Hugging Face's logo

k4black
/
roberta-large-e-snli-classification-nli-base

Text Classification
Transformers
PyTorch
roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
2
k4black commited on
Commit
d2f4eba
•
1 Parent(s): 54af404

Training in progress, step 5200

Browse files
Files changed (7) 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 +69 -5
  7. pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51c2ce7163cd0393f56a1f16f501794039c69dc4b905609c536b8d2610416be3
3
  size 2843228158
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19a0167071d6077d8f26fcfb7304a29ea809d034ec769f851d56de0c8bea89c8
3
  size 2843228158
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:860047c7dff7fb338d60a846bf0cd150c69e3ae5f5234ecc36a7a1b6c68c35c0
3
  size 1421588461
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b64bf1490035f1c45fec685049f0d6a1e6e790b80c14856fab49fcd0b7114687
3
  size 1421588461
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce1247af97fcc60eb232e79ad70b57f6a40adfdd60aca9b5b05f159818f9be36
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:493e658da36031d3825842e705fcbf542f533c87882496ee53fda9fcd47858eb
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90e2f8a70acd9fbfda3012da5136ca5cf89ee1cda6e3e2e92b1fe97de3c5a73c
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda94d2ae823993ee852e2514dee8cef8ce45edf13d5b4966c68949e7923c4ab
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1d7f009df2a5e3ebf2598687f4ede8c86c686b0f969b80266c4f9c02766b1a3
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49b37a86f5ceab52bac4fb464c21074a6c79d3fab0788b80ac9b85da08906513
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.9182731413386942,
3
- "best_model_checkpoint": "/home2/s5431786/nlp-final-project/results/roberta-large-e-snli-classification-nli-base/checkpoint-2800",
4
- "epoch": 0.4193849021435228,
5
- "global_step": 3600,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -150,11 +150,75 @@
150
  "eval_samples_per_second": 990.544,
151
  "eval_steps_per_second": 15.499,
152
  "step": 3600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
153
  }
154
  ],
155
  "max_steps": 25752,
156
  "num_train_epochs": 3,
157
- "total_flos": 2.2294086874568064e+16,
158
  "trial_name": null,
159
  "trial_params": null
160
  }
 
1
  {
2
+ "best_metric": 0.9206360860900841,
3
+ "best_model_checkpoint": "/home2/s5431786/nlp-final-project/results/roberta-large-e-snli-classification-nli-base/checkpoint-5200",
4
+ "epoch": 0.6057781919850885,
5
+ "global_step": 5200,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
150
  "eval_samples_per_second": 990.544,
151
  "eval_steps_per_second": 15.499,
152
  "step": 3600
153
+ },
154
+ {
155
+ "epoch": 0.47,
156
+ "learning_rate": 8.893476128188358e-06,
157
+ "loss": 0.3027,
158
+ "step": 4000
159
+ },
160
+ {
161
+ "epoch": 0.47,
162
+ "eval_accuracy": 0.9191221296484454,
163
+ "eval_f1": 0.9190571565466592,
164
+ "eval_loss": 0.23602379858493805,
165
+ "eval_runtime": 10.6438,
166
+ "eval_samples_per_second": 924.674,
167
+ "eval_steps_per_second": 14.469,
168
+ "step": 4000
169
+ },
170
+ {
171
+ "epoch": 0.51,
172
+ "learning_rate": 8.729970568999347e-06,
173
+ "loss": 0.2968,
174
+ "step": 4400
175
+ },
176
+ {
177
+ "epoch": 0.51,
178
+ "eval_accuracy": 0.9187157081893924,
179
+ "eval_f1": 0.9182261319193824,
180
+ "eval_loss": 0.23287305235862732,
181
+ "eval_runtime": 9.9312,
182
+ "eval_samples_per_second": 991.014,
183
+ "eval_steps_per_second": 15.507,
184
+ "step": 4400
185
+ },
186
+ {
187
+ "epoch": 0.56,
188
+ "learning_rate": 8.566465009810335e-06,
189
+ "loss": 0.2888,
190
+ "step": 4800
191
+ },
192
+ {
193
+ "epoch": 0.56,
194
+ "eval_accuracy": 0.9196301564722618,
195
+ "eval_f1": 0.9189361658403055,
196
+ "eval_loss": 0.24621723592281342,
197
+ "eval_runtime": 9.9085,
198
+ "eval_samples_per_second": 993.291,
199
+ "eval_steps_per_second": 15.542,
200
+ "step": 4800
201
+ },
202
+ {
203
+ "epoch": 0.61,
204
+ "learning_rate": 8.402959450621321e-06,
205
+ "loss": 0.2898,
206
+ "step": 5200
207
+ },
208
+ {
209
+ "epoch": 0.61,
210
+ "eval_accuracy": 0.9211542369437107,
211
+ "eval_f1": 0.9206360860900841,
212
+ "eval_loss": 0.23345668613910675,
213
+ "eval_runtime": 10.0954,
214
+ "eval_samples_per_second": 974.901,
215
+ "eval_steps_per_second": 15.254,
216
+ "step": 5200
217
  }
218
  ],
219
  "max_steps": 25752,
220
  "num_train_epochs": 3,
221
+ "total_flos": 3.2222917166779776e+16,
222
  "trial_name": null,
223
  "trial_params": null
224
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:860047c7dff7fb338d60a846bf0cd150c69e3ae5f5234ecc36a7a1b6c68c35c0
3
  size 1421588461
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b64bf1490035f1c45fec685049f0d6a1e6e790b80c14856fab49fcd0b7114687
3
  size 1421588461