Training in progress, step 2000, checkpoint
Browse files
checkpoint-2000/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 sha256:62d108d1039c932b8e27f5c3af19e82fa70d2f6fecc0509ab6ef1d3467d6c53e
|
3 |
size 1711848436
|
checkpoint-2000/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 sha256:7021356be905f6baa7bb35b42dda949627fabf841e336680a60caa358eddc411
|
3 |
size 3424043887
|
checkpoint-2000/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fedc9d05d8c53e20b8390de6f1f8081f1a35d4ebd835fabc1f6569e6c78c6e0
|
3 |
size 623
|
checkpoint-2000/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l58-l/checkpoint-2000",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,68 +9,68 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate": 4.
|
15 |
-
"loss": 0.
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"eval_loss": 1.
|
21 |
-
"eval_runtime":
|
22 |
-
"eval_samples_per_second":
|
23 |
-
"eval_steps_per_second":
|
24 |
"step": 500
|
25 |
},
|
26 |
{
|
27 |
-
"epoch": 0.
|
28 |
-
"grad_norm":
|
29 |
-
"learning_rate": 4.
|
30 |
-
"loss": 0.
|
31 |
"step": 1000
|
32 |
},
|
33 |
{
|
34 |
-
"epoch": 0.
|
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.
|
43 |
-
"grad_norm":
|
44 |
-
"learning_rate": 4.
|
45 |
-
"loss": 0.
|
46 |
"step": 1500
|
47 |
},
|
48 |
{
|
49 |
-
"epoch": 0.
|
50 |
-
"eval_loss": 1.
|
51 |
-
"eval_runtime":
|
52 |
-
"eval_samples_per_second":
|
53 |
-
"eval_steps_per_second":
|
54 |
"step": 1500
|
55 |
},
|
56 |
{
|
57 |
-
"epoch": 0.
|
58 |
-
"grad_norm":
|
59 |
-
"learning_rate": 4.
|
60 |
-
"loss": 0.
|
61 |
"step": 2000
|
62 |
},
|
63 |
{
|
64 |
-
"epoch": 0.
|
65 |
-
"eval_loss": 1.
|
66 |
-
"eval_runtime":
|
67 |
-
"eval_samples_per_second": 15.
|
68 |
-
"eval_steps_per_second": 1.
|
69 |
"step": 2000
|
70 |
}
|
71 |
],
|
72 |
"logging_steps": 500,
|
73 |
-
"max_steps":
|
74 |
"num_input_tokens_seen": 0,
|
75 |
"num_train_epochs": 4,
|
76 |
"save_steps": 500,
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.2384389638900757,
|
3 |
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l58-l/checkpoint-2000",
|
4 |
+
"epoch": 0.36845983787767134,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.09211495946941783,
|
13 |
+
"grad_norm": 20.28152847290039,
|
14 |
+
"learning_rate": 4.8848563006632274e-08,
|
15 |
+
"loss": 0.3758,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.09211495946941783,
|
20 |
+
"eval_loss": 1.418367862701416,
|
21 |
+
"eval_runtime": 73.4439,
|
22 |
+
"eval_samples_per_second": 16.434,
|
23 |
+
"eval_steps_per_second": 2.056,
|
24 |
"step": 500
|
25 |
},
|
26 |
{
|
27 |
+
"epoch": 0.18422991893883567,
|
28 |
+
"grad_norm": 47.29538345336914,
|
29 |
+
"learning_rate": 4.7697126013264556e-08,
|
30 |
+
"loss": 0.4104,
|
31 |
"step": 1000
|
32 |
},
|
33 |
{
|
34 |
+
"epoch": 0.18422991893883567,
|
35 |
+
"eval_loss": 1.3491536378860474,
|
36 |
+
"eval_runtime": 74.3404,
|
37 |
+
"eval_samples_per_second": 16.236,
|
38 |
+
"eval_steps_per_second": 2.031,
|
39 |
"step": 1000
|
40 |
},
|
41 |
{
|
42 |
+
"epoch": 0.2763448784082535,
|
43 |
+
"grad_norm": 0.5450155138969421,
|
44 |
+
"learning_rate": 4.6545689019896826e-08,
|
45 |
+
"loss": 0.4325,
|
46 |
"step": 1500
|
47 |
},
|
48 |
{
|
49 |
+
"epoch": 0.2763448784082535,
|
50 |
+
"eval_loss": 1.2877168655395508,
|
51 |
+
"eval_runtime": 75.3303,
|
52 |
+
"eval_samples_per_second": 16.023,
|
53 |
+
"eval_steps_per_second": 2.005,
|
54 |
"step": 1500
|
55 |
},
|
56 |
{
|
57 |
+
"epoch": 0.36845983787767134,
|
58 |
+
"grad_norm": 0.11449883133172989,
|
59 |
+
"learning_rate": 4.539425202652911e-08,
|
60 |
+
"loss": 0.3423,
|
61 |
"step": 2000
|
62 |
},
|
63 |
{
|
64 |
+
"epoch": 0.36845983787767134,
|
65 |
+
"eval_loss": 1.2384389638900757,
|
66 |
+
"eval_runtime": 76.113,
|
67 |
+
"eval_samples_per_second": 15.858,
|
68 |
+
"eval_steps_per_second": 1.984,
|
69 |
"step": 2000
|
70 |
}
|
71 |
],
|
72 |
"logging_steps": 500,
|
73 |
+
"max_steps": 21712,
|
74 |
"num_input_tokens_seen": 0,
|
75 |
"num_train_epochs": 4,
|
76 |
"save_steps": 500,
|
checkpoint-2000/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 sha256:595bb6f39a89ec7030e395471c015665757cb5cacaafa6bba1613fd32b629686
|
3 |
size 4847
|