Training in progress, step 300, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:572c70d38e9470cb6ddb7f4e04f9225d22ad4b031e35a48875440e7f60b0486e
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed66e422964e748da14b6b7dc889010660ab69cbddc378dc8a60c5c598c1ef9a
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e054fff86dda46808a25de07c0beb3050924b0e8866e932d68fc5577a940a2a
|
| 3 |
size 15006
|
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 sha256:28b8cb982b812d63dccde36eba38baac87d5c81ec481b19091a84b87dc4cb21d
|
| 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,
|
|
@@ -21,6 +21,13 @@
|
|
| 21 |
"learning_rate": 9.866666666666668e-05,
|
| 22 |
"loss": 1.4581,
|
| 23 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
}
|
| 25 |
],
|
| 26 |
"logging_steps": 100,
|
|
@@ -40,7 +47,7 @@
|
|
| 40 |
"attributes": {}
|
| 41 |
}
|
| 42 |
},
|
| 43 |
-
"total_flos":
|
| 44 |
"train_batch_size": 8,
|
| 45 |
"trial_name": null,
|
| 46 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.599906264646149,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 21 |
"learning_rate": 9.866666666666668e-05,
|
| 22 |
"loss": 1.4581,
|
| 23 |
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.599906264646149,
|
| 27 |
+
"grad_norm": 0.08595048636198044,
|
| 28 |
+
"learning_rate": 9.8e-05,
|
| 29 |
+
"loss": 1.4002,
|
| 30 |
+
"step": 300
|
| 31 |
}
|
| 32 |
],
|
| 33 |
"logging_steps": 100,
|
|
|
|
| 47 |
"attributes": {}
|
| 48 |
}
|
| 49 |
},
|
| 50 |
+
"total_flos": 4.682249135645e+17,
|
| 51 |
"train_batch_size": 8,
|
| 52 |
"trial_name": null,
|
| 53 |
"trial_params": null
|