Training in progress, step 790, 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 sha256:7615c04c9d80b9ce8518062552b9a19942d0d65eddbbd88f5b90d19842c58f48
|
| 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:d7d58b2fb1fe00accbeca9195c5e973fbbea153cd22df9c2b0c081317f0e764d
|
| 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 sha256:52d70c31e3dbdfd9003d4b338b97e5975a985dc7ab64260fa653a99444058a5a
|
| 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": 6.
|
| 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,
|
|
@@ -1412,6 +1412,24 @@
|
|
| 1412 |
"mean_token_accuracy": 0.6397966831922531,
|
| 1413 |
"num_tokens": 2844630.0,
|
| 1414 |
"step": 780
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1415 |
}
|
| 1416 |
],
|
| 1417 |
"logging_steps": 5,
|
|
@@ -1431,7 +1449,7 @@
|
|
| 1431 |
"attributes": {}
|
| 1432 |
}
|
| 1433 |
},
|
| 1434 |
-
"total_flos": 1.
|
| 1435 |
"train_batch_size": 4,
|
| 1436 |
"trial_name": null,
|
| 1437 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 790,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1412 |
"mean_token_accuracy": 0.6397966831922531,
|
| 1413 |
"num_tokens": 2844630.0,
|
| 1414 |
"step": 780
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 6.038461538461538,
|
| 1418 |
+
"grad_norm": 0.0,
|
| 1419 |
+
"learning_rate": 4.608e-05,
|
| 1420 |
+
"loss": 1.7057,
|
| 1421 |
+
"mean_token_accuracy": 0.6596891850233078,
|
| 1422 |
+
"num_tokens": 2863298.0,
|
| 1423 |
+
"step": 785
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 6.076923076923077,
|
| 1427 |
+
"grad_norm": 0.0,
|
| 1428 |
+
"learning_rate": 4.6055000000000005e-05,
|
| 1429 |
+
"loss": 1.7406,
|
| 1430 |
+
"mean_token_accuracy": 0.6515646994113922,
|
| 1431 |
+
"num_tokens": 2880896.0,
|
| 1432 |
+
"step": 790
|
| 1433 |
}
|
| 1434 |
],
|
| 1435 |
"logging_steps": 5,
|
|
|
|
| 1449 |
"attributes": {}
|
| 1450 |
}
|
| 1451 |
},
|
| 1452 |
+
"total_flos": 1.4603981899972608e+17,
|
| 1453 |
"train_batch_size": 4,
|
| 1454 |
"trial_name": null,
|
| 1455 |
"trial_params": null
|