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
c4fbc54
•
1 Parent(s): 26514a7

End of training

Browse files
Files changed (6) hide show
  1. all_results.json +6 -6
  2. eval_nbest_predictions.json +2 -2
  3. eval_predictions.json +0 -0
  4. eval_results.json +3 -3
  5. train_results.json +4 -4
  6. trainer_state.json +11 -11
all_results.json CHANGED
@@ -1,11 +1,11 @@
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
  }
 
1
  {
2
+ "epoch": 66.67,
3
+ "eval_exact_match": 36.12109744560075,
4
+ "eval_f1": 51.13526102544237,
5
  "eval_samples": 10790,
6
+ "train_loss": 1.6081089782714844,
7
+ "train_runtime": 133.2875,
8
  "train_samples": 64,
9
+ "train_samples_per_second": 36.012,
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:cf2ca10355fd6fe541d5ce3f46e81ce97bd3141e25290cd7edd255a47b42e59d
3
- size 50876527
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:299b5507422796cf18aafc3a70ba59a59ce665b119be29ba523699f65521fecf
3
+ size 51349704
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": 13.954588457899716,
4
- "eval_f1": 23.7308073137011,
5
  "eval_samples": 10790
6
  }
 
1
  {
2
+ "epoch": 66.67,
3
+ "eval_exact_match": 36.12109744560075,
4
+ "eval_f1": 51.13526102544237,
5
  "eval_samples": 10790
6
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
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
  }
 
1
  {
2
+ "epoch": 66.67,
3
+ "train_loss": 1.6081089782714844,
4
+ "train_runtime": 133.2875,
5
  "train_samples": 64,
6
+ "train_samples_per_second": 36.012,
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": 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
  }
 
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": 1.6081089782714844,
15
+ "train_runtime": 133.2875,
16
+ "train_samples_per_second": 36.012,
17
  "train_steps_per_second": 3.001
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
  }