Training in progress, step 9030, 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 sha256:16b345b56a5411a6f46c7776ed9d58440176065685b60a376ec83d55999af27e
|
| 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:affb4d656334c864040ffb0ae0712d2115711b4410b72019a52b62fb9677287b
|
| 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 sha256:626906830975b2c6d05a3b3dab97581c8f819aceb25efcb55fb646e06fad1cc3
|
| 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": 69.
|
| 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,
|
|
@@ -16244,6 +16244,24 @@
|
|
| 16244 |
"mean_token_accuracy": 0.6564109534025192,
|
| 16245 |
"num_tokens": 32895282.0,
|
| 16246 |
"step": 9020
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16247 |
}
|
| 16248 |
],
|
| 16249 |
"logging_steps": 5,
|
|
@@ -16263,7 +16281,7 @@
|
|
| 16263 |
"attributes": {}
|
| 16264 |
}
|
| 16265 |
},
|
| 16266 |
-
"total_flos": 1.
|
| 16267 |
"train_batch_size": 4,
|
| 16268 |
"trial_name": null,
|
| 16269 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 69.46153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9030,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16244 |
"mean_token_accuracy": 0.6564109534025192,
|
| 16245 |
"num_tokens": 32895282.0,
|
| 16246 |
"step": 9020
|
| 16247 |
+
},
|
| 16248 |
+
{
|
| 16249 |
+
"epoch": 69.42307692307692,
|
| 16250 |
+
"grad_norm": 0.0,
|
| 16251 |
+
"learning_rate": 4.880000000000001e-06,
|
| 16252 |
+
"loss": 1.7273,
|
| 16253 |
+
"mean_token_accuracy": 0.6536680698394776,
|
| 16254 |
+
"num_tokens": 32912961.0,
|
| 16255 |
+
"step": 9025
|
| 16256 |
+
},
|
| 16257 |
+
{
|
| 16258 |
+
"epoch": 69.46153846153847,
|
| 16259 |
+
"grad_norm": 0.0,
|
| 16260 |
+
"learning_rate": 4.855e-06,
|
| 16261 |
+
"loss": 1.7511,
|
| 16262 |
+
"mean_token_accuracy": 0.645021739602089,
|
| 16263 |
+
"num_tokens": 32931470.0,
|
| 16264 |
+
"step": 9030
|
| 16265 |
}
|
| 16266 |
],
|
| 16267 |
"logging_steps": 5,
|
|
|
|
| 16281 |
"attributes": {}
|
| 16282 |
}
|
| 16283 |
},
|
| 16284 |
+
"total_flos": 1.669906162006917e+18,
|
| 16285 |
"train_batch_size": 4,
|
| 16286 |
"trial_name": null,
|
| 16287 |
"trial_params": null
|