Training in progress, step 7630, 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 sha256:38fd5b11122d80adec3e9ca07181cfc1342ce4070c45fb7ebfdf14ed44f3e41f
|
| 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 sha256:72d77a3ccc153ef6292c9b6b0dbe77ec67f4469279b92636836c707cc6c9f56f
|
| 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 sha256:8514ec2cd4113b80a319b202598ec2bd9311dcb53369ae5fa50dd4526eb90c94
|
| 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": 58.
|
| 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,
|
|
@@ -13724,6 +13724,24 @@
|
|
| 13724 |
"mean_token_accuracy": 0.676550367474556,
|
| 13725 |
"num_tokens": 27788253.0,
|
| 13726 |
"step": 7620
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13727 |
}
|
| 13728 |
],
|
| 13729 |
"logging_steps": 5,
|
|
@@ -13743,7 +13761,7 @@
|
|
| 13743 |
"attributes": {}
|
| 13744 |
}
|
| 13745 |
},
|
| 13746 |
-
"total_flos": 1.
|
| 13747 |
"train_batch_size": 4,
|
| 13748 |
"trial_name": null,
|
| 13749 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 58.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7630,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13724 |
"mean_token_accuracy": 0.676550367474556,
|
| 13725 |
"num_tokens": 27788253.0,
|
| 13726 |
"step": 7620
|
| 13727 |
+
},
|
| 13728 |
+
{
|
| 13729 |
+
"epoch": 58.65384615384615,
|
| 13730 |
+
"grad_norm": 0.0,
|
| 13731 |
+
"learning_rate": 1.1880000000000001e-05,
|
| 13732 |
+
"loss": 1.7219,
|
| 13733 |
+
"mean_token_accuracy": 0.6493042975664138,
|
| 13734 |
+
"num_tokens": 27807507.0,
|
| 13735 |
+
"step": 7625
|
| 13736 |
+
},
|
| 13737 |
+
{
|
| 13738 |
+
"epoch": 58.69230769230769,
|
| 13739 |
+
"grad_norm": 0.0,
|
| 13740 |
+
"learning_rate": 1.1855e-05,
|
| 13741 |
+
"loss": 1.7596,
|
| 13742 |
+
"mean_token_accuracy": 0.6421011120080948,
|
| 13743 |
+
"num_tokens": 27825718.0,
|
| 13744 |
+
"step": 7630
|
| 13745 |
}
|
| 13746 |
],
|
| 13747 |
"logging_steps": 5,
|
|
|
|
| 13761 |
"attributes": {}
|
| 13762 |
}
|
| 13763 |
},
|
| 13764 |
+
"total_flos": 1.410763352545198e+18,
|
| 13765 |
"train_batch_size": 4,
|
| 13766 |
"trial_name": null,
|
| 13767 |
"trial_params": null
|