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 sha256:4bedc4517c4849434d43040651dfe9ff53c06e9272efe717fadfd2a31265607d
|
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 sha256:885b2061cdcb7ea517dda0b5ea934218e4df2744cbea41c20a9de35bf6698219
|
3 |
size 3424043887
|
checkpoint-2500/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-2500",
|
4 |
"epoch": 0.46057479734708917,
|
5 |
"eval_steps": 500,
|
@@ -10,77 +10,77 @@
|
|
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 |
{
|
57 |
"epoch": 0.36845983787767134,
|
58 |
-
"grad_norm": 0.
|
59 |
"learning_rate": 4.539425202652911e-08,
|
60 |
-
"loss": 0.
|
61 |
"step": 2000
|
62 |
},
|
63 |
{
|
64 |
"epoch": 0.36845983787767134,
|
65 |
-
"eval_loss": 1.
|
66 |
-
"eval_runtime":
|
67 |
-
"eval_samples_per_second":
|
68 |
-
"eval_steps_per_second":
|
69 |
"step": 2000
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.46057479734708917,
|
73 |
-
"grad_norm":
|
74 |
"learning_rate": 4.4242815033161385e-08,
|
75 |
"loss": 0.3645,
|
76 |
"step": 2500
|
77 |
},
|
78 |
{
|
79 |
"epoch": 0.46057479734708917,
|
80 |
-
"eval_loss": 1.
|
81 |
-
"eval_runtime":
|
82 |
-
"eval_samples_per_second": 15.
|
83 |
-
"eval_steps_per_second": 1.
|
84 |
"step": 2500
|
85 |
}
|
86 |
],
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.1902339458465576,
|
3 |
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l58-l/checkpoint-2500",
|
4 |
"epoch": 0.46057479734708917,
|
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 |
{
|
57 |
"epoch": 0.36845983787767134,
|
58 |
+
"grad_norm": 0.1667678952217102,
|
59 |
"learning_rate": 4.539425202652911e-08,
|
60 |
+
"loss": 0.3424,
|
61 |
"step": 2000
|
62 |
},
|
63 |
{
|
64 |
"epoch": 0.36845983787767134,
|
65 |
+
"eval_loss": 1.239119052886963,
|
66 |
+
"eval_runtime": 75.387,
|
67 |
+
"eval_samples_per_second": 16.011,
|
68 |
+
"eval_steps_per_second": 2.003,
|
69 |
"step": 2000
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.46057479734708917,
|
73 |
+
"grad_norm": 343.8175048828125,
|
74 |
"learning_rate": 4.4242815033161385e-08,
|
75 |
"loss": 0.3645,
|
76 |
"step": 2500
|
77 |
},
|
78 |
{
|
79 |
"epoch": 0.46057479734708917,
|
80 |
+
"eval_loss": 1.1902339458465576,
|
81 |
+
"eval_runtime": 75.9899,
|
82 |
+
"eval_samples_per_second": 15.884,
|
83 |
+
"eval_steps_per_second": 1.987,
|
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 sha256:9a29c2374e59ce3f57b34db9cb20d2d1bdc870c3dad128e9a4d462636c37e8b0
|
3 |
size 4847
|