Training in progress, step 7970, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd2b6a9dc05693189c34d7d240609890fd9581839b92af0c907ce0e2fa1f4fc8
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36049f7dd0fd4ef1a6f269bcf87f475b24ca23e6e34f08591ecce1dea6865301
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:879410c1a1946223d0a976fd0483a0d1693bf1557a1df37291599d47e8a1dc3a
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 61.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -14336,6 +14336,24 @@
|
|
| 14336 |
"mean_token_accuracy": 0.6459792077541351,
|
| 14337 |
"num_tokens": 29027531.0,
|
| 14338 |
"step": 7960
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14339 |
}
|
| 14340 |
],
|
| 14341 |
"logging_steps": 5,
|
|
@@ -14355,7 +14373,7 @@
|
|
| 14355 |
"attributes": {}
|
| 14356 |
}
|
| 14357 |
},
|
| 14358 |
-
"total_flos": 1.
|
| 14359 |
"train_batch_size": 4,
|
| 14360 |
"trial_name": null,
|
| 14361 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 61.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7970,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14336 |
"mean_token_accuracy": 0.6459792077541351,
|
| 14337 |
"num_tokens": 29027531.0,
|
| 14338 |
"step": 7960
|
| 14339 |
+
},
|
| 14340 |
+
{
|
| 14341 |
+
"epoch": 61.26923076923077,
|
| 14342 |
+
"grad_norm": 0.0,
|
| 14343 |
+
"learning_rate": 1.018e-05,
|
| 14344 |
+
"loss": 1.7467,
|
| 14345 |
+
"mean_token_accuracy": 0.6560082226991654,
|
| 14346 |
+
"num_tokens": 29045399.0,
|
| 14347 |
+
"step": 7965
|
| 14348 |
+
},
|
| 14349 |
+
{
|
| 14350 |
+
"epoch": 61.30769230769231,
|
| 14351 |
+
"grad_norm": 0.0,
|
| 14352 |
+
"learning_rate": 1.0155e-05,
|
| 14353 |
+
"loss": 1.6793,
|
| 14354 |
+
"mean_token_accuracy": 0.6648034691810608,
|
| 14355 |
+
"num_tokens": 29064129.0,
|
| 14356 |
+
"step": 7970
|
| 14357 |
}
|
| 14358 |
],
|
| 14359 |
"logging_steps": 5,
|
|
|
|
| 14373 |
"attributes": {}
|
| 14374 |
}
|
| 14375 |
},
|
| 14376 |
+
"total_flos": 1.4736483097509888e+18,
|
| 14377 |
"train_batch_size": 4,
|
| 14378 |
"trial_name": null,
|
| 14379 |
"trial_params": null
|