davidmezzetti commited on
Commit
4e9bed9
1 Parent(s): 0c1cc58

Update model

Browse files
Files changed (3) hide show
  1. pytorch_model.bin +1 -1
  2. trainer_state.json +21 -15
  3. training_args.bin +1 -1
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa425935c7018018ef1120dd8f73ab99eacc91ff5b8d0943beb213c4d69f1e9a
3
  size 242070267
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87b79b24d553e756dab9a8f94eef80974841a04f06f9fa5655cdf270676cd982
3
  size 242070267
trainer_state.json CHANGED
@@ -2,36 +2,42 @@
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
  "epoch": 5.0,
5
- "global_step": 1440,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
- "epoch": 1.74,
12
- "learning_rate": 3.263888888888889e-05,
13
- "loss": 0.8294,
14
  "step": 500
15
  },
16
  {
17
- "epoch": 3.47,
18
- "learning_rate": 1.527777777777778e-05,
19
- "loss": 0.0362,
20
  "step": 1000
21
  },
 
 
 
 
 
 
22
  {
23
  "epoch": 5.0,
24
- "step": 1440,
25
- "total_flos": 38943546015744.0,
26
- "train_loss": 0.3061259587605794,
27
- "train_runtime": 100.4467,
28
- "train_samples_per_second": 57.244,
29
- "train_steps_per_second": 14.336
30
  }
31
  ],
32
- "max_steps": 1440,
33
  "num_train_epochs": 5,
34
- "total_flos": 38943546015744.0,
35
  "trial_name": null,
36
  "trial_params": null
37
  }
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
  "epoch": 5.0,
5
+ "global_step": 1565,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
+ "epoch": 1.6,
12
+ "learning_rate": 3.402555910543131e-05,
13
+ "loss": 0.8327,
14
  "step": 500
15
  },
16
  {
17
+ "epoch": 3.19,
18
+ "learning_rate": 1.805111821086262e-05,
19
+ "loss": 0.0413,
20
  "step": 1000
21
  },
22
+ {
23
+ "epoch": 4.79,
24
+ "learning_rate": 2.0766773162939296e-06,
25
+ "loss": 0.0192,
26
+ "step": 1500
27
+ },
28
  {
29
  "epoch": 5.0,
30
+ "step": 1565,
31
+ "total_flos": 42196507361280.0,
32
+ "train_loss": 0.2860380729547324,
33
+ "train_runtime": 110.266,
34
+ "train_samples_per_second": 56.681,
35
+ "train_steps_per_second": 14.193
36
  }
37
  ],
38
+ "max_steps": 1565,
39
  "num_train_epochs": 5,
40
+ "total_flos": 42196507361280.0,
41
  "trial_name": null,
42
  "trial_params": null
43
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:898304cdeaa3627998b119e592b940bc31f4be6f0eddfe43583a3093a471bb09
3
  size 2991
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4a90ffcb914c1405c51f533a1e48594cb9a0b5676ef8ad519c8c88396934fc6
3
  size 2991