Hugging Face's logo

anas-awadalla
/
roberta-large-houlsby-few-shot-k-64-finetuned-squad-seed-4

generated_from_trainer
Model card Files Community
anas-awadalla commited on
Commit
c8b1629
•
1 Parent(s): 41d62e4

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": 100.0,
3
- "eval_exact_match": 28.02270577105014,
4
- "eval_f1": 42.63380231670078,
5
  "eval_samples": 10790,
6
- "train_loss": 2.4057366943359373,
7
- "train_runtime": 183.122,
8
  "train_samples": 64,
9
- "train_samples_per_second": 34.949,
10
- "train_steps_per_second": 1.092
11
  }
 
1
  {
2
+ "epoch": 66.67,
3
+ "eval_exact_match": 31.561021759697255,
4
+ "eval_f1": 46.36163127253285,
5
  "eval_samples": 10790,
6
+ "train_loss": 1.6538446044921875,
7
+ "train_runtime": 132.7135,
8
  "train_samples": 64,
9
+ "train_samples_per_second": 36.168,
10
+ "train_steps_per_second": 3.014
11
  }
eval_nbest_predictions.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef361518bf173fcc587463a5175842b01adaa1621b6e8a592ae877cbd890a154
3
- size 50851806
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a83d0597c31c0607e08eb8d7a183439f658214f65be9160fd25c919991f7e0ca
3
+ size 51781151
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": 100.0,
3
- "eval_exact_match": 28.02270577105014,
4
- "eval_f1": 42.63380231670078,
5
  "eval_samples": 10790
6
  }
 
1
  {
2
+ "epoch": 66.67,
3
+ "eval_exact_match": 31.561021759697255,
4
+ "eval_f1": 46.36163127253285,
5
  "eval_samples": 10790
6
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 100.0,
3
- "train_loss": 2.4057366943359373,
4
- "train_runtime": 183.122,
5
  "train_samples": 64,
6
- "train_samples_per_second": 34.949,
7
- "train_steps_per_second": 1.092
8
  }
 
1
  {
2
+ "epoch": 66.67,
3
+ "train_loss": 1.6538446044921875,
4
+ "train_runtime": 132.7135,
5
  "train_samples": 64,
6
+ "train_samples_per_second": 36.168,
7
+ "train_steps_per_second": 3.014
8
  }
trainer_state.json CHANGED
@@ -1,25 +1,25 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 100.0,
5
- "global_step": 200,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
- "epoch": 100.0,
12
- "step": 200,
13
- "total_flos": 4551334930022400.0,
14
- "train_loss": 2.4057366943359373,
15
- "train_runtime": 183.122,
16
- "train_samples_per_second": 34.949,
17
- "train_steps_per_second": 1.092
18
  }
19
  ],
20
- "max_steps": 200,
21
- "num_train_epochs": 100,
22
- "total_flos": 4551334930022400.0,
23
  "trial_name": null,
24
  "trial_params": null
25
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 66.66666666666667,
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": 66.67,
12
+ "step": 400,
13
+ "total_flos": 3038016065789952.0,
14
+ "train_loss": 1.6538446044921875,
15
+ "train_runtime": 132.7135,
16
+ "train_samples_per_second": 36.168,
17
+ "train_steps_per_second": 3.014
18
  }
19
  ],
20
+ "max_steps": 400,
21
+ "num_train_epochs": 67,
22
+ "total_flos": 3038016065789952.0,
23
  "trial_name": null,
24
  "trial_params": null
25
  }