Hugging Face's logo

Nadav
/
PretrainedPHD-v3

Transformers
PyTorch
pixel
Model card Files
xet
 Community
Nadav commited on
Commit
66376ec
·
1 Parent(s): c639d29

Training in progress, step 15000

Browse files
Files changed (9) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +71 -3
  7. last-checkpoint/training_args.bin +1 -1
  8. pytorch_model.bin +1 -1
  9. training_args.bin +1 -1
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:153be8a536485c83aa6dfda3ccd31cbb49591a8b1d3add03c304c0ca882f4f80
3
  size 893438545
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:623066aed91f68831295f3b25572aa8707018ca811f7426459558970e5916d97
3
  size 893438545
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5c20144a4b9e27b7911ada8d36376e0bfc98e3a7b006c69a1edf0cab2408ed8
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f7a0b7dc0ab0d4d24fe43a771ba9192940d4c56c18aa35eabf3326e53e9e49c
3
  size 449471589
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41c5109bb7103f67386e48a9ef9b3e5c761f186216810c95f00eb2eff9d2a4ec
3
  size 15523
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:739c21ae5495f031e76c1edfd236e63cbc37a2a2cf46f957641fc1da74d05fda
3
  size 15523
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70032c0133ae8be4d57f5bc088df5e80deb90ddcc920990a92103ea496b93a7d
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:883f4295fa210515c659ff9b5fb1bfbc276c06103467c487bac620d634db215a
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f42e0bd380ddae36480c7e1c1943e2b9fbad63e7f4fc190b9b9f25706bedbf28
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb29cb64d5a489d3293482bd3904f6db7e31df9cb20c7fa36ad240c627d50bc8
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.05,
5
- "global_step": 10000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -142,11 +142,79 @@
142
  "eval_samples_per_second": 121.175,
143
  "eval_steps_per_second": 1.893,
144
  "step": 10000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
145
  }
146
  ],
147
  "max_steps": 200000,
148
  "num_train_epochs": 9223372036854775807,
149
- "total_flos": 2.354930673647616e+20,
150
  "trial_name": null,
151
  "trial_params": null
152
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.025,
5
+ "global_step": 15000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
142
  "eval_samples_per_second": 121.175,
143
  "eval_steps_per_second": 1.893,
144
  "step": 10000
145
+ },
146
+ {
147
+ "epoch": 0.0,
148
+ "learning_rate": 0.00010016561664465461,
149
+ "loss": 0.4813,
150
+ "step": 10500
151
+ },
152
+ {
153
+ "epoch": 0.01,
154
+ "learning_rate": 0.00010010572071123591,
155
+ "loss": 0.481,
156
+ "step": 11000
157
+ },
158
+ {
159
+ "epoch": 0.01,
160
+ "learning_rate": 0.00010004306654008681,
161
+ "loss": 0.4797,
162
+ "step": 11500
163
+ },
164
+ {
165
+ "epoch": 0.01,
166
+ "learning_rate": 9.997765799601176e-05,
167
+ "loss": 0.4797,
168
+ "step": 12000
169
+ },
170
+ {
171
+ "epoch": 0.01,
172
+ "learning_rate": 9.990949911371783e-05,
173
+ "loss": 0.4777,
174
+ "step": 12500
175
+ },
176
+ {
177
+ "epoch": 0.01,
178
+ "learning_rate": 9.983859409756594e-05,
179
+ "loss": 0.478,
180
+ "step": 13000
181
+ },
182
+ {
183
+ "epoch": 0.02,
184
+ "learning_rate": 9.976494732131149e-05,
185
+ "loss": 0.476,
186
+ "step": 13500
187
+ },
188
+ {
189
+ "epoch": 0.02,
190
+ "learning_rate": 9.968871882446063e-05,
191
+ "loss": 0.4751,
192
+ "step": 14000
193
+ },
194
+ {
195
+ "epoch": 0.02,
196
+ "learning_rate": 9.960960778568231e-05,
197
+ "loss": 0.4756,
198
+ "step": 14500
199
+ },
200
+ {
201
+ "epoch": 0.03,
202
+ "learning_rate": 9.95279355079561e-05,
203
+ "loss": 0.475,
204
+ "step": 15000
205
+ },
206
+ {
207
+ "epoch": 0.03,
208
+ "eval_loss": 0.45417556166648865,
209
+ "eval_runtime": 68.2171,
210
+ "eval_samples_per_second": 93.818,
211
+ "eval_steps_per_second": 1.466,
212
+ "step": 15000
213
  }
214
  ],
215
  "max_steps": 200000,
216
  "num_train_epochs": 9223372036854775807,
217
+ "total_flos": 3.532396010471424e+20,
218
  "trial_name": null,
219
  "trial_params": null
220
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca762f1acf9a6f6d964307929433968af3e08f4803fb33705fe0dbbd68e4da76
3
  size 5551
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92fe998606f51cfbdaeade2ff6ed2dfa530ab49cf5bec297af470359fd69c4bc
3
  size 5551
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5c20144a4b9e27b7911ada8d36376e0bfc98e3a7b006c69a1edf0cab2408ed8
3
  size 449471589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f7a0b7dc0ab0d4d24fe43a771ba9192940d4c56c18aa35eabf3326e53e9e49c
3
  size 449471589
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca762f1acf9a6f6d964307929433968af3e08f4803fb33705fe0dbbd68e4da76
3
  size 5551
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92fe998606f51cfbdaeade2ff6ed2dfa530ab49cf5bec297af470359fd69c4bc
3
  size 5551