Training in progress, step 2000, checkpoint
Browse files
checkpoint-2000/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 932401285
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d22b85a7263581b2f995229898bfa3fbff963525eb21b6ff27842bf870f14d11
|
3 |
size 932401285
|
checkpoint-2000/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 466205145
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45866a9412bf8db18f4fb57252b2c9109cf8bbea03bebf71de24a6bbc10c5a00
|
3 |
size 466205145
|
checkpoint-2000/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1df9fb5d9a26bcf3d16f43a9e2e707cdf1b1348f36924b93d279819e285489ed
|
3 |
size 14575
|
checkpoint-2000/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
"best_model_checkpoint": "/kaggle/output/checkpoint-1000",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 1000,
|
6 |
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,45 +9,45 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
"learning_rate": 2.7777777777777777e-11,
|
14 |
-
"loss": 1.
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
-
"epoch":
|
19 |
"learning_rate": 2.7750000000000004e-08,
|
20 |
-
"loss": 1.
|
21 |
"step": 1000
|
22 |
},
|
23 |
{
|
24 |
-
"epoch":
|
25 |
-
"eval_accuracy": 0.
|
26 |
-
"eval_loss": 1.
|
27 |
-
"eval_runtime": 54.
|
28 |
-
"eval_samples_per_second":
|
29 |
-
"eval_steps_per_second": 11.
|
30 |
"step": 1000
|
31 |
},
|
32 |
{
|
33 |
-
"epoch":
|
34 |
"learning_rate": 5.5527777777777784e-08,
|
35 |
-
"loss": 1.
|
36 |
"step": 2000
|
37 |
},
|
38 |
{
|
39 |
-
"epoch":
|
40 |
-
"eval_accuracy": 0.
|
41 |
-
"eval_loss": 1.
|
42 |
-
"eval_runtime": 54.
|
43 |
-
"eval_samples_per_second":
|
44 |
-
"eval_steps_per_second": 11.
|
45 |
"step": 2000
|
46 |
}
|
47 |
],
|
48 |
"logging_steps": 1000,
|
49 |
"max_steps": 10000000,
|
50 |
-
"num_train_epochs":
|
51 |
"save_steps": 1000,
|
52 |
"total_flos": 4180710260736000.0,
|
53 |
"trial_name": null,
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.1077626943588257,
|
3 |
"best_model_checkpoint": "/kaggle/output/checkpoint-1000",
|
4 |
+
"epoch": 0.08148631029986962,
|
5 |
"eval_steps": 1000,
|
6 |
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.0,
|
13 |
"learning_rate": 2.7777777777777777e-11,
|
14 |
+
"loss": 1.1383,
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
+
"epoch": 0.04,
|
19 |
"learning_rate": 2.7750000000000004e-08,
|
20 |
+
"loss": 1.1424,
|
21 |
"step": 1000
|
22 |
},
|
23 |
{
|
24 |
+
"epoch": 0.04,
|
25 |
+
"eval_accuracy": 0.32375249500998005,
|
26 |
+
"eval_loss": 1.1077626943588257,
|
27 |
+
"eval_runtime": 54.8633,
|
28 |
+
"eval_samples_per_second": 91.318,
|
29 |
+
"eval_steps_per_second": 11.428,
|
30 |
"step": 1000
|
31 |
},
|
32 |
{
|
33 |
+
"epoch": 0.08,
|
34 |
"learning_rate": 5.5527777777777784e-08,
|
35 |
+
"loss": 1.1244,
|
36 |
"step": 2000
|
37 |
},
|
38 |
{
|
39 |
+
"epoch": 0.08,
|
40 |
+
"eval_accuracy": 0.33652694610778444,
|
41 |
+
"eval_loss": 1.1080161333084106,
|
42 |
+
"eval_runtime": 54.7384,
|
43 |
+
"eval_samples_per_second": 91.526,
|
44 |
+
"eval_steps_per_second": 11.454,
|
45 |
"step": 2000
|
46 |
}
|
47 |
],
|
48 |
"logging_steps": 1000,
|
49 |
"max_steps": 10000000,
|
50 |
+
"num_train_epochs": 408,
|
51 |
"save_steps": 1000,
|
52 |
"total_flos": 4180710260736000.0,
|
53 |
"trial_name": null,
|
checkpoint-2000/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4091
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9a52921b15d7eeb53b158a9c0f943d88288ccd9232004774ffdf3a600a048d5
|
3 |
size 4091
|