Training in progress, step 3640, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89c91d391a73deec616241fef7b3019092cfbffb46c7804a2d16997122f562f1
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:698d6bd82299e1c0a02631c0d900a2667e14512efbc640555b6a0c3af946ba34
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f42f706574071fa7839df510a30e22687dfb8e1181d42e0ccb2aa2f6c9311d6
|
| 3 |
size 14645
|
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:ecd50725762952933ccfcb8e4b8786dfe983b61f3ebe43ffe3cacd4aa67e7520
|
| 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": 0.
|
| 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,
|
|
@@ -3648,6 +3648,16 @@
|
|
| 3648 |
"mean_token_accuracy": 0.7830170378088951,
|
| 3649 |
"num_tokens": 16894959.0,
|
| 3650 |
"step": 3630
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3651 |
}
|
| 3652 |
],
|
| 3653 |
"logging_steps": 10,
|
|
@@ -3667,7 +3677,7 @@
|
|
| 3667 |
"attributes": {}
|
| 3668 |
}
|
| 3669 |
},
|
| 3670 |
-
"total_flos": 8.
|
| 3671 |
"train_batch_size": 4,
|
| 3672 |
"trial_name": null,
|
| 3673 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7765333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3640,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3648 |
"mean_token_accuracy": 0.7830170378088951,
|
| 3649 |
"num_tokens": 16894959.0,
|
| 3650 |
"step": 3630
|
| 3651 |
+
},
|
| 3652 |
+
{
|
| 3653 |
+
"entropy": 0.951847655326128,
|
| 3654 |
+
"epoch": 0.7765333333333333,
|
| 3655 |
+
"grad_norm": 0.3015543818473816,
|
| 3656 |
+
"learning_rate": 7.016065397795758e-05,
|
| 3657 |
+
"loss": 1.062761116027832,
|
| 3658 |
+
"mean_token_accuracy": 0.7644057601690293,
|
| 3659 |
+
"num_tokens": 16939640.0,
|
| 3660 |
+
"step": 3640
|
| 3661 |
}
|
| 3662 |
],
|
| 3663 |
"logging_steps": 10,
|
|
|
|
| 3677 |
"attributes": {}
|
| 3678 |
}
|
| 3679 |
},
|
| 3680 |
+
"total_flos": 8.02510780345129e+16,
|
| 3681 |
"train_batch_size": 4,
|
| 3682 |
"trial_name": null,
|
| 3683 |
"trial_params": null
|