Training in progress, step 9360, 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 sha256:3d8dd71977c1904e5e282d18e6887af67ee852210ee42c14dd14e033c9fa94d7
|
| 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:fe473229231409e0640ea7db57b568c43951ea0e08f1b460a1dd1d811de1909f
|
| 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 sha256:8f3df02e1d4ce3abe589928452ea8badb8cee99329d6080adfba4072cda4eb01
|
| 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":
|
| 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,
|
|
@@ -16838,6 +16838,24 @@
|
|
| 16838 |
"mean_token_accuracy": 0.6401098728179931,
|
| 16839 |
"num_tokens": 34099093.0,
|
| 16840 |
"step": 9350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16841 |
}
|
| 16842 |
],
|
| 16843 |
"logging_steps": 5,
|
|
@@ -16857,7 +16875,7 @@
|
|
| 16857 |
"attributes": {}
|
| 16858 |
}
|
| 16859 |
},
|
| 16860 |
-
"total_flos": 1.
|
| 16861 |
"train_batch_size": 4,
|
| 16862 |
"trial_name": null,
|
| 16863 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 72.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9360,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16838 |
"mean_token_accuracy": 0.6401098728179931,
|
| 16839 |
"num_tokens": 34099093.0,
|
| 16840 |
"step": 9350
|
| 16841 |
+
},
|
| 16842 |
+
{
|
| 16843 |
+
"epoch": 71.96153846153847,
|
| 16844 |
+
"grad_norm": 0.0,
|
| 16845 |
+
"learning_rate": 3.2300000000000004e-06,
|
| 16846 |
+
"loss": 1.8057,
|
| 16847 |
+
"mean_token_accuracy": 0.6371114939451218,
|
| 16848 |
+
"num_tokens": 34117109.0,
|
| 16849 |
+
"step": 9355
|
| 16850 |
+
},
|
| 16851 |
+
{
|
| 16852 |
+
"epoch": 72.0,
|
| 16853 |
+
"grad_norm": 0.0,
|
| 16854 |
+
"learning_rate": 3.2050000000000002e-06,
|
| 16855 |
+
"loss": 1.7633,
|
| 16856 |
+
"mean_token_accuracy": 0.6458366394042969,
|
| 16857 |
+
"num_tokens": 34135560.0,
|
| 16858 |
+
"step": 9360
|
| 16859 |
}
|
| 16860 |
],
|
| 16861 |
"logging_steps": 5,
|
|
|
|
| 16875 |
"attributes": {}
|
| 16876 |
}
|
| 16877 |
},
|
| 16878 |
+
"total_flos": 1.730948804778885e+18,
|
| 16879 |
"train_batch_size": 4,
|
| 16880 |
"trial_name": null,
|
| 16881 |
"trial_params": null
|