JoseVilla commited on
Commit
721bd2b
1 Parent(s): 2e533f4

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.82,
3
+ "eval_accuracy": 0.9583333333333334,
4
+ "eval_loss": 0.20470969378948212,
5
+ "eval_runtime": 6.386,
6
+ "eval_samples_per_second": 18.791,
7
+ "eval_steps_per_second": 0.626,
8
+ "total_flos": 7.58128847422464e+16,
9
+ "train_loss": 0.3779665194451809,
10
+ "train_runtime": 203.0983,
11
+ "train_samples_per_second": 15.909,
12
+ "train_steps_per_second": 0.118
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.82,
3
+ "eval_accuracy": 0.9583333333333334,
4
+ "eval_loss": 0.20470969378948212,
5
+ "eval_runtime": 6.386,
6
+ "eval_samples_per_second": 18.791,
7
+ "eval_steps_per_second": 0.626
8
+ }
runs/Jul25_18-25-22_66f5801cc96a/events.out.tfevents.1690309763.66f5801cc96a.11845.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93977846dd2c0061342a0ff2cae03de77b8f60e4d488324be40f1c107e55c8c4
3
+ size 405
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.82,
3
+ "total_flos": 7.58128847422464e+16,
4
+ "train_loss": 0.3779665194451809,
5
+ "train_runtime": 203.0983,
6
+ "train_samples_per_second": 15.909,
7
+ "train_steps_per_second": 0.118
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9583333333333334,
3
+ "best_model_checkpoint": "JoseVilla/cfe-telmex-classification-finetuned-v3/checkpoint-17",
4
+ "epoch": 2.8235294117647056,
5
+ "global_step": 24,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.94,
12
+ "eval_accuracy": 0.8166666666666667,
13
+ "eval_loss": 0.4386190176010132,
14
+ "eval_runtime": 6.5765,
15
+ "eval_samples_per_second": 18.247,
16
+ "eval_steps_per_second": 0.608,
17
+ "step": 8
18
+ },
19
+ {
20
+ "epoch": 1.18,
21
+ "learning_rate": 3.3333333333333335e-05,
22
+ "loss": 0.6716,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "eval_accuracy": 0.9583333333333334,
28
+ "eval_loss": 0.20470969378948212,
29
+ "eval_runtime": 6.5683,
30
+ "eval_samples_per_second": 18.27,
31
+ "eval_steps_per_second": 0.609,
32
+ "step": 17
33
+ },
34
+ {
35
+ "epoch": 2.35,
36
+ "learning_rate": 9.523809523809523e-06,
37
+ "loss": 0.1864,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 2.82,
42
+ "eval_accuracy": 0.9583333333333334,
43
+ "eval_loss": 0.1664045751094818,
44
+ "eval_runtime": 5.3954,
45
+ "eval_samples_per_second": 22.241,
46
+ "eval_steps_per_second": 0.741,
47
+ "step": 24
48
+ },
49
+ {
50
+ "epoch": 2.82,
51
+ "step": 24,
52
+ "total_flos": 7.58128847422464e+16,
53
+ "train_loss": 0.3779665194451809,
54
+ "train_runtime": 203.0983,
55
+ "train_samples_per_second": 15.909,
56
+ "train_steps_per_second": 0.118
57
+ }
58
+ ],
59
+ "max_steps": 24,
60
+ "num_train_epochs": 3,
61
+ "total_flos": 7.58128847422464e+16,
62
+ "trial_name": null,
63
+ "trial_params": null
64
+ }