anas-awadalla commited on
Commit
8aeabc8
1 Parent(s): c8de469

End of training

Browse files
all_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "epoch": 10.0,
3
- "eval_exact_match": 1.173131504257332,
4
- "eval_f1": 8.470945418890972,
5
  "eval_samples": 10784,
6
- "train_loss": 5.0594024658203125,
7
- "train_runtime": 5.4213,
8
  "train_samples": 16,
9
- "train_samples_per_second": 29.513,
10
- "train_steps_per_second": 1.845
11
  }
1
  {
2
+ "epoch": 200.0,
3
+ "eval_exact_match": 2.771996215704825,
4
+ "eval_f1": 7.077765903156844,
5
  "eval_samples": 10784,
6
+ "train_loss": 0.6765974426269531,
7
+ "train_runtime": 73.3274,
8
  "train_samples": 16,
9
+ "train_samples_per_second": 65.46,
10
+ "train_steps_per_second": 2.727
11
  }
eval_nbest_predictions.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c077f323af8ff0f74473ba72d685c1038994512842f5373281c8d2e71df5d5c
3
- size 53190150
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14e3aecd21fc2b7056d00d643ed5b6b95f07c3dedba453557f0baba5c4bcc7a6
3
+ size 48988467
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": 10.0,
3
- "eval_exact_match": 1.173131504257332,
4
- "eval_f1": 8.470945418890972,
5
  "eval_samples": 10784
6
  }
1
  {
2
+ "epoch": 200.0,
3
+ "eval_exact_match": 2.771996215704825,
4
+ "eval_f1": 7.077765903156844,
5
  "eval_samples": 10784
6
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:629f1537265a081ae4d64b8b2a44a36efa07dfdb306db36c1d178d7906d5f779
3
  size 435656113
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7c6c052cdb84591cbd88e1dbe50630cf22f81f02ea05ddd7553425ef69b751b
3
  size 435656113
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 10.0,
3
- "train_loss": 5.0594024658203125,
4
- "train_runtime": 5.4213,
5
  "train_samples": 16,
6
- "train_samples_per_second": 29.513,
7
- "train_steps_per_second": 1.845
8
  }
1
  {
2
+ "epoch": 200.0,
3
+ "train_loss": 0.6765974426269531,
4
+ "train_runtime": 73.3274,
5
  "train_samples": 16,
6
+ "train_samples_per_second": 65.46,
7
+ "train_steps_per_second": 2.727
8
  }
trainer_state.json CHANGED
@@ -1,25 +1,25 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 10.0,
5
- "global_step": 10,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
- "epoch": 10.0,
12
- "step": 10,
13
- "total_flos": 31355610808320.0,
14
- "train_loss": 5.0594024658203125,
15
- "train_runtime": 5.4213,
16
- "train_samples_per_second": 29.513,
17
- "train_steps_per_second": 1.845
18
  }
19
  ],
20
- "max_steps": 10,
21
- "num_train_epochs": 10,
22
- "total_flos": 31355610808320.0,
23
  "trial_name": null,
24
  "trial_params": null
25
  }
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 200.0,
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": 200.0,
12
+ "step": 200,
13
+ "total_flos": 627112216166400.0,
14
+ "train_loss": 0.6765974426269531,
15
+ "train_runtime": 73.3274,
16
+ "train_samples_per_second": 65.46,
17
+ "train_steps_per_second": 2.727
18
  }
19
  ],
20
+ "max_steps": 200,
21
+ "num_train_epochs": 200,
22
+ "total_flos": 627112216166400.0,
23
  "trial_name": null,
24
  "trial_params": null
25
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b286e97491099237c4d8ede807e270ced3d76fee84c8e2ccbe7ec5da77b7728d
3
  size 3055
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c12edae5245542ec0c0b9674833fed018c5c57325aa7a4df3a0aef5e60e6a2b
3
  size 3055