Training in progress, step 7220, 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:af3d4fe3d983d4995245c672a67e1b48077ad31f09c8caea19f1cf017bc0880b
|
| 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 sha256:7bf1ba6cc0af5be58e31beeabc891ef7b723c03e956356411cbed60b8c31931b
|
| 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:eed6b78e7c3149bd76fd07e5a009198c73a8d390451431cbda8b660e1a5bbdc7
|
| 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": 55.
|
| 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,
|
|
@@ -12986,6 +12986,24 @@
|
|
| 12986 |
"mean_token_accuracy": 0.6518444687128067,
|
| 12987 |
"num_tokens": 26293084.0,
|
| 12988 |
"step": 7210
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12989 |
}
|
| 12990 |
],
|
| 12991 |
"logging_steps": 5,
|
|
@@ -13005,7 +13023,7 @@
|
|
| 13005 |
"attributes": {}
|
| 13006 |
}
|
| 13007 |
},
|
| 13008 |
-
"total_flos": 1.
|
| 13009 |
"train_batch_size": 4,
|
| 13010 |
"trial_name": null,
|
| 13011 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 55.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7220,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12986 |
"mean_token_accuracy": 0.6518444687128067,
|
| 12987 |
"num_tokens": 26293084.0,
|
| 12988 |
"step": 7210
|
| 12989 |
+
},
|
| 12990 |
+
{
|
| 12991 |
+
"epoch": 55.5,
|
| 12992 |
+
"grad_norm": 0.0,
|
| 12993 |
+
"learning_rate": 1.3930000000000002e-05,
|
| 12994 |
+
"loss": 1.7744,
|
| 12995 |
+
"mean_token_accuracy": 0.6451671838760376,
|
| 12996 |
+
"num_tokens": 26310728.0,
|
| 12997 |
+
"step": 7215
|
| 12998 |
+
},
|
| 12999 |
+
{
|
| 13000 |
+
"epoch": 55.53846153846154,
|
| 13001 |
+
"grad_norm": 0.0,
|
| 13002 |
+
"learning_rate": 1.3905000000000002e-05,
|
| 13003 |
+
"loss": 1.7131,
|
| 13004 |
+
"mean_token_accuracy": 0.6529065489768981,
|
| 13005 |
+
"num_tokens": 26329504.0,
|
| 13006 |
+
"step": 7220
|
| 13007 |
}
|
| 13008 |
],
|
| 13009 |
"logging_steps": 5,
|
|
|
|
| 13023 |
"attributes": {}
|
| 13024 |
}
|
| 13025 |
},
|
| 13026 |
+
"total_flos": 1.3350372906663936e+18,
|
| 13027 |
"train_batch_size": 4,
|
| 13028 |
"trial_name": null,
|
| 13029 |
"trial_params": null
|