Training in progress, step 3190, 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:e4dcd1cb2b53832fc849b61c877afd33c25aa299c3817d13c41da3bc10dcf8aa
|
| 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:afb74141768f05fab416757878c44eaaae79022c3d1209a18391bc5a6ea9971c
|
| 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 sha256:73a8a220ad5bfe7624024afd0d5764203c3bcc72fea1abfc31d2a1e7714adf5d
|
| 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": 24.
|
| 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,
|
|
@@ -5732,6 +5732,24 @@
|
|
| 5732 |
"mean_token_accuracy": 0.6548975586891175,
|
| 5733 |
"num_tokens": 11597057.0,
|
| 5734 |
"step": 3180
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5735 |
}
|
| 5736 |
],
|
| 5737 |
"logging_steps": 5,
|
|
@@ -5751,7 +5769,7 @@
|
|
| 5751 |
"attributes": {}
|
| 5752 |
}
|
| 5753 |
},
|
| 5754 |
-
"total_flos": 5.
|
| 5755 |
"train_batch_size": 4,
|
| 5756 |
"trial_name": null,
|
| 5757 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 24.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3190,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5732 |
"mean_token_accuracy": 0.6548975586891175,
|
| 5733 |
"num_tokens": 11597057.0,
|
| 5734 |
"step": 3180
|
| 5735 |
+
},
|
| 5736 |
+
{
|
| 5737 |
+
"epoch": 24.5,
|
| 5738 |
+
"grad_norm": 0.0,
|
| 5739 |
+
"learning_rate": 3.408e-05,
|
| 5740 |
+
"loss": 1.8287,
|
| 5741 |
+
"mean_token_accuracy": 0.6332879096269608,
|
| 5742 |
+
"num_tokens": 11614420.0,
|
| 5743 |
+
"step": 3185
|
| 5744 |
+
},
|
| 5745 |
+
{
|
| 5746 |
+
"epoch": 24.53846153846154,
|
| 5747 |
+
"grad_norm": 0.0,
|
| 5748 |
+
"learning_rate": 3.4055000000000005e-05,
|
| 5749 |
+
"loss": 1.6783,
|
| 5750 |
+
"mean_token_accuracy": 0.6583501130342484,
|
| 5751 |
+
"num_tokens": 11633485.0,
|
| 5752 |
+
"step": 3190
|
| 5753 |
}
|
| 5754 |
],
|
| 5755 |
"logging_steps": 5,
|
|
|
|
| 5769 |
"attributes": {}
|
| 5770 |
}
|
| 5771 |
},
|
| 5772 |
+
"total_flos": 5.894155008560333e+17,
|
| 5773 |
"train_batch_size": 4,
|
| 5774 |
"trial_name": null,
|
| 5775 |
"trial_params": null
|