Training in progress, step 3220, 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 sha256:67058f6aea1a7cf530884e142e1f20fab4fb380a1132164ef28e01a5a9fa034e
|
| 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 sha256:3d00e5e081f6ecde3eb9e84547816ef1009831c31032b0a4516a5de99ca58ac7
|
| 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 sha256:8b9cd864d65e9986dc26542dcc470a3b8af073cbf58564496a0b8573f4c5af6d
|
| 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,
|
|
@@ -5786,6 +5786,24 @@
|
|
| 5786 |
"mean_token_accuracy": 0.636654618382454,
|
| 5787 |
"num_tokens": 11705825.0,
|
| 5788 |
"step": 3210
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5789 |
}
|
| 5790 |
],
|
| 5791 |
"logging_steps": 5,
|
|
@@ -5805,7 +5823,7 @@
|
|
| 5805 |
"attributes": {}
|
| 5806 |
}
|
| 5807 |
},
|
| 5808 |
-
"total_flos": 5.
|
| 5809 |
"train_batch_size": 4,
|
| 5810 |
"trial_name": null,
|
| 5811 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 24.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3220,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5786 |
"mean_token_accuracy": 0.636654618382454,
|
| 5787 |
"num_tokens": 11705825.0,
|
| 5788 |
"step": 3210
|
| 5789 |
+
},
|
| 5790 |
+
{
|
| 5791 |
+
"epoch": 24.73076923076923,
|
| 5792 |
+
"grad_norm": 0.0,
|
| 5793 |
+
"learning_rate": 3.393e-05,
|
| 5794 |
+
"loss": 1.7292,
|
| 5795 |
+
"mean_token_accuracy": 0.6524395048618317,
|
| 5796 |
+
"num_tokens": 11723774.0,
|
| 5797 |
+
"step": 3215
|
| 5798 |
+
},
|
| 5799 |
+
{
|
| 5800 |
+
"epoch": 24.76923076923077,
|
| 5801 |
+
"grad_norm": 0.0,
|
| 5802 |
+
"learning_rate": 3.3905e-05,
|
| 5803 |
+
"loss": 1.7275,
|
| 5804 |
+
"mean_token_accuracy": 0.6529559135437012,
|
| 5805 |
+
"num_tokens": 11741969.0,
|
| 5806 |
+
"step": 3220
|
| 5807 |
}
|
| 5808 |
],
|
| 5809 |
"logging_steps": 5,
|
|
|
|
| 5823 |
"attributes": {}
|
| 5824 |
}
|
| 5825 |
},
|
| 5826 |
+
"total_flos": 5.949632442256589e+17,
|
| 5827 |
"train_batch_size": 4,
|
| 5828 |
"trial_name": null,
|
| 5829 |
"trial_params": null
|