Training in progress, step 2690, 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:bbd43126cf7df7f326d254141bd3c2dd0fb010fc06775f33d63e001e942b73de
|
| 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:ca794ea2fd5270fabcaa83fffefc57fec51f7f07fd757440bd9bafcff6f8d0d5
|
| 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:b511d00056c6a07f6d71766ac4a134733fc9103b09a5075d32792d42c5cbf85e
|
| 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": 20.
|
| 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,
|
|
@@ -4832,6 +4832,24 @@
|
|
| 4832 |
"mean_token_accuracy": 0.660412722826004,
|
| 4833 |
"num_tokens": 9771848.0,
|
| 4834 |
"step": 2680
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4835 |
}
|
| 4836 |
],
|
| 4837 |
"logging_steps": 5,
|
|
@@ -4851,7 +4869,7 @@
|
|
| 4851 |
"attributes": {}
|
| 4852 |
}
|
| 4853 |
},
|
| 4854 |
-
"total_flos": 4.
|
| 4855 |
"train_batch_size": 4,
|
| 4856 |
"trial_name": null,
|
| 4857 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 20.692307692307693,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2690,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4832 |
"mean_token_accuracy": 0.660412722826004,
|
| 4833 |
"num_tokens": 9771848.0,
|
| 4834 |
"step": 2680
|
| 4835 |
+
},
|
| 4836 |
+
{
|
| 4837 |
+
"epoch": 20.653846153846153,
|
| 4838 |
+
"grad_norm": 0.0,
|
| 4839 |
+
"learning_rate": 3.6580000000000006e-05,
|
| 4840 |
+
"loss": 1.7466,
|
| 4841 |
+
"mean_token_accuracy": 0.6478160947561264,
|
| 4842 |
+
"num_tokens": 9789801.0,
|
| 4843 |
+
"step": 2685
|
| 4844 |
+
},
|
| 4845 |
+
{
|
| 4846 |
+
"epoch": 20.692307692307693,
|
| 4847 |
+
"grad_norm": 0.0,
|
| 4848 |
+
"learning_rate": 3.6555e-05,
|
| 4849 |
+
"loss": 1.7047,
|
| 4850 |
+
"mean_token_accuracy": 0.6545427888631821,
|
| 4851 |
+
"num_tokens": 9808227.0,
|
| 4852 |
+
"step": 2690
|
| 4853 |
}
|
| 4854 |
],
|
| 4855 |
"logging_steps": 5,
|
|
|
|
| 4869 |
"attributes": {}
|
| 4870 |
}
|
| 4871 |
},
|
| 4872 |
+
"total_flos": 4.970030209405747e+17,
|
| 4873 |
"train_batch_size": 4,
|
| 4874 |
"trial_name": null,
|
| 4875 |
"trial_params": null
|