All Dunn!!!
Browse files
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 5930277461969802.0,
|
4 |
+
"train_loss": 0.18313796083265071,
|
5 |
+
"train_runtime": 2584.8342,
|
6 |
+
"train_samples_per_second": 19.469,
|
7 |
+
"train_steps_per_second": 2.434
|
8 |
+
}
|
runs/Aug10_18-43-29_b6821e1c31c4/events.out.tfevents.1691695729.b6821e1c31c4.294.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3eaec998dc69c668ca5fcdac33b8ac51968d817bbb2cbcfbc6c408f0fb8b4ee
|
3 |
+
size 508
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 5930277461969802.0,
|
4 |
+
"train_loss": 0.18313796083265071,
|
5 |
+
"train_runtime": 2584.8342,
|
6 |
+
"train_samples_per_second": 19.469,
|
7 |
+
"train_steps_per_second": 2.434
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8404789494013132,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-Research_Articles_Multilabel/checkpoint-6291",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 6291,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 1.9996820855189955e-05,
|
13 |
+
"loss": 0.6859,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"learning_rate": 1.3333333333333333e-05,
|
19 |
+
"loss": 0.2425,
|
20 |
+
"step": 2097
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.0,
|
24 |
+
"eval_accuracy": 0.7067238912732475,
|
25 |
+
"eval_f1": 0.8347927612375948,
|
26 |
+
"eval_loss": 0.19481222331523895,
|
27 |
+
"eval_roc_auc": 0.8920854689886804,
|
28 |
+
"eval_runtime": 51.1647,
|
29 |
+
"eval_samples_per_second": 40.985,
|
30 |
+
"eval_steps_per_second": 5.14,
|
31 |
+
"step": 2097
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 2.0,
|
35 |
+
"learning_rate": 6.666666666666667e-06,
|
36 |
+
"loss": 0.1739,
|
37 |
+
"step": 4194
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 2.0,
|
41 |
+
"eval_accuracy": 0.7072007629947544,
|
42 |
+
"eval_f1": 0.83478936128907,
|
43 |
+
"eval_loss": 0.1986200213432312,
|
44 |
+
"eval_roc_auc": 0.8926225806531218,
|
45 |
+
"eval_runtime": 51.1631,
|
46 |
+
"eval_samples_per_second": 40.987,
|
47 |
+
"eval_steps_per_second": 5.14,
|
48 |
+
"step": 4194
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"learning_rate": 0.0,
|
53 |
+
"loss": 0.1328,
|
54 |
+
"step": 6291
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 3.0,
|
58 |
+
"eval_accuracy": 0.7081545064377682,
|
59 |
+
"eval_f1": 0.8404789494013132,
|
60 |
+
"eval_loss": 0.20385245978832245,
|
61 |
+
"eval_roc_auc": 0.897647591573035,
|
62 |
+
"eval_runtime": 51.1537,
|
63 |
+
"eval_samples_per_second": 40.994,
|
64 |
+
"eval_steps_per_second": 5.141,
|
65 |
+
"step": 6291
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 3.0,
|
69 |
+
"step": 6291,
|
70 |
+
"total_flos": 5930277461969802.0,
|
71 |
+
"train_loss": 0.18313796083265071,
|
72 |
+
"train_runtime": 2584.8342,
|
73 |
+
"train_samples_per_second": 19.469,
|
74 |
+
"train_steps_per_second": 2.434
|
75 |
+
}
|
76 |
+
],
|
77 |
+
"max_steps": 6291,
|
78 |
+
"num_train_epochs": 3,
|
79 |
+
"total_flos": 5930277461969802.0,
|
80 |
+
"trial_name": null,
|
81 |
+
"trial_params": null
|
82 |
+
}
|