terry69 commited on
Commit
3af7bb2
1 Parent(s): 9c2e969

Model save

Browse files
README.md CHANGED
@@ -2,13 +2,10 @@
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
5
- - alignment-handbook
6
  - trl
7
  - sft
8
  - generated_from_trainer
9
  base_model: mistralai/Mistral-7B-v0.1
10
- datasets:
11
- - HuggingFaceH4/ultrachat_200k
12
  model-index:
13
  - name: mistral_poe_small
14
  results: []
@@ -19,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # mistral_poe_small
21
 
22
- This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
23
  It achieves the following results on the evaluation set:
24
  - Loss: nan
25
 
@@ -58,7 +55,7 @@ The following hyperparameters were used during training:
58
 
59
  | Training Loss | Epoch | Step | Validation Loss |
60
  |:-------------:|:-----:|:----:|:---------------:|
61
- | 0.0056 | 1.0 | 217 | nan |
62
 
63
 
64
  ### Framework versions
 
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
  base_model: mistralai/Mistral-7B-v0.1
 
 
9
  model-index:
10
  - name: mistral_poe_small
11
  results: []
 
16
 
17
  # mistral_poe_small
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 None dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: nan
22
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss |
57
  |:-------------:|:-----:|:----:|:---------------:|
58
+ | 0.5259 | 1.0 | 974 | nan |
59
 
60
 
61
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6002c03875fbe7829e0706f61ade88c8d77c0dea12f12e6f796b2e50f79b909
3
  size 31516744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ea937dfef3266ef73ee962b94e5522b6162e2aadfa768fbd8a6832d81c7b2c3
3
  size 31516744
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.0019402640651178403,
4
- "train_runtime": 4565.6051,
5
- "train_samples": 10393,
6
- "train_samples_per_second": 2.276,
7
- "train_steps_per_second": 0.048
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.2056859987472362,
4
+ "train_runtime": 8762.8151,
5
+ "train_samples": 31179,
6
+ "train_samples_per_second": 3.558,
7
+ "train_steps_per_second": 0.111
8
  }
runs/May14_21-37-53_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715722693.ip-172-31-69-60.ec2.internal.30215.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bc71cd0d07b2e5953c57e7c2aa553fee4b0d7c82848b2cffec9e93ead3f0082
3
- size 18185
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3631462a16b5f04e649ff051d87fa6d5ff39c319369b13d66eff3b939eeb8d9
3
+ size 20920
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.0019402640651178403,
4
- "train_runtime": 4565.6051,
5
- "train_samples": 10393,
6
- "train_samples_per_second": 2.276,
7
- "train_steps_per_second": 0.048
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.2056859987472362,
4
+ "train_runtime": 8762.8151,
5
+ "train_samples": 31179,
6
+ "train_samples_per_second": 3.558,
7
+ "train_steps_per_second": 0.111
8
  }
trainer_state.json CHANGED
@@ -1,346 +1,1403 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 217,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.0,
13
- "grad_norm": 5.18852740291647,
14
- "learning_rate": 9.090909090909091e-06,
15
- "loss": 5.3084,
16
  "step": 1
17
  },
18
  {
19
- "epoch": 0.02,
20
- "grad_norm": 5.03901362055586,
21
- "learning_rate": 4.545454545454546e-05,
22
- "loss": 5.0728,
23
  "step": 5
24
  },
25
  {
26
- "epoch": 0.05,
27
- "grad_norm": 4.459588393324012,
28
- "learning_rate": 9.090909090909092e-05,
29
- "loss": 2.37,
30
  "step": 10
31
  },
32
  {
33
- "epoch": 0.07,
34
- "grad_norm": 0.43459848938578693,
35
- "learning_rate": 0.00013636363636363637,
36
- "loss": 0.1307,
37
  "step": 15
38
  },
39
  {
40
- "epoch": 0.09,
41
- "grad_norm": 0.0299929460934137,
42
- "learning_rate": 0.00018181818181818183,
43
- "loss": 0.0483,
44
  "step": 20
45
  },
46
  {
47
- "epoch": 0.12,
48
- "grad_norm": 0.013812266692594782,
49
- "learning_rate": 0.00019988322268323268,
50
- "loss": 0.0225,
51
  "step": 25
52
  },
53
  {
54
- "epoch": 0.14,
55
- "grad_norm": 0.009773102416496118,
56
- "learning_rate": 0.0001991705709821562,
57
- "loss": 0.0198,
58
  "step": 30
59
  },
60
  {
61
- "epoch": 0.16,
62
- "grad_norm": 0.0039386428485718465,
63
- "learning_rate": 0.00019781476007338058,
64
- "loss": 0.015,
65
  "step": 35
66
  },
67
  {
68
- "epoch": 0.18,
69
- "grad_norm": 0.002196082201771653,
70
- "learning_rate": 0.00019582458291091663,
71
- "loss": 0.0096,
72
  "step": 40
73
  },
74
  {
75
- "epoch": 0.21,
76
- "grad_norm": 0.018430687632200037,
77
- "learning_rate": 0.0001932129465573568,
78
- "loss": 0.0024,
79
  "step": 45
80
  },
81
  {
82
- "epoch": 0.23,
83
- "grad_norm": 0.9834813463855321,
84
- "learning_rate": 0.0001899967884766212,
85
- "loss": 0.0281,
86
  "step": 50
87
  },
88
  {
89
- "epoch": 0.25,
90
- "grad_norm": 0.005069811100933593,
91
- "learning_rate": 0.00018619696668800492,
92
- "loss": 0.0001,
93
  "step": 55
94
  },
95
  {
96
- "epoch": 0.28,
97
- "grad_norm": 0.007249668030582534,
98
- "learning_rate": 0.0001818381244939187,
99
- "loss": 0.0001,
100
  "step": 60
101
  },
102
  {
103
- "epoch": 0.3,
104
- "grad_norm": 0.0071458935911795545,
105
- "learning_rate": 0.00017694853065861662,
106
- "loss": 0.0001,
107
  "step": 65
108
  },
109
  {
110
- "epoch": 0.32,
111
- "grad_norm": 0.004757395926328272,
112
- "learning_rate": 0.00017155989607441213,
113
- "loss": 0.0001,
114
  "step": 70
115
  },
116
  {
117
- "epoch": 0.35,
118
- "grad_norm": 0.0027371110149472387,
119
- "learning_rate": 0.0001657071681043731,
120
- "loss": 0.0001,
121
  "step": 75
122
  },
123
  {
124
- "epoch": 0.37,
125
- "grad_norm": 0.0015303804705887707,
126
- "learning_rate": 0.00015942830393526176,
127
- "loss": 0.0,
128
  "step": 80
129
  },
130
  {
131
- "epoch": 0.39,
132
- "grad_norm": 0.0019029295128688208,
133
- "learning_rate": 0.0001527640244106133,
134
- "loss": 0.0191,
135
  "step": 85
136
  },
137
  {
138
- "epoch": 0.41,
139
- "grad_norm": 0.002913339239522618,
140
- "learning_rate": 0.00014575754994043956,
141
- "loss": 0.0,
142
  "step": 90
143
  },
144
  {
145
- "epoch": 0.44,
146
- "grad_norm": 0.002526914206171285,
147
- "learning_rate": 0.0001384543202002851,
148
- "loss": 0.0,
149
  "step": 95
150
  },
151
  {
152
- "epoch": 0.46,
153
- "grad_norm": 0.002364320350741189,
154
- "learning_rate": 0.00013090169943749476,
155
- "loss": 0.0,
156
  "step": 100
157
  },
158
  {
159
- "epoch": 0.48,
160
- "grad_norm": 0.001415040670977836,
161
- "learning_rate": 0.00012314866929589432,
162
- "loss": 0.0,
163
  "step": 105
164
  },
165
  {
166
- "epoch": 0.51,
167
- "grad_norm": 0.0014806660372118452,
168
- "learning_rate": 0.00011524551115103454,
169
- "loss": 0.0,
170
  "step": 110
171
  },
172
  {
173
- "epoch": 0.53,
174
- "grad_norm": 0.0009238152395960922,
175
- "learning_rate": 0.00010724348001617625,
176
- "loss": 0.0,
177
  "step": 115
178
  },
179
  {
180
- "epoch": 0.55,
181
- "grad_norm": 0.316858259539684,
182
- "learning_rate": 9.919447213386103e-05,
183
- "loss": 0.0175,
184
  "step": 120
185
  },
186
  {
187
- "epoch": 0.58,
188
- "grad_norm": 0.0013793498850558623,
189
- "learning_rate": 9.115068840886417e-05,
190
- "loss": 0.0,
191
  "step": 125
192
  },
193
  {
194
- "epoch": 0.6,
195
- "grad_norm": 0.03179793467382126,
196
- "learning_rate": 8.316429586529615e-05,
197
- "loss": 0.0,
198
  "step": 130
199
  },
200
  {
201
- "epoch": 0.62,
202
- "grad_norm": 0.008302429594092641,
203
- "learning_rate": 7.528708932343304e-05,
204
- "loss": 0.0104,
205
  "step": 135
206
  },
207
  {
208
- "epoch": 0.65,
209
- "grad_norm": 0.024284403402931108,
210
- "learning_rate": 6.757015549043175e-05,
211
- "loss": 0.0001,
212
  "step": 140
213
  },
214
  {
215
- "epoch": 0.67,
216
- "grad_norm": 0.007160721938093322,
217
- "learning_rate": 6.006354164343046e-05,
218
- "loss": 0.0001,
219
  "step": 145
220
  },
221
  {
222
- "epoch": 0.69,
223
- "grad_norm": 0.00442645759914904,
224
- "learning_rate": 5.28159310537518e-05,
225
- "loss": 0.0,
226
  "step": 150
227
  },
228
  {
229
- "epoch": 0.71,
230
- "grad_norm": 0.001965826516583593,
231
- "learning_rate": 4.587432725720687e-05,
232
- "loss": 0.0,
233
  "step": 155
234
  },
235
  {
236
- "epoch": 0.74,
237
- "grad_norm": 0.0012986955816234175,
238
- "learning_rate": 3.9283749218128885e-05,
239
- "loss": 0.0,
240
  "step": 160
241
  },
242
  {
243
- "epoch": 0.76,
244
- "grad_norm": 0.0010247882146462446,
245
- "learning_rate": 3.308693936411421e-05,
246
- "loss": 0.0,
247
  "step": 165
248
  },
249
  {
250
- "epoch": 0.78,
251
- "grad_norm": 0.000977980722589858,
252
- "learning_rate": 2.7324086384977698e-05,
253
- "loss": 0.0,
254
  "step": 170
255
  },
256
  {
257
- "epoch": 0.81,
258
- "grad_norm": 0.0008640860356404602,
259
- "learning_rate": 2.2032564593677774e-05,
260
- "loss": 0.0,
261
  "step": 175
262
  },
263
  {
264
- "epoch": 0.83,
265
- "grad_norm": 0.0007152715573634965,
266
- "learning_rate": 1.7246691539555028e-05,
267
- "loss": 0.0,
268
  "step": 180
269
  },
270
  {
271
- "epoch": 0.85,
272
- "grad_norm": 0.0008068934592673394,
273
- "learning_rate": 1.2997505445856084e-05,
274
- "loss": 0.0,
275
  "step": 185
276
  },
277
  {
278
- "epoch": 0.88,
279
- "grad_norm": 0.000785102458262206,
280
- "learning_rate": 9.31256391494546e-06,
281
- "loss": 0.0,
282
  "step": 190
283
  },
284
  {
285
- "epoch": 0.9,
286
- "grad_norm": 0.0006662070791456656,
287
- "learning_rate": 6.215765206679569e-06,
288
- "loss": 0.0,
289
  "step": 195
290
  },
291
  {
292
- "epoch": 0.92,
293
- "grad_norm": 0.0006676407776271578,
294
- "learning_rate": 3.7271932490209328e-06,
295
- "loss": 0.0,
296
  "step": 200
297
  },
298
  {
299
- "epoch": 0.94,
300
- "grad_norm": 0.0006248827839313129,
301
- "learning_rate": 1.8629873860586566e-06,
302
- "loss": 0.0,
303
  "step": 205
304
  },
305
  {
306
- "epoch": 0.97,
307
- "grad_norm": 0.0006849249794092451,
308
- "learning_rate": 6.352377081687011e-07,
309
- "loss": 0.0,
310
  "step": 210
311
  },
312
  {
313
- "epoch": 0.99,
314
- "grad_norm": 0.0007915981269703633,
315
- "learning_rate": 5.190664313851068e-08,
316
- "loss": 0.0056,
317
  "step": 215
318
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
319
  {
320
  "epoch": 1.0,
321
  "eval_loss": NaN,
322
- "eval_runtime": 745.5269,
323
- "eval_samples_per_second": 1.551,
324
- "eval_steps_per_second": 0.388,
325
- "step": 217
326
  },
327
  {
328
  "epoch": 1.0,
329
- "step": 217,
330
- "total_flos": 1973257544663040.0,
331
- "train_loss": 0.0019402640651178403,
332
- "train_runtime": 4565.6051,
333
- "train_samples_per_second": 2.276,
334
- "train_steps_per_second": 0.048
335
  }
336
  ],
337
  "logging_steps": 5,
338
- "max_steps": 217,
339
  "num_input_tokens_seen": 0,
340
  "num_train_epochs": 1,
341
  "save_steps": 40,
342
- "total_flos": 1973257544663040.0,
343
- "train_batch_size": 6,
344
  "trial_name": null,
345
  "trial_params": null
346
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9994869163673679,
5
  "eval_steps": 500,
6
+ "global_step": 974,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.0,
13
+ "grad_norm": 3.351157385916466,
14
+ "learning_rate": 2.040816326530612e-06,
15
+ "loss": 1.6096,
16
  "step": 1
17
  },
18
  {
19
+ "epoch": 0.01,
20
+ "grad_norm": 2.2833707241529,
21
+ "learning_rate": 1.0204081632653061e-05,
22
+ "loss": 1.307,
23
  "step": 5
24
  },
25
  {
26
+ "epoch": 0.01,
27
+ "grad_norm": 1.2912917729665443,
28
+ "learning_rate": 2.0408163265306123e-05,
29
+ "loss": 1.0807,
30
  "step": 10
31
  },
32
  {
33
+ "epoch": 0.02,
34
+ "grad_norm": 0.9989739565689935,
35
+ "learning_rate": 3.061224489795919e-05,
36
+ "loss": 1.0011,
37
  "step": 15
38
  },
39
  {
40
+ "epoch": 0.02,
41
+ "grad_norm": 1.079400758509174,
42
+ "learning_rate": 4.0816326530612245e-05,
43
+ "loss": 0.6897,
44
  "step": 20
45
  },
46
  {
47
+ "epoch": 0.03,
48
+ "grad_norm": 0.6210959789194382,
49
+ "learning_rate": 5.102040816326531e-05,
50
+ "loss": 0.6209,
51
  "step": 25
52
  },
53
  {
54
+ "epoch": 0.03,
55
+ "grad_norm": 0.604422455243622,
56
+ "learning_rate": 6.122448979591838e-05,
57
+ "loss": 0.6185,
58
  "step": 30
59
  },
60
  {
61
+ "epoch": 0.04,
62
+ "grad_norm": 0.5170498833821362,
63
+ "learning_rate": 7.142857142857143e-05,
64
+ "loss": 0.5902,
65
  "step": 35
66
  },
67
  {
68
+ "epoch": 0.04,
69
+ "grad_norm": 0.2650153905272352,
70
+ "learning_rate": 8.163265306122449e-05,
71
+ "loss": 0.5035,
72
  "step": 40
73
  },
74
  {
75
+ "epoch": 0.05,
76
+ "grad_norm": 0.3188138819665904,
77
+ "learning_rate": 9.183673469387756e-05,
78
+ "loss": 0.5295,
79
  "step": 45
80
  },
81
  {
82
+ "epoch": 0.05,
83
+ "grad_norm": 0.36979118306554615,
84
+ "learning_rate": 0.00010204081632653062,
85
+ "loss": 0.5734,
86
  "step": 50
87
  },
88
  {
89
+ "epoch": 0.06,
90
+ "grad_norm": 0.3973602747604989,
91
+ "learning_rate": 0.00011224489795918367,
92
+ "loss": 0.594,
93
  "step": 55
94
  },
95
  {
96
+ "epoch": 0.06,
97
+ "grad_norm": 0.30107519885544926,
98
+ "learning_rate": 0.00012244897959183676,
99
+ "loss": 0.5777,
100
  "step": 60
101
  },
102
  {
103
+ "epoch": 0.07,
104
+ "grad_norm": 0.35967504356035196,
105
+ "learning_rate": 0.0001326530612244898,
106
+ "loss": 0.547,
107
  "step": 65
108
  },
109
  {
110
+ "epoch": 0.07,
111
+ "grad_norm": 0.4161565630483454,
112
+ "learning_rate": 0.00014285714285714287,
113
+ "loss": 0.6266,
114
  "step": 70
115
  },
116
  {
117
+ "epoch": 0.08,
118
+ "grad_norm": 0.46021023477325246,
119
+ "learning_rate": 0.0001530612244897959,
120
+ "loss": 0.5249,
121
  "step": 75
122
  },
123
  {
124
+ "epoch": 0.08,
125
+ "grad_norm": 0.5486875740290827,
126
+ "learning_rate": 0.00016326530612244898,
127
+ "loss": 0.6381,
128
  "step": 80
129
  },
130
  {
131
+ "epoch": 0.09,
132
+ "grad_norm": 0.3715332784286634,
133
+ "learning_rate": 0.00017346938775510205,
134
+ "loss": 0.5778,
135
  "step": 85
136
  },
137
  {
138
+ "epoch": 0.09,
139
+ "grad_norm": 0.25669849660669547,
140
+ "learning_rate": 0.00018367346938775512,
141
+ "loss": 0.5461,
142
  "step": 90
143
  },
144
  {
145
+ "epoch": 0.1,
146
+ "grad_norm": 0.30206213988264413,
147
+ "learning_rate": 0.00019387755102040816,
148
+ "loss": 0.4736,
149
  "step": 95
150
  },
151
  {
152
+ "epoch": 0.1,
153
+ "grad_norm": 0.33277431668095503,
154
+ "learning_rate": 0.0001999974277115551,
155
+ "loss": 0.5328,
156
  "step": 100
157
  },
158
  {
159
+ "epoch": 0.11,
160
+ "grad_norm": 0.3336885386817361,
161
+ "learning_rate": 0.00019996849098629418,
162
+ "loss": 0.62,
163
  "step": 105
164
  },
165
  {
166
+ "epoch": 0.11,
167
+ "grad_norm": 0.3468751205649051,
168
+ "learning_rate": 0.00019990741151022301,
169
+ "loss": 0.5247,
170
  "step": 110
171
  },
172
  {
173
+ "epoch": 0.12,
174
+ "grad_norm": 0.3115320559980584,
175
+ "learning_rate": 0.0001998142089221534,
176
+ "loss": 0.4816,
177
  "step": 115
178
  },
179
  {
180
+ "epoch": 0.12,
181
+ "grad_norm": 1.7970263609657833,
182
+ "learning_rate": 0.0001996889131894033,
183
+ "loss": 0.5282,
184
  "step": 120
185
  },
186
  {
187
+ "epoch": 0.13,
188
+ "grad_norm": 0.420052571262797,
189
+ "learning_rate": 0.00019953156459816179,
190
+ "loss": 0.5812,
191
  "step": 125
192
  },
193
  {
194
+ "epoch": 0.13,
195
+ "grad_norm": 0.2997887688631509,
196
+ "learning_rate": 0.0001993422137405354,
197
+ "loss": 0.5722,
198
  "step": 130
199
  },
200
  {
201
+ "epoch": 0.14,
202
+ "grad_norm": 0.4538126671892769,
203
+ "learning_rate": 0.00019912092149828174,
204
+ "loss": 0.4534,
205
  "step": 135
206
  },
207
  {
208
+ "epoch": 0.14,
209
+ "grad_norm": 0.33254418592286095,
210
+ "learning_rate": 0.00019886775902323405,
211
+ "loss": 0.5745,
212
  "step": 140
213
  },
214
  {
215
+ "epoch": 0.15,
216
+ "grad_norm": 0.3406819289335851,
217
+ "learning_rate": 0.00019858280771442385,
218
+ "loss": 0.4937,
219
  "step": 145
220
  },
221
  {
222
+ "epoch": 0.15,
223
+ "grad_norm": 0.44532117964605517,
224
+ "learning_rate": 0.00019826615919190887,
225
+ "loss": 0.5034,
226
  "step": 150
227
  },
228
  {
229
+ "epoch": 0.16,
230
+ "grad_norm": 0.26124089824170305,
231
+ "learning_rate": 0.00019791791526731445,
232
+ "loss": 0.4308,
233
  "step": 155
234
  },
235
  {
236
+ "epoch": 0.16,
237
+ "grad_norm": 0.41699002376176875,
238
+ "learning_rate": 0.00019753818791109828,
239
+ "loss": 0.5843,
240
  "step": 160
241
  },
242
  {
243
+ "epoch": 0.17,
244
+ "grad_norm": 0.30966016172554256,
245
+ "learning_rate": 0.0001971270992165486,
246
+ "loss": 0.6161,
247
  "step": 165
248
  },
249
  {
250
+ "epoch": 0.17,
251
+ "grad_norm": 0.35777456904642235,
252
+ "learning_rate": 0.00019668478136052774,
253
+ "loss": 0.5352,
254
  "step": 170
255
  },
256
  {
257
+ "epoch": 0.18,
258
+ "grad_norm": 0.30456414186376835,
259
+ "learning_rate": 0.0001962113765609735,
260
+ "loss": 0.5787,
261
  "step": 175
262
  },
263
  {
264
+ "epoch": 0.18,
265
+ "grad_norm": 0.42315137043021306,
266
+ "learning_rate": 0.0001957070370311717,
267
+ "loss": 0.5959,
268
  "step": 180
269
  },
270
  {
271
+ "epoch": 0.19,
272
+ "grad_norm": 0.3294546389618734,
273
+ "learning_rate": 0.00019517192493081565,
274
+ "loss": 0.4895,
275
  "step": 185
276
  },
277
  {
278
+ "epoch": 0.19,
279
+ "grad_norm": 0.3169197670504051,
280
+ "learning_rate": 0.00019460621231386676,
281
+ "loss": 0.5021,
282
  "step": 190
283
  },
284
  {
285
+ "epoch": 0.2,
286
+ "grad_norm": 0.2834179242800674,
287
+ "learning_rate": 0.00019401008107323455,
288
+ "loss": 0.6374,
289
  "step": 195
290
  },
291
  {
292
+ "epoch": 0.21,
293
+ "grad_norm": 0.47305112179270714,
294
+ "learning_rate": 0.0001933837228822925,
295
+ "loss": 0.6208,
296
  "step": 200
297
  },
298
  {
299
+ "epoch": 0.21,
300
+ "grad_norm": 0.28157269728650575,
301
+ "learning_rate": 0.0001927273391332499,
302
+ "loss": 0.5011,
303
  "step": 205
304
  },
305
  {
306
+ "epoch": 0.22,
307
+ "grad_norm": 0.34262878952387293,
308
+ "learning_rate": 0.00019204114087239806,
309
+ "loss": 0.6011,
310
  "step": 210
311
  },
312
  {
313
+ "epoch": 0.22,
314
+ "grad_norm": 0.2720473437585886,
315
+ "learning_rate": 0.00019132534873225323,
316
+ "loss": 0.5448,
317
  "step": 215
318
  },
319
+ {
320
+ "epoch": 0.23,
321
+ "grad_norm": 0.23695943062888203,
322
+ "learning_rate": 0.00019058019286061665,
323
+ "loss": 0.5199,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.23,
328
+ "grad_norm": 0.38061349949148005,
329
+ "learning_rate": 0.00018980591284657535,
330
+ "loss": 0.5167,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.24,
335
+ "grad_norm": 0.31515458071917996,
336
+ "learning_rate": 0.00018900275764346768,
337
+ "loss": 0.5201,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.24,
342
+ "grad_norm": 0.3592571813640925,
343
+ "learning_rate": 0.0001881709854888372,
344
+ "loss": 0.5638,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.25,
349
+ "grad_norm": 0.2780598506887593,
350
+ "learning_rate": 0.00018731086382140226,
351
+ "loss": 0.5052,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.25,
356
+ "grad_norm": 0.34554750179980265,
357
+ "learning_rate": 0.00018642266919506644,
358
+ "loss": 0.6022,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.26,
363
+ "grad_norm": 0.35137223950131713,
364
+ "learning_rate": 0.00018550668718999872,
365
+ "loss": 0.5534,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.26,
370
+ "grad_norm": 0.27529845988300145,
371
+ "learning_rate": 0.0001845632123208111,
372
+ "loss": 0.5037,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.27,
377
+ "grad_norm": 0.3706754129199105,
378
+ "learning_rate": 0.0001835925479418637,
379
+ "loss": 0.5209,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.27,
384
+ "grad_norm": 0.3098529350262172,
385
+ "learning_rate": 0.0001825950061497276,
386
+ "loss": 0.5844,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.28,
391
+ "grad_norm": 0.3548275391577921,
392
+ "learning_rate": 0.00018157090768283678,
393
+ "loss": 0.5311,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.28,
398
+ "grad_norm": 0.3284638012761491,
399
+ "learning_rate": 0.00018052058181836151,
400
+ "loss": 0.5675,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.29,
405
+ "grad_norm": 0.38114338073859594,
406
+ "learning_rate": 0.00017944436626633623,
407
+ "loss": 0.5932,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.29,
412
+ "grad_norm": 0.3299526601897124,
413
+ "learning_rate": 0.00017834260706107595,
414
+ "loss": 0.5857,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.3,
419
+ "grad_norm": 0.327976106509182,
420
+ "learning_rate": 0.00017721565844991643,
421
+ "loss": 0.5068,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.3,
426
+ "grad_norm": 0.35435043972661756,
427
+ "learning_rate": 0.00017606388277931328,
428
+ "loss": 0.5429,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.31,
433
+ "grad_norm": 0.38328377811579767,
434
+ "learning_rate": 0.0001748876503783373,
435
+ "loss": 0.6278,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.31,
440
+ "grad_norm": 0.3261327232654444,
441
+ "learning_rate": 0.00017368733943960276,
442
+ "loss": 0.5533,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.32,
447
+ "grad_norm": 0.3009811720038025,
448
+ "learning_rate": 0.00017246333589766787,
449
+ "loss": 0.5083,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.32,
454
+ "grad_norm": 0.3342684613566798,
455
+ "learning_rate": 0.00017121603330494544,
456
+ "loss": 0.6145,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.33,
461
+ "grad_norm": 0.31521187564836095,
462
+ "learning_rate": 0.0001699458327051647,
463
+ "loss": 0.5734,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.33,
468
+ "grad_norm": 0.3840993018659151,
469
+ "learning_rate": 0.00016865314250442398,
470
+ "loss": 0.5061,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.34,
475
+ "grad_norm": 0.4041050776935621,
476
+ "learning_rate": 0.00016733837833987633,
477
+ "loss": 0.5413,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.34,
482
+ "grad_norm": 0.402488525664061,
483
+ "learning_rate": 0.00016600196294609045,
484
+ "loss": 0.5306,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.35,
489
+ "grad_norm": 0.34505184031782365,
490
+ "learning_rate": 0.00016464432601912912,
491
+ "loss": 0.4892,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.35,
496
+ "grad_norm": 0.4416727448065266,
497
+ "learning_rate": 0.0001632659040783897,
498
+ "loss": 0.6394,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.36,
503
+ "grad_norm": 0.2902721265803442,
504
+ "learning_rate": 0.00016186714032625035,
505
+ "loss": 0.422,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.36,
510
+ "grad_norm": 0.34038881357193446,
511
+ "learning_rate": 0.00016044848450556787,
512
+ "loss": 0.4897,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.37,
517
+ "grad_norm": 0.3537467402249508,
518
+ "learning_rate": 0.00015901039275507245,
519
+ "loss": 0.5271,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.37,
524
+ "grad_norm": 0.3096464093822923,
525
+ "learning_rate": 0.00015755332746270572,
526
+ "loss": 0.4851,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.38,
531
+ "grad_norm": 0.33349578622268794,
532
+ "learning_rate": 0.00015607775711694977,
533
+ "loss": 0.4433,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.38,
538
+ "grad_norm": 0.3984031583488789,
539
+ "learning_rate": 0.00015458415615619484,
540
+ "loss": 0.5227,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.39,
545
+ "grad_norm": 0.3791504242897034,
546
+ "learning_rate": 0.00015307300481619333,
547
+ "loss": 0.5553,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.4,
552
+ "grad_norm": 0.3624413301072706,
553
+ "learning_rate": 0.00015154478897565045,
554
+ "loss": 0.6114,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.4,
559
+ "grad_norm": 0.3660206278643239,
560
+ "learning_rate": 0.00015000000000000001,
561
+ "loss": 0.5811,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.41,
566
+ "grad_norm": 0.3465368400413121,
567
+ "learning_rate": 0.00014843913458341645,
568
+ "loss": 0.5336,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.41,
573
+ "grad_norm": 0.3962794628289249,
574
+ "learning_rate": 0.00014686269458911332,
575
+ "loss": 0.5364,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.42,
580
+ "grad_norm": 0.3039345955854238,
581
+ "learning_rate": 0.00014527118688797963,
582
+ "loss": 0.5545,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.42,
587
+ "grad_norm": 0.3884998390679994,
588
+ "learning_rate": 0.0001436651231956064,
589
+ "loss": 0.6274,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.43,
594
+ "grad_norm": 0.43141743992301423,
595
+ "learning_rate": 0.00014204501990775533,
596
+ "loss": 0.6474,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.43,
601
+ "grad_norm": 0.31938982955473066,
602
+ "learning_rate": 0.00014041139793432274,
603
+ "loss": 0.5153,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.44,
608
+ "grad_norm": 0.3760731825930333,
609
+ "learning_rate": 0.00013876478253185183,
610
+ "loss": 0.5613,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.44,
615
+ "grad_norm": 0.2586169946555733,
616
+ "learning_rate": 0.00013710570313464778,
617
+ "loss": 0.61,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.45,
622
+ "grad_norm": 0.2412655626604391,
623
+ "learning_rate": 0.0001354346931845492,
624
+ "loss": 0.4844,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.45,
629
+ "grad_norm": 0.3116268309859188,
630
+ "learning_rate": 0.00013375228995941133,
631
+ "loss": 0.5836,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.46,
636
+ "grad_norm": 0.3358278406427287,
637
+ "learning_rate": 0.0001320590344003557,
638
+ "loss": 0.5687,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.46,
643
+ "grad_norm": 0.3678466240784056,
644
+ "learning_rate": 0.00013035547093784186,
645
+ "loss": 0.5203,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.47,
650
+ "grad_norm": 0.30727587441358567,
651
+ "learning_rate": 0.00012864214731661742,
652
+ "loss": 0.5356,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.47,
657
+ "grad_norm": 0.3488513387485165,
658
+ "learning_rate": 0.00012691961441960238,
659
+ "loss": 0.5693,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.48,
664
+ "grad_norm": 0.36921204919306894,
665
+ "learning_rate": 0.00012518842609076413,
666
+ "loss": 0.6275,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.48,
671
+ "grad_norm": 0.23691846553937704,
672
+ "learning_rate": 0.00012344913895704097,
673
+ "loss": 0.5006,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.49,
678
+ "grad_norm": 0.3452667363717209,
679
+ "learning_rate": 0.00012170231224937032,
680
+ "loss": 0.4681,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.49,
685
+ "grad_norm": 0.3547204515478599,
686
+ "learning_rate": 0.00011994850762287989,
687
+ "loss": 0.4838,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.5,
692
+ "grad_norm": 0.29663657465334964,
693
+ "learning_rate": 0.0001181882889762994,
694
+ "loss": 0.5503,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.5,
699
+ "grad_norm": 0.4673130847127176,
700
+ "learning_rate": 0.00011642222227065089,
701
+ "loss": 0.4547,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.51,
706
+ "grad_norm": 0.32632856811462063,
707
+ "learning_rate": 0.00011465087534727587,
708
+ "loss": 0.639,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.51,
713
+ "grad_norm": 0.2884311338934753,
714
+ "learning_rate": 0.0001128748177452581,
715
+ "loss": 0.5277,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.52,
720
+ "grad_norm": 0.31893330070055553,
721
+ "learning_rate": 0.00011109462051830017,
722
+ "loss": 0.607,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.52,
727
+ "grad_norm": 0.30741665764408194,
728
+ "learning_rate": 0.00010931085605111354,
729
+ "loss": 0.53,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.53,
734
+ "grad_norm": 0.3697277160270557,
735
+ "learning_rate": 0.00010752409787538,
736
+ "loss": 0.5399,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.53,
741
+ "grad_norm": 0.2544618124964993,
742
+ "learning_rate": 0.00010573492048534515,
743
+ "loss": 0.5838,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.54,
748
+ "grad_norm": 0.293117155180105,
749
+ "learning_rate": 0.00010394389915310149,
750
+ "loss": 0.6265,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.54,
755
+ "grad_norm": 0.253262019800845,
756
+ "learning_rate": 0.00010215160974362223,
757
+ "loss": 0.458,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.55,
762
+ "grad_norm": 0.3086878679373377,
763
+ "learning_rate": 0.00010035862852960387,
764
+ "loss": 0.558,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.55,
769
+ "grad_norm": 0.26554052796001515,
770
+ "learning_rate": 9.856553200617805e-05,
771
+ "loss": 0.4748,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.56,
776
+ "grad_norm": 0.3957125840673903,
777
+ "learning_rate": 9.677289670555169e-05,
778
+ "loss": 0.4904,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.56,
783
+ "grad_norm": 0.3311345580462952,
784
+ "learning_rate": 9.49812990116353e-05,
785
+ "loss": 0.5189,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.57,
790
+ "grad_norm": 0.3452796566826953,
791
+ "learning_rate": 9.319131497471894e-05,
792
+ "loss": 0.5287,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.57,
797
+ "grad_norm": 0.3026098766078991,
798
+ "learning_rate": 9.140352012625537e-05,
799
+ "loss": 0.6037,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.58,
804
+ "grad_norm": 0.33840602079777765,
805
+ "learning_rate": 8.961848929381026e-05,
806
+ "loss": 0.5232,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.58,
811
+ "grad_norm": 0.26523037796888355,
812
+ "learning_rate": 8.783679641623845e-05,
813
+ "loss": 0.5282,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.59,
818
+ "grad_norm": 0.30471264337335136,
819
+ "learning_rate": 8.605901435914607e-05,
820
+ "loss": 0.4891,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.6,
825
+ "grad_norm": 0.4626790163374621,
826
+ "learning_rate": 8.428571473069775e-05,
827
+ "loss": 0.4732,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.6,
832
+ "grad_norm": 0.36758855634493254,
833
+ "learning_rate": 8.25174676978282e-05,
834
+ "loss": 0.6205,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.61,
839
+ "grad_norm": 0.40307304885776646,
840
+ "learning_rate": 8.075484180291701e-05,
841
+ "loss": 0.5508,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.61,
846
+ "grad_norm": 0.2696699367170565,
847
+ "learning_rate": 7.899840378098588e-05,
848
+ "loss": 0.444,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.62,
853
+ "grad_norm": 0.30148215688959473,
854
+ "learning_rate": 7.724871837747707e-05,
855
+ "loss": 0.5485,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.62,
860
+ "grad_norm": 0.3348894175707125,
861
+ "learning_rate": 7.550634816667142e-05,
862
+ "loss": 0.5062,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.63,
867
+ "grad_norm": 0.3337832447029819,
868
+ "learning_rate": 7.377185337080442e-05,
869
+ "loss": 0.6384,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.63,
874
+ "grad_norm": 0.32562651669263704,
875
+ "learning_rate": 7.204579167993881e-05,
876
+ "loss": 0.5165,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.64,
881
+ "grad_norm": 0.3488615725937723,
882
+ "learning_rate": 7.032871807265096e-05,
883
+ "loss": 0.5548,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.64,
888
+ "grad_norm": 0.2911657658627874,
889
+ "learning_rate": 6.862118463758943e-05,
890
+ "loss": 0.4718,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.65,
895
+ "grad_norm": 0.3027034627321655,
896
+ "learning_rate": 6.69237403959624e-05,
897
+ "loss": 0.5289,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.65,
902
+ "grad_norm": 0.28279412370215407,
903
+ "learning_rate": 6.52369311250116e-05,
904
+ "loss": 0.6282,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.66,
909
+ "grad_norm": 0.325397208023914,
910
+ "learning_rate": 6.356129918252927e-05,
911
+ "loss": 0.5032,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.66,
916
+ "grad_norm": 0.4468881362131618,
917
+ "learning_rate": 6.189738333247432e-05,
918
+ "loss": 0.548,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.67,
923
+ "grad_norm": 0.32616567931810037,
924
+ "learning_rate": 6.024571857174443e-05,
925
+ "loss": 0.4915,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.67,
930
+ "grad_norm": 0.29764758497214333,
931
+ "learning_rate": 5.860683595815893e-05,
932
+ "loss": 0.572,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.68,
937
+ "grad_norm": 0.3463962850271051,
938
+ "learning_rate": 5.698126243970845e-05,
939
+ "loss": 0.5181,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.68,
944
+ "grad_norm": 0.346392219127237,
945
+ "learning_rate": 5.536952068512608e-05,
946
+ "loss": 0.6312,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.69,
951
+ "grad_norm": 0.27525269488138604,
952
+ "learning_rate": 5.3772128915834184e-05,
953
+ "loss": 0.5446,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.69,
958
+ "grad_norm": 0.3098672923380687,
959
+ "learning_rate": 5.218960073932122e-05,
960
+ "loss": 0.4164,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.7,
965
+ "grad_norm": 0.30953891133733785,
966
+ "learning_rate": 5.062244498400228e-05,
967
+ "loss": 0.5787,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.7,
972
+ "grad_norm": 0.29936249031132967,
973
+ "learning_rate": 4.907116553561607e-05,
974
+ "loss": 0.5776,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.71,
979
+ "grad_norm": 0.267987992377413,
980
+ "learning_rate": 4.753626117521103e-05,
981
+ "loss": 0.5566,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.71,
986
+ "grad_norm": 0.33079494946575233,
987
+ "learning_rate": 4.601822541877291e-05,
988
+ "loss": 0.5182,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.72,
993
+ "grad_norm": 0.25868748114720685,
994
+ "learning_rate": 4.451754635854517e-05,
995
+ "loss": 0.559,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.72,
1000
+ "grad_norm": 0.3290802188517225,
1001
+ "learning_rate": 4.303470650609325e-05,
1002
+ "loss": 0.5881,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.73,
1007
+ "grad_norm": 0.32058655048671514,
1008
+ "learning_rate": 4.1570182637163155e-05,
1009
+ "loss": 0.4518,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.73,
1014
+ "grad_norm": 0.33971870382433816,
1015
+ "learning_rate": 4.0124445638384366e-05,
1016
+ "loss": 0.6093,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.74,
1021
+ "grad_norm": 0.4086041810801181,
1022
+ "learning_rate": 3.869796035586625e-05,
1023
+ "loss": 0.6063,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.74,
1028
+ "grad_norm": 0.3648240136823399,
1029
+ "learning_rate": 3.7291185445736444e-05,
1030
+ "loss": 0.4986,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.75,
1035
+ "grad_norm": 0.37137184349965324,
1036
+ "learning_rate": 3.590457322666997e-05,
1037
+ "loss": 0.5459,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.75,
1042
+ "grad_norm": 0.3202982297697742,
1043
+ "learning_rate": 3.453856953445557e-05,
1044
+ "loss": 0.5487,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.76,
1049
+ "grad_norm": 0.2743331793572931,
1050
+ "learning_rate": 3.319361357864663e-05,
1051
+ "loss": 0.5254,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.76,
1056
+ "grad_norm": 0.3002561379742104,
1057
+ "learning_rate": 3.187013780134291e-05,
1058
+ "loss": 0.5548,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.77,
1063
+ "grad_norm": 0.35602828538254794,
1064
+ "learning_rate": 3.05685677381475e-05,
1065
+ "loss": 0.5441,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.77,
1070
+ "grad_norm": 0.34925281382951245,
1071
+ "learning_rate": 2.9289321881345254e-05,
1072
+ "loss": 0.5641,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.78,
1077
+ "grad_norm": 0.3365150010367925,
1078
+ "learning_rate": 2.8032811545345294e-05,
1079
+ "loss": 0.6116,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.79,
1084
+ "grad_norm": 0.3475156862552588,
1085
+ "learning_rate": 2.679944073443158e-05,
1086
+ "loss": 0.6135,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.79,
1091
+ "grad_norm": 0.3146717649143792,
1092
+ "learning_rate": 2.5589606012863963e-05,
1093
+ "loss": 0.5197,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.8,
1098
+ "grad_norm": 0.3211819564312899,
1099
+ "learning_rate": 2.4403696377371142e-05,
1100
+ "loss": 0.5392,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 0.8,
1105
+ "grad_norm": 0.3409828677067338,
1106
+ "learning_rate": 2.324209313207736e-05,
1107
+ "loss": 0.5052,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 0.81,
1112
+ "grad_norm": 0.2557678515935505,
1113
+ "learning_rate": 2.210516976590179e-05,
1114
+ "loss": 0.4917,
1115
+ "step": 785
1116
+ },
1117
+ {
1118
+ "epoch": 0.81,
1119
+ "grad_norm": 0.24519712151032516,
1120
+ "learning_rate": 2.099329183247126e-05,
1121
+ "loss": 0.3827,
1122
+ "step": 790
1123
+ },
1124
+ {
1125
+ "epoch": 0.82,
1126
+ "grad_norm": 0.32798523064161217,
1127
+ "learning_rate": 1.9906816832584253e-05,
1128
+ "loss": 0.4955,
1129
+ "step": 795
1130
+ },
1131
+ {
1132
+ "epoch": 0.82,
1133
+ "grad_norm": 0.21681035987591052,
1134
+ "learning_rate": 1.8846094099263912e-05,
1135
+ "loss": 0.4815,
1136
+ "step": 800
1137
+ },
1138
+ {
1139
+ "epoch": 0.83,
1140
+ "grad_norm": 0.3625179077510228,
1141
+ "learning_rate": 1.781146468543765e-05,
1142
+ "loss": 0.5803,
1143
+ "step": 805
1144
+ },
1145
+ {
1146
+ "epoch": 0.83,
1147
+ "grad_norm": 0.4443723352307208,
1148
+ "learning_rate": 1.6803261254278636e-05,
1149
+ "loss": 0.5739,
1150
+ "step": 810
1151
+ },
1152
+ {
1153
+ "epoch": 0.84,
1154
+ "grad_norm": 0.42475678943437195,
1155
+ "learning_rate": 1.582180797224507e-05,
1156
+ "loss": 0.5068,
1157
+ "step": 815
1158
+ },
1159
+ {
1160
+ "epoch": 0.84,
1161
+ "grad_norm": 0.46644455691617004,
1162
+ "learning_rate": 1.4867420404851307e-05,
1163
+ "loss": 0.5777,
1164
+ "step": 820
1165
+ },
1166
+ {
1167
+ "epoch": 0.85,
1168
+ "grad_norm": 0.2850490204012201,
1169
+ "learning_rate": 1.3940405415204416e-05,
1170
+ "loss": 0.6615,
1171
+ "step": 825
1172
+ },
1173
+ {
1174
+ "epoch": 0.85,
1175
+ "grad_norm": 0.38102633045200973,
1176
+ "learning_rate": 1.30410610653389e-05,
1177
+ "loss": 0.5049,
1178
+ "step": 830
1179
+ },
1180
+ {
1181
+ "epoch": 0.86,
1182
+ "grad_norm": 0.2792649404054081,
1183
+ "learning_rate": 1.2169676520381168e-05,
1184
+ "loss": 0.4754,
1185
+ "step": 835
1186
+ },
1187
+ {
1188
+ "epoch": 0.86,
1189
+ "grad_norm": 0.2655446144792418,
1190
+ "learning_rate": 1.1326531955574526e-05,
1191
+ "loss": 0.5295,
1192
+ "step": 840
1193
+ },
1194
+ {
1195
+ "epoch": 0.87,
1196
+ "grad_norm": 0.2775130936028629,
1197
+ "learning_rate": 1.0511898466194903e-05,
1198
+ "loss": 0.4933,
1199
+ "step": 845
1200
+ },
1201
+ {
1202
+ "epoch": 0.87,
1203
+ "grad_norm": 0.24711621838841755,
1204
+ "learning_rate": 9.726037980385738e-06,
1205
+ "loss": 0.5456,
1206
+ "step": 850
1207
+ },
1208
+ {
1209
+ "epoch": 0.88,
1210
+ "grad_norm": 0.393271652854802,
1211
+ "learning_rate": 8.969203174940654e-06,
1212
+ "loss": 0.5453,
1213
+ "step": 855
1214
+ },
1215
+ {
1216
+ "epoch": 0.88,
1217
+ "grad_norm": 0.2694238731763909,
1218
+ "learning_rate": 8.24163739406062e-06,
1219
+ "loss": 0.5382,
1220
+ "step": 860
1221
+ },
1222
+ {
1223
+ "epoch": 0.89,
1224
+ "grad_norm": 0.29367966818919566,
1225
+ "learning_rate": 7.543574571111655e-06,
1226
+ "loss": 0.4812,
1227
+ "step": 865
1228
+ },
1229
+ {
1230
+ "epoch": 0.89,
1231
+ "grad_norm": 0.3400136578447068,
1232
+ "learning_rate": 6.875239153408542e-06,
1233
+ "loss": 0.5184,
1234
+ "step": 870
1235
+ },
1236
+ {
1237
+ "epoch": 0.9,
1238
+ "grad_norm": 0.4285681368195809,
1239
+ "learning_rate": 6.236846030048604e-06,
1240
+ "loss": 0.611,
1241
+ "step": 875
1242
+ },
1243
+ {
1244
+ "epoch": 0.9,
1245
+ "grad_norm": 0.46776985117421765,
1246
+ "learning_rate": 5.6286004628186675e-06,
1247
+ "loss": 0.4348,
1248
+ "step": 880
1249
+ },
1250
+ {
1251
+ "epoch": 0.91,
1252
+ "grad_norm": 0.3617441270450328,
1253
+ "learning_rate": 5.0506980201973974e-06,
1254
+ "loss": 0.5767,
1255
+ "step": 885
1256
+ },
1257
+ {
1258
+ "epoch": 0.91,
1259
+ "grad_norm": 0.33384517109285833,
1260
+ "learning_rate": 4.503324514474483e-06,
1261
+ "loss": 0.5594,
1262
+ "step": 890
1263
+ },
1264
+ {
1265
+ "epoch": 0.92,
1266
+ "grad_norm": 0.4731448498076414,
1267
+ "learning_rate": 3.986655942006579e-06,
1268
+ "loss": 0.4884,
1269
+ "step": 895
1270
+ },
1271
+ {
1272
+ "epoch": 0.92,
1273
+ "grad_norm": 0.3078236949280879,
1274
+ "learning_rate": 3.5008584266294386e-06,
1275
+ "loss": 0.5628,
1276
+ "step": 900
1277
+ },
1278
+ {
1279
+ "epoch": 0.93,
1280
+ "grad_norm": 0.32888917087743735,
1281
+ "learning_rate": 3.0460881662442763e-06,
1282
+ "loss": 0.4988,
1283
+ "step": 905
1284
+ },
1285
+ {
1286
+ "epoch": 0.93,
1287
+ "grad_norm": 0.29639144474137563,
1288
+ "learning_rate": 2.622491382595693e-06,
1289
+ "loss": 0.5666,
1290
+ "step": 910
1291
+ },
1292
+ {
1293
+ "epoch": 0.94,
1294
+ "grad_norm": 0.37502576344896726,
1295
+ "learning_rate": 2.2302042742571193e-06,
1296
+ "loss": 0.4814,
1297
+ "step": 915
1298
+ },
1299
+ {
1300
+ "epoch": 0.94,
1301
+ "grad_norm": 0.3978025873196548,
1302
+ "learning_rate": 1.869352972839067e-06,
1303
+ "loss": 0.4309,
1304
+ "step": 920
1305
+ },
1306
+ {
1307
+ "epoch": 0.95,
1308
+ "grad_norm": 0.37364204566135195,
1309
+ "learning_rate": 1.5400535024342022e-06,
1310
+ "loss": 0.4488,
1311
+ "step": 925
1312
+ },
1313
+ {
1314
+ "epoch": 0.95,
1315
+ "grad_norm": 0.2906768898262274,
1316
+ "learning_rate": 1.2424117423122328e-06,
1317
+ "loss": 0.5843,
1318
+ "step": 930
1319
+ },
1320
+ {
1321
+ "epoch": 0.96,
1322
+ "grad_norm": 0.2940342755596854,
1323
+ "learning_rate": 9.765233928766493e-07,
1324
+ "loss": 0.6249,
1325
+ "step": 935
1326
+ },
1327
+ {
1328
+ "epoch": 0.96,
1329
+ "grad_norm": 0.40595136224277073,
1330
+ "learning_rate": 7.42473944894384e-07,
1331
+ "loss": 0.5441,
1332
+ "step": 940
1333
+ },
1334
+ {
1335
+ "epoch": 0.97,
1336
+ "grad_norm": 0.3682171569394288,
1337
+ "learning_rate": 5.403386520079323e-07,
1338
+ "loss": 0.4915,
1339
+ "step": 945
1340
+ },
1341
+ {
1342
+ "epoch": 0.97,
1343
+ "grad_norm": 0.3409683342269183,
1344
+ "learning_rate": 3.701825065392184e-07,
1345
+ "loss": 0.4854,
1346
+ "step": 950
1347
+ },
1348
+ {
1349
+ "epoch": 0.98,
1350
+ "grad_norm": 0.3753876090426702,
1351
+ "learning_rate": 2.320602185927001e-07,
1352
+ "loss": 0.4656,
1353
+ "step": 955
1354
+ },
1355
+ {
1356
+ "epoch": 0.99,
1357
+ "grad_norm": 0.3824583155896019,
1358
+ "learning_rate": 1.2601619846444035e-07,
1359
+ "loss": 0.5535,
1360
+ "step": 960
1361
+ },
1362
+ {
1363
+ "epoch": 0.99,
1364
+ "grad_norm": 0.33353700957958915,
1365
+ "learning_rate": 5.208454236296234e-08,
1366
+ "loss": 0.5956,
1367
+ "step": 965
1368
+ },
1369
+ {
1370
+ "epoch": 1.0,
1371
+ "grad_norm": 0.460947189729548,
1372
+ "learning_rate": 1.0289021446308056e-08,
1373
+ "loss": 0.5259,
1374
+ "step": 970
1375
+ },
1376
  {
1377
  "epoch": 1.0,
1378
  "eval_loss": NaN,
1379
+ "eval_runtime": 1480.6147,
1380
+ "eval_samples_per_second": 1.561,
1381
+ "eval_steps_per_second": 0.39,
1382
+ "step": 974
1383
  },
1384
  {
1385
  "epoch": 1.0,
1386
+ "step": 974,
1387
+ "total_flos": 4299354448986112.0,
1388
+ "train_loss": 0.2056859987472362,
1389
+ "train_runtime": 8762.8151,
1390
+ "train_samples_per_second": 3.558,
1391
+ "train_steps_per_second": 0.111
1392
  }
1393
  ],
1394
  "logging_steps": 5,
1395
+ "max_steps": 974,
1396
  "num_input_tokens_seen": 0,
1397
  "num_train_epochs": 1,
1398
  "save_steps": 40,
1399
+ "total_flos": 4299354448986112.0,
1400
+ "train_batch_size": 4,
1401
  "trial_name": null,
1402
  "trial_params": null
1403
  }