Training in progress, step 1620, 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 sha256:7c47ac11794e937bfa85dee2d44492a9bf16df8fd1e0329a747b54b39d8483e7
|
| 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 sha256:16212b012fbad10441ede1301743d7f920083ef7f4a23b6dd3d0949e500177d2
|
| 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 sha256:08a00a5c0893885629226b9ac66a6dd9baae189eddb9445d2ef7c99a64ca90b5
|
| 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": 12.
|
| 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,
|
|
@@ -2906,6 +2906,24 @@
|
|
| 2906 |
"mean_token_accuracy": 0.6425417333841323,
|
| 2907 |
"num_tokens": 5868205.0,
|
| 2908 |
"step": 1610
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2909 |
}
|
| 2910 |
],
|
| 2911 |
"logging_steps": 5,
|
|
@@ -2925,7 +2943,7 @@
|
|
| 2925 |
"attributes": {}
|
| 2926 |
}
|
| 2927 |
},
|
| 2928 |
-
"total_flos": 2.
|
| 2929 |
"train_batch_size": 4,
|
| 2930 |
"trial_name": null,
|
| 2931 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 12.461538461538462,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1620,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2906 |
"mean_token_accuracy": 0.6425417333841323,
|
| 2907 |
"num_tokens": 5868205.0,
|
| 2908 |
"step": 1610
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 12.423076923076923,
|
| 2912 |
+
"grad_norm": 0.0,
|
| 2913 |
+
"learning_rate": 4.193e-05,
|
| 2914 |
+
"loss": 1.6777,
|
| 2915 |
+
"mean_token_accuracy": 0.6608704894781112,
|
| 2916 |
+
"num_tokens": 5887309.0,
|
| 2917 |
+
"step": 1615
|
| 2918 |
+
},
|
| 2919 |
+
{
|
| 2920 |
+
"epoch": 12.461538461538462,
|
| 2921 |
+
"grad_norm": 0.0,
|
| 2922 |
+
"learning_rate": 4.1905e-05,
|
| 2923 |
+
"loss": 1.7262,
|
| 2924 |
+
"mean_token_accuracy": 0.651836696267128,
|
| 2925 |
+
"num_tokens": 5906272.0,
|
| 2926 |
+
"step": 1620
|
| 2927 |
}
|
| 2928 |
],
|
| 2929 |
"logging_steps": 5,
|
|
|
|
| 2943 |
"attributes": {}
|
| 2944 |
}
|
| 2945 |
},
|
| 2946 |
+
"total_flos": 2.9906068072218624e+17,
|
| 2947 |
"train_batch_size": 4,
|
| 2948 |
"trial_name": null,
|
| 2949 |
"trial_params": null
|