k4black commited on
Commit
a7400d8
1 Parent(s): 24c72f3

Training in progress, step 18000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a963e17d63c5311d4177c813a94a2aef757d599b9e54238d21dc7910cea8d38
3
  size 1135685
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668500daa8ad28ba1752adb76902631efe71bbfbbc7b58dc2a77ad0e0c886cc9
3
  size 1135685
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ffb6cb62074cb556e4605433d13ffd9119d9af77cd667c007bfe11a29bc9c8a
3
  size 307910149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2db8cdbb361aabc881d1114a73ac035104bb1e898fd8f7acd4145c5c89c907a5
3
  size 307910149
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e64fd0c22b4f678e997dcb527fccba5e7f7f0718a533bfc0e960d81e6c062ad4
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48fd37244d36e382ee4075e21f2271ce2b40181f69c1a4ed518bee64527c87ad
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3c7bfd871284a6faa92f94aee9c5ea71a9bdcdd13ee2b820e7d8b41939b332d
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62302b41ef27e8715d8b2f0e96943911ec884bb406e266f83a8ca9d79997b602
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": 1.692925214767456,
3
  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-16000",
4
- "epoch": 1.8639328984156571,
5
- "global_step": 16000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -182,11 +182,33 @@
182
  "eval_samples_per_second": 59.433,
183
  "eval_steps_per_second": 0.93,
184
  "step": 16000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
185
  }
186
  ],
187
  "max_steps": 85840,
188
  "num_train_epochs": 10,
189
- "total_flos": 2.417528886921216e+16,
190
  "trial_name": null,
191
  "trial_params": null
192
  }
 
1
  {
2
  "best_metric": 1.692925214767456,
3
  "best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-16000",
4
+ "epoch": 2.096924510717614,
5
+ "global_step": 18000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
182
  "eval_samples_per_second": 59.433,
183
  "eval_steps_per_second": 0.93,
184
  "step": 16000
185
+ },
186
+ {
187
+ "epoch": 2.1,
188
+ "learning_rate": 0.0008319026830823564,
189
+ "loss": 1.2084,
190
+ "step": 18000
191
+ },
192
+ {
193
+ "epoch": 2.1,
194
+ "eval_accuracy": null,
195
+ "eval_bertscore_f1": 0.9346273795566624,
196
+ "eval_bleu": 0.4082124628614291,
197
+ "eval_f1": null,
198
+ "eval_loss": 1.7380170822143555,
199
+ "eval_rouge1": 0.6207188358704087,
200
+ "eval_rouge2": 0.4177034932099197,
201
+ "eval_rougeL": 0.5656127494093233,
202
+ "eval_rougeLsum": 0.5677652123372579,
203
+ "eval_runtime": 171.9389,
204
+ "eval_samples_per_second": 57.241,
205
+ "eval_steps_per_second": 0.896,
206
+ "step": 18000
207
  }
208
  ],
209
  "max_steps": 85840,
210
  "num_train_epochs": 10,
211
+ "total_flos": 2.720624988644352e+16,
212
  "trial_name": null,
213
  "trial_params": null
214
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ffb6cb62074cb556e4605433d13ffd9119d9af77cd667c007bfe11a29bc9c8a
3
  size 307910149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2db8cdbb361aabc881d1114a73ac035104bb1e898fd8f7acd4145c5c89c907a5
3
  size 307910149