Hugging Face's logo

anas-awadalla
/
roberta-large-houlsby-few-shot-k-32-finetuned-squad-seed-0

generated_from_trainer
Model card Files Community
anas-awadalla commited on
Commit
09f3e35
•
1 Parent(s): 5b824d7

End of training

Browse files
Files changed (6) hide show
  1. all_results.json +7 -7
  2. eval_nbest_predictions.json +2 -2
  3. eval_predictions.json +0 -0
  4. eval_results.json +3 -3
  5. train_results.json +5 -5
  6. trainer_state.json +12 -12
all_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "epoch": 133.33,
3
- "eval_exact_match": 15.250709555345317,
4
- "eval_f1": 27.7827023848963,
5
  "eval_samples": 10790,
6
- "train_loss": 1.3465371704101563,
7
- "train_runtime": 132.5961,
8
  "train_samples": 32,
9
- "train_samples_per_second": 36.2,
10
- "train_steps_per_second": 3.017
11
  }
 
1
  {
2
+ "epoch": 75.0,
3
+ "eval_exact_match": 2.403027436140019,
4
+ "eval_f1": 8.966878595472302,
5
  "eval_samples": 10790,
6
+ "train_loss": 4.382401936848958,
7
+ "train_runtime": 36.3224,
8
  "train_samples": 32,
9
+ "train_samples_per_second": 264.3,
10
+ "train_steps_per_second": 2.065
11
  }
eval_nbest_predictions.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e862de20d449bbd6fa1c66d00e7f7f08bb9bce912bd7ad017fbf59cbeadf8445
3
- size 51431119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:025d5db50c4f0ba323cb7e57e3091c367c4df11aa95aa74096162d86dfec4a47
3
+ size 52082151
eval_predictions.json CHANGED
The diff for this file is too large to render. See raw diff
 
eval_results.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "epoch": 133.33,
3
- "eval_exact_match": 15.250709555345317,
4
- "eval_f1": 27.7827023848963,
5
  "eval_samples": 10790
6
  }
 
1
  {
2
+ "epoch": 75.0,
3
+ "eval_exact_match": 2.403027436140019,
4
+ "eval_f1": 8.966878595472302,
5
  "eval_samples": 10790
6
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 133.33,
3
- "train_loss": 1.3465371704101563,
4
- "train_runtime": 132.5961,
5
  "train_samples": 32,
6
- "train_samples_per_second": 36.2,
7
- "train_steps_per_second": 3.017
8
  }
 
1
  {
2
+ "epoch": 75.0,
3
+ "train_loss": 4.382401936848958,
4
+ "train_runtime": 36.3224,
5
  "train_samples": 32,
6
+ "train_samples_per_second": 264.3,
7
+ "train_steps_per_second": 2.065
8
  }
trainer_state.json CHANGED
@@ -1,25 +1,25 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 133.33333333333334,
5
- "global_step": 400,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
- "epoch": 133.33,
12
- "step": 400,
13
- "total_flos": 3035171481458688.0,
14
- "train_loss": 1.3465371704101563,
15
- "train_runtime": 132.5961,
16
- "train_samples_per_second": 36.2,
17
- "train_steps_per_second": 3.017
18
  }
19
  ],
20
- "max_steps": 400,
21
- "num_train_epochs": 134,
22
- "total_flos": 3035171481458688.0,
23
  "trial_name": null,
24
  "trial_params": null
25
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 75.0,
5
+ "global_step": 75,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
+ "epoch": 75.0,
12
+ "step": 75,
13
+ "total_flos": 1706750612865024.0,
14
+ "train_loss": 4.382401936848958,
15
+ "train_runtime": 36.3224,
16
+ "train_samples_per_second": 264.3,
17
+ "train_steps_per_second": 2.065
18
  }
19
  ],
20
+ "max_steps": 75,
21
+ "num_train_epochs": 75,
22
+ "total_flos": 1706750612865024.0,
23
  "trial_name": null,
24
  "trial_params": null
25
  }