Hugging Face's logo

anas-awadalla
/
roberta-large-houlsby-few-shot-k-64-finetuned-squad-seed-2

Generated from Trainer
Model card Files Community
anas-awadalla commited on
Commit
b52ee3b
•
1 Parent(s): 07573d1

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": 33.33,
3
- "eval_exact_match": 5.127719962157048,
4
- "eval_f1": 11.952538313785295,
5
  "eval_samples": 10790,
6
- "train_loss": 3.7366351318359374,
7
- "train_runtime": 66.5732,
8
  "train_samples": 64,
9
- "train_samples_per_second": 36.051,
10
- "train_steps_per_second": 3.004
11
  }
 
1
  {
2
+ "epoch": 66.67,
3
+ "eval_exact_match": 25.666982024597917,
4
+ "eval_f1": 39.34881625093024,
5
  "eval_samples": 10790,
6
+ "train_loss": 1.8005227661132812,
7
+ "train_runtime": 133.5338,
8
  "train_samples": 64,
9
+ "train_samples_per_second": 35.946,
10
+ "train_steps_per_second": 2.995
11
  }
eval_nbest_predictions.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e75c0e62c10e9a8c0c799b3edbce90113f425f37cabc73bc4699e4a772bc052
3
- size 51980549
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7f0a87b69f28f4b1fbaaa1ebe22334a2313e4c914bf8f4acd941a7f0a5b1b47
3
+ size 51829522
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": 33.33,
3
- "eval_exact_match": 5.127719962157048,
4
- "eval_f1": 11.952538313785295,
5
  "eval_samples": 10790
6
  }
 
1
  {
2
+ "epoch": 66.67,
3
+ "eval_exact_match": 25.666982024597917,
4
+ "eval_f1": 39.34881625093024,
5
  "eval_samples": 10790
6
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 33.33,
3
- "train_loss": 3.7366351318359374,
4
- "train_runtime": 66.5732,
5
  "train_samples": 64,
6
- "train_samples_per_second": 36.051,
7
- "train_steps_per_second": 3.004
8
  }
 
1
  {
2
+ "epoch": 66.67,
3
+ "train_loss": 1.8005227661132812,
4
+ "train_runtime": 133.5338,
5
  "train_samples": 64,
6
+ "train_samples_per_second": 35.946,
7
+ "train_steps_per_second": 2.995
8
  }
trainer_state.json CHANGED
@@ -1,25 +1,25 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 33.333333333333336,
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": 33.33,
12
- "step": 200,
13
- "total_flos": 1519008032894976.0,
14
- "train_loss": 3.7366351318359374,
15
- "train_runtime": 66.5732,
16
- "train_samples_per_second": 36.051,
17
- "train_steps_per_second": 3.004
18
  }
19
  ],
20
- "max_steps": 200,
21
- "num_train_epochs": 34,
22
- "total_flos": 1519008032894976.0,
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": 1.8005227661132812,
15
+ "train_runtime": 133.5338,
16
+ "train_samples_per_second": 35.946,
17
+ "train_steps_per_second": 2.995
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
  }