Training in progress, step 8010, 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 sha256:85789479d4a128d30058d7c69ce8613b8d73665d4a1917d16131b7e5e07bc3db
|
| 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:f638e2a8d4d048597a96e2ebc08ee66743f17cc92bf9e9b52869a2f27d69333f
|
| 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:f414d349759eba8725bf96e39205ffd7c644ec4880a6e4ece35c0e125b8c285c
|
| 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": 61.
|
| 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,
|
|
@@ -14408,6 +14408,24 @@
|
|
| 14408 |
"mean_token_accuracy": 0.6461439549922943,
|
| 14409 |
"num_tokens": 29174330.0,
|
| 14410 |
"step": 8000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14411 |
}
|
| 14412 |
],
|
| 14413 |
"logging_steps": 5,
|
|
@@ -14427,7 +14445,7 @@
|
|
| 14427 |
"attributes": {}
|
| 14428 |
}
|
| 14429 |
},
|
| 14430 |
-
"total_flos": 1.
|
| 14431 |
"train_batch_size": 4,
|
| 14432 |
"trial_name": null,
|
| 14433 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 61.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8010,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14408 |
"mean_token_accuracy": 0.6461439549922943,
|
| 14409 |
"num_tokens": 29174330.0,
|
| 14410 |
"step": 8000
|
| 14411 |
+
},
|
| 14412 |
+
{
|
| 14413 |
+
"epoch": 61.57692307692308,
|
| 14414 |
+
"grad_norm": 0.0,
|
| 14415 |
+
"learning_rate": 9.980000000000001e-06,
|
| 14416 |
+
"loss": 1.7046,
|
| 14417 |
+
"mean_token_accuracy": 0.661187008023262,
|
| 14418 |
+
"num_tokens": 29192595.0,
|
| 14419 |
+
"step": 8005
|
| 14420 |
+
},
|
| 14421 |
+
{
|
| 14422 |
+
"epoch": 61.61538461538461,
|
| 14423 |
+
"grad_norm": 0.0,
|
| 14424 |
+
"learning_rate": 9.955e-06,
|
| 14425 |
+
"loss": 1.6992,
|
| 14426 |
+
"mean_token_accuracy": 0.6574147075414658,
|
| 14427 |
+
"num_tokens": 29211106.0,
|
| 14428 |
+
"step": 8010
|
| 14429 |
}
|
| 14430 |
],
|
| 14431 |
"logging_steps": 5,
|
|
|
|
| 14445 |
"attributes": {}
|
| 14446 |
}
|
| 14447 |
},
|
| 14448 |
+
"total_flos": 1.4810140743450624e+18,
|
| 14449 |
"train_batch_size": 4,
|
| 14450 |
"trial_name": null,
|
| 14451 |
"trial_params": null
|