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 45118424
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b945bed4e9b50189d80389328cb4366660fa960bd834e45a1bad1c55d78956f9
|
3 |
size 45118424
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 23159546
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:154a09bdf67e4563553a2c20510c24113da8a86dff2d5aa4276e81f3358e266f
|
3 |
size 23159546
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b5fc63c96f74081eb7d3ebe7cd62cb476ba8f9a3d76715567e25f7a6ba36f4b
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -28,6 +28,13 @@
|
|
28 |
"learning_rate": 0.0001875918325566888,
|
29 |
"loss": 2.6147,
|
30 |
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
}
|
32 |
],
|
33 |
"logging_steps": 100,
|
@@ -47,7 +54,7 @@
|
|
47 |
"attributes": {}
|
48 |
}
|
49 |
},
|
50 |
-
"total_flos": 1.
|
51 |
"train_batch_size": 8,
|
52 |
"trial_name": null,
|
53 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2966808826256258,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
28 |
"learning_rate": 0.0001875918325566888,
|
29 |
"loss": 2.6147,
|
30 |
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.2966808826256258,
|
34 |
+
"grad_norm": 0.7540659308433533,
|
35 |
+
"learning_rate": 0.00017281409538757883,
|
36 |
+
"loss": 2.5387,
|
37 |
+
"step": 400
|
38 |
}
|
39 |
],
|
40 |
"logging_steps": 100,
|
|
|
54 |
"attributes": {}
|
55 |
}
|
56 |
},
|
57 |
+
"total_flos": 1.548356111302656e+17,
|
58 |
"train_batch_size": 8,
|
59 |
"trial_name": null,
|
60 |
"trial_params": null
|