Hugging Face's logo

joelniklaus
/
legal-swiss-longformer-base

Fill-Mask
Transformers
PyTorch
Safetensors
4 languages
longformer
Inference Endpoints
4 papers
Model card Files Community
7
joelniklaus commited on
Commit
77c9afd
•
1 Parent(s): f4865ae

Training in progress, step 30000

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 +72 -3
  7. last-checkpoint/training_args.bin +2 -2
  8. pytorch_model.bin +1 -1
  9. training_args.bin +2 -2
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:291f9655e8deedacd6ba5d051af226c4cb8ebd7310cc9e38474e2a0f61b6d10e
3
  size 1668076741
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59a55d6487c86c6aead5e0412dc7bc934e36a0aa93b9f0928222c619b3a6dc26
3
  size 1668076741
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abbe85aaf27562d1d64f10fe9cebefd891fb599fac4d07e142f8b427c63c674d
3
  size 834053717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afa3a23b0ea1a2c3ccb9f24eefca4b14ffcdafa3ff984873e38ddff2e7290345
3
  size 834053717
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f5b5027ca54bd16ebf7bcd1124e301f3adcb854fc2dbe6bf992e7e1ea1ae077
3
  size 15597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a94832b74f59af89e3b9e9505954479af47d9b9be6a042d5dc4a4c83a1ee819
3
  size 15597
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0876994cba4fff49c925c2a122534ea9fff9a44c01c8ac7813ec4131482c3100
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4fbddc5e4f36733a366bb458aab68ef6c96dc3f630fcba928b847be47bc6ff6
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32d54ab2a4c0dda7883ab94b84e46d25097c34cdf01933d23db795cca974f4ce
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bbda704539dc18bceb7e94b4d3dd8ba0647f895bc67af2d0be585b02bce7e37
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.4,
5
- "global_step": 20000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -144,11 +144,80 @@
144
  "eval_samples_per_second": 33.07,
145
  "eval_steps_per_second": 2.07,
146
  "step": 20000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
147
  }
148
  ],
149
  "max_steps": 50000,
150
  "num_train_epochs": 9223372036854775807,
151
- "total_flos": 1.34684268822528e+19,
152
  "trial_name": null,
153
  "trial_params": null
154
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.6,
5
+ "global_step": 30000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
144
  "eval_samples_per_second": 33.07,
145
  "eval_steps_per_second": 2.07,
146
  "step": 20000
147
+ },
148
+ {
149
+ "epoch": 0.42,
150
+ "learning_rate": 2.011652308828144e-05,
151
+ "loss": 0.7647,
152
+ "step": 21000
153
+ },
154
+ {
155
+ "epoch": 0.44,
156
+ "learning_rate": 1.917343299405194e-05,
157
+ "loss": 0.7081,
158
+ "step": 22000
159
+ },
160
+ {
161
+ "epoch": 0.46,
162
+ "learning_rate": 1.8212093539217514e-05,
163
+ "loss": 0.7579,
164
+ "step": 23000
165
+ },
166
+ {
167
+ "epoch": 0.48,
168
+ "learning_rate": 1.72367084166133e-05,
169
+ "loss": 0.7132,
170
+ "step": 24000
171
+ },
172
+ {
173
+ "epoch": 0.5,
174
+ "learning_rate": 1.6252531357090434e-05,
175
+ "loss": 0.7895,
176
+ "step": 25000
177
+ },
178
+ {
179
+ "epoch": 0.52,
180
+ "learning_rate": 1.52618963110846e-05,
181
+ "loss": 0.7258,
182
+ "step": 26000
183
+ },
184
+ {
185
+ "epoch": 0.54,
186
+ "learning_rate": 1.4270116059146648e-05,
187
+ "loss": 0.7327,
188
+ "step": 27000
189
+ },
190
+ {
191
+ "epoch": 0.56,
192
+ "learning_rate": 1.328152740397216e-05,
193
+ "loss": 0.8063,
194
+ "step": 28000
195
+ },
196
+ {
197
+ "epoch": 0.58,
198
+ "learning_rate": 1.2301429081434528e-05,
199
+ "loss": 0.7966,
200
+ "step": 29000
201
+ },
202
+ {
203
+ "epoch": 0.6,
204
+ "learning_rate": 1.1332145369350178e-05,
205
+ "loss": 0.7693,
206
+ "step": 30000
207
+ },
208
+ {
209
+ "epoch": 0.6,
210
+ "eval_accuracy": 0.8589594943032635,
211
+ "eval_loss": 0.6138944029808044,
212
+ "eval_runtime": 125.8255,
213
+ "eval_samples_per_second": 39.738,
214
+ "eval_steps_per_second": 2.488,
215
+ "step": 30000
216
  }
217
  ],
218
  "max_steps": 50000,
219
  "num_train_epochs": 9223372036854775807,
220
+ "total_flos": 2.02026403233792e+19,
221
  "trial_name": null,
222
  "trial_params": null
223
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b0babeabcb0232c54abbc734323546866d0c776b0a65f83be54dbb867e9e640
3
- size 3707
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc7a2fca956110fa8feafc0aa6cd21981160f54c916ff419fbc9ee0826ac6859
3
+ size 3771
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abbe85aaf27562d1d64f10fe9cebefd891fb599fac4d07e142f8b427c63c674d
3
  size 834053717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afa3a23b0ea1a2c3ccb9f24eefca4b14ffcdafa3ff984873e38ddff2e7290345
3
  size 834053717
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b0babeabcb0232c54abbc734323546866d0c776b0a65f83be54dbb867e9e640
3
- size 3707
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc7a2fca956110fa8feafc0aa6cd21981160f54c916ff419fbc9ee0826ac6859
3
+ size 3771