Training in progress, step 6290, 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 sha256:3b782aa4bda985a39ec676fc44d341bf8e305c7a2f890539bf6d9a9f31e27ba8
|
| 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 sha256:6458c1b56bda3af89b3944a88d2b6e8227c45d203fac11c3cfa0c0f9aa528af4
|
| 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:bc465ff5d331645b8a8ceccfb43ad16666d26cd57e99bccbdf3ae1b6ddf3637f
|
| 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": 48.
|
| 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,
|
|
@@ -11312,6 +11312,24 @@
|
|
| 11312 |
"mean_token_accuracy": 0.6414877325296402,
|
| 11313 |
"num_tokens": 22902483.0,
|
| 11314 |
"step": 6280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11315 |
}
|
| 11316 |
],
|
| 11317 |
"logging_steps": 5,
|
|
@@ -11331,7 +11349,7 @@
|
|
| 11331 |
"attributes": {}
|
| 11332 |
}
|
| 11333 |
},
|
| 11334 |
-
"total_flos": 1.
|
| 11335 |
"train_batch_size": 4,
|
| 11336 |
"trial_name": null,
|
| 11337 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 48.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6290,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11312 |
"mean_token_accuracy": 0.6414877325296402,
|
| 11313 |
"num_tokens": 22902483.0,
|
| 11314 |
"step": 6280
|
| 11315 |
+
},
|
| 11316 |
+
{
|
| 11317 |
+
"epoch": 48.34615384615385,
|
| 11318 |
+
"grad_norm": 0.0,
|
| 11319 |
+
"learning_rate": 1.858e-05,
|
| 11320 |
+
"loss": 1.7391,
|
| 11321 |
+
"mean_token_accuracy": 0.6488156080245971,
|
| 11322 |
+
"num_tokens": 22921114.0,
|
| 11323 |
+
"step": 6285
|
| 11324 |
+
},
|
| 11325 |
+
{
|
| 11326 |
+
"epoch": 48.38461538461539,
|
| 11327 |
+
"grad_norm": 0.0,
|
| 11328 |
+
"learning_rate": 1.8555e-05,
|
| 11329 |
+
"loss": 1.7538,
|
| 11330 |
+
"mean_token_accuracy": 0.6502360552549362,
|
| 11331 |
+
"num_tokens": 22938888.0,
|
| 11332 |
+
"step": 6290
|
| 11333 |
}
|
| 11334 |
],
|
| 11335 |
"logging_steps": 5,
|
|
|
|
| 11349 |
"attributes": {}
|
| 11350 |
}
|
| 11351 |
},
|
| 11352 |
+
"total_flos": 1.1627477856519782e+18,
|
| 11353 |
"train_batch_size": 4,
|
| 11354 |
"trial_name": null,
|
| 11355 |
"trial_params": null
|