Edison commited on
Commit
d62fe27
·
1 Parent(s): 90a84c1

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +13 -13
  2. eval_results.json +9 -9
  3. train_results.json +4 -4
  4. trainer_state.json +22 -22
all_results.json CHANGED
@@ -1,18 +1,18 @@
1
  {
2
  "epoch": 3.0,
3
- "eval_accuracy": 0.9273952095808383,
4
- "eval_f1": 0.9438332368268674,
5
- "eval_loss": 0.23274052143096924,
6
- "eval_precision": 0.9690844233055886,
7
- "eval_recall": 0.9198645598194131,
8
- "eval_roc_auc": 0.9310433910208176,
9
- "eval_runtime": 1.9896,
10
  "eval_samples": 1336,
11
- "eval_samples_per_second": 671.502,
12
- "eval_steps_per_second": 5.529,
13
- "train_loss": 0.19368775685628256,
14
- "train_runtime": 134.498,
15
  "train_samples": 5342,
16
- "train_samples_per_second": 119.154,
17
- "train_steps_per_second": 0.937
18
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "eval_accuracy": 0.9086826347305389,
4
+ "eval_f1": 0.9304446978335233,
5
+ "eval_loss": 0.22467140853405,
6
+ "eval_precision": 0.9400921658986175,
7
+ "eval_recall": 0.9209932279909706,
8
+ "eval_roc_auc": 0.9027188362177077,
9
+ "eval_runtime": 1.0843,
10
  "eval_samples": 1336,
11
+ "eval_samples_per_second": 1232.185,
12
+ "eval_steps_per_second": 5.534,
13
+ "train_loss": 0.2692271187191918,
14
+ "train_runtime": 63.0344,
15
  "train_samples": 5342,
16
+ "train_samples_per_second": 254.242,
17
+ "train_steps_per_second": 0.999
18
  }
eval_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 3.0,
3
- "eval_accuracy": 0.9273952095808383,
4
- "eval_f1": 0.9438332368268674,
5
- "eval_loss": 0.23274052143096924,
6
- "eval_precision": 0.9690844233055886,
7
- "eval_recall": 0.9198645598194131,
8
- "eval_roc_auc": 0.9310433910208176,
9
- "eval_runtime": 1.9896,
10
  "eval_samples": 1336,
11
- "eval_samples_per_second": 671.502,
12
- "eval_steps_per_second": 5.529
13
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "eval_accuracy": 0.9086826347305389,
4
+ "eval_f1": 0.9304446978335233,
5
+ "eval_loss": 0.22467140853405,
6
+ "eval_precision": 0.9400921658986175,
7
+ "eval_recall": 0.9209932279909706,
8
+ "eval_roc_auc": 0.9027188362177077,
9
+ "eval_runtime": 1.0843,
10
  "eval_samples": 1336,
11
+ "eval_samples_per_second": 1232.185,
12
+ "eval_steps_per_second": 5.534
13
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
- "train_loss": 0.19368775685628256,
4
- "train_runtime": 134.498,
5
  "train_samples": 5342,
6
- "train_samples_per_second": 119.154,
7
- "train_steps_per_second": 0.937
8
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "train_loss": 0.2692271187191918,
4
+ "train_runtime": 63.0344,
5
  "train_samples": 5342,
6
+ "train_samples_per_second": 254.242,
7
+ "train_steps_per_second": 0.999
8
  }
trainer_state.json CHANGED
@@ -2,43 +2,43 @@
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
  "epoch": 3.0,
5
- "global_step": 126,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 1.57,
12
- "learning_rate": 4.9206349206349204e-05,
13
- "loss": 0.2872,
14
- "step": 66
15
  },
16
  {
17
  "epoch": 1.57,
18
- "eval_accuracy": 0.9176646706586826,
19
- "eval_f1": 0.9374999999999999,
20
- "eval_loss": 0.20166487991809845,
21
- "eval_precision": 0.9439359267734554,
22
- "eval_recall": 0.9311512415349887,
23
- "eval_roc_auc": 0.9111311763230499,
24
- "eval_runtime": 1.9771,
25
- "eval_samples_per_second": 675.722,
26
- "eval_steps_per_second": 5.564,
27
- "step": 66
28
  },
29
  {
30
  "epoch": 3.0,
31
- "step": 126,
32
- "total_flos": 2108308886599680.0,
33
- "train_loss": 0.19368775685628256,
34
- "train_runtime": 134.498,
35
- "train_samples_per_second": 119.154,
36
- "train_steps_per_second": 0.937
37
  }
38
  ],
39
- "max_steps": 126,
40
  "num_train_epochs": 3,
41
- "total_flos": 2108308886599680.0,
42
  "trial_name": null,
43
  "trial_params": null
44
  }
 
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
  "epoch": 3.0,
5
+ "global_step": 63,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 1.57,
12
+ "learning_rate": 4.761904761904762e-05,
13
+ "loss": 0.36,
14
+ "step": 33
15
  },
16
  {
17
  "epoch": 1.57,
18
+ "eval_accuracy": 0.9124251497005988,
19
+ "eval_f1": 0.9341586944288126,
20
+ "eval_loss": 0.22648876905441284,
21
+ "eval_precision": 0.9315375982042648,
22
+ "eval_recall": 0.9367945823927766,
23
+ "eval_roc_auc": 0.9006195134186106,
24
+ "eval_runtime": 1.0671,
25
+ "eval_samples_per_second": 1252.042,
26
+ "eval_steps_per_second": 5.623,
27
+ "step": 33
28
  },
29
  {
30
  "epoch": 3.0,
31
+ "step": 63,
32
+ "total_flos": 1061461265430528.0,
33
+ "train_loss": 0.2692271187191918,
34
+ "train_runtime": 63.0344,
35
+ "train_samples_per_second": 254.242,
36
+ "train_steps_per_second": 0.999
37
  }
38
  ],
39
+ "max_steps": 63,
40
  "num_train_epochs": 3,
41
+ "total_flos": 1061461265430528.0,
42
  "trial_name": null,
43
  "trial_params": null
44
  }