Training in progress, epoch 1, checkpoint
Browse files- checkpoint-56/config.json +1 -1
- checkpoint-56/model.safetensors +1 -1
- checkpoint-56/optimizer.pt +1 -1
- checkpoint-56/rng_state.pth +1 -1
- checkpoint-56/scheduler.pt +1 -1
- checkpoint-56/trainer_state.json +53 -44
- checkpoint-56/training_args.bin +1 -1
checkpoint-56/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.1,
|
4 |
"apply_spec_augment": false,
|
5 |
"architectures": [
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "arshsin/distilhubert-finetuned-gtzan",
|
3 |
"activation_dropout": 0.1,
|
4 |
"apply_spec_augment": false,
|
5 |
"architectures": [
|
checkpoint-56/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 94771728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd1b842eac14f882f0845e06fa92fabb046e1eeb806e542205a6cc56313e26db
|
3 |
size 94771728
|
checkpoint-56/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 189575930
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:413edb1c807262ce125f49a6659f79a3b35a9f6fb2b4e3819a201d6a68904a98
|
3 |
size 189575930
|
checkpoint-56/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ec53eaa68c4c55193fc6d3f84ff83ddf726625d2b43eae85fb551c775a1de57
|
3 |
size 14244
|
checkpoint-56/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85b8f0c1d2ac8d82fdab4d399b07207b3f536098dd46f5762c5f40d75530538b
|
3 |
size 1064
|
checkpoint-56/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-56",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 56,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,86 +9,95 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"learning_rate":
|
14 |
-
"loss":
|
15 |
"step": 5
|
16 |
},
|
17 |
{
|
18 |
-
"epoch": 0.
|
19 |
-
"learning_rate":
|
20 |
-
"loss":
|
21 |
"step": 10
|
22 |
},
|
23 |
{
|
24 |
-
"epoch": 0.
|
25 |
-
"learning_rate":
|
26 |
-
"loss":
|
27 |
"step": 15
|
28 |
},
|
29 |
{
|
30 |
-
"epoch": 0.
|
31 |
-
"learning_rate":
|
32 |
-
"loss":
|
33 |
"step": 20
|
34 |
},
|
35 |
{
|
36 |
-
"epoch": 0.
|
37 |
-
"learning_rate":
|
38 |
-
"loss":
|
39 |
"step": 25
|
40 |
},
|
41 |
{
|
42 |
-
"epoch": 0.
|
43 |
-
"
|
44 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
"step": 30
|
46 |
},
|
47 |
{
|
48 |
-
"epoch":
|
49 |
-
"learning_rate":
|
50 |
-
"loss":
|
51 |
"step": 35
|
52 |
},
|
53 |
{
|
54 |
-
"epoch":
|
55 |
-
"learning_rate":
|
56 |
-
"loss":
|
57 |
"step": 40
|
58 |
},
|
59 |
{
|
60 |
-
"epoch":
|
61 |
-
"learning_rate":
|
62 |
-
"loss":
|
63 |
"step": 45
|
64 |
},
|
65 |
{
|
66 |
-
"epoch":
|
67 |
-
"learning_rate":
|
68 |
-
"loss":
|
69 |
"step": 50
|
70 |
},
|
71 |
{
|
72 |
-
"epoch":
|
73 |
-
"learning_rate":
|
74 |
-
"loss":
|
75 |
"step": 55
|
76 |
},
|
77 |
{
|
78 |
-
"epoch":
|
79 |
-
"eval_accuracy": 0.
|
80 |
-
"eval_loss": 1.
|
81 |
-
"eval_runtime":
|
82 |
-
"eval_samples_per_second": 1.
|
83 |
-
"eval_steps_per_second": 0.
|
84 |
"step": 56
|
85 |
}
|
86 |
],
|
87 |
"logging_steps": 5,
|
88 |
-
"max_steps":
|
89 |
-
"num_train_epochs":
|
90 |
"save_steps": 500,
|
91 |
-
"total_flos":
|
92 |
"trial_name": null,
|
93 |
"trial_params": null
|
94 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.83,
|
3 |
"best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-56",
|
4 |
+
"epoch": 1.9823008849557522,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 56,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.18,
|
13 |
+
"learning_rate": 3.5714285714285718e-06,
|
14 |
+
"loss": 0.0338,
|
15 |
"step": 5
|
16 |
},
|
17 |
{
|
18 |
+
"epoch": 0.35,
|
19 |
+
"learning_rate": 7.1428571428571436e-06,
|
20 |
+
"loss": 0.0053,
|
21 |
"step": 10
|
22 |
},
|
23 |
{
|
24 |
+
"epoch": 0.53,
|
25 |
+
"learning_rate": 9.920634920634922e-06,
|
26 |
+
"loss": 0.0056,
|
27 |
"step": 15
|
28 |
},
|
29 |
{
|
30 |
+
"epoch": 0.71,
|
31 |
+
"learning_rate": 9.523809523809525e-06,
|
32 |
+
"loss": 0.0437,
|
33 |
"step": 20
|
34 |
},
|
35 |
{
|
36 |
+
"epoch": 0.88,
|
37 |
+
"learning_rate": 9.126984126984127e-06,
|
38 |
+
"loss": 0.0017,
|
39 |
"step": 25
|
40 |
},
|
41 |
{
|
42 |
+
"epoch": 0.99,
|
43 |
+
"eval_accuracy": 0.82,
|
44 |
+
"eval_loss": 1.0909959077835083,
|
45 |
+
"eval_runtime": 72.1207,
|
46 |
+
"eval_samples_per_second": 1.387,
|
47 |
+
"eval_steps_per_second": 0.18,
|
48 |
+
"step": 28
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.06,
|
52 |
+
"learning_rate": 8.730158730158731e-06,
|
53 |
+
"loss": 0.0013,
|
54 |
"step": 30
|
55 |
},
|
56 |
{
|
57 |
+
"epoch": 1.24,
|
58 |
+
"learning_rate": 8.333333333333334e-06,
|
59 |
+
"loss": 0.0373,
|
60 |
"step": 35
|
61 |
},
|
62 |
{
|
63 |
+
"epoch": 1.42,
|
64 |
+
"learning_rate": 7.936507936507936e-06,
|
65 |
+
"loss": 0.0041,
|
66 |
"step": 40
|
67 |
},
|
68 |
{
|
69 |
+
"epoch": 1.59,
|
70 |
+
"learning_rate": 7.53968253968254e-06,
|
71 |
+
"loss": 0.0012,
|
72 |
"step": 45
|
73 |
},
|
74 |
{
|
75 |
+
"epoch": 1.77,
|
76 |
+
"learning_rate": 7.1428571428571436e-06,
|
77 |
+
"loss": 0.0338,
|
78 |
"step": 50
|
79 |
},
|
80 |
{
|
81 |
+
"epoch": 1.95,
|
82 |
+
"learning_rate": 6.746031746031747e-06,
|
83 |
+
"loss": 0.0143,
|
84 |
"step": 55
|
85 |
},
|
86 |
{
|
87 |
+
"epoch": 1.98,
|
88 |
+
"eval_accuracy": 0.83,
|
89 |
+
"eval_loss": 1.1379410028457642,
|
90 |
+
"eval_runtime": 71.5138,
|
91 |
+
"eval_samples_per_second": 1.398,
|
92 |
+
"eval_steps_per_second": 0.182,
|
93 |
"step": 56
|
94 |
}
|
95 |
],
|
96 |
"logging_steps": 5,
|
97 |
+
"max_steps": 140,
|
98 |
+
"num_train_epochs": 5,
|
99 |
"save_steps": 500,
|
100 |
+
"total_flos": 1.2267976549248e+17,
|
101 |
"trial_name": null,
|
102 |
"trial_params": null
|
103 |
}
|
checkpoint-56/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94c8327b62c2d89df2d87b86e12181649733dbdfae7f66da82435847a359e69a
|
3 |
size 4600
|