Training in progress, step 6580, 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 sha256:9918ade432a3e73d7f0286831a6d33cf788af0093f5963a67c48a530d5bc4fef
|
| 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 sha256:4c096cea3349e9813981a29c07bfefe9a8fa6ef1a8c3b15bfc3a51caeb491c90
|
| 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:f957c99b5a09b104d995c4c514469b6bbd3665be5d2b35c4c30291492c6a1c76
|
| 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": 50.
|
| 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,
|
|
@@ -11834,6 +11834,24 @@
|
|
| 11834 |
"mean_token_accuracy": 0.6348341315984726,
|
| 11835 |
"num_tokens": 23961264.0,
|
| 11836 |
"step": 6570
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11837 |
}
|
| 11838 |
],
|
| 11839 |
"logging_steps": 5,
|
|
@@ -11853,7 +11871,7 @@
|
|
| 11853 |
"attributes": {}
|
| 11854 |
}
|
| 11855 |
},
|
| 11856 |
-
"total_flos": 1.
|
| 11857 |
"train_batch_size": 4,
|
| 11858 |
"trial_name": null,
|
| 11859 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 50.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6580,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11834 |
"mean_token_accuracy": 0.6348341315984726,
|
| 11835 |
"num_tokens": 23961264.0,
|
| 11836 |
"step": 6570
|
| 11837 |
+
},
|
| 11838 |
+
{
|
| 11839 |
+
"epoch": 50.57692307692308,
|
| 11840 |
+
"grad_norm": 0.0,
|
| 11841 |
+
"learning_rate": 1.713e-05,
|
| 11842 |
+
"loss": 1.6595,
|
| 11843 |
+
"mean_token_accuracy": 0.6654309093952179,
|
| 11844 |
+
"num_tokens": 23980824.0,
|
| 11845 |
+
"step": 6575
|
| 11846 |
+
},
|
| 11847 |
+
{
|
| 11848 |
+
"epoch": 50.61538461538461,
|
| 11849 |
+
"grad_norm": 0.0,
|
| 11850 |
+
"learning_rate": 1.7105000000000003e-05,
|
| 11851 |
+
"loss": 1.7533,
|
| 11852 |
+
"mean_token_accuracy": 0.6445026308298111,
|
| 11853 |
+
"num_tokens": 23998733.0,
|
| 11854 |
+
"step": 6580
|
| 11855 |
}
|
| 11856 |
],
|
| 11857 |
"logging_steps": 5,
|
|
|
|
| 11871 |
"attributes": {}
|
| 11872 |
}
|
| 11873 |
},
|
| 11874 |
+
"total_flos": 1.2167668328900198e+18,
|
| 11875 |
"train_batch_size": 4,
|
| 11876 |
"trial_name": null,
|
| 11877 |
"trial_params": null
|