Training in progress, step 4630, 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:c47b3616c50f8701bb66e6f8182cdb0dcd543320edc836d0be68e49a33637e70
|
| 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 sha256:81af3e3c465a2b2503f65b42a4c0fa792c5e671ee5c42d7686a9ffd06c92dd5f
|
| 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 sha256:56942615e8ecd12938813981686ea78c6fc1506144f924bdcb3ab04aa0fab360
|
| 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": 35.
|
| 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,
|
|
@@ -8324,6 +8324,24 @@
|
|
| 8324 |
"mean_token_accuracy": 0.6578234076499939,
|
| 8325 |
"num_tokens": 16848720.0,
|
| 8326 |
"step": 4620
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8327 |
}
|
| 8328 |
],
|
| 8329 |
"logging_steps": 5,
|
|
@@ -8343,7 +8361,7 @@
|
|
| 8343 |
"attributes": {}
|
| 8344 |
}
|
| 8345 |
},
|
| 8346 |
-
"total_flos": 8.
|
| 8347 |
"train_batch_size": 4,
|
| 8348 |
"trial_name": null,
|
| 8349 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 35.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4630,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8324 |
"mean_token_accuracy": 0.6578234076499939,
|
| 8325 |
"num_tokens": 16848720.0,
|
| 8326 |
"step": 4620
|
| 8327 |
+
},
|
| 8328 |
+
{
|
| 8329 |
+
"epoch": 35.57692307692308,
|
| 8330 |
+
"grad_norm": 0.0,
|
| 8331 |
+
"learning_rate": 2.688e-05,
|
| 8332 |
+
"loss": 1.6978,
|
| 8333 |
+
"mean_token_accuracy": 0.653961855173111,
|
| 8334 |
+
"num_tokens": 16867266.0,
|
| 8335 |
+
"step": 4625
|
| 8336 |
+
},
|
| 8337 |
+
{
|
| 8338 |
+
"epoch": 35.61538461538461,
|
| 8339 |
+
"grad_norm": 0.0,
|
| 8340 |
+
"learning_rate": 2.6855000000000003e-05,
|
| 8341 |
+
"loss": 1.7421,
|
| 8342 |
+
"mean_token_accuracy": 0.6451707929372787,
|
| 8343 |
+
"num_tokens": 16885165.0,
|
| 8344 |
+
"step": 4630
|
| 8345 |
}
|
| 8346 |
],
|
| 8347 |
"logging_steps": 5,
|
|
|
|
| 8361 |
"attributes": {}
|
| 8362 |
}
|
| 8363 |
},
|
| 8364 |
+
"total_flos": 8.557960989199565e+17,
|
| 8365 |
"train_batch_size": 4,
|
| 8366 |
"trial_name": null,
|
| 8367 |
"trial_params": null
|