Training in progress, step 4160, 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 sha256:8be2b0a1656fc6940a40d62692307720f9de3724353cdd7d08f5d2e813ce8d0c
|
| 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 sha256:2bb9f9f4e5400c76cbdbd2531551ddc041db61e498e18f3a16f266aa68ef1578
|
| 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:ebe2c21b4c74404917b710ce4a4399f22d3bdc7f2e1f67c6752fee6517d917ae
|
| 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,
|
|
@@ -7478,6 +7478,24 @@
|
|
| 7478 |
"mean_token_accuracy": 0.6480780899524688,
|
| 7479 |
"num_tokens": 15135132.0,
|
| 7480 |
"step": 4150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7481 |
}
|
| 7482 |
],
|
| 7483 |
"logging_steps": 5,
|
|
@@ -7497,7 +7515,7 @@
|
|
| 7497 |
"attributes": {}
|
| 7498 |
}
|
| 7499 |
},
|
| 7500 |
-
"total_flos": 7.
|
| 7501 |
"train_batch_size": 4,
|
| 7502 |
"trial_name": null,
|
| 7503 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 32.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4160,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7478 |
"mean_token_accuracy": 0.6480780899524688,
|
| 7479 |
"num_tokens": 15135132.0,
|
| 7480 |
"step": 4150
|
| 7481 |
+
},
|
| 7482 |
+
{
|
| 7483 |
+
"epoch": 31.96153846153846,
|
| 7484 |
+
"grad_norm": 0.0,
|
| 7485 |
+
"learning_rate": 2.9230000000000003e-05,
|
| 7486 |
+
"loss": 1.7548,
|
| 7487 |
+
"mean_token_accuracy": 0.6506118953227997,
|
| 7488 |
+
"num_tokens": 15152655.0,
|
| 7489 |
+
"step": 4155
|
| 7490 |
+
},
|
| 7491 |
+
{
|
| 7492 |
+
"epoch": 32.0,
|
| 7493 |
+
"grad_norm": 0.0,
|
| 7494 |
+
"learning_rate": 2.9205e-05,
|
| 7495 |
+
"loss": 1.7498,
|
| 7496 |
+
"mean_token_accuracy": 0.6500423729419709,
|
| 7497 |
+
"num_tokens": 15171360.0,
|
| 7498 |
+
"step": 4160
|
| 7499 |
}
|
| 7500 |
],
|
| 7501 |
"logging_steps": 5,
|
|
|
|
| 7515 |
"attributes": {}
|
| 7516 |
}
|
| 7517 |
},
|
| 7518 |
+
"total_flos": 7.688759484520858e+17,
|
| 7519 |
"train_batch_size": 4,
|
| 7520 |
"trial_name": null,
|
| 7521 |
"trial_params": null
|