Training in progress, step 2060, 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 sha256:6e4064f9bff6a583959c29c4a44e8b386e47a973e89ea5eadbc27734af2c3320
|
| 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:caeec5c40c0731d410ecc70a0a21305c38385f27de507612adc6d68f89d512d0
|
| 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:d33e8fe077c15ede77b641ba3f18debf636614e8a87f4af673670880d87e7120
|
| 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": 15.
|
| 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,
|
|
@@ -3698,6 +3698,24 @@
|
|
| 3698 |
"mean_token_accuracy": 0.6410402476787567,
|
| 3699 |
"num_tokens": 7473972.0,
|
| 3700 |
"step": 2050
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3701 |
}
|
| 3702 |
],
|
| 3703 |
"logging_steps": 5,
|
|
@@ -3717,7 +3735,7 @@
|
|
| 3717 |
"attributes": {}
|
| 3718 |
}
|
| 3719 |
},
|
| 3720 |
-
"total_flos": 3.
|
| 3721 |
"train_batch_size": 4,
|
| 3722 |
"trial_name": null,
|
| 3723 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 15.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2060,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3698 |
"mean_token_accuracy": 0.6410402476787567,
|
| 3699 |
"num_tokens": 7473972.0,
|
| 3700 |
"step": 2050
|
| 3701 |
+
},
|
| 3702 |
+
{
|
| 3703 |
+
"epoch": 15.807692307692308,
|
| 3704 |
+
"grad_norm": 0.0,
|
| 3705 |
+
"learning_rate": 3.973e-05,
|
| 3706 |
+
"loss": 1.6997,
|
| 3707 |
+
"mean_token_accuracy": 0.6587257742881775,
|
| 3708 |
+
"num_tokens": 7493430.0,
|
| 3709 |
+
"step": 2055
|
| 3710 |
+
},
|
| 3711 |
+
{
|
| 3712 |
+
"epoch": 15.846153846153847,
|
| 3713 |
+
"grad_norm": 0.0,
|
| 3714 |
+
"learning_rate": 3.9705e-05,
|
| 3715 |
+
"loss": 1.7487,
|
| 3716 |
+
"mean_token_accuracy": 0.648233824968338,
|
| 3717 |
+
"num_tokens": 7511123.0,
|
| 3718 |
+
"step": 2060
|
| 3719 |
}
|
| 3720 |
],
|
| 3721 |
"logging_steps": 5,
|
|
|
|
| 3735 |
"attributes": {}
|
| 3736 |
}
|
| 3737 |
},
|
| 3738 |
+
"total_flos": 3.8052152780488704e+17,
|
| 3739 |
"train_batch_size": 4,
|
| 3740 |
"trial_name": null,
|
| 3741 |
"trial_params": null
|