Training in progress, step 820, 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 sha256:8b5700b8619200a633a3da7d7da99f201dba6d7c0fb71cf982d089608cd173b8
|
| 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 sha256:5bcba4099322e48aa173bc81b00571e6dbd53ec16301c6de3d79d78d8589f45b
|
| 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 sha256:6192913e0d79f6b42d15c29949dbb5c38558770d20866a20c4955c216e1cbb06
|
| 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:e568151bce63cf2a47418ee600b11181a87b25acaab164421ab3d3363afa7a7a
|
| 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,
|
|
@@ -828,6 +828,16 @@
|
|
| 828 |
"mean_token_accuracy": 0.7545588746666908,
|
| 829 |
"num_tokens": 3764739.0,
|
| 830 |
"step": 810
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 831 |
}
|
| 832 |
],
|
| 833 |
"logging_steps": 10,
|
|
@@ -847,7 +857,7 @@
|
|
| 847 |
"attributes": {}
|
| 848 |
}
|
| 849 |
},
|
| 850 |
-
"total_flos": 1.
|
| 851 |
"train_batch_size": 4,
|
| 852 |
"trial_name": null,
|
| 853 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.17493333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 820,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 828 |
"mean_token_accuracy": 0.7545588746666908,
|
| 829 |
"num_tokens": 3764739.0,
|
| 830 |
"step": 810
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"entropy": 1.0871834971010685,
|
| 834 |
+
"epoch": 0.17493333333333333,
|
| 835 |
+
"grad_norm": 0.22862163186073303,
|
| 836 |
+
"learning_rate": 9.919533119399438e-05,
|
| 837 |
+
"loss": 1.1718174934387207,
|
| 838 |
+
"mean_token_accuracy": 0.7301450505852699,
|
| 839 |
+
"num_tokens": 3810938.0,
|
| 840 |
+
"step": 820
|
| 841 |
}
|
| 842 |
],
|
| 843 |
"logging_steps": 10,
|
|
|
|
| 857 |
"attributes": {}
|
| 858 |
}
|
| 859 |
},
|
| 860 |
+
"total_flos": 1.805221484900352e+16,
|
| 861 |
"train_batch_size": 4,
|
| 862 |
"trial_name": null,
|
| 863 |
"trial_params": null
|