Training in progress, step 1500, checkpoint
Browse files
checkpoint-1500/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 sha256:1fa66ad784fad6ae8d40efdfcf61d061140aef7290fd6c3b05c24f39f7169a31
|
3 |
size 1711848436
|
checkpoint-1500/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:a17afe0145a0cd7cd342bda26013a060e11677ea7818dd76af66b68d564fb205
|
3 |
size 3424043887
|
checkpoint-1500/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l58-l/checkpoint-1500",
|
4 |
"epoch": 0.2763448784082535,
|
5 |
"eval_steps": 500,
|
@@ -10,47 +10,47 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.09211495946941783,
|
13 |
-
"grad_norm": 20.
|
14 |
"learning_rate": 4.8848563006632274e-08,
|
15 |
"loss": 0.3758,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.09211495946941783,
|
20 |
-
"eval_loss": 1.
|
21 |
-
"eval_runtime":
|
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": 4.7697126013264556e-08,
|
30 |
-
"loss": 0.
|
31 |
"step": 1000
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.18422991893883567,
|
35 |
-
"eval_loss": 1.
|
36 |
-
"eval_runtime":
|
37 |
-
"eval_samples_per_second":
|
38 |
-
"eval_steps_per_second":
|
39 |
"step": 1000
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.2763448784082535,
|
43 |
-
"grad_norm": 0.
|
44 |
"learning_rate": 4.6545689019896826e-08,
|
45 |
-
"loss": 0.
|
46 |
"step": 1500
|
47 |
},
|
48 |
{
|
49 |
"epoch": 0.2763448784082535,
|
50 |
-
"eval_loss": 1.
|
51 |
-
"eval_runtime": 75.
|
52 |
-
"eval_samples_per_second": 16.
|
53 |
-
"eval_steps_per_second": 2.
|
54 |
"step": 1500
|
55 |
}
|
56 |
],
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.2885024547576904,
|
3 |
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l58-l/checkpoint-1500",
|
4 |
"epoch": 0.2763448784082535,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.09211495946941783,
|
13 |
+
"grad_norm": 20.04043960571289,
|
14 |
"learning_rate": 4.8848563006632274e-08,
|
15 |
"loss": 0.3758,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.09211495946941783,
|
20 |
+
"eval_loss": 1.4184927940368652,
|
21 |
+
"eval_runtime": 74.3562,
|
22 |
+
"eval_samples_per_second": 16.233,
|
23 |
+
"eval_steps_per_second": 2.031,
|
24 |
"step": 500
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.18422991893883567,
|
28 |
+
"grad_norm": 74.25025939941406,
|
29 |
"learning_rate": 4.7697126013264556e-08,
|
30 |
+
"loss": 0.4103,
|
31 |
"step": 1000
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.18422991893883567,
|
35 |
+
"eval_loss": 1.3500770330429077,
|
36 |
+
"eval_runtime": 75.7013,
|
37 |
+
"eval_samples_per_second": 15.944,
|
38 |
+
"eval_steps_per_second": 1.995,
|
39 |
"step": 1000
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.2763448784082535,
|
43 |
+
"grad_norm": 0.5102410912513733,
|
44 |
"learning_rate": 4.6545689019896826e-08,
|
45 |
+
"loss": 0.433,
|
46 |
"step": 1500
|
47 |
},
|
48 |
{
|
49 |
"epoch": 0.2763448784082535,
|
50 |
+
"eval_loss": 1.2885024547576904,
|
51 |
+
"eval_runtime": 75.197,
|
52 |
+
"eval_samples_per_second": 16.051,
|
53 |
+
"eval_steps_per_second": 2.008,
|
54 |
"step": 1500
|
55 |
}
|
56 |
],
|
checkpoint-1500/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 sha256:9a29c2374e59ce3f57b34db9cb20d2d1bdc870c3dad128e9a4d462636c37e8b0
|
3 |
size 4847
|