Training in progress, step 6180, 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:afeaa2378e9a91cc88e840c3a8e08f7b33cfbad47f38741a9bd105fe7dd4cb6e
|
| 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 sha256:2fe13f01a5bb6b75b0dfac947dd0116faa60eafbd2313fab1610bd7b16c40b8e
|
| 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:ae1e131df88558415de649e3396bc90c4c3cd06d9868b563d7267d23679826bb
|
| 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": 47.
|
| 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,
|
|
@@ -11114,6 +11114,24 @@
|
|
| 11114 |
"mean_token_accuracy": 0.6439648687839508,
|
| 11115 |
"num_tokens": 22504172.0,
|
| 11116 |
"step": 6170
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11117 |
}
|
| 11118 |
],
|
| 11119 |
"logging_steps": 5,
|
|
@@ -11133,7 +11151,7 @@
|
|
| 11133 |
"attributes": {}
|
| 11134 |
}
|
| 11135 |
},
|
| 11136 |
-
"total_flos": 1.
|
| 11137 |
"train_batch_size": 4,
|
| 11138 |
"trial_name": null,
|
| 11139 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 47.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6180,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11114 |
"mean_token_accuracy": 0.6439648687839508,
|
| 11115 |
"num_tokens": 22504172.0,
|
| 11116 |
"step": 6170
|
| 11117 |
+
},
|
| 11118 |
+
{
|
| 11119 |
+
"epoch": 47.5,
|
| 11120 |
+
"grad_norm": 0.0,
|
| 11121 |
+
"learning_rate": 1.913e-05,
|
| 11122 |
+
"loss": 1.7398,
|
| 11123 |
+
"mean_token_accuracy": 0.6509507864713668,
|
| 11124 |
+
"num_tokens": 22521860.0,
|
| 11125 |
+
"step": 6175
|
| 11126 |
+
},
|
| 11127 |
+
{
|
| 11128 |
+
"epoch": 47.53846153846154,
|
| 11129 |
+
"grad_norm": 0.0,
|
| 11130 |
+
"learning_rate": 1.9105e-05,
|
| 11131 |
+
"loss": 1.7535,
|
| 11132 |
+
"mean_token_accuracy": 0.6506534874439239,
|
| 11133 |
+
"num_tokens": 22539795.0,
|
| 11134 |
+
"step": 6180
|
| 11135 |
}
|
| 11136 |
],
|
| 11137 |
"logging_steps": 5,
|
|
|
|
| 11151 |
"attributes": {}
|
| 11152 |
}
|
| 11153 |
},
|
| 11154 |
+
"total_flos": 1.1424256427247206e+18,
|
| 11155 |
"train_batch_size": 4,
|
| 11156 |
"trial_name": null,
|
| 11157 |
"trial_params": null
|