Hugging Face's logo

anas-awadalla
/
roberta-large-houlsby-few-shot-k-64-finetuned-squad-seed-0

Generated from Trainer
Model card Files Community
anas-awadalla commited on
Commit
4358b08
•
1 Parent(s): 7b7c973

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 +9 -9
all_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "epoch": 100.0,
3
- "eval_exact_match": 27.653736991485335,
4
- "eval_f1": 42.22693104851322,
5
  "eval_samples": 10790,
6
- "train_loss": 2.3457405090332033,
7
- "train_runtime": 183.1997,
8
  "train_samples": 64,
9
- "train_samples_per_second": 34.935,
10
- "train_steps_per_second": 1.092
11
  }
 
1
  {
2
+ "epoch": 33.33,
3
+ "eval_exact_match": 13.954588457899716,
4
+ "eval_f1": 23.7308073137011,
5
  "eval_samples": 10790,
6
+ "train_loss": 3.4594744873046874,
7
+ "train_runtime": 66.6429,
8
  "train_samples": 64,
9
+ "train_samples_per_second": 36.013,
10
+ "train_steps_per_second": 3.001
11
  }
eval_nbest_predictions.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:384213d47b74f819c90a84feabfdeec8406537195ef5b2828a1708ff221906f6
3
- size 50582382
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf2ca10355fd6fe541d5ce3f46e81ce97bd3141e25290cd7edd255a47b42e59d
3
+ size 50876527
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": 27.653736991485335,
4
- "eval_f1": 42.22693104851322,
5
  "eval_samples": 10790
6
  }
 
1
  {
2
+ "epoch": 33.33,
3
+ "eval_exact_match": 13.954588457899716,
4
+ "eval_f1": 23.7308073137011,
5
  "eval_samples": 10790
6
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 100.0,
3
- "train_loss": 2.3457405090332033,
4
- "train_runtime": 183.1997,
5
  "train_samples": 64,
6
- "train_samples_per_second": 34.935,
7
- "train_steps_per_second": 1.092
8
  }
 
1
  {
2
+ "epoch": 33.33,
3
+ "train_loss": 3.4594744873046874,
4
+ "train_runtime": 66.6429,
5
  "train_samples": 64,
6
+ "train_samples_per_second": 36.013,
7
+ "train_steps_per_second": 3.001
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": 2.3457405090332033,
15
- "train_runtime": 183.1997,
16
- "train_samples_per_second": 34.935,
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": 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": 3.4594744873046874,
15
+ "train_runtime": 66.6429,
16
+ "train_samples_per_second": 36.013,
17
+ "train_steps_per_second": 3.001
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
  }