Training in progress, step 730, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63fdcb9bc3e6d07fc2a7613712e20fdddfc0082758697cd04ad161f93a7750e5
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eab76774f7146f484fdbecd44e27d79d31bb82e48a6c0403aec0a8eae98e45bf
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b48869528bf508d3a1e510877ff0b496a88c9c68d27133d809e241e623afe2f0
|
| 3 |
size 14645
|
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:d4dd1fe0881a329983c3df6ea0ded9f3b753faddab6eabf73568a4386b772df3
|
| 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": 0.
|
| 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,
|
|
@@ -738,6 +738,16 @@
|
|
| 738 |
"mean_token_accuracy": 0.750363714993,
|
| 739 |
"num_tokens": 3335092.0,
|
| 740 |
"step": 720
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 741 |
}
|
| 742 |
],
|
| 743 |
"logging_steps": 10,
|
|
@@ -757,7 +767,7 @@
|
|
| 757 |
"attributes": {}
|
| 758 |
}
|
| 759 |
},
|
| 760 |
-
"total_flos": 1.
|
| 761 |
"train_batch_size": 4,
|
| 762 |
"trial_name": null,
|
| 763 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.15573333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 730,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 738 |
"mean_token_accuracy": 0.750363714993,
|
| 739 |
"num_tokens": 3335092.0,
|
| 740 |
"step": 720
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"entropy": 1.1284249052405357,
|
| 744 |
+
"epoch": 0.15573333333333333,
|
| 745 |
+
"grad_norm": 0.2954626679420471,
|
| 746 |
+
"learning_rate": 9.944974097995581e-05,
|
| 747 |
+
"loss": 1.2494465827941894,
|
| 748 |
+
"mean_token_accuracy": 0.7387717284262181,
|
| 749 |
+
"num_tokens": 3380879.0,
|
| 750 |
+
"step": 730
|
| 751 |
}
|
| 752 |
],
|
| 753 |
"logging_steps": 10,
|
|
|
|
| 767 |
"attributes": {}
|
| 768 |
}
|
| 769 |
},
|
| 770 |
+
"total_flos": 1.6016559882160128e+16,
|
| 771 |
"train_batch_size": 4,
|
| 772 |
"trial_name": null,
|
| 773 |
"trial_params": null
|