Training in progress, step 8000, 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:b517c76540318ca23786b652aafde62d4bdf8d854c2ccca593c403c041593c71
|
| 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 sha256:3fc3a763445ee6ec85abe96d6e69004782fbf0364e986a2224fc09bf65c0dd15
|
| 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:b22116fbe60fe2fe3e5d6133fc3a734aa188efddbd79301c7c1367a0685c2a30
|
| 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,
|
|
@@ -14390,6 +14390,24 @@
|
|
| 14390 |
"mean_token_accuracy": 0.6455101191997528,
|
| 14391 |
"num_tokens": 29137065.0,
|
| 14392 |
"step": 7990
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14393 |
}
|
| 14394 |
],
|
| 14395 |
"logging_steps": 5,
|
|
@@ -14409,7 +14427,7 @@
|
|
| 14409 |
"attributes": {}
|
| 14410 |
}
|
| 14411 |
},
|
| 14412 |
-
"total_flos": 1.
|
| 14413 |
"train_batch_size": 4,
|
| 14414 |
"trial_name": null,
|
| 14415 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 61.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14390 |
"mean_token_accuracy": 0.6455101191997528,
|
| 14391 |
"num_tokens": 29137065.0,
|
| 14392 |
"step": 7990
|
| 14393 |
+
},
|
| 14394 |
+
{
|
| 14395 |
+
"epoch": 61.5,
|
| 14396 |
+
"grad_norm": 0.0,
|
| 14397 |
+
"learning_rate": 1.003e-05,
|
| 14398 |
+
"loss": 1.7622,
|
| 14399 |
+
"mean_token_accuracy": 0.6454584419727325,
|
| 14400 |
+
"num_tokens": 29156036.0,
|
| 14401 |
+
"step": 7995
|
| 14402 |
+
},
|
| 14403 |
+
{
|
| 14404 |
+
"epoch": 61.53846153846154,
|
| 14405 |
+
"grad_norm": 0.0,
|
| 14406 |
+
"learning_rate": 1.0005e-05,
|
| 14407 |
+
"loss": 1.7365,
|
| 14408 |
+
"mean_token_accuracy": 0.6461439549922943,
|
| 14409 |
+
"num_tokens": 29174330.0,
|
| 14410 |
+
"step": 8000
|
| 14411 |
}
|
| 14412 |
],
|
| 14413 |
"logging_steps": 5,
|
|
|
|
| 14427 |
"attributes": {}
|
| 14428 |
}
|
| 14429 |
},
|
| 14430 |
+
"total_flos": 1.479183192009769e+18,
|
| 14431 |
"train_batch_size": 4,
|
| 14432 |
"trial_name": null,
|
| 14433 |
"trial_params": null
|