Training in progress, step 6890, 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 sha256:79428d9de019e3e7b5b058514d99ee3ea1d9f838341410a673605223e00a0730
|
| 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:cb5e7c981d3c56825963e462737c58cbc593c86a90a89af00041aa0b08158b65
|
| 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 sha256:1a7d62ea5c3dc200d58ceda5cfa41ac0e0aa32330ae60cc7ce909460239e4e50
|
| 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":
|
| 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,
|
|
@@ -12392,6 +12392,24 @@
|
|
| 12392 |
"mean_token_accuracy": 0.6448877215385437,
|
| 12393 |
"num_tokens": 25092178.0,
|
| 12394 |
"step": 6880
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12395 |
}
|
| 12396 |
],
|
| 12397 |
"logging_steps": 5,
|
|
@@ -12411,7 +12429,7 @@
|
|
| 12411 |
"attributes": {}
|
| 12412 |
}
|
| 12413 |
},
|
| 12414 |
-
"total_flos": 1.
|
| 12415 |
"train_batch_size": 4,
|
| 12416 |
"trial_name": null,
|
| 12417 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 53.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6890,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12392 |
"mean_token_accuracy": 0.6448877215385437,
|
| 12393 |
"num_tokens": 25092178.0,
|
| 12394 |
"step": 6880
|
| 12395 |
+
},
|
| 12396 |
+
{
|
| 12397 |
+
"epoch": 52.96153846153846,
|
| 12398 |
+
"grad_norm": 0.0,
|
| 12399 |
+
"learning_rate": 1.558e-05,
|
| 12400 |
+
"loss": 1.7896,
|
| 12401 |
+
"mean_token_accuracy": 0.6419251203536988,
|
| 12402 |
+
"num_tokens": 25109978.0,
|
| 12403 |
+
"step": 6885
|
| 12404 |
+
},
|
| 12405 |
+
{
|
| 12406 |
+
"epoch": 53.0,
|
| 12407 |
+
"grad_norm": 0.0,
|
| 12408 |
+
"learning_rate": 1.5555e-05,
|
| 12409 |
+
"loss": 1.8081,
|
| 12410 |
+
"mean_token_accuracy": 0.6363903671503067,
|
| 12411 |
+
"num_tokens": 25127565.0,
|
| 12412 |
+
"step": 6890
|
| 12413 |
}
|
| 12414 |
],
|
| 12415 |
"logging_steps": 5,
|
|
|
|
| 12429 |
"attributes": {}
|
| 12430 |
}
|
| 12431 |
},
|
| 12432 |
+
"total_flos": 1.2740132250545357e+18,
|
| 12433 |
"train_batch_size": 4,
|
| 12434 |
"trial_name": null,
|
| 12435 |
"trial_params": null
|