Training in progress, step 400, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 250422888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:143eb999e252a44bfaec3f6dc65ccaadd527995ccf2e5917e89c6ae977c6b0e8
|
3 |
size 250422888
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc2af1b572ea70609763b0c346a5e5569c0bd0ad35d5d5abe812e24aabdff71a
|
3 |
+
size 126034975
|
last-checkpoint/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 sha256:8c51ea51ba43ad9523a9def313e3c5a6e90b133318988b18624df83ba715cc8b
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 200,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -20,13 +20,26 @@
|
|
20 |
"eval_samples_per_second": 4.006,
|
21 |
"eval_steps_per_second": 0.132,
|
22 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
}
|
24 |
],
|
25 |
"logging_steps": 200,
|
26 |
"max_steps": 1535,
|
27 |
"num_train_epochs": 5,
|
28 |
"save_steps": 200,
|
29 |
-
"total_flos":
|
30 |
"trial_name": null,
|
31 |
"trial_params": null
|
32 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.3029315960912053,
|
5 |
"eval_steps": 200,
|
6 |
+
"global_step": 400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
20 |
"eval_samples_per_second": 4.006,
|
21 |
"eval_steps_per_second": 0.132,
|
22 |
"step": 200
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 1.3,
|
26 |
+
"learning_rate": 0.0002,
|
27 |
+
"loss": 0.1455,
|
28 |
+
"step": 400
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 1.3,
|
32 |
+
"eval_runtime": 128.7972,
|
33 |
+
"eval_samples_per_second": 4.006,
|
34 |
+
"eval_steps_per_second": 0.132,
|
35 |
+
"step": 400
|
36 |
}
|
37 |
],
|
38 |
"logging_steps": 200,
|
39 |
"max_steps": 1535,
|
40 |
"num_train_epochs": 5,
|
41 |
"save_steps": 200,
|
42 |
+
"total_flos": 5.0683133362176e+17,
|
43 |
"trial_name": null,
|
44 |
"trial_params": null
|
45 |
}
|