Training in progress, step 3640, 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 sha256:8b4a1d4527eafea5417b2b98945a2b7bca210f14261e672769bfec42800eec21
|
| 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 sha256:5e4b1a745bb39215ef840f1aa961a64ac65b209816b3f6f91e93d74749ca90fe
|
| 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 sha256:9efca231bb925e4e88984bdc430942bb99b028015692e6d27cb0b7c0394c4950
|
| 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 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -6542,6 +6542,24 @@
|
|
| 6542 |
"mean_token_accuracy": 0.6449559360742569,
|
| 6543 |
"num_tokens": 13238217.0,
|
| 6544 |
"step": 3630
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6545 |
}
|
| 6546 |
],
|
| 6547 |
"logging_steps": 5,
|
|
@@ -6561,7 +6579,7 @@
|
|
| 6561 |
"attributes": {}
|
| 6562 |
}
|
| 6563 |
},
|
| 6564 |
-
"total_flos": 6.
|
| 6565 |
"train_batch_size": 4,
|
| 6566 |
"trial_name": null,
|
| 6567 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 28.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3640,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6542 |
"mean_token_accuracy": 0.6449559360742569,
|
| 6543 |
"num_tokens": 13238217.0,
|
| 6544 |
"step": 3630
|
| 6545 |
+
},
|
| 6546 |
+
{
|
| 6547 |
+
"epoch": 27.96153846153846,
|
| 6548 |
+
"grad_norm": 0.0,
|
| 6549 |
+
"learning_rate": 3.1830000000000005e-05,
|
| 6550 |
+
"loss": 1.7167,
|
| 6551 |
+
"mean_token_accuracy": 0.6618435323238373,
|
| 6552 |
+
"num_tokens": 13256740.0,
|
| 6553 |
+
"step": 3635
|
| 6554 |
+
},
|
| 6555 |
+
{
|
| 6556 |
+
"epoch": 28.0,
|
| 6557 |
+
"grad_norm": 0.0,
|
| 6558 |
+
"learning_rate": 3.1805000000000005e-05,
|
| 6559 |
+
"loss": 1.723,
|
| 6560 |
+
"mean_token_accuracy": 0.6585237294435501,
|
| 6561 |
+
"num_tokens": 13274940.0,
|
| 6562 |
+
"step": 3640
|
| 6563 |
}
|
| 6564 |
],
|
| 6565 |
"logging_steps": 5,
|
|
|
|
| 6579 |
"attributes": {}
|
| 6580 |
}
|
| 6581 |
},
|
| 6582 |
+
"total_flos": 6.726635660088115e+17,
|
| 6583 |
"train_batch_size": 4,
|
| 6584 |
"trial_name": null,
|
| 6585 |
"trial_params": null
|