Upload folder using huggingface_hub
Browse files- checkpoint-6059/config.json +1 -1
- checkpoint-6059/model.safetensors +1 -1
- checkpoint-6059/optimizer.pt +1 -1
- checkpoint-6059/trainer_state.json +30 -30
- model.safetensors +1 -1
- training_args.bin +1 -1
checkpoint-6059/config.json
CHANGED
@@ -1824,5 +1824,5 @@
|
|
1824 |
"problem_type": "single_label_classification",
|
1825 |
"qkv_bias": true,
|
1826 |
"torch_dtype": "float32",
|
1827 |
-
"transformers_version": "4.40.
|
1828 |
}
|
|
|
1824 |
"problem_type": "single_label_classification",
|
1825 |
"qkv_bias": true,
|
1826 |
"torch_dtype": "float32",
|
1827 |
+
"transformers_version": "4.40.2"
|
1828 |
}
|
checkpoint-6059/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 345986248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95e1dc49da0286f9d7a5a5ca04cef4198bd9830b0cad96ba2873b07ea678f673
|
3 |
size 345986248
|
checkpoint-6059/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 692092933
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae3f5e8862a261e93c9e722d6e563f36f9d7f9846468509fa5249925e1ac3108
|
3 |
size 692092933
|
checkpoint-6059/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
"best_model_checkpoint": "flowers_image_detection/checkpoint-6059",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
@@ -10,95 +10,95 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0825218682950982,
|
13 |
-
"grad_norm": 1.
|
14 |
"learning_rate": 1.8502246630054915e-07,
|
15 |
-
"loss":
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.1650437365901964,
|
20 |
-
"grad_norm": 1.
|
21 |
"learning_rate": 1.6838076219004824e-07,
|
22 |
-
"loss": 5.
|
23 |
"step": 1000
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.2475656048852946,
|
27 |
-
"grad_norm": 1.
|
28 |
"learning_rate": 1.5173905807954736e-07,
|
29 |
-
"loss": 5.
|
30 |
"step": 1500
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.3300874731803928,
|
34 |
-
"grad_norm": 1.
|
35 |
"learning_rate": 1.3509735396904642e-07,
|
36 |
-
"loss": 5.
|
37 |
"step": 2000
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.412609341475491,
|
41 |
-
"grad_norm": 1.
|
42 |
"learning_rate": 1.184556498585455e-07,
|
43 |
-
"loss": 5.
|
44 |
"step": 2500
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.4951312097705892,
|
48 |
-
"grad_norm": 1.
|
49 |
"learning_rate": 1.018139457480446e-07,
|
50 |
-
"loss": 5.
|
51 |
"step": 3000
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.5776530780656874,
|
55 |
-
"grad_norm": 1.
|
56 |
"learning_rate": 8.517224163754369e-08,
|
57 |
-
"loss": 5.
|
58 |
"step": 3500
|
59 |
},
|
60 |
{
|
61 |
"epoch": 0.6601749463607856,
|
62 |
-
"grad_norm": 1.
|
63 |
"learning_rate": 6.853053752704277e-08,
|
64 |
-
"loss": 5.
|
65 |
"step": 4000
|
66 |
},
|
67 |
{
|
68 |
"epoch": 0.7426968146558838,
|
69 |
-
"grad_norm": 1.
|
70 |
"learning_rate": 5.188883341654186e-08,
|
71 |
-
"loss": 5.
|
72 |
"step": 4500
|
73 |
},
|
74 |
{
|
75 |
"epoch": 0.825218682950982,
|
76 |
-
"grad_norm": 1.
|
77 |
"learning_rate": 3.5247129306040934e-08,
|
78 |
-
"loss": 5.
|
79 |
"step": 5000
|
80 |
},
|
81 |
{
|
82 |
"epoch": 0.9077405512460802,
|
83 |
-
"grad_norm": 1.
|
84 |
"learning_rate": 1.8605425195540024e-08,
|
85 |
-
"loss": 5.
|
86 |
"step": 5500
|
87 |
},
|
88 |
{
|
89 |
"epoch": 0.9902624195411784,
|
90 |
-
"grad_norm": 1.
|
91 |
"learning_rate": 1.963721085039108e-09,
|
92 |
-
"loss": 5.
|
93 |
"step": 6000
|
94 |
},
|
95 |
{
|
96 |
"epoch": 1.0,
|
97 |
-
"eval_accuracy": 0.
|
98 |
-
"eval_loss":
|
99 |
-
"eval_runtime":
|
100 |
-
"eval_samples_per_second":
|
101 |
-
"eval_steps_per_second": 12.
|
102 |
"step": 6059
|
103 |
}
|
104 |
],
|
|
|
1 |
{
|
2 |
+
"best_metric": 5.945035457611084,
|
3 |
"best_model_checkpoint": "flowers_image_detection/checkpoint-6059",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0825218682950982,
|
13 |
+
"grad_norm": 1.8405259847640991,
|
14 |
"learning_rate": 1.8502246630054915e-07,
|
15 |
+
"loss": 5.9052,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.1650437365901964,
|
20 |
+
"grad_norm": 1.7937499284744263,
|
21 |
"learning_rate": 1.6838076219004824e-07,
|
22 |
+
"loss": 5.9037,
|
23 |
"step": 1000
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.2475656048852946,
|
27 |
+
"grad_norm": 1.78463613986969,
|
28 |
"learning_rate": 1.5173905807954736e-07,
|
29 |
+
"loss": 5.8934,
|
30 |
"step": 1500
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.3300874731803928,
|
34 |
+
"grad_norm": 1.9137163162231445,
|
35 |
"learning_rate": 1.3509735396904642e-07,
|
36 |
+
"loss": 5.9058,
|
37 |
"step": 2000
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.412609341475491,
|
41 |
+
"grad_norm": 1.856957197189331,
|
42 |
"learning_rate": 1.184556498585455e-07,
|
43 |
+
"loss": 5.9006,
|
44 |
"step": 2500
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.4951312097705892,
|
48 |
+
"grad_norm": 1.7443772554397583,
|
49 |
"learning_rate": 1.018139457480446e-07,
|
50 |
+
"loss": 5.8992,
|
51 |
"step": 3000
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.5776530780656874,
|
55 |
+
"grad_norm": 1.7190455198287964,
|
56 |
"learning_rate": 8.517224163754369e-08,
|
57 |
+
"loss": 5.9,
|
58 |
"step": 3500
|
59 |
},
|
60 |
{
|
61 |
"epoch": 0.6601749463607856,
|
62 |
+
"grad_norm": 1.7764075994491577,
|
63 |
"learning_rate": 6.853053752704277e-08,
|
64 |
+
"loss": 5.8941,
|
65 |
"step": 4000
|
66 |
},
|
67 |
{
|
68 |
"epoch": 0.7426968146558838,
|
69 |
+
"grad_norm": 1.8612918853759766,
|
70 |
"learning_rate": 5.188883341654186e-08,
|
71 |
+
"loss": 5.8934,
|
72 |
"step": 4500
|
73 |
},
|
74 |
{
|
75 |
"epoch": 0.825218682950982,
|
76 |
+
"grad_norm": 1.7310786247253418,
|
77 |
"learning_rate": 3.5247129306040934e-08,
|
78 |
+
"loss": 5.893,
|
79 |
"step": 5000
|
80 |
},
|
81 |
{
|
82 |
"epoch": 0.9077405512460802,
|
83 |
+
"grad_norm": 1.859296441078186,
|
84 |
"learning_rate": 1.8605425195540024e-08,
|
85 |
+
"loss": 5.8914,
|
86 |
"step": 5500
|
87 |
},
|
88 |
{
|
89 |
"epoch": 0.9902624195411784,
|
90 |
+
"grad_norm": 1.7598336935043335,
|
91 |
"learning_rate": 1.963721085039108e-09,
|
92 |
+
"loss": 5.8977,
|
93 |
"step": 6000
|
94 |
},
|
95 |
{
|
96 |
"epoch": 1.0,
|
97 |
+
"eval_accuracy": 0.6603837821108016,
|
98 |
+
"eval_loss": 5.945035457611084,
|
99 |
+
"eval_runtime": 1277.9432,
|
100 |
+
"eval_samples_per_second": 101.131,
|
101 |
+
"eval_steps_per_second": 12.641,
|
102 |
"step": 6059
|
103 |
}
|
104 |
],
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 345986248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95e1dc49da0286f9d7a5a5ca04cef4198bd9830b0cad96ba2873b07ea678f673
|
3 |
size 345986248
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4475
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feeaecfab3a2455bbac86494aba142b9f143e0fd873b66c049a0f5d34caad804
|
3 |
size 4475
|