001,
430
+ "loss": 1.1233,
431
+ "step": 138
432
+ },
433
+ {
434
+ "epoch": 1.03,
435
+ "learning_rate": 0.001,
436
+ "loss": 1.0893,
437
+ "step": 140
438
+ },
439
+ {
440
+ "epoch": 1.04,
441
+ "learning_rate": 0.001,
442
+ "loss": 1.0353,
443
+ "step": 142
444
+ },
445
+ {
446
+ "epoch": 1.06,
447
+ "learning_rate": 0.001,
448
+ "loss": 1.0348,
449
+ "step": 144
450
+ },
451
+ {
452
+ "epoch": 1.07,
453
+ "learning_rate": 0.001,
454
+ "loss": 1.092,
455
+ "step": 146
456
+ },
457
+ {
458
+ "epoch": 1.09,
459
+ "learning_rate": 0.001,
460
+ "loss": 1.026,
461
+ "step": 148
462
+ },
463
+ {
464
+ "epoch": 1.1,
465
+ "learning_rate": 0.001,
466
+ "loss": 1.0482,
467
+ "step": 150
468
+ },
469
+ {
470
+ "epoch": 1.11,
471
+ "learning_rate": 0.001,
472
+ "loss": 1.0594,
473
+ "step": 152
474
+ },
475
+ {
476
+ "epoch": 1.13,
477
+ "learning_rate": 0.001,
478
+ "loss": 1.0549,
479
+ "step": 154
480
+ },
481
+ {
482
+ "epoch": 1.14,
483
+ "learning_rate": 0.001,
484
+ "loss": 1.0491,
485
+ "step": 156
486
+ },
487
+ {
488
+ "epoch": 1.16,
489
+ "learning_rate": 0.001,
490
+ "loss": 1.0767,
491
+ "step": 158
492
+ },
493
+ {
494
+ "epoch": 1.17,
495
+ "learning_rate": 0.001,
496
+ "loss": 1.0524,
497
+ "step": 160
498
+ },
499
+ {
500
+ "epoch": 1.19,
501
+ "learning_rate": 0.001,
502
+ "loss": 1.066,
503
+ "step": 162
504
+ },
505
+ {
506
+ "epoch": 1.2,
507
+ "learning_rate": 0.001,
508
+ "loss": 1.0855,
509
+ "step": 164
510
+ },
511
+ {
512
+ "epoch": 1.22,
513
+ "learning_rate": 0.001,
514
+ "loss": 1.0437,
515
+ "step": 166
516
+ },
517
+ {
518
+ "epoch": 1.23,
519
+ "learning_rate": 0.001,
520
+ "loss": 1.0676,
521
+ "step": 168
522
+ },
523
+ {
524
+ "epoch": 1.25,
525
+ "learning_rate": 0.001,
526
+ "loss": 1.0375,
527
+ "step": 170
528
+ },
529
+ {
530
+ "epoch": 1.26,
531
+ "learning_rate": 0.001,
532
+ "loss": 1.07,
533
+ "step": 172
534
+ },
535
+ {
536
+ "epoch": 1.28,
537
+ "learning_rate": 0.001,
538
+ "loss": 1.0586,
539
+ "step": 174
540
+ },
541
+ {
542
+ "epoch": 1.29,
543
+ "learning_rate": 0.001,
544
+ "loss": 1.0273,
545
+ "step": 176
546
+ },
547
+ {
548
+ "epoch": 1.31,
549
+ "learning_rate": 0.001,
550
+ "loss": 1.0596,
551
+ "step": 178
552
+ },
553
+ {
554
+ "epoch": 1.32,
555
+ "learning_rate": 0.001,
556
+ "loss": 1.0757,
557
+ "step": 180
558
+ },
559
+ {
560
+ "epoch": 1.33,
561
+ "learning_rate": 0.001,
562
+ "loss": 1.0609,
563
+ "step": 182
564
+ },
565
+ {
566
+ "epoch": 1.35,
567
+ "learning_rate": 0.001,
568
+ "loss": 1.0696,
569
+ "step": 184
570
+ },
571
+ {
572
+ "epoch": 1.36,
573
+ "learning_rate": 0.001,
574
+ "loss": 1.0687,
575
+ "step": 186
576
+ },
577
+ {
578
+ "epoch": 1.38,
579
+ "learning_rate": 0.001,
580
+ "loss": 1.054,
581
+ "step": 188
582
+ },
583
+ {
584
+ "epoch": 1.39,
585
+ "learning_rate": 0.001,
586
+ "loss": 1.0753,
587
+ "step": 190
588
+ },
589
+ {
590
+ "epoch": 1.41,
591
+ "learning_rate": 0.001,
592
+ "loss": 1.1042,
593
+ "step": 192
594
+ },
595
+ {
596
+ "epoch": 1.42,
597
+ "learning_rate": 0.001,
598
+ "loss": 1.0651,
599
+ "step": 194
600
+ },
601
+ {
602
+ "epoch": 1.44,
603
+ "learning_rate": 0.001,
604
+ "loss": 1.0476,
605
+ "step": 196
606
+ },
607
+ {
608
+ "epoch": 1.45,
609
+ "learning_rate": 0.001,
610
+ "loss": 1.0378,
611
+ "step": 198
612
+ },
613
+ {
614
+ "epoch": 1.47,
615
+ "learning_rate": 0.001,
616
+ "loss": 1.0697,
617
+ "step": 200
618
+ },
619
+ {
620
+ "epoch": 1.48,
621
+ "learning_rate": 0.001,
622
+ "loss": 1.0581,
623
+ "step": 202
624
+ },
625
+ {
626
+ "epoch": 1.5,
627
+ "learning_rate": 0.001,
628
+ "loss": 1.1033,
629
+ "step": 204
630
+ },
631
+ {
632
+ "epoch": 1.51,
633
+ "learning_rate": 0.001,
634
+ "loss": 1.0651,
635
+ "step": 206
636
+ },
637
+ {
638
+ "epoch": 1.53,
639
+ "learning_rate": 0.001,
640
+ "loss": 1.0576,
641
+ "step": 208
642
+ },
643
+ {
644
+ "epoch": 1.54,
645
+ "learning_rate": 0.001,
646
+ "loss": 1.069,
647
+ "step": 210
648
+ },
649
+ {
650
+ "epoch": 1.55,
651
+ "learning_rate": 0.001,
652
+ "loss": 1.0694,
653
+ "step": 212
654
+ },
655
+ {
656
+ "epoch": 1.57,
657
+ "learning_rate": 0.001,
658
+ "loss": 1.0658,
659
+ "step": 214
660
+ },
661
+ {
662
+ "epoch": 1.58,
663
+ "learning_rate": 0.001,
664
+ "loss": 1.092,
665
+ "step": 216
666
+ },
667
+ {
668
+ "epoch": 1.6,
669
+ "learning_rate": 0.001,
670
+ "loss": 1.0601,
671
+ "step": 218
672
+ },
673
+ {
674
+ "epoch": 1.61,
675
+ "learning_rate": 0.001,
676
+ "loss": 1.0932,
677
+ "step": 220
678
+ },
679
+ {
680
+ "epoch": 1.63,
681
+ "learning_rate": 0.001,
682
+ "loss": 1.0967,
683
+ "step": 222
684
+ },
685
+ {
686
+ "epoch": 1.64,
687
+ "learning_rate": 0.001,
688
+ "loss": 1.0453,
689
+ "step": 224
690
+ },
691
+ {
692
+ "epoch": 1.66,
693
+ "learning_rate": 0.001,
694
+ "loss": 1.0823,
695
+ "step": 226
696
+ },
697
+ {
698
+ "epoch": 1.67,
699
+ "learning_rate": 0.001,
700
+ "loss": 1.0855,
701
+ "step": 228
702
+ },
703
+ {
704
+ "epoch": 1.69,
705
+ "learning_rate": 0.001,
706
+ "loss": 1.0768,
707
+ "step": 230
708
+ },
709
+ {
710
+ "epoch": 1.7,
711
+ "learning_rate": 0.001,
712
+ "loss": 1.0624,
713
+ "step": 232
714
+ },
715
+ {
716
+ "epoch": 1.72,
717
+ "learning_rate": 0.001,
718
+ "loss": 1.0709,
719
+ "step": 234
720
+ },
721
+ {
722
+ "epoch": 1.73,
723
+ "learning_rate": 0.001,
724
+ "loss": 1.0691,
725
+ "step": 236
726
+ },
727
+ {
728
+ "epoch": 1.74,
729
+ "learning_rate": 0.001,
730
+ "loss": 1.1166,
731
+ "step": 238
732
+ },
733
+ {
734
+ "epoch": 1.76,
735
+ "learning_rate": 0.001,
736
+ "loss": 1.0805,
737
+ "step": 240
738
+ },
739
+ {
740
+ "epoch": 1.77,
741
+ "learning_rate": 0.001,
742
+ "loss": 1.0843,
743
+ "step": 242
744
+ },
745
+ {
746
+ "epoch": 1.79,
747
+ "learning_rate": 0.001,
748
+ "loss": 1.1022,
749
+ "step": 244
750
+ },
751
+ {
752
+ "epoch": 1.8,
753
+ "learning_rate": 0.001,
754
+ "loss": 1.1194,
755
+ "step": 246
756
+ },
757
+ {
758
+ "epoch": 1.82,
759
+ "learning_rate": 0.001,
760
+ "loss": 1.0949,
761
+ "step": 248
762
+ },
763
+ {
764
+ "epoch": 1.83,
765
+ "learning_rate": 0.001,
766
+ "loss": 1.1043,
767
+ "step": 250
768
+ },
769
+ {
770
+ "epoch": 1.85,
771
+ "learning_rate": 0.001,
772
+ "loss": 1.0643,
773
+ "step": 252
774
+ },
775
+ {
776
+ "epoch": 1.86,
777
+ "learning_rate": 0.001,
778
+ "loss": 1.1155,
779
+ "step": 254
780
+ },
781
+ {
782
+ "epoch": 1.88,
783
+ "learning_rate": 0.001,
784
+ "loss": 1.087,
785
+ "step": 256
786
+ },
787
+ {
788
+ "epoch": 1.89,
789
+ "learning_rate": 0.001,
790
+ "loss": 1.0645,
791
+ "step": 258
792
+ },
793
+ {
794
+ "epoch": 1.91,
795
+ "learning_rate": 0.001,
796
+ "loss": 1.055,
797
+ "step": 260
798
+ },
799
+ {
800
+ "epoch": 1.92,
801
+ "learning_rate": 0.001,
802
+ "loss": 1.0605,
803
+ "step": 262
804
+ },
805
+ {
806
+ "epoch": 1.94,
807
+ "learning_rate": 0.001,
808
+ "loss": 1.046,
809
+ "step": 264
810
+ },
811
+ {
812
+ "epoch": 1.95,
813
+ "learning_rate": 0.001,
814
+ "loss": 1.0929,
815
+ "step": 266
816
+ },
817
+ {
818
+ "epoch": 1.96,
819
+ "learning_rate": 0.001,
820
+ "loss": 1.0614,
821
+ "step": 268
822
+ },
823
+ {
824
+ "epoch": 1.98,
825
+ "learning_rate": 0.001,
826
+ "loss": 1.0798,
827
+ "step": 270
828
+ },
829
+ {
830
+ "epoch": 1.99,
831
+ "learning_rate": 0.001,
832
+ "loss": 1.0664,
833
+ "step": 272
834
+ },
835
+ {
836
+ "epoch": 1.99,
837
+ "eval_loss": 1.3287441730499268,
838
+ "eval_runtime": 149.8298,
839
+ "eval_samples_per_second": 6.487,
840
+ "eval_steps_per_second": 3.244,
841
+ "step": 272
842
+ },
843
+ {
844
+ "epoch": 2.01,
845
+ "learning_rate": 0.001,
846
+ "loss": 0.9871,
847
+ "step": 274
848
+ },
849
+ {
850
+ "epoch": 2.02,
851
+ "learning_rate": 0.001,
852
+ "loss": 0.8602,
853
+ "step": 276
854
+ },
855
+ {
856
+ "epoch": 2.04,
857
+ "learning_rate": 0.001,
858
+ "loss": 0.8521,
859
+ "step": 278
860
+ },
861
+ {
862
+ "epoch": 2.05,
863
+ "learning_rate": 0.001,
864
+ "loss": 0.8629,
865
+ "step": 280
866
+ },
867
+ {
868
+ "epoch": 2.07,
869
+ "learning_rate": 0.001,
870
+ "loss": 0.8637,
871
+ "step": 282
872
+ },
873
+ {
874
+ "epoch": 2.08,
875
+ "learning_rate": 0.001,
876
+ "loss": 0.864,
877
+ "step": 284
878
+ },
879
+ {
880
+ "epoch": 2.1,
881
+ "learning_rate": 0.001,
882
+ "loss": 0.8554,
883
+ "step": 286
884
+ },
885
+ {
886
+ "epoch": 2.11,
887
+ "learning_rate": 0.001,
888
+ "loss": 0.8431,
889
+ "step": 288
890
+ },
891
+ {
892
+ "epoch": 2.13,
893
+ "learning_rate": 0.001,
894
+ "loss": 0.8256,
895
+ "step": 290
896
+ },
897
+ {
898
+ "epoch": 2.14,
899
+ "learning_rate": 0.001,
900
+ "loss": 0.8791,
901
+ "step": 292
902
+ },
903
+ {
904
+ "epoch": 2.16,
905
+ "learning_rate": 0.001,
906
+ "loss": 0.8687,
907
+ "step": 294
908
+ },
909
+ {
910
+ "epoch": 2.17,
911
+ "learning_rate": 0.001,
912
+ "loss": 0.879,
913
+ "step": 296
914
+ },
915
+ {
916
+ "epoch": 2.18,
917
+ "learning_rate": 0.001,
918
+ "loss": 0.858,
919
+ "step": 298
920
+ },
921
+ {
922
+ "epoch": 2.2,
923
+ "learning_rate": 0.001,
924
+ "loss": 0.8616,
925
+ "step": 300
926
+ },
927
+ {
928
+ "epoch": 2.21,
929
+ "learning_rate": 0.001,
930
+ "loss": 0.8453,
931
+ "step": 302
932
+ },
933
+ {
934
+ "epoch": 2.23,
935
+ "learning_rate": 0.001,
936
+ "loss": 0.8552,
937
+ "step": 304
938
+ },
939
+ {
940
+ "epoch": 2.24,
941
+ "learning_rate": 0.001,
942
+ "loss": 0.8529,
943
+ "step": 306
944
+ },
945
+ {
946
+ "epoch": 2.26,
947
+ "learning_rate": 0.001,
948
+ "loss": 0.843,
949
+ "step": 308
950
+ },
951
+ {
952
+ "epoch": 2.27,
953
+ "learning_rate": 0.001,
954
+ "loss": 0.8697,
955
+ "step": 310
956
+ },
957
+ {
958
+ "epoch": 2.29,
959
+ "learning_rate": 0.001,
960
+ "loss": 0.8326,
961
+ "step": 312
962
+ },
963
+ {
964
+ "epoch": 2.3,
965
+ "learning_rate": 0.001,
966
+ "loss": 0.8547,
967
+ "step": 314
968
+ },
969
+ {
970
+ "epoch": 2.32,
971
+ "learning_rate": 0.001,
972
+ "loss": 0.8952,
973
+ "step": 316
974
+ },
975
+ {
976
+ "epoch": 2.33,
977
+ "learning_rate": 0.001,
978
+ "loss": 0.872,
979
+ "step": 318
980
+ },
981
+ {
982
+ "epoch": 2.35,
983
+ "learning_rate": 0.001,
984
+ "loss": 0.8729,
985
+ "step": 320
986
+ },
987
+ {
988
+ "epoch": 2.36,
989
+ "learning_rate": 0.001,
990
+ "loss": 0.8739,
991
+ "step": 322
992
+ },
993
+ {
994
+ "epoch": 2.38,
995
+ "learning_rate": 0.001,
996
+ "loss": 0.8782,
997
+ "step": 324
998
+ },
999
+ {
1000
+ "epoch": 2.39,
1001
+ "learning_rate": 0.001,
1002
+ "loss": 0.8909,
1003
+ "step": 326
1004
+ },
1005
+ {
1006
+ "epoch": 2.4,
1007
+ "learning_rate": 0.001,
1008
+ "loss": 0.8596,
1009
+ "step": 328
1010
+ },
1011
+ {
1012
+ "epoch": 2.42,
1013
+ "learning_rate": 0.001,
1014
+ "loss": 0.8474,
1015
+ "step": 330
1016
+ },
1017
+ {
1018
+ "epoch": 2.43,
1019
+ "learning_rate": 0.001,
1020
+ "loss": 0.8748,
1021
+ "step": 332
1022
+ },
1023
+ {
1024
+ "epoch": 2.45,
1025
+ "learning_rate": 0.001,
1026
+ "loss": 0.8721,
1027
+ "step": 334
1028
+ },
1029
+ {
1030
+ "epoch": 2.46,
1031
+ "learning_rate": 0.001,
1032
+ "loss": 0.8572,
1033
+ "step": 336
1034
+ },
1035
+ {
1036
+ "epoch": 2.48,
1037
+ "learning_rate": 0.001,
1038
+ "loss": 0.8851,
1039
+ "step": 338
1040
+ },
1041
+ {
1042
+ "epoch": 2.49,
1043
+ "learning_rate": 0.001,
1044
+ "loss": 0.871,
1045
+ "step": 340
1046
+ },
1047
+ {
1048
+ "epoch": 2.51,
1049
+ "learning_rate": 0.001,
1050
+ "loss": 0.8807,
1051
+ "step": 342
1052
+ },
1053
+ {
1054
+ "epoch": 2.52,
1055
+ "learning_rate": 0.001,
1056
+ "loss": 0.912,
1057
+ "step": 344
1058
+ },
1059
+ {
1060
+ "epoch": 2.54,
1061
+ "learning_rate": 0.001,
1062
+ "loss": 0.8771,
1063
+ "step": 346
1064
+ },
1065
+ {
1066
+ "epoch": 2.55,
1067
+ "learning_rate": 0.001,
1068
+ "loss": 0.8695,
1069
+ "step": 348
1070
+ },
1071
+ {
1072
+ "epoch": 2.57,
1073
+ "learning_rate": 0.001,
1074
+ "loss": 0.856,
1075
+ "step": 350
1076
+ },
1077
+ {
1078
+ "epoch": 2.58,
1079
+ "learning_rate": 0.001,
1080
+ "loss": 0.8843,
1081
+ "step": 352
1082
+ },
1083
+ {
1084
+ "epoch": 2.6,
1085
+ "learning_rate": 0.001,
1086
+ "loss": 0.8536,
1087
+ "step": 354
1088
+ },
1089
+ {
1090
+ "epoch": 2.61,
1091
+ "learning_rate": 0.001,
1092
+ "loss": 0.9263,
1093
+ "step": 356
1094
+ },
1095
+ {
1096
+ "epoch": 2.62,
1097
+ "learning_rate": 0.001,
1098
+ "loss": 0.9067,
1099
+ "step": 358
1100
+ },
1101
+ {
1102
+ "epoch": 2.64,
1103
+ "learning_rate": 0.001,
1104
+ "loss": 0.8815,
1105
+ "step": 360
1106
+ },
1107
+ {
1108
+ "epoch": 2.65,
1109
+ "learning_rate": 0.001,
1110
+ "loss": 0.9093,
1111
+ "step": 362
1112
+ },
1113
+ {
1114
+ "epoch": 2.67,
1115
+ "learning_rate": 0.001,
1116
+ "loss": 0.895,
1117
+ "step": 364
1118
+ },
1119
+ {
1120
+ "epoch": 2.68,
1121
+ "learning_rate": 0.001,
1122
+ "loss": 0.9214,
1123
+ "step": 366
1124
+ },
1125
+ {
1126
+ "epoch": 2.7,
1127
+ "learning_rate": 0.001,
1128
+ "loss": 0.8839,
1129
+ "step": 368
1130
+ },
1131
+ {
1132
+ "epoch": 2.71,
1133
+ "learning_rate": 0.001,
1134
+ "loss": 0.8827,
1135
+ "step": 370
1136
+ },
1137
+ {
1138
+ "epoch": 2.73,
1139
+ "learning_rate": 0.001,
1140
+ "loss": 0.8841,
1141
+ "step": 372
1142
+ },
1143
+ {
1144
+ "epoch": 2.74,
1145
+ "learning_rate": 0.001,
1146
+ "loss": 0.8947,
1147
+ "step": 374
1148
+ },
1149
+ {
1150
+ "epoch": 2.76,
1151
+ "learning_rate": 0.001,
1152
+ "loss": 0.8807,
1153
+ "step": 376
1154
+ },
1155
+ {
1156
+ "epoch": 2.77,
1157
+ "learning_rate": 0.001,
1158
+ "loss": 0.8794,
1159
+ "step": 378
1160
+ },
1161
+ {
1162
+ "epoch": 2.79,
1163
+ "learning_rate": 0.001,
1164
+ "loss": 0.8812,
1165
+ "step": 380
1166
+ },
1167
+ {
1168
+ "epoch": 2.8,
1169
+ "learning_rate": 0.001,
1170
+ "loss": 0.8799,
1171
+ "step": 382
1172
+ },
1173
+ {
1174
+ "epoch": 2.82,
1175
+ "learning_rate": 0.001,
1176
+ "loss": 0.8923,
1177
+ "step": 384
1178
+ },
1179
+ {
1180
+ "epoch": 2.83,
1181
+ "learning_rate": 0.001,
1182
+ "loss": 0.8808,
1183
+ "step": 386
1184
+ },
1185
+ {
1186
+ "epoch": 2.84,
1187
+ "learning_rate": 0.001,
1188
+ "loss": 0.8808,
1189
+ "step": 388
1190
+ },
1191
+ {
1192
+ "epoch": 2.86,
1193
+ "learning_rate": 0.001,
1194
+ "loss": 0.9125,
1195
+ "step": 390
1196
+ },
1197
+ {
1198
+ "epoch": 2.87,
1199
+ "learning_rate": 0.001,
1200
+ "loss": 0.9253,
1201
+ "step": 392
1202
+ },
1203
+ {
1204
+ "epoch": 2.89,
1205
+ "learning_rate": 0.001,
1206
+ "loss": 0.9075,
1207
+ "step": 394
1208
+ },
1209
+ {
1210
+ "epoch": 2.9,
1211
+ "learning_rate": 0.001,
1212
+ "loss": 0.8753,
1213
+ "step": 396
1214
+ },
1215
+ {
1216
+ "epoch": 2.92,
1217
+ "learning_rate": 0.001,
1218
+ "loss": 0.9002,
1219
+ "step": 398
1220
+ },
1221
+ {
1222
+ "epoch": 2.93,
1223
+ "learning_rate": 0.001,
1224
+ "loss": 0.8959,
1225
+ "step": 400
1226
+ },
1227
+ {
1228
+ "epoch": 2.95,
1229
+ "learning_rate": 0.001,
1230
+ "loss": 0.9016,
1231
+ "step": 402
1232
+ },
1233
+ {
1234
+ "epoch": 2.96,
1235
+ "learning_rate": 0.001,
1236
+ "loss": 0.8797,
1237
+ "step": 404
1238
+ },
1239
+ {
1240
+ "epoch": 2.98,
1241
+ "learning_rate": 0.001,
1242
+ "loss": 0.8898,
1243
+ "step": 406
1244
+ },
1245
+ {
1246
+ "epoch": 2.99,
1247
+ "learning_rate": 0.001,
1248
+ "loss": 0.9068,
1249
+ "step": 408
1250
+ },
1251
+ {
1252
+ "epoch": 3.0,
1253
+ "eval_loss": 1.3887747526168823,
1254
+ "eval_runtime": 148.9955,
1255
+ "eval_samples_per_second": 6.524,
1256
+ "eval_steps_per_second": 3.262,
1257
+ "step": 409
1258
+ },
1259
+ {
1260
+ "epoch": 3.01,
1261
+ "learning_rate": 0.001,
1262
+ "loss": 0.8114,
1263
+ "step": 410
1264
+ },
1265
+ {
1266
+ "epoch": 3.02,
1267
+ "learning_rate": 0.001,
1268
+ "loss": 0.693,
1269
+ "step": 412
1270
+ },
1271
+ {
1272
+ "epoch": 3.04,
1273
+ "learning_rate": 0.001,
1274
+ "loss": 0.7207,
1275
+ "step": 414
1276
+ },
1277
+ {
1278
+ "epoch": 3.05,
1279
+ "learning_rate": 0.001,
1280
+ "loss": 0.6572,
1281
+ "step": 416
1282
+ },
1283
+ {
1284
+ "epoch": 3.06,
1285
+ "learning_rate": 0.001,
1286
+ "loss": 0.6794,
1287
+ "step": 418
1288
+ },
1289
+ {
1290
+ "epoch": 3.08,
1291
+ "learning_rate": 0.001,
1292
+ "loss": 0.684,
1293
+ "step": 420
1294
+ },
1295
+ {
1296
+ "epoch": 3.09,
1297
+ "learning_rate": 0.001,
1298
+ "loss": 0.6748,
1299
+ "step": 422
1300
+ },
1301
+ {
1302
+ "epoch": 3.11,
1303
+ "learning_rate": 0.001,
1304
+ "loss": 0.6896,
1305
+ "step": 424
1306
+ },
1307
+ {
1308
+ "epoch": 3.12,
1309
+ "learning_rate": 0.001,
1310
+ "loss": 0.6973,
1311
+ "step": 426
1312
+ },
1313
+ {
1314
+ "epoch": 3.14,
1315
+ "learning_rate": 0.001,
1316
+ "loss": 0.7095,
1317
+ "step": 428
1318
+ },
1319
+ {
1320
+ "epoch": 3.15,
1321
+ "learning_rate": 0.001,
1322
+ "loss": 0.6898,
1323
+ "step": 430
1324
+ },
1325
+ {
1326
+ "epoch": 3.17,
1327
+ "learning_rate": 0.001,
1328
+ "loss": 0.7104,
1329
+ "step": 432
1330
+ },
1331
+ {
1332
+ "epoch": 3.18,
1333
+ "learning_rate": 0.001,
1334
+ "loss": 0.6956,
1335
+ "step": 434
1336
+ },
1337
+ {
1338
+ "epoch": 3.2,
1339
+ "learning_rate": 0.001,
1340
+ "loss": 0.705,
1341
+ "step": 436
1342
+ },
1343
+ {
1344
+ "epoch": 3.21,
1345
+ "learning_rate": 0.001,
1346
+ "loss": 0.683,
1347
+ "step": 438
1348
+ },
1349
+ {
1350
+ "epoch": 3.23,
1351
+ "learning_rate": 0.001,
1352
+ "loss": 0.711,
1353
+ "step": 440
1354
+ },
1355
+ {
1356
+ "epoch": 3.24,
1357
+ "learning_rate": 0.001,
1358
+ "loss": 0.688,
1359
+ "step": 442
1360
+ },
1361
+ {
1362
+ "epoch": 3.26,
1363
+ "learning_rate": 0.001,
1364
+ "loss": 0.7051,
1365
+ "step": 444
1366
+ },
1367
+ {
1368
+ "epoch": 3.27,
1369
+ "learning_rate": 0.001,
1370
+ "loss": 0.7034,
1371
+ "step": 446
1372
+ },
1373
+ {
1374
+ "epoch": 3.28,
1375
+ "learning_rate": 0.001,
1376
+ "loss": 0.724,
1377
+ "step": 448
1378
+ },
1379
+ {
1380
+ "epoch": 3.3,
1381
+ "learning_rate": 0.001,
1382
+ "loss": 0.7236,
1383
+ "step": 450
1384
+ },
1385
+ {
1386
+ "epoch": 3.31,
1387
+ "learning_rate": 0.001,
1388
+ "loss": 0.7068,
1389
+ "step": 452
1390
+ },
1391
+ {
1392
+ "epoch": 3.33,
1393
+ "learning_rate": 0.001,
1394
+ "loss": 0.7207,
1395
+ "step": 454
1396
+ },
1397
+ {
1398
+ "epoch": 3.34,
1399
+ "learning_rate": 0.001,
1400
+ "loss": 0.7174,
1401
+ "step": 456
1402
+ },
1403
+ {
1404
+ "epoch": 3.36,
1405
+ "learning_rate": 0.001,
1406
+ "loss": 0.7115,
1407
+ "step": 458
1408
+ },
1409
+ {
1410
+ "epoch": 3.37,
1411
+ "learning_rate": 0.001,
1412
+ "loss": 0.7115,
1413
+ "step": 460
1414
+ },
1415
+ {
1416
+ "epoch": 3.39,
1417
+ "learning_rate": 0.001,
1418
+ "loss": 0.7355,
1419
+ "step": 462
1420
+ },
1421
+ {
1422
+ "epoch": 3.4,
1423
+ "learning_rate": 0.001,
1424
+ "loss": 0.7517,
1425
+ "step": 464
1426
+ },
1427
+ {
1428
+ "epoch": 3.42,
1429
+ "learning_rate": 0.001,
1430
+ "loss": 0.7187,
1431
+ "step": 466
1432
+ },
1433
+ {
1434
+ "epoch": 3.43,
1435
+ "learning_rate": 0.001,
1436
+ "loss": 0.7169,
1437
+ "step": 468
1438
+ },
1439
+ {
1440
+ "epoch": 3.45,
1441
+ "learning_rate": 0.001,
1442
+ "loss": 0.7022,
1443
+ "step": 470
1444
+ },
1445
+ {
1446
+ "epoch": 3.46,
1447
+ "learning_rate": 0.001,
1448
+ "loss": 0.7153,
1449
+ "step": 472
1450
+ },
1451
+ {
1452
+ "epoch": 3.48,
1453
+ "learning_rate": 0.001,
1454
+ "loss": 0.7166,
1455
+ "step": 474
1456
+ },
1457
+ {
1458
+ "epoch": 3.49,
1459
+ "learning_rate": 0.001,
1460
+ "loss": 0.7443,
1461
+ "step": 476
1462
+ },
1463
+ {
1464
+ "epoch": 3.5,
1465
+ "learning_rate": 0.001,
1466
+ "loss": 0.7399,
1467
+ "step": 478
1468
+ },
1469
+ {
1470
+ "epoch": 3.52,
1471
+ "learning_rate": 0.001,
1472
+ "loss": 0.7227,
1473
+ "step": 480
1474
+ },
1475
+ {
1476
+ "epoch": 3.53,
1477
+ "learning_rate": 0.001,
1478
+ "loss": 0.7217,
1479
+ "step": 482
1480
+ },
1481
+ {
1482
+ "epoch": 3.55,
1483
+ "learning_rate": 0.001,
1484
+ "loss": 0.7238,
1485
+ "step": 484
1486
+ },
1487
+ {
1488
+ "epoch": 3.56,
1489
+ "learning_rate": 0.001,
1490
+ "loss": 0.7054,
1491
+ "step": 486
1492
+ },
1493
+ {
1494
+ "epoch": 3.58,
1495
+ "learning_rate": 0.001,
1496
+ "loss": 0.7412,
1497
+ "step": 488
1498
+ },
1499
+ {
1500
+ "epoch": 3.59,
1501
+ "learning_rate": 0.001,
1502
+ "loss": 0.7251,
1503
+ "step": 490
1504
+ },
1505
+ {
1506
+ "epoch": 3.61,
1507
+ "learning_rate": 0.001,
1508
+ "loss": 0.7402,
1509
+ "step": 492
1510
+ },
1511
+ {
1512
+ "epoch": 3.62,
1513
+ "learning_rate": 0.001,
1514
+ "loss": 0.7274,
1515
+ "step": 494
1516
+ },
1517
+ {
1518
+ "epoch": 3.64,
1519
+ "learning_rate": 0.001,
1520
+ "loss": 0.7704,
1521
+ "step": 496
1522
+ },
1523
+ {
1524
+ "epoch": 3.65,
1525
+ "learning_rate": 0.001,
1526
+ "loss": 0.7462,
1527
+ "step": 498
1528
+ },
1529
+ {
1530
+ "epoch": 3.67,
1531
+ "learning_rate": 0.001,
1532
+ "loss": 0.7275,
1533
+ "step": 500
1534
+ },
1535
+ {
1536
+ "epoch": 3.68,
1537
+ "learning_rate": 0.001,
1538
+ "loss": 0.7158,
1539
+ "step": 502
1540
+ },
1541
+ {
1542
+ "epoch": 3.7,
1543
+ "learning_rate": 0.001,
1544
+ "loss": 0.7306,
1545
+ "step": 504
1546
+ },
1547
+ {
1548
+ "epoch": 3.71,
1549
+ "learning_rate": 0.001,
1550
+ "loss": 0.7054,
1551
+ "step": 506
1552
+ },
1553
+ {
1554
+ "epoch": 3.72,
1555
+ "learning_rate": 0.001,
1556
+ "loss": 0.7388,
1557
+ "step": 508
1558
+ },
1559
+ {
1560
+ "epoch": 3.74,
1561
+ "learning_rate": 0.001,
1562
+ "loss": 0.7232,
1563
+ "step": 510
1564
+ },
1565
+ {
1566
+ "epoch": 3.75,
1567
+ "learning_rate": 0.001,
1568
+ "loss": 0.7424,
1569
+ "step": 512
1570
+ },
1571
+ {
1572
+ "epoch": 3.77,
1573
+ "learning_rate": 0.001,
1574
+ "loss": 0.7687,
1575
+ "step": 514
1576
+ },
1577
+ {
1578
+ "epoch": 3.78,
1579
+ "learning_rate": 0.001,
1580
+ "loss": 0.7519,
1581
+ "step": 516
1582
+ },
1583
+ {
1584
+ "epoch": 3.8,
1585
+ "learning_rate": 0.001,
1586
+ "loss": 0.7629,
1587
+ "step": 518
1588
+ },
1589
+ {
1590
+ "epoch": 3.81,
1591
+ "learning_rate": 0.001,
1592
+ "loss": 0.7541,
1593
+ "step": 520
1594
+ },
1595
+ {
1596
+ "epoch": 3.83,
1597
+ "learning_rate": 0.001,
1598
+ "loss": 0.7405,
1599
+ "step": 522
1600
+ },
1601
+ {
1602
+ "epoch": 3.84,
1603
+ "learning_rate": 0.001,
1604
+ "loss": 0.7302,
1605
+ "step": 524
1606
+ },
1607
+ {
1608
+ "epoch": 3.86,
1609
+ "learning_rate": 0.001,
1610
+ "loss": 0.7365,
1611
+ "step": 526
1612
+ },
1613
+ {
1614
+ "epoch": 3.87,
1615
+ "learning_rate": 0.001,
1616
+ "loss": 0.771,
1617
+ "step": 528
1618
+ },
1619
+ {
1620
+ "epoch": 3.89,
1621
+ "learning_rate": 0.001,
1622
+ "loss": 0.7443,
1623
+ "step": 530
1624
+ },
1625
+ {
1626
+ "epoch": 3.9,
1627
+ "learning_rate": 0.001,
1628
+ "loss": 0.7737,
1629
+ "step": 532
1630
+ },
1631
+ {
1632
+ "epoch": 3.92,
1633
+ "learning_rate": 0.001,
1634
+ "loss": 0.7428,
1635
+ "step": 534
1636
+ },
1637
+ {
1638
+ "epoch": 3.93,
1639
+ "learning_rate": 0.001,
1640
+ "loss": 0.7588,
1641
+ "step": 536
1642
+ },
1643
+ {
1644
+ "epoch": 3.94,
1645
+ "learning_rate": 0.001,
1646
+ "loss": 0.7499,
1647
+ "step": 538
1648
+ },
1649
+ {
1650
+ "epoch": 3.96,
1651
+ "learning_rate": 0.001,
1652
+ "loss": 0.7572,
1653
+ "step": 540
1654
+ },
1655
+ {
1656
+ "epoch": 3.97,
1657
+ "learning_rate": 0.001,
1658
+ "loss": 0.7856,
1659
+ "step": 542
1660
+ },
1661
+ {
1662
+ "epoch": 3.99,
1663
+ "learning_rate": 0.001,
1664
+ "loss": 0.7479,
1665
+ "step": 544
1666
+ },
1667
+ {
1668
+ "epoch": 3.99,
1669
+ "eval_loss": 1.4472731351852417,
1670
+ "eval_runtime": 151.0119,
1671
+ "eval_samples_per_second": 6.437,
1672
+ "eval_steps_per_second": 3.218,
1673
+ "step": 544
1674
+ },
1675
+ {
1676
+ "epoch": 3.99,
1677
+ "step": 544,
1678
+ "total_flos": 9.892708089415188e+17,
1679
+ "train_loss": 1.0100317417698748,
1680
+ "train_runtime": 34968.4642,
1681
+ "train_samples_per_second": 1.997,
1682
+ "train_steps_per_second": 0.016
1683
+ }
1684
+ ],
1685
+ "logging_steps": 2,
1686
+ "max_steps": 544,
1687
+ "num_train_epochs": 4,
1688
+ "save_steps": 500,
1689
+ "total_flos": 9.892708089415188e+17,
1690
+ "trial_name": null,
1691
+ "trial_params": null
1692
+ }