Training in progress, step 2680, 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 sha256:29f3a14f7f9016d934855c6e6cd7734a44712cbcae4f26b4b1e028f66ffa753d
|
| 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:cf34d232156d42bd794e526b230e39daf91f2e60f95dabec717284d741bab5b5
|
| 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:de9a704f61f2108b99044e083830c41da55f34fbe5cbd8150a1b121ee8233db2
|
| 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 sha256:8493c33cdf90c4faca39097f7302eb2f78bf170861b6aa2bc9ec6e4451c38e75
|
| 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,
|
|
@@ -2688,6 +2688,16 @@
|
|
| 2688 |
"mean_token_accuracy": 0.7895583346486091,
|
| 2689 |
"num_tokens": 12406871.0,
|
| 2690 |
"step": 2670
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2691 |
}
|
| 2692 |
],
|
| 2693 |
"logging_steps": 10,
|
|
@@ -2707,7 +2717,7 @@
|
|
| 2707 |
"attributes": {}
|
| 2708 |
}
|
| 2709 |
},
|
| 2710 |
-
"total_flos": 5.
|
| 2711 |
"train_batch_size": 4,
|
| 2712 |
"trial_name": null,
|
| 2713 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5717333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2680,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2688 |
"mean_token_accuracy": 0.7895583346486091,
|
| 2689 |
"num_tokens": 12406871.0,
|
| 2690 |
"step": 2670
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"entropy": 0.942859411239624,
|
| 2694 |
+
"epoch": 0.5717333333333333,
|
| 2695 |
+
"grad_norm": 0.27082499861717224,
|
| 2696 |
+
"learning_rate": 8.398385920126874e-05,
|
| 2697 |
+
"loss": 1.0009033203125,
|
| 2698 |
+
"mean_token_accuracy": 0.7650713473558426,
|
| 2699 |
+
"num_tokens": 12451365.0,
|
| 2700 |
+
"step": 2680
|
| 2701 |
}
|
| 2702 |
],
|
| 2703 |
"logging_steps": 10,
|
|
|
|
| 2717 |
"attributes": {}
|
| 2718 |
}
|
| 2719 |
},
|
| 2720 |
+
"total_flos": 5.902536066827059e+16,
|
| 2721 |
"train_batch_size": 4,
|
| 2722 |
"trial_name": null,
|
| 2723 |
"trial_params": null
|