Training in progress, step 3380, 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:c37a7580f76c377335564319cdd3e57107c501e9fa59c8f79f0159aa6130eeb4
|
| 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 sha256:7ee0a49cb4103b85f393a9cb147357bd12545b9f22c79efadae067c5a23920ee
|
| 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 sha256:9c55e1839d2e16a3dece8ec6c4e8f4fea2db27be5a9d62ecf7fd18477e41458f
|
| 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,
|
|
@@ -6074,6 +6074,24 @@
|
|
| 6074 |
"mean_token_accuracy": 0.6468665450811386,
|
| 6075 |
"num_tokens": 12289329.0,
|
| 6076 |
"step": 3370
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6077 |
}
|
| 6078 |
],
|
| 6079 |
"logging_steps": 5,
|
|
@@ -6093,7 +6111,7 @@
|
|
| 6093 |
"attributes": {}
|
| 6094 |
}
|
| 6095 |
},
|
| 6096 |
-
"total_flos": 6.
|
| 6097 |
"train_batch_size": 4,
|
| 6098 |
"trial_name": null,
|
| 6099 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 26.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3380,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6074 |
"mean_token_accuracy": 0.6468665450811386,
|
| 6075 |
"num_tokens": 12289329.0,
|
| 6076 |
"step": 3370
|
| 6077 |
+
},
|
| 6078 |
+
{
|
| 6079 |
+
"epoch": 25.96153846153846,
|
| 6080 |
+
"grad_norm": 0.0,
|
| 6081 |
+
"learning_rate": 3.313e-05,
|
| 6082 |
+
"loss": 1.764,
|
| 6083 |
+
"mean_token_accuracy": 0.6430284142494201,
|
| 6084 |
+
"num_tokens": 12307193.0,
|
| 6085 |
+
"step": 3375
|
| 6086 |
+
},
|
| 6087 |
+
{
|
| 6088 |
+
"epoch": 26.0,
|
| 6089 |
+
"grad_norm": 0.0,
|
| 6090 |
+
"learning_rate": 3.3105e-05,
|
| 6091 |
+
"loss": 1.6559,
|
| 6092 |
+
"mean_token_accuracy": 0.6661966532468796,
|
| 6093 |
+
"num_tokens": 12326730.0,
|
| 6094 |
+
"step": 3380
|
| 6095 |
}
|
| 6096 |
],
|
| 6097 |
"logging_steps": 5,
|
|
|
|
| 6111 |
"attributes": {}
|
| 6112 |
}
|
| 6113 |
},
|
| 6114 |
+
"total_flos": 6.245058509542195e+17,
|
| 6115 |
"train_batch_size": 4,
|
| 6116 |
"trial_name": null,
|
| 6117 |
"trial_params": null
|