Training in progress, step 200, 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 9444296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4ee5c977b6e57fa0e1b2d72c5810005c22442b05d173a256d52ae29c1daa91a
|
3 |
size 9444296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18902665
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3a6928ddc55fc8ef68932e3d9fb349e182f7d178123f27ffd0db54e66436ee7
|
3 |
size 18902665
|
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:bb3d217570474ed44ac994697c08a6231247f4bb9ecce7bb8af4dbe390e8d62a
|
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 sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -21,13 +21,27 @@
|
|
21 |
"eval_samples_per_second": 30.567,
|
22 |
"eval_steps_per_second": 3.825,
|
23 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 100,
|
27 |
"max_steps": 4116,
|
28 |
"num_train_epochs": 3,
|
29 |
"save_steps": 100,
|
30 |
-
"total_flos":
|
31 |
"trial_name": null,
|
32 |
"trial_params": null
|
33 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.5923426151275635,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-200",
|
4 |
+
"epoch": 0.14571948998178508,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
21 |
"eval_samples_per_second": 30.567,
|
22 |
"eval_steps_per_second": 3.825,
|
23 |
"step": 100
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.15,
|
27 |
+
"learning_rate": 0.0002,
|
28 |
+
"loss": 2.606,
|
29 |
+
"step": 200
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.15,
|
33 |
+
"eval_loss": 2.5923426151275635,
|
34 |
+
"eval_runtime": 208.3105,
|
35 |
+
"eval_samples_per_second": 30.119,
|
36 |
+
"eval_steps_per_second": 3.768,
|
37 |
+
"step": 200
|
38 |
}
|
39 |
],
|
40 |
"logging_steps": 100,
|
41 |
"max_steps": 4116,
|
42 |
"num_train_epochs": 3,
|
43 |
"save_steps": 100,
|
44 |
+
"total_flos": 5821275858370560.0,
|
45 |
"trial_name": null,
|
46 |
"trial_params": null
|
47 |
}
|