Commit ·
20f269e
1
Parent(s): 4f7512e
Training in progress, step 275, checkpoint
Browse files
last-checkpoint/adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 369214349
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ce98f62475b02d813fa9bd1dd46b5ad660334919ce95229266ec72e208f43c2
|
| 3 |
size 369214349
|
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 369142184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:450984270a23cb97a2dd0f60f50472bf351b7604d52ecdece7fb5595fc2cac05
|
| 3 |
size 369142184
|
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 sha256:7dc41291a38a5c28e39990bba3efdeb6ea338e042566d4499bcd2b4ecc010783
|
| 3 |
+
size 738393861
|
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 sha256:97f77450e7afc93bbfe7a27620bd8b3946dcc669a2b02cf05621bea9dbe06306
|
| 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:e2e59c9c1891f28f7a253d8cfa64a90e72929c37d9ac3b14d0d53c3958894e77
|
| 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": 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,
|
|
@@ -67,13 +67,19 @@
|
|
| 67 |
"learning_rate": 0.0002,
|
| 68 |
"loss": 0.8211,
|
| 69 |
"step": 250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
}
|
| 71 |
],
|
| 72 |
"logging_steps": 25,
|
| 73 |
"max_steps": 728,
|
| 74 |
"num_train_epochs": 1,
|
| 75 |
"save_steps": 25,
|
| 76 |
-
"total_flos":
|
| 77 |
"trial_name": null,
|
| 78 |
"trial_params": null
|
| 79 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.37774725274725274,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 275,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 67 |
"learning_rate": 0.0002,
|
| 68 |
"loss": 0.8211,
|
| 69 |
"step": 250
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.38,
|
| 73 |
+
"learning_rate": 0.0002,
|
| 74 |
+
"loss": 1.0453,
|
| 75 |
+
"step": 275
|
| 76 |
}
|
| 77 |
],
|
| 78 |
"logging_steps": 25,
|
| 79 |
"max_steps": 728,
|
| 80 |
"num_train_epochs": 1,
|
| 81 |
"save_steps": 25,
|
| 82 |
+
"total_flos": 2722709348352000.0,
|
| 83 |
"trial_name": null,
|
| 84 |
"trial_params": null
|
| 85 |
}
|