Training in progress, step 7470, 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 sha256:9dd39578bc5a26902161484e911ca1e7a8adbd60835821377f732e859d8cab68
|
| 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 sha256:86533c357352fcffbd6e68d0bb4c9dfdac7f384551b523f3f0e9aeb260814d3c
|
| 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:db44cb4941a74e9782a93b606a879a728fec4b533ea17f234d19bbbc4ac5f65c
|
| 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": 57.
|
| 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,
|
|
@@ -13436,6 +13436,24 @@
|
|
| 13436 |
"mean_token_accuracy": 0.6489328056573868,
|
| 13437 |
"num_tokens": 27207207.0,
|
| 13438 |
"step": 7460
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13439 |
}
|
| 13440 |
],
|
| 13441 |
"logging_steps": 5,
|
|
@@ -13455,7 +13473,7 @@
|
|
| 13455 |
"attributes": {}
|
| 13456 |
}
|
| 13457 |
},
|
| 13458 |
-
"total_flos": 1.
|
| 13459 |
"train_batch_size": 4,
|
| 13460 |
"trial_name": null,
|
| 13461 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 57.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7470,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13436 |
"mean_token_accuracy": 0.6489328056573868,
|
| 13437 |
"num_tokens": 27207207.0,
|
| 13438 |
"step": 7460
|
| 13439 |
+
},
|
| 13440 |
+
{
|
| 13441 |
+
"epoch": 57.42307692307692,
|
| 13442 |
+
"grad_norm": 0.0,
|
| 13443 |
+
"learning_rate": 1.268e-05,
|
| 13444 |
+
"loss": 1.7531,
|
| 13445 |
+
"mean_token_accuracy": 0.6518824428319931,
|
| 13446 |
+
"num_tokens": 27225139.0,
|
| 13447 |
+
"step": 7465
|
| 13448 |
+
},
|
| 13449 |
+
{
|
| 13450 |
+
"epoch": 57.46153846153846,
|
| 13451 |
+
"grad_norm": 0.0,
|
| 13452 |
+
"learning_rate": 1.2655e-05,
|
| 13453 |
+
"loss": 1.7544,
|
| 13454 |
+
"mean_token_accuracy": 0.6468398660421372,
|
| 13455 |
+
"num_tokens": 27243113.0,
|
| 13456 |
+
"step": 7470
|
| 13457 |
}
|
| 13458 |
],
|
| 13459 |
"logging_steps": 5,
|
|
|
|
| 13473 |
"attributes": {}
|
| 13474 |
}
|
| 13475 |
},
|
| 13476 |
+
"total_flos": 1.3813055338807296e+18,
|
| 13477 |
"train_batch_size": 4,
|
| 13478 |
"trial_name": null,
|
| 13479 |
"trial_params": null
|