Training in progress, step 3200, 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 sha256:24f7d91673f474e9a8cd601e0f5cf17212fbecb42ccccbd206aedc97eb2c9cc1
|
| 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 sha256:044676fe3a92bcc48dd1394efa7506a91ea4f759cea96bff743df75b9fcc365f
|
| 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:ea16ff86c0e46750d94dbe927a32909174204ea2ff6540d0f12b3954af8effa9
|
| 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:aa7f1f688ca7eb435671386a20903cb451ba5b1cd69370d7986bb81bc7a9b54b
|
| 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": 6.
|
| 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,
|
|
@@ -272,6 +272,13 @@
|
|
| 272 |
"learning_rate": 7.933333333333334e-05,
|
| 273 |
"loss": 1.2739,
|
| 274 |
"step": 3100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 275 |
}
|
| 276 |
],
|
| 277 |
"logging_steps": 100,
|
|
@@ -291,7 +298,7 @@
|
|
| 291 |
"attributes": {}
|
| 292 |
}
|
| 293 |
},
|
| 294 |
-
"total_flos": 4.
|
| 295 |
"train_batch_size": 8,
|
| 296 |
"trial_name": null,
|
| 297 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.39900015622559,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 3200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 272 |
"learning_rate": 7.933333333333334e-05,
|
| 273 |
"loss": 1.2739,
|
| 274 |
"step": 3100
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 6.39900015622559,
|
| 278 |
+
"grad_norm": 0.18602177500724792,
|
| 279 |
+
"learning_rate": 7.866666666666666e-05,
|
| 280 |
+
"loss": 1.2743,
|
| 281 |
+
"step": 3200
|
| 282 |
}
|
| 283 |
],
|
| 284 |
"logging_steps": 100,
|
|
|
|
| 298 |
"attributes": {}
|
| 299 |
}
|
| 300 |
},
|
| 301 |
+
"total_flos": 4.994344136799683e+18,
|
| 302 |
"train_batch_size": 8,
|
| 303 |
"trial_name": null,
|
| 304 |
"trial_params": null
|