Training in progress, step 3730, 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 sha256:688ddbc5e6da4aeff2040625a2ba58ea5ff4ec20212de735056c74aa7b1f444c
|
| 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 sha256:89561f3af8e1e94edf329de9559200df7a6e6565a9e26f549eb079ac24897c2d
|
| 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:b09de1e8e88774abf106e9b70ad700f60d7ec79b7edbff113d3835f28503487e
|
| 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": 28.
|
| 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,
|
|
@@ -6704,6 +6704,24 @@
|
|
| 6704 |
"mean_token_accuracy": 0.6495319962501526,
|
| 6705 |
"num_tokens": 13566473.0,
|
| 6706 |
"step": 3720
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6707 |
}
|
| 6708 |
],
|
| 6709 |
"logging_steps": 5,
|
|
@@ -6723,7 +6741,7 @@
|
|
| 6723 |
"attributes": {}
|
| 6724 |
}
|
| 6725 |
},
|
| 6726 |
-
"total_flos": 6.
|
| 6727 |
"train_batch_size": 4,
|
| 6728 |
"trial_name": null,
|
| 6729 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 28.692307692307693,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3730,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6704 |
"mean_token_accuracy": 0.6495319962501526,
|
| 6705 |
"num_tokens": 13566473.0,
|
| 6706 |
"step": 3720
|
| 6707 |
+
},
|
| 6708 |
+
{
|
| 6709 |
+
"epoch": 28.653846153846153,
|
| 6710 |
+
"grad_norm": 0.0,
|
| 6711 |
+
"learning_rate": 3.138e-05,
|
| 6712 |
+
"loss": 1.7426,
|
| 6713 |
+
"mean_token_accuracy": 0.6494800269603729,
|
| 6714 |
+
"num_tokens": 13584724.0,
|
| 6715 |
+
"step": 3725
|
| 6716 |
+
},
|
| 6717 |
+
{
|
| 6718 |
+
"epoch": 28.692307692307693,
|
| 6719 |
+
"grad_norm": 0.0,
|
| 6720 |
+
"learning_rate": 3.1355e-05,
|
| 6721 |
+
"loss": 1.7341,
|
| 6722 |
+
"mean_token_accuracy": 0.6527552962303161,
|
| 6723 |
+
"num_tokens": 13603304.0,
|
| 6724 |
+
"step": 3730
|
| 6725 |
}
|
| 6726 |
],
|
| 6727 |
"logging_steps": 5,
|
|
|
|
| 6741 |
"attributes": {}
|
| 6742 |
}
|
| 6743 |
},
|
| 6744 |
+
"total_flos": 6.894258804773683e+17,
|
| 6745 |
"train_batch_size": 4,
|
| 6746 |
"trial_name": null,
|
| 6747 |
"trial_params": null
|