Training in progress, step 2500, checkpoint
Browse files
checkpoint-2500/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1711848436
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2f8c320b35583f64bbe7f6c2bf1db9d3307672a13b6e30c15beb24527fd33e0
|
3 |
size 1711848436
|
checkpoint-2500/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3424043887
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59e43bfba6c13e07a0d7cbab30936fefebc70c91de14eca244fcb45dbd0bb13b
|
3 |
size 3424043887
|
checkpoint-2500/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l57-l/checkpoint-2500",
|
4 |
"epoch": 0.46057479734708917,
|
5 |
"eval_steps": 500,
|
@@ -10,77 +10,77 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.09211495946941783,
|
13 |
-
"grad_norm":
|
14 |
"learning_rate": 4.84647506755097e-07,
|
15 |
-
"loss": 0.
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.09211495946941783,
|
20 |
-
"eval_loss": 1.
|
21 |
-
"eval_runtime": 74.
|
22 |
-
"eval_samples_per_second": 16.
|
23 |
-
"eval_steps_per_second": 2.
|
24 |
"step": 500
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.18422991893883567,
|
28 |
-
"grad_norm":
|
29 |
"learning_rate": 4.69295013510194e-07,
|
30 |
-
"loss": 0.
|
31 |
"step": 1000
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.18422991893883567,
|
35 |
-
"eval_loss": 0.
|
36 |
-
"eval_runtime": 74.
|
37 |
-
"eval_samples_per_second": 16.
|
38 |
-
"eval_steps_per_second": 2.
|
39 |
"step": 1000
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.2763448784082535,
|
43 |
-
"grad_norm": 0.
|
44 |
"learning_rate": 4.5394252026529107e-07,
|
45 |
-
"loss": 0.
|
46 |
"step": 1500
|
47 |
},
|
48 |
{
|
49 |
"epoch": 0.2763448784082535,
|
50 |
-
"eval_loss": 0.
|
51 |
-
"eval_runtime": 75.
|
52 |
-
"eval_samples_per_second":
|
53 |
-
"eval_steps_per_second":
|
54 |
"step": 1500
|
55 |
},
|
56 |
{
|
57 |
"epoch": 0.36845983787767134,
|
58 |
-
"grad_norm": 0.
|
59 |
"learning_rate": 4.385900270203881e-07,
|
60 |
-
"loss": 0.
|
61 |
"step": 2000
|
62 |
},
|
63 |
{
|
64 |
"epoch": 0.36845983787767134,
|
65 |
-
"eval_loss": 0.
|
66 |
-
"eval_runtime": 76.
|
67 |
-
"eval_samples_per_second": 15.
|
68 |
-
"eval_steps_per_second": 1.
|
69 |
"step": 2000
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.46057479734708917,
|
73 |
-
"grad_norm":
|
74 |
"learning_rate": 4.232375337754851e-07,
|
75 |
-
"loss": 0.
|
76 |
"step": 2500
|
77 |
},
|
78 |
{
|
79 |
"epoch": 0.46057479734708917,
|
80 |
-
"eval_loss": 0.
|
81 |
-
"eval_runtime":
|
82 |
-
"eval_samples_per_second":
|
83 |
-
"eval_steps_per_second":
|
84 |
"step": 2500
|
85 |
}
|
86 |
],
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7660450339317322,
|
3 |
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l57-l/checkpoint-2500",
|
4 |
"epoch": 0.46057479734708917,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.09211495946941783,
|
13 |
+
"grad_norm": 2.6780805587768555,
|
14 |
"learning_rate": 4.84647506755097e-07,
|
15 |
+
"loss": 0.2705,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.09211495946941783,
|
20 |
+
"eval_loss": 1.0680681467056274,
|
21 |
+
"eval_runtime": 74.5723,
|
22 |
+
"eval_samples_per_second": 16.186,
|
23 |
+
"eval_steps_per_second": 2.025,
|
24 |
"step": 500
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.18422991893883567,
|
28 |
+
"grad_norm": 8.301130294799805,
|
29 |
"learning_rate": 4.69295013510194e-07,
|
30 |
+
"loss": 0.2545,
|
31 |
"step": 1000
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.18422991893883567,
|
35 |
+
"eval_loss": 0.9443553686141968,
|
36 |
+
"eval_runtime": 74.9643,
|
37 |
+
"eval_samples_per_second": 16.101,
|
38 |
+
"eval_steps_per_second": 2.014,
|
39 |
"step": 1000
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.2763448784082535,
|
43 |
+
"grad_norm": 0.018898434937000275,
|
44 |
"learning_rate": 4.5394252026529107e-07,
|
45 |
+
"loss": 0.234,
|
46 |
"step": 1500
|
47 |
},
|
48 |
{
|
49 |
"epoch": 0.2763448784082535,
|
50 |
+
"eval_loss": 0.876915693283081,
|
51 |
+
"eval_runtime": 75.6401,
|
52 |
+
"eval_samples_per_second": 15.957,
|
53 |
+
"eval_steps_per_second": 1.996,
|
54 |
"step": 1500
|
55 |
},
|
56 |
{
|
57 |
"epoch": 0.36845983787767134,
|
58 |
+
"grad_norm": 0.00010984255641233176,
|
59 |
"learning_rate": 4.385900270203881e-07,
|
60 |
+
"loss": 0.1539,
|
61 |
"step": 2000
|
62 |
},
|
63 |
{
|
64 |
"epoch": 0.36845983787767134,
|
65 |
+
"eval_loss": 0.8415330648422241,
|
66 |
+
"eval_runtime": 76.9959,
|
67 |
+
"eval_samples_per_second": 15.676,
|
68 |
+
"eval_steps_per_second": 1.961,
|
69 |
"step": 2000
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.46057479734708917,
|
73 |
+
"grad_norm": 395.890625,
|
74 |
"learning_rate": 4.232375337754851e-07,
|
75 |
+
"loss": 0.1766,
|
76 |
"step": 2500
|
77 |
},
|
78 |
{
|
79 |
"epoch": 0.46057479734708917,
|
80 |
+
"eval_loss": 0.7660450339317322,
|
81 |
+
"eval_runtime": 76.733,
|
82 |
+
"eval_samples_per_second": 15.73,
|
83 |
+
"eval_steps_per_second": 1.968,
|
84 |
"step": 2500
|
85 |
}
|
86 |
],
|
checkpoint-2500/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4847
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea34fd4333686a44a60d290faa4ae8e00df783131842d9ae3ef1b9e874a39349
|
3 |
size 4847
|