spoiled commited on
Commit
cc0d517
1 Parent(s): f83f700

End of training

Browse files
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
- "epoch": 1.0,
3
- "eval_loss": 4.919972896575928,
4
- "eval_runtime": 0.7846,
5
  "eval_samples": 50,
6
- "eval_samples_per_second": 63.724,
7
- "eval_steps_per_second": 1.274,
8
- "train_loss": 5.883035182952881,
9
- "train_runtime": 70.8565,
10
  "train_samples": 150,
11
- "train_samples_per_second": 2.117,
12
- "train_steps_per_second": 0.056
13
  }
 
1
  {
2
+ "epoch": 2.0,
3
+ "eval_loss": 3.560474157333374,
4
+ "eval_runtime": 0.7801,
5
  "eval_samples": 50,
6
+ "eval_samples_per_second": 64.095,
7
+ "eval_steps_per_second": 1.282,
8
+ "train_loss": 5.096200942993164,
9
+ "train_runtime": 318.685,
10
  "train_samples": 150,
11
+ "train_samples_per_second": 0.941,
12
+ "train_steps_per_second": 0.025
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.0,
3
- "eval_loss": 4.919972896575928,
4
- "eval_runtime": 0.7846,
5
  "eval_samples": 50,
6
- "eval_samples_per_second": 63.724,
7
- "eval_steps_per_second": 1.274
8
  }
 
1
  {
2
+ "epoch": 2.0,
3
+ "eval_loss": 3.560474157333374,
4
+ "eval_runtime": 0.7801,
5
  "eval_samples": 50,
6
+ "eval_samples_per_second": 64.095,
7
+ "eval_steps_per_second": 1.282
8
  }
runs/Nov13_14-18-47_dell-NF5468M6/events.out.tfevents.1668321241.dell-NF5468M6.6637.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcec4812307c433de971a8d91307cc0346d34b6e428282cc9f87e7fb05a9f864
3
+ size 306
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.0,
3
- "train_loss": 5.883035182952881,
4
- "train_runtime": 70.8565,
5
  "train_samples": 150,
6
- "train_samples_per_second": 2.117,
7
- "train_steps_per_second": 0.056
8
  }
 
1
  {
2
+ "epoch": 2.0,
3
+ "train_loss": 5.096200942993164,
4
+ "train_runtime": 318.685,
5
  "train_samples": 150,
6
+ "train_samples_per_second": 0.941,
7
+ "train_steps_per_second": 0.025
8
  }
trainer_state.json CHANGED
@@ -1,33 +1,41 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.0,
5
- "global_step": 4,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 1.0,
12
- "eval_loss": 4.919972896575928,
13
- "eval_runtime": 0.8786,
14
- "eval_samples_per_second": 56.911,
15
- "eval_steps_per_second": 1.138,
16
  "step": 4
17
  },
18
  {
19
- "epoch": 1.0,
20
- "step": 4,
21
- "total_flos": 8347272192000.0,
22
- "train_loss": 5.883035182952881,
23
- "train_runtime": 70.8565,
24
- "train_samples_per_second": 2.117,
25
- "train_steps_per_second": 0.056
 
 
 
 
 
 
 
 
26
  }
27
  ],
28
- "max_steps": 4,
29
- "num_train_epochs": 1,
30
- "total_flos": 8347272192000.0,
31
  "trial_name": null,
32
  "trial_params": null
33
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 8,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 1.0,
12
+ "eval_loss": 4.192291259765625,
13
+ "eval_runtime": 0.896,
14
+ "eval_samples_per_second": 55.802,
15
+ "eval_steps_per_second": 1.116,
16
  "step": 4
17
  },
18
  {
19
+ "epoch": 2.0,
20
+ "eval_loss": 3.560474157333374,
21
+ "eval_runtime": 0.8672,
22
+ "eval_samples_per_second": 57.66,
23
+ "eval_steps_per_second": 1.153,
24
+ "step": 8
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "step": 8,
29
+ "total_flos": 16719916032000.0,
30
+ "train_loss": 5.096200942993164,
31
+ "train_runtime": 318.685,
32
+ "train_samples_per_second": 0.941,
33
+ "train_steps_per_second": 0.025
34
  }
35
  ],
36
+ "max_steps": 8,
37
+ "num_train_epochs": 2,
38
+ "total_flos": 16719916032000.0,
39
  "trial_name": null,
40
  "trial_params": null
41
  }