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:dcd9de5ce390c1026c83b8caa26ed7c052d1b31642c82cd39343cee3bb983f52
|
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 sha256:32ceee045457291dc5e7652e940a7b5bd4e6d47a6828f15d30292a2a19fed5a2
|
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-e4l57-l/checkpoint-2500",
|
4 |
"epoch": 0.2666382252559727,
|
5 |
"eval_steps": 500,
|
@@ -10,77 +10,77 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.05332764505119454,
|
13 |
-
"grad_norm":
|
14 |
"learning_rate": 4.911120591581342e-07,
|
15 |
-
"loss": 0.
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.05332764505119454,
|
20 |
-
"eval_loss": 1.
|
21 |
-
"eval_runtime":
|
22 |
-
"eval_samples_per_second": 15.
|
23 |
-
"eval_steps_per_second": 1.
|
24 |
"step": 500
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.10665529010238908,
|
28 |
-
"grad_norm":
|
29 |
"learning_rate": 4.822241183162685e-07,
|
30 |
-
"loss": 0.
|
31 |
"step": 1000
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.10665529010238908,
|
35 |
-
"eval_loss": 0.
|
36 |
-
"eval_runtime":
|
37 |
-
"eval_samples_per_second": 15.
|
38 |
-
"eval_steps_per_second": 1.
|
39 |
"step": 1000
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.1599829351535836,
|
43 |
-
"grad_norm":
|
44 |
"learning_rate": 4.733361774744027e-07,
|
45 |
-
"loss": 0.
|
46 |
"step": 1500
|
47 |
},
|
48 |
{
|
49 |
"epoch": 0.1599829351535836,
|
50 |
-
"eval_loss": 0.
|
51 |
-
"eval_runtime":
|
52 |
-
"eval_samples_per_second": 15.
|
53 |
-
"eval_steps_per_second": 1.
|
54 |
"step": 1500
|
55 |
},
|
56 |
{
|
57 |
"epoch": 0.21331058020477817,
|
58 |
-
"grad_norm": 0.
|
59 |
"learning_rate": 4.6444823663253695e-07,
|
60 |
-
"loss": 0.
|
61 |
"step": 2000
|
62 |
},
|
63 |
{
|
64 |
"epoch": 0.21331058020477817,
|
65 |
-
"eval_loss": 0.
|
66 |
-
"eval_runtime": 63.
|
67 |
-
"eval_samples_per_second": 15.
|
68 |
-
"eval_steps_per_second": 1.
|
69 |
"step": 2000
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.2666382252559727,
|
73 |
-
"grad_norm":
|
74 |
"learning_rate": 4.5556029579067116e-07,
|
75 |
-
"loss": 0.
|
76 |
"step": 2500
|
77 |
},
|
78 |
{
|
79 |
"epoch": 0.2666382252559727,
|
80 |
-
"eval_loss": 0.
|
81 |
-
"eval_runtime":
|
82 |
-
"eval_samples_per_second": 15.
|
83 |
-
"eval_steps_per_second": 1.
|
84 |
"step": 2500
|
85 |
}
|
86 |
],
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7947371006011963,
|
3 |
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l57-l/checkpoint-2500",
|
4 |
"epoch": 0.2666382252559727,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.05332764505119454,
|
13 |
+
"grad_norm": 401.61187744140625,
|
14 |
"learning_rate": 4.911120591581342e-07,
|
15 |
+
"loss": 0.3808,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.05332764505119454,
|
20 |
+
"eval_loss": 1.1107642650604248,
|
21 |
+
"eval_runtime": 62.4169,
|
22 |
+
"eval_samples_per_second": 15.813,
|
23 |
+
"eval_steps_per_second": 1.987,
|
24 |
"step": 500
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.10665529010238908,
|
28 |
+
"grad_norm": 42.57551193237305,
|
29 |
"learning_rate": 4.822241183162685e-07,
|
30 |
+
"loss": 0.2666,
|
31 |
"step": 1000
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.10665529010238908,
|
35 |
+
"eval_loss": 0.9644754528999329,
|
36 |
+
"eval_runtime": 63.4304,
|
37 |
+
"eval_samples_per_second": 15.56,
|
38 |
+
"eval_steps_per_second": 1.955,
|
39 |
"step": 1000
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.1599829351535836,
|
43 |
+
"grad_norm": 518.2286376953125,
|
44 |
"learning_rate": 4.733361774744027e-07,
|
45 |
+
"loss": 0.2085,
|
46 |
"step": 1500
|
47 |
},
|
48 |
{
|
49 |
"epoch": 0.1599829351535836,
|
50 |
+
"eval_loss": 0.9051361680030823,
|
51 |
+
"eval_runtime": 63.9009,
|
52 |
+
"eval_samples_per_second": 15.446,
|
53 |
+
"eval_steps_per_second": 1.941,
|
54 |
"step": 1500
|
55 |
},
|
56 |
{
|
57 |
"epoch": 0.21331058020477817,
|
58 |
+
"grad_norm": 0.0223398394882679,
|
59 |
"learning_rate": 4.6444823663253695e-07,
|
60 |
+
"loss": 0.1867,
|
61 |
"step": 2000
|
62 |
},
|
63 |
{
|
64 |
"epoch": 0.21331058020477817,
|
65 |
+
"eval_loss": 0.8611643314361572,
|
66 |
+
"eval_runtime": 63.9649,
|
67 |
+
"eval_samples_per_second": 15.43,
|
68 |
+
"eval_steps_per_second": 1.939,
|
69 |
"step": 2000
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.2666382252559727,
|
73 |
+
"grad_norm": 175.0380096435547,
|
74 |
"learning_rate": 4.5556029579067116e-07,
|
75 |
+
"loss": 0.2068,
|
76 |
"step": 2500
|
77 |
},
|
78 |
{
|
79 |
"epoch": 0.2666382252559727,
|
80 |
+
"eval_loss": 0.7947371006011963,
|
81 |
+
"eval_runtime": 64.0455,
|
82 |
+
"eval_samples_per_second": 15.411,
|
83 |
+
"eval_steps_per_second": 1.936,
|
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 sha256:54c5f1c69a0ead76c168a8c74b80758f8f8eb77228d72de2bfc13a6b8cdc784b
|
3 |
size 4847
|