Training in progress, step 8520, 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:bff53949b5af1cc7f4f33d9cc64571682051c73f23b4e28c2849adef9b8cead8
|
| 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 sha256:00f0d1d7c9353efd6aee1e539f5671d48a6c3af83ffabee62e07808206560d44
|
| 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 sha256:14937abeba95bf5c88ab802b1207982cc4e754e7e72d9b77b24e42eca156483d
|
| 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": 65.
|
| 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,
|
|
@@ -15326,6 +15326,24 @@
|
|
| 15326 |
"mean_token_accuracy": 0.6543114900588989,
|
| 15327 |
"num_tokens": 31038288.0,
|
| 15328 |
"step": 8510
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15329 |
}
|
| 15330 |
],
|
| 15331 |
"logging_steps": 5,
|
|
@@ -15345,7 +15363,7 @@
|
|
| 15345 |
"attributes": {}
|
| 15346 |
}
|
| 15347 |
},
|
| 15348 |
-
"total_flos": 1.
|
| 15349 |
"train_batch_size": 4,
|
| 15350 |
"trial_name": null,
|
| 15351 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 65.53846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8520,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15326 |
"mean_token_accuracy": 0.6543114900588989,
|
| 15327 |
"num_tokens": 31038288.0,
|
| 15328 |
"step": 8510
|
| 15329 |
+
},
|
| 15330 |
+
{
|
| 15331 |
+
"epoch": 65.5,
|
| 15332 |
+
"grad_norm": 0.0,
|
| 15333 |
+
"learning_rate": 7.430000000000001e-06,
|
| 15334 |
+
"loss": 1.8082,
|
| 15335 |
+
"mean_token_accuracy": 0.6374682754278183,
|
| 15336 |
+
"num_tokens": 31055635.0,
|
| 15337 |
+
"step": 8515
|
| 15338 |
+
},
|
| 15339 |
+
{
|
| 15340 |
+
"epoch": 65.53846153846153,
|
| 15341 |
+
"grad_norm": 0.0,
|
| 15342 |
+
"learning_rate": 7.405000000000001e-06,
|
| 15343 |
+
"loss": 1.718,
|
| 15344 |
+
"mean_token_accuracy": 0.6601694732904434,
|
| 15345 |
+
"num_tokens": 31073830.0,
|
| 15346 |
+
"step": 8520
|
| 15347 |
}
|
| 15348 |
],
|
| 15349 |
"logging_steps": 5,
|
|
|
|
| 15363 |
"attributes": {}
|
| 15364 |
}
|
| 15365 |
},
|
| 15366 |
+
"total_flos": 1.5755903964654797e+18,
|
| 15367 |
"train_batch_size": 4,
|
| 15368 |
"trial_name": null,
|
| 15369 |
"trial_params": null
|