Training in progress, step 6970, 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:d88629734b89e69010a72ae3e6826fcec50f317389ee54702f9f53b808a2423e
|
| 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:dcdf5ca6b5a67d27184264842e516d6620638c1e6a5613c74b34cd7efc62ef54
|
| 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:ddd2d3283ef810477c5e3ccc89778b356fdcde7335d121fb1b8c7d830d5eb815
|
| 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": 53.
|
| 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,
|
|
@@ -12536,6 +12536,24 @@
|
|
| 12536 |
"mean_token_accuracy": 0.6465272456407547,
|
| 12537 |
"num_tokens": 25382179.0,
|
| 12538 |
"step": 6960
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12539 |
}
|
| 12540 |
],
|
| 12541 |
"logging_steps": 5,
|
|
@@ -12555,7 +12573,7 @@
|
|
| 12555 |
"attributes": {}
|
| 12556 |
}
|
| 12557 |
},
|
| 12558 |
-
"total_flos": 1.
|
| 12559 |
"train_batch_size": 4,
|
| 12560 |
"trial_name": null,
|
| 12561 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 53.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6970,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12536 |
"mean_token_accuracy": 0.6465272456407547,
|
| 12537 |
"num_tokens": 25382179.0,
|
| 12538 |
"step": 6960
|
| 12539 |
+
},
|
| 12540 |
+
{
|
| 12541 |
+
"epoch": 53.57692307692308,
|
| 12542 |
+
"grad_norm": 0.0,
|
| 12543 |
+
"learning_rate": 1.518e-05,
|
| 12544 |
+
"loss": 1.7934,
|
| 12545 |
+
"mean_token_accuracy": 0.6389431089162827,
|
| 12546 |
+
"num_tokens": 25400797.0,
|
| 12547 |
+
"step": 6965
|
| 12548 |
+
},
|
| 12549 |
+
{
|
| 12550 |
+
"epoch": 53.61538461538461,
|
| 12551 |
+
"grad_norm": 0.0,
|
| 12552 |
+
"learning_rate": 1.5155e-05,
|
| 12553 |
+
"loss": 1.71,
|
| 12554 |
+
"mean_token_accuracy": 0.6540043205022812,
|
| 12555 |
+
"num_tokens": 25418880.0,
|
| 12556 |
+
"step": 6970
|
| 12557 |
}
|
| 12558 |
],
|
| 12559 |
"logging_steps": 5,
|
|
|
|
| 12573 |
"attributes": {}
|
| 12574 |
}
|
| 12575 |
},
|
| 12576 |
+
"total_flos": 1.2888028674102067e+18,
|
| 12577 |
"train_batch_size": 4,
|
| 12578 |
"trial_name": null,
|
| 12579 |
"trial_params": null
|