End of training
Browse files
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.9,
|
3 |
+
"eval_accuracy": 0.6298701298701299,
|
4 |
+
"eval_loss": 1.020005226135254,
|
5 |
+
"eval_runtime": 214.1957,
|
6 |
+
"eval_samples_per_second": 0.719,
|
7 |
+
"eval_steps_per_second": 0.047,
|
8 |
+
"total_flos": 7.096469891763732e+17,
|
9 |
+
"train_loss": 1.1854457893068828,
|
10 |
+
"train_runtime": 20863.7263,
|
11 |
+
"train_samples_per_second": 0.198,
|
12 |
+
"train_steps_per_second": 0.003
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.9,
|
3 |
+
"eval_accuracy": 0.6298701298701299,
|
4 |
+
"eval_loss": 1.020005226135254,
|
5 |
+
"eval_runtime": 214.1957,
|
6 |
+
"eval_samples_per_second": 0.719,
|
7 |
+
"eval_steps_per_second": 0.047
|
8 |
+
}
|
runs/Jun09_09-10-44_453c17f9ab55/events.out.tfevents.1686323047.453c17f9ab55.2054.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:562c7d854ea877c5232cc28ecc9e3c68d4d3f9cfd19801bbc553f7379b8f340e
|
3 |
+
size 405
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.9,
|
3 |
+
"total_flos": 7.096469891763732e+17,
|
4 |
+
"train_loss": 1.1854457893068828,
|
5 |
+
"train_runtime": 20863.7263,
|
6 |
+
"train_samples_per_second": 0.198,
|
7 |
+
"train_steps_per_second": 0.003
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6298701298701299,
|
3 |
+
"best_model_checkpoint": "convnext-large-224-finetuned-drugsclass-conv/checkpoint-63",
|
4 |
+
"epoch": 2.896551724137931,
|
5 |
+
"global_step": 63,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.46,
|
12 |
+
"learning_rate": 4.732142857142857e-05,
|
13 |
+
"loss": 1.367,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.92,
|
18 |
+
"learning_rate": 3.839285714285715e-05,
|
19 |
+
"loss": 1.2917,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.97,
|
24 |
+
"eval_accuracy": 0.551948051948052,
|
25 |
+
"eval_loss": 1.20426607131958,
|
26 |
+
"eval_runtime": 211.0899,
|
27 |
+
"eval_samples_per_second": 0.73,
|
28 |
+
"eval_steps_per_second": 0.047,
|
29 |
+
"step": 21
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 1.38,
|
33 |
+
"learning_rate": 2.9464285714285718e-05,
|
34 |
+
"loss": 1.1821,
|
35 |
+
"step": 30
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 1.84,
|
39 |
+
"learning_rate": 2.0535714285714285e-05,
|
40 |
+
"loss": 1.1389,
|
41 |
+
"step": 40
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 1.98,
|
45 |
+
"eval_accuracy": 0.5844155844155844,
|
46 |
+
"eval_loss": 1.0590707063674927,
|
47 |
+
"eval_runtime": 216.0679,
|
48 |
+
"eval_samples_per_second": 0.713,
|
49 |
+
"eval_steps_per_second": 0.046,
|
50 |
+
"step": 43
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 2.3,
|
54 |
+
"learning_rate": 1.1607142857142857e-05,
|
55 |
+
"loss": 1.1035,
|
56 |
+
"step": 50
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 2.76,
|
60 |
+
"learning_rate": 2.6785714285714285e-06,
|
61 |
+
"loss": 1.0622,
|
62 |
+
"step": 60
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 2.9,
|
66 |
+
"eval_accuracy": 0.6298701298701299,
|
67 |
+
"eval_loss": 1.020005226135254,
|
68 |
+
"eval_runtime": 213.721,
|
69 |
+
"eval_samples_per_second": 0.721,
|
70 |
+
"eval_steps_per_second": 0.047,
|
71 |
+
"step": 63
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 2.9,
|
75 |
+
"step": 63,
|
76 |
+
"total_flos": 7.096469891763732e+17,
|
77 |
+
"train_loss": 1.1854457893068828,
|
78 |
+
"train_runtime": 20863.7263,
|
79 |
+
"train_samples_per_second": 0.198,
|
80 |
+
"train_steps_per_second": 0.003
|
81 |
+
}
|
82 |
+
],
|
83 |
+
"max_steps": 63,
|
84 |
+
"num_train_epochs": 3,
|
85 |
+
"total_flos": 7.096469891763732e+17,
|
86 |
+
"trial_name": null,
|
87 |
+
"trial_params": null
|
88 |
+
}
|