mariolinml commited on
Commit
1987d9a
1 Parent(s): 1a5d222

Model save

Browse files
Files changed (3) hide show
  1. all_results.json +8 -0
  2. train_results.json +8 -0
  3. trainer_state.json +73 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 4253792717481984.0,
4
+ "train_loss": 0.2017434086910514,
5
+ "train_runtime": 2127.2243,
6
+ "train_samples_per_second": 30.4,
7
+ "train_steps_per_second": 1.9
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 4253792717481984.0,
4
+ "train_loss": 0.2017434086910514,
5
+ "train_runtime": 2127.2243,
6
+ "train_samples_per_second": 30.4,
7
+ "train_steps_per_second": 1.9
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 4042,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.25,
12
+ "learning_rate": 2e-05,
13
+ "loss": 0.4813,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.49,
18
+ "learning_rate": 1.717673630717109e-05,
19
+ "loss": 0.2314,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.74,
24
+ "learning_rate": 1.435347261434218e-05,
25
+ "loss": 0.2052,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.99,
30
+ "learning_rate": 1.1530208921513271e-05,
31
+ "loss": 0.1919,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.24,
36
+ "learning_rate": 8.70694522868436e-06,
37
+ "loss": 0.1372,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.48,
42
+ "learning_rate": 5.883681535855449e-06,
43
+ "loss": 0.126,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.73,
48
+ "learning_rate": 3.0604178430265392e-06,
49
+ "loss": 0.1267,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.98,
54
+ "learning_rate": 2.3715415019762845e-07,
55
+ "loss": 0.1206,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 2.0,
60
+ "step": 4042,
61
+ "total_flos": 4253792717481984.0,
62
+ "train_loss": 0.2017434086910514,
63
+ "train_runtime": 2127.2243,
64
+ "train_samples_per_second": 30.4,
65
+ "train_steps_per_second": 1.9
66
+ }
67
+ ],
68
+ "max_steps": 4042,
69
+ "num_train_epochs": 2,
70
+ "total_flos": 4253792717481984.0,
71
+ "trial_name": null,
72
+ "trial_params": null
73
+ }