Training in progress, step 2710, 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 sha256:957d4df147552dccc03b5064da9940fbc96240e86d61616c67371be9873d17c2
|
| 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 sha256:06324cba1fcd52a3281fa6591c0e7d79c7acb68c99ee700e5d9f84ceecc36f9b
|
| 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 sha256:047660a9cac5c5e004a2144f019fb08fcdcdbf76a9e4287f79b301d86876a187
|
| 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 sha256:08ad4f20a1fc4d01dd7776b063f1c7e8407abd02883f001aa8104a2ad0539776
|
| 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,
|
|
@@ -2718,6 +2718,16 @@
|
|
| 2718 |
"mean_token_accuracy": 0.7581366948783398,
|
| 2719 |
"num_tokens": 12541298.0,
|
| 2720 |
"step": 2700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2721 |
}
|
| 2722 |
],
|
| 2723 |
"logging_steps": 10,
|
|
@@ -2737,7 +2747,7 @@
|
|
| 2737 |
"attributes": {}
|
| 2738 |
}
|
| 2739 |
},
|
| 2740 |
-
"total_flos": 5.
|
| 2741 |
"train_batch_size": 4,
|
| 2742 |
"trial_name": null,
|
| 2743 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5781333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2710,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2718 |
"mean_token_accuracy": 0.7581366948783398,
|
| 2719 |
"num_tokens": 12541298.0,
|
| 2720 |
"step": 2700
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"entropy": 1.001559029519558,
|
| 2724 |
+
"epoch": 0.5781333333333334,
|
| 2725 |
+
"grad_norm": 0.3141133487224579,
|
| 2726 |
+
"learning_rate": 8.360118417451113e-05,
|
| 2727 |
+
"loss": 1.1159303665161133,
|
| 2728 |
+
"mean_token_accuracy": 0.7509155049920082,
|
| 2729 |
+
"num_tokens": 12586250.0,
|
| 2730 |
+
"step": 2710
|
| 2731 |
}
|
| 2732 |
],
|
| 2733 |
"logging_steps": 10,
|
|
|
|
| 2747 |
"attributes": {}
|
| 2748 |
}
|
| 2749 |
},
|
| 2750 |
+
"total_flos": 5.966754642983731e+16,
|
| 2751 |
"train_batch_size": 4,
|
| 2752 |
"trial_name": null,
|
| 2753 |
"trial_params": null
|