Training in progress, step 8540, 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 sha256:66489519c5f7b23707827b5637d851db06e9dbff2bfc17628caa4cd487bba26e
|
| 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 sha256:2c202a1a0ae11fe69c3e64d8a4d476cbe937d8a79d923140c57e265355e33eb2
|
| 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:cd29ceda718e2975fc29cb2f5042265089f2d837222d271d176a730c965be212
|
| 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,
|
|
@@ -15362,6 +15362,24 @@
|
|
| 15362 |
"mean_token_accuracy": 0.6394985377788543,
|
| 15363 |
"num_tokens": 31110126.0,
|
| 15364 |
"step": 8530
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15365 |
}
|
| 15366 |
],
|
| 15367 |
"logging_steps": 5,
|
|
@@ -15381,7 +15399,7 @@
|
|
| 15381 |
"attributes": {}
|
| 15382 |
}
|
| 15383 |
},
|
| 15384 |
-
"total_flos": 1.
|
| 15385 |
"train_batch_size": 4,
|
| 15386 |
"trial_name": null,
|
| 15387 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 65.6923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8540,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15362 |
"mean_token_accuracy": 0.6394985377788543,
|
| 15363 |
"num_tokens": 31110126.0,
|
| 15364 |
"step": 8530
|
| 15365 |
+
},
|
| 15366 |
+
{
|
| 15367 |
+
"epoch": 65.65384615384616,
|
| 15368 |
+
"grad_norm": 0.0,
|
| 15369 |
+
"learning_rate": 7.330000000000001e-06,
|
| 15370 |
+
"loss": 1.7496,
|
| 15371 |
+
"mean_token_accuracy": 0.6522016197443008,
|
| 15372 |
+
"num_tokens": 31128158.0,
|
| 15373 |
+
"step": 8535
|
| 15374 |
+
},
|
| 15375 |
+
{
|
| 15376 |
+
"epoch": 65.6923076923077,
|
| 15377 |
+
"grad_norm": 0.0,
|
| 15378 |
+
"learning_rate": 7.305e-06,
|
| 15379 |
+
"loss": 1.7608,
|
| 15380 |
+
"mean_token_accuracy": 0.6444296389818192,
|
| 15381 |
+
"num_tokens": 31146338.0,
|
| 15382 |
+
"step": 8540
|
| 15383 |
}
|
| 15384 |
],
|
| 15385 |
"logging_steps": 5,
|
|
|
|
| 15399 |
"attributes": {}
|
| 15400 |
}
|
| 15401 |
},
|
| 15402 |
+
"total_flos": 1.5792602588725248e+18,
|
| 15403 |
"train_batch_size": 4,
|
| 15404 |
"trial_name": null,
|
| 15405 |
"trial_params": null
|