Training in progress, step 1100, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d11c198de96d913ceb744ae87b53ac74dc6245baf78fcc2a8a89eda92fcaf3c
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b3e1e52fbce562e771a742f5ad6b2e697d3f0f09e728c7c268e58208f7ae300
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0629240a7d81f4909c38b7f49a61ab2a8d41f48ac717724e08827e5ebfe5e4cc
|
| 3 |
size 14645
|
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 sha256:6fe12d5a15f606fb2e4985861955b0277bfa18a91815a68a3a508e2afb1758b0
|
| 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": 0.
|
| 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,
|
|
@@ -1108,6 +1108,16 @@
|
|
| 1108 |
"mean_token_accuracy": 0.7671207025647163,
|
| 1109 |
"num_tokens": 5074269.0,
|
| 1110 |
"step": 1090
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1111 |
}
|
| 1112 |
],
|
| 1113 |
"logging_steps": 10,
|
|
@@ -1127,7 +1137,7 @@
|
|
| 1127 |
"attributes": {}
|
| 1128 |
}
|
| 1129 |
},
|
| 1130 |
-
"total_flos": 2.
|
| 1131 |
"train_batch_size": 4,
|
| 1132 |
"trial_name": null,
|
| 1133 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.23466666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1100,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1108 |
"mean_token_accuracy": 0.7671207025647163,
|
| 1109 |
"num_tokens": 5074269.0,
|
| 1110 |
"step": 1090
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"entropy": 0.9240864880383015,
|
| 1114 |
+
"epoch": 0.23466666666666666,
|
| 1115 |
+
"grad_norm": 0.23331928253173828,
|
| 1116 |
+
"learning_rate": 9.809990940509911e-05,
|
| 1117 |
+
"loss": 1.0010904312133788,
|
| 1118 |
+
"mean_token_accuracy": 0.7657159030437469,
|
| 1119 |
+
"num_tokens": 5120632.0,
|
| 1120 |
+
"step": 1100
|
| 1121 |
}
|
| 1122 |
],
|
| 1123 |
"logging_steps": 10,
|
|
|
|
| 1137 |
"attributes": {}
|
| 1138 |
}
|
| 1139 |
},
|
| 1140 |
+
"total_flos": 2.4204599567640576e+16,
|
| 1141 |
"train_batch_size": 4,
|
| 1142 |
"trial_name": null,
|
| 1143 |
"trial_params": null
|