Training in progress, step 6200, 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:f3d25e508891c7d9de23918cf202120eb36c3fb791ebd9802524e30c3508ef50
|
| 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 sha256:3eb16fbc6ff9ccbca0f39cf7de85175db50b47aa4c146f75e5af210db51c1819
|
| 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:ab49a7b8b6369ffe0208e7f23e4e214225a45f7bb0648ad79c2174cd44d21258
|
| 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,
|
|
@@ -11150,6 +11150,24 @@
|
|
| 11150 |
"mean_token_accuracy": 0.6529056757688523,
|
| 11151 |
"num_tokens": 22576706.0,
|
| 11152 |
"step": 6190
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11153 |
}
|
| 11154 |
],
|
| 11155 |
"logging_steps": 5,
|
|
@@ -11169,7 +11187,7 @@
|
|
| 11169 |
"attributes": {}
|
| 11170 |
}
|
| 11171 |
},
|
| 11172 |
-
"total_flos": 1.
|
| 11173 |
"train_batch_size": 4,
|
| 11174 |
"trial_name": null,
|
| 11175 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 47.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11150 |
"mean_token_accuracy": 0.6529056757688523,
|
| 11151 |
"num_tokens": 22576706.0,
|
| 11152 |
"step": 6190
|
| 11153 |
+
},
|
| 11154 |
+
{
|
| 11155 |
+
"epoch": 47.65384615384615,
|
| 11156 |
+
"grad_norm": 0.0,
|
| 11157 |
+
"learning_rate": 1.903e-05,
|
| 11158 |
+
"loss": 1.7892,
|
| 11159 |
+
"mean_token_accuracy": 0.6409416913986206,
|
| 11160 |
+
"num_tokens": 22594485.0,
|
| 11161 |
+
"step": 6195
|
| 11162 |
+
},
|
| 11163 |
+
{
|
| 11164 |
+
"epoch": 47.69230769230769,
|
| 11165 |
+
"grad_norm": 0.0,
|
| 11166 |
+
"learning_rate": 1.9005000000000002e-05,
|
| 11167 |
+
"loss": 1.6885,
|
| 11168 |
+
"mean_token_accuracy": 0.6648684412240982,
|
| 11169 |
+
"num_tokens": 22613662.0,
|
| 11170 |
+
"step": 6200
|
| 11171 |
}
|
| 11172 |
],
|
| 11173 |
"logging_steps": 5,
|
|
|
|
| 11187 |
"attributes": {}
|
| 11188 |
}
|
| 11189 |
},
|
| 11190 |
+
"total_flos": 1.1462715912049459e+18,
|
| 11191 |
"train_batch_size": 4,
|
| 11192 |
"trial_name": null,
|
| 11193 |
"trial_params": null
|