Hugging Face's logo

anas-awadalla
/
roberta-large-houlsby-few-shot-k-16-finetuned-squad-seed-4

generated_from_trainer
Model card Files Community
anas-awadalla commited on
Commit
c471b3e
•
1 Parent(s): d803096

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": 200.0,
3
- "eval_exact_match": 13.055818353831599,
4
- "eval_f1": 25.229126879285918,
5
  "eval_samples": 10790,
6
- "train_loss": 1.2634832763671875,
7
- "train_runtime": 103.6991,
8
  "train_samples": 16,
9
- "train_samples_per_second": 46.288,
10
- "train_steps_per_second": 3.857
11
  }
 
1
  {
2
+ "epoch": 75.0,
3
+ "eval_exact_match": 0.8703878902554399,
4
+ "eval_f1": 8.803204201941334,
5
  "eval_samples": 10790,
6
+ "train_loss": 4.361583658854166,
7
+ "train_runtime": 20.3399,
8
  "train_samples": 16,
9
+ "train_samples_per_second": 471.978,
10
+ "train_steps_per_second": 3.687
11
  }
eval_nbest_predictions.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:842d7ec77b46bc7b5d35e1ace1a12becf11bfc98643d6082c1e304ac4b915dcf
3
- size 50137399
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b2a76c7fe99edd8e5cc08785feed5135e4f1d23ca0f8d3b65a1a9df848e852a
3
+ size 53141914
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": 200.0,
3
- "eval_exact_match": 13.055818353831599,
4
- "eval_f1": 25.229126879285918,
5
  "eval_samples": 10790
6
  }
 
1
  {
2
+ "epoch": 75.0,
3
+ "eval_exact_match": 0.8703878902554399,
4
+ "eval_f1": 8.803204201941334,
5
  "eval_samples": 10790
6
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 200.0,
3
- "train_loss": 1.2634832763671875,
4
- "train_runtime": 103.6991,
5
  "train_samples": 16,
6
- "train_samples_per_second": 46.288,
7
- "train_steps_per_second": 3.857
8
  }
 
1
  {
2
+ "epoch": 75.0,
3
+ "train_loss": 4.361583658854166,
4
+ "train_runtime": 20.3399,
5
  "train_samples": 16,
6
+ "train_samples_per_second": 471.978,
7
+ "train_steps_per_second": 3.687
8
  }
trainer_state.json CHANGED
@@ -1,25 +1,25 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 200.0,
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": 200.0,
12
- "step": 400,
13
- "total_flos": 2275667465011200.0,
14
- "train_loss": 1.2634832763671875,
15
- "train_runtime": 103.6991,
16
- "train_samples_per_second": 46.288,
17
- "train_steps_per_second": 3.857
18
  }
19
  ],
20
- "max_steps": 400,
21
- "num_train_epochs": 200,
22
- "total_flos": 2275667465011200.0,
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": 853375306432512.0,
14
+ "train_loss": 4.361583658854166,
15
+ "train_runtime": 20.3399,
16
+ "train_samples_per_second": 471.978,
17
+ "train_steps_per_second": 3.687
18
  }
19
  ],
20
+ "max_steps": 75,
21
+ "num_train_epochs": 75,
22
+ "total_flos": 853375306432512.0,
23
  "trial_name": null,
24
  "trial_params": null
25
  }