Training in progress, step 6820, 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:c31fa48bdcc8a58023b75d40d4f7f3837ce1b8fd6910d814fba77b20f113b731
|
| 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:a3ea81cc85c2a65dcf124c2d90f45b0340f273bb5053ccf5f76fd1d138d19b56
|
| 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:c2ff0e5ff0000d0eeb2e9eaf88e7c4d292ab945545b13e366d636e20732f40a3
|
| 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": 52.
|
| 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,
|
|
@@ -12266,6 +12266,24 @@
|
|
| 12266 |
"mean_token_accuracy": 0.6593423992395401,
|
| 12267 |
"num_tokens": 24837669.0,
|
| 12268 |
"step": 6810
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12269 |
}
|
| 12270 |
],
|
| 12271 |
"logging_steps": 5,
|
|
@@ -12285,7 +12303,7 @@
|
|
| 12285 |
"attributes": {}
|
| 12286 |
}
|
| 12287 |
},
|
| 12288 |
-
"total_flos": 1.
|
| 12289 |
"train_batch_size": 4,
|
| 12290 |
"trial_name": null,
|
| 12291 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 52.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6820,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12266 |
"mean_token_accuracy": 0.6593423992395401,
|
| 12267 |
"num_tokens": 24837669.0,
|
| 12268 |
"step": 6810
|
| 12269 |
+
},
|
| 12270 |
+
{
|
| 12271 |
+
"epoch": 52.42307692307692,
|
| 12272 |
+
"grad_norm": 0.0,
|
| 12273 |
+
"learning_rate": 1.593e-05,
|
| 12274 |
+
"loss": 1.7498,
|
| 12275 |
+
"mean_token_accuracy": 0.6527423232793808,
|
| 12276 |
+
"num_tokens": 24855694.0,
|
| 12277 |
+
"step": 6815
|
| 12278 |
+
},
|
| 12279 |
+
{
|
| 12280 |
+
"epoch": 52.46153846153846,
|
| 12281 |
+
"grad_norm": 0.0,
|
| 12282 |
+
"learning_rate": 1.5905e-05,
|
| 12283 |
+
"loss": 1.7311,
|
| 12284 |
+
"mean_token_accuracy": 0.6554641664028168,
|
| 12285 |
+
"num_tokens": 24874368.0,
|
| 12286 |
+
"step": 6820
|
| 12287 |
}
|
| 12288 |
],
|
| 12289 |
"logging_steps": 5,
|
|
|
|
| 12303 |
"attributes": {}
|
| 12304 |
}
|
| 12305 |
},
|
| 12306 |
+
"total_flos": 1.2611810120137114e+18,
|
| 12307 |
"train_batch_size": 4,
|
| 12308 |
"trial_name": null,
|
| 12309 |
"trial_params": null
|