gchhablani commited on
Commit
bccfadc
1 Parent(s): 8b5b5f7

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.628158844765343,
4
+ "eval_loss": 0.6978281736373901,
5
+ "eval_runtime": 2.0316,
6
+ "eval_samples": 277,
7
+ "eval_samples_per_second": 136.343,
8
+ "eval_steps_per_second": 17.227,
9
+ "train_loss": 0.6048059545011601,
10
+ "train_runtime": 204.1282,
11
+ "train_samples": 2490,
12
+ "train_samples_per_second": 36.595,
13
+ "train_steps_per_second": 2.293
14
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.628158844765343,
4
+ "eval_loss": 0.6978281736373901,
5
+ "eval_runtime": 2.0316,
6
+ "eval_samples": 277,
7
+ "eval_samples_per_second": 136.343,
8
+ "eval_steps_per_second": 17.227
9
+ }
runs/Sep19_05-47-04_patrick-general-gpu/events.out.tfevents.1632030438.patrick-general-gpu.457696.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9bc8feff1907d548c781d25e898b20690750cf8c160312ef8e882aed9cd34ea
3
- size 4620
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66fd48181f47ba3e3df941be66f828d001c166cc61d83aa6ce978621e5485dbc
3
+ size 4974
runs/Sep19_05-47-04_patrick-general-gpu/events.out.tfevents.1632030648.patrick-general-gpu.457696.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:360af4fb7ccc83ba2252fe607fca84a300f7d8ba99ebc87e44568560bc39160c
3
+ size 363
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.6048059545011601,
4
+ "train_runtime": 204.1282,
5
+ "train_samples": 2490,
6
+ "train_samples_per_second": 36.595,
7
+ "train_steps_per_second": 2.293
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 468,
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
+ "learning_rate": 1.3333333333333333e-05,
13
+ "loss": 0.6829,
14
+ "step": 156
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.5703971119133574,
19
+ "eval_loss": 0.6657100915908813,
20
+ "eval_runtime": 2.0131,
21
+ "eval_samples_per_second": 137.6,
22
+ "eval_steps_per_second": 17.386,
23
+ "step": 156
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 6.666666666666667e-06,
28
+ "loss": 0.6174,
29
+ "step": 312
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.6101083032490975,
34
+ "eval_loss": 0.6784032583236694,
35
+ "eval_runtime": 2.013,
36
+ "eval_samples_per_second": 137.609,
37
+ "eval_steps_per_second": 17.387,
38
+ "step": 312
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 0.0,
43
+ "loss": 0.5141,
44
+ "step": 468
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.628158844765343,
49
+ "eval_loss": 0.6978281736373901,
50
+ "eval_runtime": 2.0128,
51
+ "eval_samples_per_second": 137.616,
52
+ "eval_steps_per_second": 17.388,
53
+ "step": 468
54
+ },
55
+ {
56
+ "epoch": 3.0,
57
+ "step": 468,
58
+ "total_flos": 1328457479639040.0,
59
+ "train_loss": 0.6048059545011601,
60
+ "train_runtime": 204.1282,
61
+ "train_samples_per_second": 36.595,
62
+ "train_steps_per_second": 2.293
63
+ }
64
+ ],
65
+ "max_steps": 468,
66
+ "num_train_epochs": 3,
67
+ "total_flos": 1328457479639040.0,
68
+ "trial_name": null,
69
+ "trial_params": null
70
+ }