Training in progress, step 5240, 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:ef12489c25d4378f162d86e6f3b1ae8a2cd50947e8228bab04038db8d1010cb0
|
| 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 sha256:4a14aef6b86a7ffe3fe0ed965fffb503c0d81824ba0c4998628504511898aa05
|
| 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 sha256:4e6dabf067e3c709da212c1fe583ba36cb2d2b98cb3b85a3eb1b4c2cf5462b4f
|
| 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": 40.
|
| 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,
|
|
@@ -9422,6 +9422,24 @@
|
|
| 9422 |
"mean_token_accuracy": 0.634826073050499,
|
| 9423 |
"num_tokens": 19071438.0,
|
| 9424 |
"step": 5230
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9425 |
}
|
| 9426 |
],
|
| 9427 |
"logging_steps": 5,
|
|
@@ -9441,7 +9459,7 @@
|
|
| 9441 |
"attributes": {}
|
| 9442 |
}
|
| 9443 |
},
|
| 9444 |
-
"total_flos": 9.
|
| 9445 |
"train_batch_size": 4,
|
| 9446 |
"trial_name": null,
|
| 9447 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 40.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5240,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9422 |
"mean_token_accuracy": 0.634826073050499,
|
| 9423 |
"num_tokens": 19071438.0,
|
| 9424 |
"step": 5230
|
| 9425 |
+
},
|
| 9426 |
+
{
|
| 9427 |
+
"epoch": 40.26923076923077,
|
| 9428 |
+
"grad_norm": 0.0,
|
| 9429 |
+
"learning_rate": 2.3830000000000004e-05,
|
| 9430 |
+
"loss": 1.7791,
|
| 9431 |
+
"mean_token_accuracy": 0.641825932264328,
|
| 9432 |
+
"num_tokens": 19089581.0,
|
| 9433 |
+
"step": 5235
|
| 9434 |
+
},
|
| 9435 |
+
{
|
| 9436 |
+
"epoch": 40.30769230769231,
|
| 9437 |
+
"grad_norm": 0.0,
|
| 9438 |
+
"learning_rate": 2.3805000000000003e-05,
|
| 9439 |
+
"loss": 1.7551,
|
| 9440 |
+
"mean_token_accuracy": 0.651043924689293,
|
| 9441 |
+
"num_tokens": 19107710.0,
|
| 9442 |
+
"step": 5240
|
| 9443 |
}
|
| 9444 |
],
|
| 9445 |
"logging_steps": 5,
|
|
|
|
| 9459 |
"attributes": {}
|
| 9460 |
}
|
| 9461 |
},
|
| 9462 |
+
"total_flos": 9.682423788331008e+17,
|
| 9463 |
"train_batch_size": 4,
|
| 9464 |
"trial_name": null,
|
| 9465 |
"trial_params": null
|