Training in progress, step 9040, 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 sha256:54becf4aecd7c397cee7278a8f679c1e65d95a78d697f4f36e93c997664740fe
|
| 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:eef05c33a2490f87d04e0082c2bfa8a088200ac8e26761cdeebeb7ff2d823e37
|
| 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:bd8a8a707c57496a9a259b9ab12002294d7189fc69670588728576fa35ec146c
|
| 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,
|
|
@@ -16262,6 +16262,24 @@
|
|
| 16262 |
"mean_token_accuracy": 0.645021739602089,
|
| 16263 |
"num_tokens": 32931470.0,
|
| 16264 |
"step": 9030
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16265 |
}
|
| 16266 |
],
|
| 16267 |
"logging_steps": 5,
|
|
@@ -16281,7 +16299,7 @@
|
|
| 16281 |
"attributes": {}
|
| 16282 |
}
|
| 16283 |
},
|
| 16284 |
-
"total_flos": 1.
|
| 16285 |
"train_batch_size": 4,
|
| 16286 |
"trial_name": null,
|
| 16287 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 69.53846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9040,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16262 |
"mean_token_accuracy": 0.645021739602089,
|
| 16263 |
"num_tokens": 32931470.0,
|
| 16264 |
"step": 9030
|
| 16265 |
+
},
|
| 16266 |
+
{
|
| 16267 |
+
"epoch": 69.5,
|
| 16268 |
+
"grad_norm": 0.0,
|
| 16269 |
+
"learning_rate": 4.83e-06,
|
| 16270 |
+
"loss": 1.8157,
|
| 16271 |
+
"mean_token_accuracy": 0.6354044616222382,
|
| 16272 |
+
"num_tokens": 32949088.0,
|
| 16273 |
+
"step": 9035
|
| 16274 |
+
},
|
| 16275 |
+
{
|
| 16276 |
+
"epoch": 69.53846153846153,
|
| 16277 |
+
"grad_norm": 0.0,
|
| 16278 |
+
"learning_rate": 4.805000000000001e-06,
|
| 16279 |
+
"loss": 1.7142,
|
| 16280 |
+
"mean_token_accuracy": 0.6553671360015869,
|
| 16281 |
+
"num_tokens": 32967668.0,
|
| 16282 |
+
"step": 9040
|
| 16283 |
}
|
| 16284 |
],
|
| 16285 |
"logging_steps": 5,
|
|
|
|
| 16299 |
"attributes": {}
|
| 16300 |
}
|
| 16301 |
},
|
| 16302 |
+
"total_flos": 1.6717210076484403e+18,
|
| 16303 |
"train_batch_size": 4,
|
| 16304 |
"trial_name": null,
|
| 16305 |
"trial_params": null
|