Training in progress, step 9090, 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 sha256:7f7340a5f2f9c9fa22c1ff4ccedd0acd9100bd99b630110811e69aa5e3cc771d
|
| 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 sha256:84cd0310219fb049a3c906ac6b80c473720e46bcaa334c17a303ecd175bbeb46
|
| 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 sha256:4ff6c6538f1626748ecf40fa510189aba6c75fe793887bf3af34037a6bd1e98c
|
| 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": 69.
|
| 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,
|
|
@@ -16352,6 +16352,24 @@
|
|
| 16352 |
"mean_token_accuracy": 0.6580096065998078,
|
| 16353 |
"num_tokens": 33113524.0,
|
| 16354 |
"step": 9080
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16355 |
}
|
| 16356 |
],
|
| 16357 |
"logging_steps": 5,
|
|
@@ -16371,7 +16389,7 @@
|
|
| 16371 |
"attributes": {}
|
| 16372 |
}
|
| 16373 |
},
|
| 16374 |
-
"total_flos": 1.
|
| 16375 |
"train_batch_size": 4,
|
| 16376 |
"trial_name": null,
|
| 16377 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 69.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9090,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16352 |
"mean_token_accuracy": 0.6580096065998078,
|
| 16353 |
"num_tokens": 33113524.0,
|
| 16354 |
"step": 9080
|
| 16355 |
+
},
|
| 16356 |
+
{
|
| 16357 |
+
"epoch": 69.88461538461539,
|
| 16358 |
+
"grad_norm": 0.0,
|
| 16359 |
+
"learning_rate": 4.58e-06,
|
| 16360 |
+
"loss": 1.7544,
|
| 16361 |
+
"mean_token_accuracy": 0.6489035278558731,
|
| 16362 |
+
"num_tokens": 33131870.0,
|
| 16363 |
+
"step": 9085
|
| 16364 |
+
},
|
| 16365 |
+
{
|
| 16366 |
+
"epoch": 69.92307692307692,
|
| 16367 |
+
"grad_norm": 0.0,
|
| 16368 |
+
"learning_rate": 4.5550000000000004e-06,
|
| 16369 |
+
"loss": 1.7172,
|
| 16370 |
+
"mean_token_accuracy": 0.6561585962772369,
|
| 16371 |
+
"num_tokens": 33150722.0,
|
| 16372 |
+
"step": 9090
|
| 16373 |
}
|
| 16374 |
],
|
| 16375 |
"logging_steps": 5,
|
|
|
|
| 16389 |
"attributes": {}
|
| 16390 |
}
|
| 16391 |
},
|
| 16392 |
+
"total_flos": 1.681000060954706e+18,
|
| 16393 |
"train_batch_size": 4,
|
| 16394 |
"trial_name": null,
|
| 16395 |
"trial_params": null
|