Training in progress, step 8710, 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 sha256:8568d44c6ba6a0627f18fb5a1d0ae43e198d4f8a1a4bcf1f9f0cd054ed3892db
|
| 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 sha256:2b9a63340359295df57937fb7d7a59105f323172fbbf97aaf957d92fc7da4f9a
|
| 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:b5591b1185f2339707555047efdd9fd4df8331f61413fb6bb044aba2d7f70808
|
| 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,
|
|
@@ -15668,6 +15668,24 @@
|
|
| 15668 |
"mean_token_accuracy": 0.6562155693769455,
|
| 15669 |
"num_tokens": 31729323.0,
|
| 15670 |
"step": 8700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15671 |
}
|
| 15672 |
],
|
| 15673 |
"logging_steps": 5,
|
|
@@ -15687,7 +15705,7 @@
|
|
| 15687 |
"attributes": {}
|
| 15688 |
}
|
| 15689 |
},
|
| 15690 |
-
"total_flos": 1.
|
| 15691 |
"train_batch_size": 4,
|
| 15692 |
"trial_name": null,
|
| 15693 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 67.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8710,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15668 |
"mean_token_accuracy": 0.6562155693769455,
|
| 15669 |
"num_tokens": 31729323.0,
|
| 15670 |
"step": 8700
|
| 15671 |
+
},
|
| 15672 |
+
{
|
| 15673 |
+
"epoch": 66.96153846153847,
|
| 15674 |
+
"grad_norm": 0.0,
|
| 15675 |
+
"learning_rate": 6.48e-06,
|
| 15676 |
+
"loss": 1.8384,
|
| 15677 |
+
"mean_token_accuracy": 0.6272630810737609,
|
| 15678 |
+
"num_tokens": 31746601.0,
|
| 15679 |
+
"step": 8705
|
| 15680 |
+
},
|
| 15681 |
+
{
|
| 15682 |
+
"epoch": 67.0,
|
| 15683 |
+
"grad_norm": 0.0,
|
| 15684 |
+
"learning_rate": 6.455e-06,
|
| 15685 |
+
"loss": 1.6929,
|
| 15686 |
+
"mean_token_accuracy": 0.6641561448574066,
|
| 15687 |
+
"num_tokens": 31765035.0,
|
| 15688 |
+
"step": 8710
|
| 15689 |
}
|
| 15690 |
],
|
| 15691 |
"logging_steps": 5,
|
|
|
|
| 15705 |
"attributes": {}
|
| 15706 |
}
|
| 15707 |
},
|
| 15708 |
+
"total_flos": 1.6107180596630323e+18,
|
| 15709 |
"train_batch_size": 4,
|
| 15710 |
"trial_name": null,
|
| 15711 |
"trial_params": null
|