Training in progress, step 1000, checkpoint
Browse files
checkpoint-1000/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:aa35702e504f2f43273920e87d00bcc0bf84cf60b32f09effa629b0605f223b6
|
3 |
size 1711848436
|
checkpoint-1000/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:cf1c7e8251a1becdbd3f41af87f9668b7781a0b4419f80e69e3e4c81b57c211b
|
3 |
size 3424043887
|
checkpoint-1000/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l17-l/checkpoint-1000",
|
4 |
"epoch": 0.10665529010238908,
|
5 |
"eval_steps": 500,
|
@@ -10,32 +10,32 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.05332764505119454,
|
13 |
-
"grad_norm":
|
14 |
"learning_rate": 9.822241183162683e-08,
|
15 |
"loss": 0.4515,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.05332764505119454,
|
20 |
-
"eval_loss": 1.
|
21 |
-
"eval_runtime": 63.
|
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": 9.64448236632537e-08,
|
30 |
-
"loss": 0.
|
31 |
"step": 1000
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.10665529010238908,
|
35 |
-
"eval_loss": 1.
|
36 |
-
"eval_runtime":
|
37 |
-
"eval_samples_per_second": 15.
|
38 |
-
"eval_steps_per_second": 1.
|
39 |
"step": 1000
|
40 |
}
|
41 |
],
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.284144401550293,
|
3 |
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l17-l/checkpoint-1000",
|
4 |
"epoch": 0.10665529010238908,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.05332764505119454,
|
13 |
+
"grad_norm": 246.1711883544922,
|
14 |
"learning_rate": 9.822241183162683e-08,
|
15 |
"loss": 0.4515,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.05332764505119454,
|
20 |
+
"eval_loss": 1.3850886821746826,
|
21 |
+
"eval_runtime": 63.8439,
|
22 |
+
"eval_samples_per_second": 15.46,
|
23 |
+
"eval_steps_per_second": 1.942,
|
24 |
"step": 500
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.10665529010238908,
|
28 |
+
"grad_norm": 81.48503875732422,
|
29 |
"learning_rate": 9.64448236632537e-08,
|
30 |
+
"loss": 0.4148,
|
31 |
"step": 1000
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.10665529010238908,
|
35 |
+
"eval_loss": 1.284144401550293,
|
36 |
+
"eval_runtime": 63.853,
|
37 |
+
"eval_samples_per_second": 15.457,
|
38 |
+
"eval_steps_per_second": 1.942,
|
39 |
"step": 1000
|
40 |
}
|
41 |
],
|
checkpoint-1000/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 sha256:52c8db40c27633302368150be011282e1650a78d29cdfc5e366df6966e8e6c70
|
3 |
size 4847
|