Training in progress, step 1750, 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:de0554991b14b7f68ec4557853cba19505adcd1ccfeb166bc22a2875dd24fd80
|
| 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 sha256:00960b1186e24c4e09c7902032a383f5860085f00e9ba295ccf8972c8012bd4f
|
| 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 sha256:8631da7f3d81e34988bef387e6d9466592c4a772e476986c832977b41f1b4a16
|
| 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 sha256:5a64b7e7ff55c7126c1169c0c41bd866d8a3f18d85cdaf2c1db2a45052a9484a
|
| 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,
|
|
@@ -1758,6 +1758,16 @@
|
|
| 1758 |
"mean_token_accuracy": 0.7833232149481774,
|
| 1759 |
"num_tokens": 8071410.0,
|
| 1760 |
"step": 1740
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1761 |
}
|
| 1762 |
],
|
| 1763 |
"logging_steps": 10,
|
|
@@ -1777,7 +1787,7 @@
|
|
| 1777 |
"attributes": {}
|
| 1778 |
}
|
| 1779 |
},
|
| 1780 |
-
"total_flos": 3.
|
| 1781 |
"train_batch_size": 4,
|
| 1782 |
"trial_name": null,
|
| 1783 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.37333333333333335,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1750,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1758 |
"mean_token_accuracy": 0.7833232149481774,
|
| 1759 |
"num_tokens": 8071410.0,
|
| 1760 |
"step": 1740
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"entropy": 0.8095596194267273,
|
| 1764 |
+
"epoch": 0.37333333333333335,
|
| 1765 |
+
"grad_norm": 0.36941683292388916,
|
| 1766 |
+
"learning_rate": 9.38416551705078e-05,
|
| 1767 |
+
"loss": 0.8782508850097657,
|
| 1768 |
+
"mean_token_accuracy": 0.7895680025219918,
|
| 1769 |
+
"num_tokens": 8113695.0,
|
| 1770 |
+
"step": 1750
|
| 1771 |
}
|
| 1772 |
],
|
| 1773 |
"logging_steps": 10,
|
|
|
|
| 1787 |
"attributes": {}
|
| 1788 |
}
|
| 1789 |
},
|
| 1790 |
+
"total_flos": 3.849319671502541e+16,
|
| 1791 |
"train_batch_size": 4,
|
| 1792 |
"trial_name": null,
|
| 1793 |
"trial_params": null
|