Ahmed9275 commited on
Commit
b760e8b
1 Parent(s): 8991268

🍻 cheers

Browse files
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.8985,
4
+ "eval_loss": 0.4420098662376404,
5
+ "eval_runtime": 101.557,
6
+ "eval_samples_per_second": 98.467,
7
+ "eval_steps_per_second": 12.308,
8
+ "total_flos": 1.55120108322816e+19,
9
+ "train_loss": 0.41695240966796876,
10
+ "train_runtime": 5380.0705,
11
+ "train_samples_per_second": 37.174,
12
+ "train_steps_per_second": 2.323
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.8985,
4
+ "eval_loss": 0.4420098662376404,
5
+ "eval_runtime": 101.557,
6
+ "eval_samples_per_second": 98.467,
7
+ "eval_steps_per_second": 12.308
8
+ }
runs/May18_23-36-34_12b95d1959eb/events.out.tfevents.1652922962.12b95d1959eb.80.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:044cf088baf5800f91124434264f543418e3c43ab118ea10cfe370fa6ec4ddee
3
+ size 363
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "total_flos": 1.55120108322816e+19,
4
+ "train_loss": 0.41695240966796876,
5
+ "train_runtime": 5380.0705,
6
+ "train_samples_per_second": 37.174,
7
+ "train_steps_per_second": 2.323
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "global_step": 12500,
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": 0.000150048,
13
+ "loss": 1.08,
14
+ "step": 3125
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.8262,
19
+ "eval_loss": 0.6196413040161133,
20
+ "eval_runtime": 100.3985,
21
+ "eval_samples_per_second": 99.603,
22
+ "eval_steps_per_second": 12.45,
23
+ "step": 3125
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 0.000100048,
28
+ "loss": 0.3816,
29
+ "step": 6250
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.8555,
34
+ "eval_loss": 0.5322445034980774,
35
+ "eval_runtime": 99.8169,
36
+ "eval_samples_per_second": 100.183,
37
+ "eval_steps_per_second": 12.523,
38
+ "step": 6250
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 5.0064e-05,
43
+ "loss": 0.1619,
44
+ "step": 9375
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.8765,
49
+ "eval_loss": 0.4817411005496979,
50
+ "eval_runtime": 100.5682,
51
+ "eval_samples_per_second": 99.435,
52
+ "eval_steps_per_second": 12.429,
53
+ "step": 9375
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "learning_rate": 9.600000000000001e-08,
58
+ "loss": 0.0443,
59
+ "step": 12500
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_accuracy": 0.8985,
64
+ "eval_loss": 0.4420098662376404,
65
+ "eval_runtime": 101.737,
66
+ "eval_samples_per_second": 98.293,
67
+ "eval_steps_per_second": 12.287,
68
+ "step": 12500
69
+ },
70
+ {
71
+ "epoch": 4.0,
72
+ "step": 12500,
73
+ "total_flos": 1.55120108322816e+19,
74
+ "train_loss": 0.41695240966796876,
75
+ "train_runtime": 5380.0705,
76
+ "train_samples_per_second": 37.174,
77
+ "train_steps_per_second": 2.323
78
+ }
79
+ ],
80
+ "max_steps": 12500,
81
+ "num_train_epochs": 4,
82
+ "total_flos": 1.55120108322816e+19,
83
+ "trial_name": null,
84
+ "trial_params": null
85
+ }