Stefania Radu commited on
Commit
a2e3ded
·
1 Parent(s): 743f00e

Training in progress, step 30000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee973dee881c5bbb9553780888e05cd3cf06c2fe7faa346f130b252302d96138
3
  size 893440890
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94126fac29d2c419d928052a1ba6da3d5312d5c0ce553618c0ca3f2d0f390db3
3
  size 893440890
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:510c615128a96b868de4797db5b25ab26dbfd6df018d383c8dbc0eaaa9fcd9c2
3
  size 454197066
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad1608fffadb053a124278f04351297d190ac574d4e2aa6f7854883ee815b50
3
  size 454197066
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:864ecc2b308501cc2ea6f5fa3cf2e14e19432fd64f93279b35f4b6a21d7c9564
3
- size 14180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f8be78b6c50233c2196c2487bcd27a3d37929b5c914995616274c9c01052e02
3
+ size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:473b532c01401932ca54c4b6b84b8944c851f847bafe7fb2740f6e4f5e92d972
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2721929e2fd780de1abcf69285610702c2e5a259eb8058539c927f793ffdfa53
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.02,
5
- "global_step": 20000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -154,11 +154,85 @@
154
  "eval_samples_per_second": 104.047,
155
  "eval_steps_per_second": 13.006,
156
  "step": 20000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
157
  }
158
  ],
159
  "max_steps": 1000000,
160
  "num_train_epochs": 9223372036854775807,
161
- "total_flos": 1.7709220346462208e+20,
162
  "trial_name": null,
163
  "trial_params": null
164
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.03,
5
+ "global_step": 30000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
154
  "eval_samples_per_second": 104.047,
155
  "eval_steps_per_second": 13.006,
156
  "step": 20000
157
+ },
158
+ {
159
+ "epoch": 0.02,
160
+ "learning_rate": 7.874999999999998e-06,
161
+ "loss": 0.736,
162
+ "step": 21000
163
+ },
164
+ {
165
+ "epoch": 0.02,
166
+ "learning_rate": 8.249999999999999e-06,
167
+ "loss": 0.7356,
168
+ "step": 22000
169
+ },
170
+ {
171
+ "epoch": 0.02,
172
+ "learning_rate": 8.625e-06,
173
+ "loss": 0.7345,
174
+ "step": 23000
175
+ },
176
+ {
177
+ "epoch": 0.02,
178
+ "learning_rate": 8.999999999999999e-06,
179
+ "loss": 0.7352,
180
+ "step": 24000
181
+ },
182
+ {
183
+ "epoch": 0.03,
184
+ "learning_rate": 9.375e-06,
185
+ "loss": 0.7363,
186
+ "step": 25000
187
+ },
188
+ {
189
+ "epoch": 0.03,
190
+ "eval_runtime": 3202.6438,
191
+ "eval_samples_per_second": 106.054,
192
+ "eval_steps_per_second": 13.257,
193
+ "step": 25000
194
+ },
195
+ {
196
+ "epoch": 0.03,
197
+ "learning_rate": 9.75e-06,
198
+ "loss": 0.7336,
199
+ "step": 26000
200
+ },
201
+ {
202
+ "epoch": 0.03,
203
+ "learning_rate": 1.0125e-05,
204
+ "loss": 0.7194,
205
+ "step": 27000
206
+ },
207
+ {
208
+ "epoch": 0.03,
209
+ "learning_rate": 1.05e-05,
210
+ "loss": 0.7003,
211
+ "step": 28000
212
+ },
213
+ {
214
+ "epoch": 0.03,
215
+ "learning_rate": 1.0874999999999998e-05,
216
+ "loss": 0.6844,
217
+ "step": 29000
218
+ },
219
+ {
220
+ "epoch": 0.03,
221
+ "learning_rate": 1.1249999999999999e-05,
222
+ "loss": 0.6632,
223
+ "step": 30000
224
+ },
225
+ {
226
+ "epoch": 0.03,
227
+ "eval_runtime": 3180.4112,
228
+ "eval_samples_per_second": 106.795,
229
+ "eval_steps_per_second": 13.35,
230
+ "step": 30000
231
  }
232
  ],
233
  "max_steps": 1000000,
234
  "num_train_epochs": 9223372036854775807,
235
+ "total_flos": 2.6563830519693312e+20,
236
  "trial_name": null,
237
  "trial_params": null
238
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:510c615128a96b868de4797db5b25ab26dbfd6df018d383c8dbc0eaaa9fcd9c2
3
  size 454197066
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad1608fffadb053a124278f04351297d190ac574d4e2aa6f7854883ee815b50
3
  size 454197066