Training in progress, step 470, 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 sha256:2faa8027fdd54cd5df55bda7eedb7afeb27b7be8d39b1e14907ff4695fdd131c
|
| 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:ca3cf716dc7cbf53a30b28a6efd2d3353a60fa11ff7c16fa9641691a9fa7eb86
|
| 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 sha256:0def3f9137eb84ebfd2c6e28e4c4df6fffcce77c73d4f6fac947cb8be846b026
|
| 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": 3.
|
| 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,
|
|
@@ -836,6 +836,24 @@
|
|
| 836 |
"mean_token_accuracy": 0.6357834041118622,
|
| 837 |
"num_tokens": 1678569.0,
|
| 838 |
"step": 460
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 839 |
}
|
| 840 |
],
|
| 841 |
"logging_steps": 5,
|
|
@@ -855,7 +873,7 @@
|
|
| 855 |
"attributes": {}
|
| 856 |
}
|
| 857 |
},
|
| 858 |
-
"total_flos": 8.
|
| 859 |
"train_batch_size": 4,
|
| 860 |
"trial_name": null,
|
| 861 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.6153846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 470,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 836 |
"mean_token_accuracy": 0.6357834041118622,
|
| 837 |
"num_tokens": 1678569.0,
|
| 838 |
"step": 460
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 3.5769230769230766,
|
| 842 |
+
"grad_norm": 0.0,
|
| 843 |
+
"learning_rate": 4.7680000000000004e-05,
|
| 844 |
+
"loss": 1.7048,
|
| 845 |
+
"mean_token_accuracy": 0.6561109334230423,
|
| 846 |
+
"num_tokens": 1697511.0,
|
| 847 |
+
"step": 465
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 3.6153846153846154,
|
| 851 |
+
"grad_norm": 0.0,
|
| 852 |
+
"learning_rate": 4.7655e-05,
|
| 853 |
+
"loss": 1.6402,
|
| 854 |
+
"mean_token_accuracy": 0.6671018153429031,
|
| 855 |
+
"num_tokens": 1717113.0,
|
| 856 |
+
"step": 470
|
| 857 |
}
|
| 858 |
],
|
| 859 |
"logging_steps": 5,
|
|
|
|
| 873 |
"attributes": {}
|
| 874 |
}
|
| 875 |
},
|
| 876 |
+
"total_flos": 8.69720712486912e+16,
|
| 877 |
"train_batch_size": 4,
|
| 878 |
"trial_name": null,
|
| 879 |
"trial_params": null
|