🍻 cheers
Browse files- README.md +6 -5
- all_results.json +14 -0
- eval_results.json +10 -0
- runs/Mar28_11-58-46_ryanserver/events.out.tfevents.1711669541.ryanserver.10171.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +3593 -0
README.md
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
| 7 |
- name: ryan03282024
|
|
@@ -13,12 +14,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# ryan03282024
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.
|
| 19 |
-
- Ordinal Mae: 0.
|
| 20 |
-
- Ordinal Accuracy: 0.
|
| 21 |
-
- Na Accuracy: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
- name: ryan03282024
|
|
|
|
| 14 |
|
| 15 |
# ryan03282024
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the properties dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.2238
|
| 20 |
+
- Ordinal Mae: 0.4441
|
| 21 |
+
- Ordinal Accuracy: 0.6446
|
| 22 |
+
- Na Accuracy: 0.7992
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_loss": 0.22382062673568726,
|
| 4 |
+
"eval_na_accuracy": 0.799227774143219,
|
| 5 |
+
"eval_ordinal_accuracy": 0.6446113586425781,
|
| 6 |
+
"eval_ordinal_mae": 0.4441048502922058,
|
| 7 |
+
"eval_runtime": 157.4798,
|
| 8 |
+
"eval_samples_per_second": 25.267,
|
| 9 |
+
"eval_steps_per_second": 3.162,
|
| 10 |
+
"train_loss": 0.11642740544208273,
|
| 11 |
+
"train_runtime": 27830.4973,
|
| 12 |
+
"train_samples_per_second": 5.264,
|
| 13 |
+
"train_steps_per_second": 0.329
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_loss": 0.22382062673568726,
|
| 4 |
+
"eval_na_accuracy": 0.799227774143219,
|
| 5 |
+
"eval_ordinal_accuracy": 0.6446113586425781,
|
| 6 |
+
"eval_ordinal_mae": 0.4441048502922058,
|
| 7 |
+
"eval_runtime": 157.4798,
|
| 8 |
+
"eval_samples_per_second": 25.267,
|
| 9 |
+
"eval_steps_per_second": 3.162
|
| 10 |
+
}
|
runs/Mar28_11-58-46_ryanserver/events.out.tfevents.1711669541.ryanserver.10171.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:beb3106d42fdca38428b89da366f29ddc0f087107017a62b41ab93b211ca43b3
|
| 3 |
+
size 529
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"train_loss": 0.11642740544208273,
|
| 4 |
+
"train_runtime": 27830.4973,
|
| 5 |
+
"train_samples_per_second": 5.264,
|
| 6 |
+
"train_steps_per_second": 0.329
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3593 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.22382062673568726,
|
| 3 |
+
"best_model_checkpoint": "./ryan03282024/checkpoint-1600",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 9160,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"grad_norm": 0.5509258508682251,
|
| 14 |
+
"learning_rate": 9.972707423580787e-05,
|
| 15 |
+
"loss": 0.4095,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02,
|
| 20 |
+
"grad_norm": 0.37446415424346924,
|
| 21 |
+
"learning_rate": 9.945414847161573e-05,
|
| 22 |
+
"loss": 0.3743,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"grad_norm": 0.36988818645477295,
|
| 28 |
+
"learning_rate": 9.918122270742359e-05,
|
| 29 |
+
"loss": 0.3766,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.04,
|
| 34 |
+
"grad_norm": 2.9999992847442627,
|
| 35 |
+
"learning_rate": 9.890829694323145e-05,
|
| 36 |
+
"loss": 0.3421,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04,
|
| 41 |
+
"eval_loss": 0.33314022421836853,
|
| 42 |
+
"eval_na_accuracy": 0.6911196708679199,
|
| 43 |
+
"eval_ordinal_accuracy": 0.3816815912723541,
|
| 44 |
+
"eval_ordinal_mae": 0.8749264478683472,
|
| 45 |
+
"eval_runtime": 311.6641,
|
| 46 |
+
"eval_samples_per_second": 12.767,
|
| 47 |
+
"eval_steps_per_second": 1.598,
|
| 48 |
+
"step": 100
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.05,
|
| 52 |
+
"grad_norm": 0.6784111261367798,
|
| 53 |
+
"learning_rate": 9.863537117903931e-05,
|
| 54 |
+
"loss": 0.3422,
|
| 55 |
+
"step": 125
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.07,
|
| 59 |
+
"grad_norm": 1.7690809965133667,
|
| 60 |
+
"learning_rate": 9.836244541484717e-05,
|
| 61 |
+
"loss": 0.3059,
|
| 62 |
+
"step": 150
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.08,
|
| 66 |
+
"grad_norm": 0.5732172131538391,
|
| 67 |
+
"learning_rate": 9.808951965065503e-05,
|
| 68 |
+
"loss": 0.3654,
|
| 69 |
+
"step": 175
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.09,
|
| 73 |
+
"grad_norm": 0.3226703405380249,
|
| 74 |
+
"learning_rate": 9.781659388646288e-05,
|
| 75 |
+
"loss": 0.2813,
|
| 76 |
+
"step": 200
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.09,
|
| 80 |
+
"eval_loss": 0.29995909333229065,
|
| 81 |
+
"eval_na_accuracy": 0.7953668236732483,
|
| 82 |
+
"eval_ordinal_accuracy": 0.5117018222808838,
|
| 83 |
+
"eval_ordinal_mae": 0.7492409348487854,
|
| 84 |
+
"eval_runtime": 157.8026,
|
| 85 |
+
"eval_samples_per_second": 25.215,
|
| 86 |
+
"eval_steps_per_second": 3.156,
|
| 87 |
+
"step": 200
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.1,
|
| 91 |
+
"grad_norm": 0.44079920649528503,
|
| 92 |
+
"learning_rate": 9.754366812227075e-05,
|
| 93 |
+
"loss": 0.3359,
|
| 94 |
+
"step": 225
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.11,
|
| 98 |
+
"grad_norm": 1.5866132974624634,
|
| 99 |
+
"learning_rate": 9.727074235807861e-05,
|
| 100 |
+
"loss": 0.3131,
|
| 101 |
+
"step": 250
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.12,
|
| 105 |
+
"grad_norm": 1.5666215419769287,
|
| 106 |
+
"learning_rate": 9.699781659388647e-05,
|
| 107 |
+
"loss": 0.2723,
|
| 108 |
+
"step": 275
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.13,
|
| 112 |
+
"grad_norm": 0.2892788350582123,
|
| 113 |
+
"learning_rate": 9.672489082969433e-05,
|
| 114 |
+
"loss": 0.2619,
|
| 115 |
+
"step": 300
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.13,
|
| 119 |
+
"eval_loss": 0.3019290566444397,
|
| 120 |
+
"eval_na_accuracy": 0.7046331763267517,
|
| 121 |
+
"eval_ordinal_accuracy": 0.5273042321205139,
|
| 122 |
+
"eval_ordinal_mae": 0.6840940117835999,
|
| 123 |
+
"eval_runtime": 158.8663,
|
| 124 |
+
"eval_samples_per_second": 25.046,
|
| 125 |
+
"eval_steps_per_second": 3.135,
|
| 126 |
+
"step": 300
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.14,
|
| 130 |
+
"grad_norm": 0.24918608367443085,
|
| 131 |
+
"learning_rate": 9.645196506550219e-05,
|
| 132 |
+
"loss": 0.303,
|
| 133 |
+
"step": 325
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.15,
|
| 137 |
+
"grad_norm": 1.626022219657898,
|
| 138 |
+
"learning_rate": 9.617903930131005e-05,
|
| 139 |
+
"loss": 0.2867,
|
| 140 |
+
"step": 350
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.16,
|
| 144 |
+
"grad_norm": 2.1694397926330566,
|
| 145 |
+
"learning_rate": 9.59061135371179e-05,
|
| 146 |
+
"loss": 0.249,
|
| 147 |
+
"step": 375
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.17,
|
| 151 |
+
"grad_norm": 0.3259480893611908,
|
| 152 |
+
"learning_rate": 9.563318777292577e-05,
|
| 153 |
+
"loss": 0.2863,
|
| 154 |
+
"step": 400
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.17,
|
| 158 |
+
"eval_loss": 0.2960417866706848,
|
| 159 |
+
"eval_na_accuracy": 0.7335907220840454,
|
| 160 |
+
"eval_ordinal_accuracy": 0.5096792578697205,
|
| 161 |
+
"eval_ordinal_mae": 0.6538078188896179,
|
| 162 |
+
"eval_runtime": 159.697,
|
| 163 |
+
"eval_samples_per_second": 24.916,
|
| 164 |
+
"eval_steps_per_second": 3.118,
|
| 165 |
+
"step": 400
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.19,
|
| 169 |
+
"grad_norm": 1.1021641492843628,
|
| 170 |
+
"learning_rate": 9.536026200873362e-05,
|
| 171 |
+
"loss": 0.2729,
|
| 172 |
+
"step": 425
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.2,
|
| 176 |
+
"grad_norm": 1.3987232446670532,
|
| 177 |
+
"learning_rate": 9.50873362445415e-05,
|
| 178 |
+
"loss": 0.2544,
|
| 179 |
+
"step": 450
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.21,
|
| 183 |
+
"grad_norm": 1.7090039253234863,
|
| 184 |
+
"learning_rate": 9.481441048034934e-05,
|
| 185 |
+
"loss": 0.2776,
|
| 186 |
+
"step": 475
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.22,
|
| 190 |
+
"grad_norm": 1.737847924232483,
|
| 191 |
+
"learning_rate": 9.454148471615721e-05,
|
| 192 |
+
"loss": 0.2159,
|
| 193 |
+
"step": 500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.22,
|
| 197 |
+
"eval_loss": 0.26019465923309326,
|
| 198 |
+
"eval_na_accuracy": 0.8243243098258972,
|
| 199 |
+
"eval_ordinal_accuracy": 0.5660213828086853,
|
| 200 |
+
"eval_ordinal_mae": 0.540388822555542,
|
| 201 |
+
"eval_runtime": 157.5356,
|
| 202 |
+
"eval_samples_per_second": 25.258,
|
| 203 |
+
"eval_steps_per_second": 3.161,
|
| 204 |
+
"step": 500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.23,
|
| 208 |
+
"grad_norm": 3.2989888191223145,
|
| 209 |
+
"learning_rate": 9.426855895196508e-05,
|
| 210 |
+
"loss": 0.2554,
|
| 211 |
+
"step": 525
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.24,
|
| 215 |
+
"grad_norm": 0.7149298191070557,
|
| 216 |
+
"learning_rate": 9.399563318777294e-05,
|
| 217 |
+
"loss": 0.272,
|
| 218 |
+
"step": 550
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.25,
|
| 222 |
+
"grad_norm": 0.90256667137146,
|
| 223 |
+
"learning_rate": 9.37227074235808e-05,
|
| 224 |
+
"loss": 0.2595,
|
| 225 |
+
"step": 575
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.26,
|
| 229 |
+
"grad_norm": 2.2932217121124268,
|
| 230 |
+
"learning_rate": 9.344978165938864e-05,
|
| 231 |
+
"loss": 0.2235,
|
| 232 |
+
"step": 600
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.26,
|
| 236 |
+
"eval_loss": 0.2556995749473572,
|
| 237 |
+
"eval_na_accuracy": 0.7779922485351562,
|
| 238 |
+
"eval_ordinal_accuracy": 0.5874024629592896,
|
| 239 |
+
"eval_ordinal_mae": 0.5014671683311462,
|
| 240 |
+
"eval_runtime": 159.648,
|
| 241 |
+
"eval_samples_per_second": 24.924,
|
| 242 |
+
"eval_steps_per_second": 3.119,
|
| 243 |
+
"step": 600
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.27,
|
| 247 |
+
"grad_norm": 0.8714308142662048,
|
| 248 |
+
"learning_rate": 9.317685589519652e-05,
|
| 249 |
+
"loss": 0.2871,
|
| 250 |
+
"step": 625
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.28,
|
| 254 |
+
"grad_norm": 0.699299156665802,
|
| 255 |
+
"learning_rate": 9.290393013100436e-05,
|
| 256 |
+
"loss": 0.2489,
|
| 257 |
+
"step": 650
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.29,
|
| 261 |
+
"grad_norm": 3.3761134147644043,
|
| 262 |
+
"learning_rate": 9.263100436681224e-05,
|
| 263 |
+
"loss": 0.2696,
|
| 264 |
+
"step": 675
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.31,
|
| 268 |
+
"grad_norm": 0.5747934579849243,
|
| 269 |
+
"learning_rate": 9.235807860262009e-05,
|
| 270 |
+
"loss": 0.285,
|
| 271 |
+
"step": 700
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.31,
|
| 275 |
+
"eval_loss": 0.2563941180706024,
|
| 276 |
+
"eval_na_accuracy": 0.6853281855583191,
|
| 277 |
+
"eval_ordinal_accuracy": 0.6180294752120972,
|
| 278 |
+
"eval_ordinal_mae": 0.49999386072158813,
|
| 279 |
+
"eval_runtime": 160.5887,
|
| 280 |
+
"eval_samples_per_second": 24.778,
|
| 281 |
+
"eval_steps_per_second": 3.101,
|
| 282 |
+
"step": 700
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.32,
|
| 286 |
+
"grad_norm": 0.6936819553375244,
|
| 287 |
+
"learning_rate": 9.208515283842796e-05,
|
| 288 |
+
"loss": 0.2379,
|
| 289 |
+
"step": 725
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.33,
|
| 293 |
+
"grad_norm": 1.3918662071228027,
|
| 294 |
+
"learning_rate": 9.18122270742358e-05,
|
| 295 |
+
"loss": 0.2509,
|
| 296 |
+
"step": 750
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.34,
|
| 300 |
+
"grad_norm": 0.46456876397132874,
|
| 301 |
+
"learning_rate": 9.153930131004367e-05,
|
| 302 |
+
"loss": 0.2531,
|
| 303 |
+
"step": 775
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.35,
|
| 307 |
+
"grad_norm": 0.516076385974884,
|
| 308 |
+
"learning_rate": 9.126637554585154e-05,
|
| 309 |
+
"loss": 0.2028,
|
| 310 |
+
"step": 800
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.35,
|
| 314 |
+
"eval_loss": 0.2861529588699341,
|
| 315 |
+
"eval_na_accuracy": 0.7220077514648438,
|
| 316 |
+
"eval_ordinal_accuracy": 0.5067899227142334,
|
| 317 |
+
"eval_ordinal_mae": 0.633837103843689,
|
| 318 |
+
"eval_runtime": 154.4747,
|
| 319 |
+
"eval_samples_per_second": 25.758,
|
| 320 |
+
"eval_steps_per_second": 3.224,
|
| 321 |
+
"step": 800
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.36,
|
| 325 |
+
"grad_norm": 1.5322011709213257,
|
| 326 |
+
"learning_rate": 9.100436681222709e-05,
|
| 327 |
+
"loss": 0.2936,
|
| 328 |
+
"step": 825
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.37,
|
| 332 |
+
"grad_norm": 0.49020248651504517,
|
| 333 |
+
"learning_rate": 9.073144104803494e-05,
|
| 334 |
+
"loss": 0.2206,
|
| 335 |
+
"step": 850
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.38,
|
| 339 |
+
"grad_norm": 0.8753771781921387,
|
| 340 |
+
"learning_rate": 9.045851528384281e-05,
|
| 341 |
+
"loss": 0.2031,
|
| 342 |
+
"step": 875
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.39,
|
| 346 |
+
"grad_norm": 1.1926873922348022,
|
| 347 |
+
"learning_rate": 9.018558951965066e-05,
|
| 348 |
+
"loss": 0.2006,
|
| 349 |
+
"step": 900
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.39,
|
| 353 |
+
"eval_loss": 0.24949249625205994,
|
| 354 |
+
"eval_na_accuracy": 0.7586872577667236,
|
| 355 |
+
"eval_ordinal_accuracy": 0.6298757791519165,
|
| 356 |
+
"eval_ordinal_mae": 0.4830287992954254,
|
| 357 |
+
"eval_runtime": 156.0615,
|
| 358 |
+
"eval_samples_per_second": 25.496,
|
| 359 |
+
"eval_steps_per_second": 3.191,
|
| 360 |
+
"step": 900
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.4,
|
| 364 |
+
"grad_norm": 1.0290440320968628,
|
| 365 |
+
"learning_rate": 8.991266375545852e-05,
|
| 366 |
+
"loss": 0.2648,
|
| 367 |
+
"step": 925
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.41,
|
| 371 |
+
"grad_norm": 0.615397036075592,
|
| 372 |
+
"learning_rate": 8.963973799126638e-05,
|
| 373 |
+
"loss": 0.1866,
|
| 374 |
+
"step": 950
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.43,
|
| 378 |
+
"grad_norm": 0.4451560974121094,
|
| 379 |
+
"learning_rate": 8.936681222707424e-05,
|
| 380 |
+
"loss": 0.2641,
|
| 381 |
+
"step": 975
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.44,
|
| 385 |
+
"grad_norm": 0.9014913439750671,
|
| 386 |
+
"learning_rate": 8.90938864628821e-05,
|
| 387 |
+
"loss": 0.2663,
|
| 388 |
+
"step": 1000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.44,
|
| 392 |
+
"eval_loss": 0.26604241132736206,
|
| 393 |
+
"eval_na_accuracy": 0.8610038757324219,
|
| 394 |
+
"eval_ordinal_accuracy": 0.602138102054596,
|
| 395 |
+
"eval_ordinal_mae": 0.4893138110637665,
|
| 396 |
+
"eval_runtime": 155.5971,
|
| 397 |
+
"eval_samples_per_second": 25.572,
|
| 398 |
+
"eval_steps_per_second": 3.201,
|
| 399 |
+
"step": 1000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.45,
|
| 403 |
+
"grad_norm": 2.4818997383117676,
|
| 404 |
+
"learning_rate": 8.882096069868996e-05,
|
| 405 |
+
"loss": 0.2454,
|
| 406 |
+
"step": 1025
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.46,
|
| 410 |
+
"grad_norm": 0.7425001859664917,
|
| 411 |
+
"learning_rate": 8.854803493449782e-05,
|
| 412 |
+
"loss": 0.215,
|
| 413 |
+
"step": 1050
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.47,
|
| 417 |
+
"grad_norm": 2.0386316776275635,
|
| 418 |
+
"learning_rate": 8.827510917030568e-05,
|
| 419 |
+
"loss": 0.2368,
|
| 420 |
+
"step": 1075
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.48,
|
| 424 |
+
"grad_norm": 0.6596102714538574,
|
| 425 |
+
"learning_rate": 8.800218340611354e-05,
|
| 426 |
+
"loss": 0.2062,
|
| 427 |
+
"step": 1100
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.48,
|
| 431 |
+
"eval_loss": 0.24812151491641998,
|
| 432 |
+
"eval_na_accuracy": 0.8436293601989746,
|
| 433 |
+
"eval_ordinal_accuracy": 0.6266974806785583,
|
| 434 |
+
"eval_ordinal_mae": 0.47125470638275146,
|
| 435 |
+
"eval_runtime": 157.0377,
|
| 436 |
+
"eval_samples_per_second": 25.338,
|
| 437 |
+
"eval_steps_per_second": 3.171,
|
| 438 |
+
"step": 1100
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.49,
|
| 442 |
+
"grad_norm": 0.4987865686416626,
|
| 443 |
+
"learning_rate": 8.77292576419214e-05,
|
| 444 |
+
"loss": 0.2151,
|
| 445 |
+
"step": 1125
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.5,
|
| 449 |
+
"grad_norm": 1.0523704290390015,
|
| 450 |
+
"learning_rate": 8.745633187772926e-05,
|
| 451 |
+
"loss": 0.2092,
|
| 452 |
+
"step": 1150
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.51,
|
| 456 |
+
"grad_norm": 0.6211034059524536,
|
| 457 |
+
"learning_rate": 8.718340611353712e-05,
|
| 458 |
+
"loss": 0.2452,
|
| 459 |
+
"step": 1175
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.52,
|
| 463 |
+
"grad_norm": 0.49944034218788147,
|
| 464 |
+
"learning_rate": 8.691048034934498e-05,
|
| 465 |
+
"loss": 0.1749,
|
| 466 |
+
"step": 1200
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.52,
|
| 470 |
+
"eval_loss": 0.25862136483192444,
|
| 471 |
+
"eval_na_accuracy": 0.6737451553344727,
|
| 472 |
+
"eval_ordinal_accuracy": 0.6422998905181885,
|
| 473 |
+
"eval_ordinal_mae": 0.4958673417568207,
|
| 474 |
+
"eval_runtime": 161.9513,
|
| 475 |
+
"eval_samples_per_second": 24.569,
|
| 476 |
+
"eval_steps_per_second": 3.075,
|
| 477 |
+
"step": 1200
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.53,
|
| 481 |
+
"grad_norm": 0.30346667766571045,
|
| 482 |
+
"learning_rate": 8.663755458515284e-05,
|
| 483 |
+
"loss": 0.202,
|
| 484 |
+
"step": 1225
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.55,
|
| 488 |
+
"grad_norm": 0.8414286971092224,
|
| 489 |
+
"learning_rate": 8.63646288209607e-05,
|
| 490 |
+
"loss": 0.2019,
|
| 491 |
+
"step": 1250
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.56,
|
| 495 |
+
"grad_norm": 1.1115086078643799,
|
| 496 |
+
"learning_rate": 8.609170305676856e-05,
|
| 497 |
+
"loss": 0.2037,
|
| 498 |
+
"step": 1275
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.57,
|
| 502 |
+
"grad_norm": 0.7678231000900269,
|
| 503 |
+
"learning_rate": 8.581877729257642e-05,
|
| 504 |
+
"loss": 0.2197,
|
| 505 |
+
"step": 1300
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.57,
|
| 509 |
+
"eval_loss": 0.23488646745681763,
|
| 510 |
+
"eval_na_accuracy": 0.8030887842178345,
|
| 511 |
+
"eval_ordinal_accuracy": 0.5980930328369141,
|
| 512 |
+
"eval_ordinal_mae": 0.48411670327186584,
|
| 513 |
+
"eval_runtime": 161.4724,
|
| 514 |
+
"eval_samples_per_second": 24.642,
|
| 515 |
+
"eval_steps_per_second": 3.084,
|
| 516 |
+
"step": 1300
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.58,
|
| 520 |
+
"grad_norm": 0.33742988109588623,
|
| 521 |
+
"learning_rate": 8.554585152838429e-05,
|
| 522 |
+
"loss": 0.226,
|
| 523 |
+
"step": 1325
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.59,
|
| 527 |
+
"grad_norm": 1.6625324487686157,
|
| 528 |
+
"learning_rate": 8.527292576419215e-05,
|
| 529 |
+
"loss": 0.2612,
|
| 530 |
+
"step": 1350
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.6,
|
| 534 |
+
"grad_norm": 1.5984447002410889,
|
| 535 |
+
"learning_rate": 8.5e-05,
|
| 536 |
+
"loss": 0.1812,
|
| 537 |
+
"step": 1375
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.61,
|
| 541 |
+
"grad_norm": 1.39547860622406,
|
| 542 |
+
"learning_rate": 8.472707423580787e-05,
|
| 543 |
+
"loss": 0.2073,
|
| 544 |
+
"step": 1400
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.61,
|
| 548 |
+
"eval_loss": 0.25865110754966736,
|
| 549 |
+
"eval_na_accuracy": 0.6949806809425354,
|
| 550 |
+
"eval_ordinal_accuracy": 0.6012713313102722,
|
| 551 |
+
"eval_ordinal_mae": 0.4877532422542572,
|
| 552 |
+
"eval_runtime": 161.5877,
|
| 553 |
+
"eval_samples_per_second": 24.624,
|
| 554 |
+
"eval_steps_per_second": 3.082,
|
| 555 |
+
"step": 1400
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.62,
|
| 559 |
+
"grad_norm": 0.6241037845611572,
|
| 560 |
+
"learning_rate": 8.445414847161573e-05,
|
| 561 |
+
"loss": 0.2783,
|
| 562 |
+
"step": 1425
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.63,
|
| 566 |
+
"grad_norm": 1.9269381761550903,
|
| 567 |
+
"learning_rate": 8.418122270742357e-05,
|
| 568 |
+
"loss": 0.1813,
|
| 569 |
+
"step": 1450
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.64,
|
| 573 |
+
"grad_norm": 0.5204592943191528,
|
| 574 |
+
"learning_rate": 8.390829694323145e-05,
|
| 575 |
+
"loss": 0.1753,
|
| 576 |
+
"step": 1475
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.66,
|
| 580 |
+
"grad_norm": 1.156730055809021,
|
| 581 |
+
"learning_rate": 8.36353711790393e-05,
|
| 582 |
+
"loss": 0.1915,
|
| 583 |
+
"step": 1500
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.66,
|
| 587 |
+
"eval_loss": 0.23929761350154877,
|
| 588 |
+
"eval_na_accuracy": 0.7683397531509399,
|
| 589 |
+
"eval_ordinal_accuracy": 0.6321872472763062,
|
| 590 |
+
"eval_ordinal_mae": 0.4770694673061371,
|
| 591 |
+
"eval_runtime": 160.096,
|
| 592 |
+
"eval_samples_per_second": 24.854,
|
| 593 |
+
"eval_steps_per_second": 3.111,
|
| 594 |
+
"step": 1500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.67,
|
| 598 |
+
"grad_norm": 0.31671473383903503,
|
| 599 |
+
"learning_rate": 8.336244541484717e-05,
|
| 600 |
+
"loss": 0.2555,
|
| 601 |
+
"step": 1525
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.68,
|
| 605 |
+
"grad_norm": 1.452971339225769,
|
| 606 |
+
"learning_rate": 8.308951965065503e-05,
|
| 607 |
+
"loss": 0.2321,
|
| 608 |
+
"step": 1550
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.69,
|
| 612 |
+
"grad_norm": 0.7802607417106628,
|
| 613 |
+
"learning_rate": 8.281659388646289e-05,
|
| 614 |
+
"loss": 0.2013,
|
| 615 |
+
"step": 1575
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.7,
|
| 619 |
+
"grad_norm": 1.238275408744812,
|
| 620 |
+
"learning_rate": 8.254366812227075e-05,
|
| 621 |
+
"loss": 0.2374,
|
| 622 |
+
"step": 1600
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.7,
|
| 626 |
+
"eval_loss": 0.22382062673568726,
|
| 627 |
+
"eval_na_accuracy": 0.799227774143219,
|
| 628 |
+
"eval_ordinal_accuracy": 0.6446113586425781,
|
| 629 |
+
"eval_ordinal_mae": 0.4441048502922058,
|
| 630 |
+
"eval_runtime": 161.7443,
|
| 631 |
+
"eval_samples_per_second": 24.601,
|
| 632 |
+
"eval_steps_per_second": 3.079,
|
| 633 |
+
"step": 1600
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.71,
|
| 637 |
+
"grad_norm": 0.8560432195663452,
|
| 638 |
+
"learning_rate": 8.227074235807861e-05,
|
| 639 |
+
"loss": 0.2055,
|
| 640 |
+
"step": 1625
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.72,
|
| 644 |
+
"grad_norm": 2.4070003032684326,
|
| 645 |
+
"learning_rate": 8.199781659388647e-05,
|
| 646 |
+
"loss": 0.2357,
|
| 647 |
+
"step": 1650
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.73,
|
| 651 |
+
"grad_norm": 2.119150161743164,
|
| 652 |
+
"learning_rate": 8.172489082969432e-05,
|
| 653 |
+
"loss": 0.2145,
|
| 654 |
+
"step": 1675
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.74,
|
| 658 |
+
"grad_norm": 1.8999676704406738,
|
| 659 |
+
"learning_rate": 8.145196506550219e-05,
|
| 660 |
+
"loss": 0.2278,
|
| 661 |
+
"step": 1700
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.74,
|
| 665 |
+
"eval_loss": 0.24530412256717682,
|
| 666 |
+
"eval_na_accuracy": 0.7277992367744446,
|
| 667 |
+
"eval_ordinal_accuracy": 0.6538572907447815,
|
| 668 |
+
"eval_ordinal_mae": 0.4410313367843628,
|
| 669 |
+
"eval_runtime": 160.7764,
|
| 670 |
+
"eval_samples_per_second": 24.749,
|
| 671 |
+
"eval_steps_per_second": 3.097,
|
| 672 |
+
"step": 1700
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.75,
|
| 676 |
+
"grad_norm": 1.699065923690796,
|
| 677 |
+
"learning_rate": 8.117903930131004e-05,
|
| 678 |
+
"loss": 0.2416,
|
| 679 |
+
"step": 1725
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 0.76,
|
| 683 |
+
"grad_norm": 1.4952126741409302,
|
| 684 |
+
"learning_rate": 8.090611353711791e-05,
|
| 685 |
+
"loss": 0.188,
|
| 686 |
+
"step": 1750
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.78,
|
| 690 |
+
"grad_norm": 0.4823841452598572,
|
| 691 |
+
"learning_rate": 8.063318777292576e-05,
|
| 692 |
+
"loss": 0.2148,
|
| 693 |
+
"step": 1775
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.79,
|
| 697 |
+
"grad_norm": 0.9280353784561157,
|
| 698 |
+
"learning_rate": 8.036026200873363e-05,
|
| 699 |
+
"loss": 0.2033,
|
| 700 |
+
"step": 1800
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 0.79,
|
| 704 |
+
"eval_loss": 0.22507312893867493,
|
| 705 |
+
"eval_na_accuracy": 0.8185328245162964,
|
| 706 |
+
"eval_ordinal_accuracy": 0.6298757791519165,
|
| 707 |
+
"eval_ordinal_mae": 0.4584101140499115,
|
| 708 |
+
"eval_runtime": 160.7672,
|
| 709 |
+
"eval_samples_per_second": 24.75,
|
| 710 |
+
"eval_steps_per_second": 3.098,
|
| 711 |
+
"step": 1800
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.8,
|
| 715 |
+
"grad_norm": 0.9829936027526855,
|
| 716 |
+
"learning_rate": 8.00873362445415e-05,
|
| 717 |
+
"loss": 0.2015,
|
| 718 |
+
"step": 1825
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.81,
|
| 722 |
+
"grad_norm": 0.5692235231399536,
|
| 723 |
+
"learning_rate": 7.981441048034934e-05,
|
| 724 |
+
"loss": 0.2213,
|
| 725 |
+
"step": 1850
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.82,
|
| 729 |
+
"grad_norm": 0.4303966164588928,
|
| 730 |
+
"learning_rate": 7.954148471615722e-05,
|
| 731 |
+
"loss": 0.2156,
|
| 732 |
+
"step": 1875
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.83,
|
| 736 |
+
"grad_norm": 1.4745689630508423,
|
| 737 |
+
"learning_rate": 7.926855895196506e-05,
|
| 738 |
+
"loss": 0.1843,
|
| 739 |
+
"step": 1900
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.83,
|
| 743 |
+
"eval_loss": 0.2280111461877823,
|
| 744 |
+
"eval_na_accuracy": 0.8127413392066956,
|
| 745 |
+
"eval_ordinal_accuracy": 0.6512568593025208,
|
| 746 |
+
"eval_ordinal_mae": 0.4446066617965698,
|
| 747 |
+
"eval_runtime": 160.0671,
|
| 748 |
+
"eval_samples_per_second": 24.858,
|
| 749 |
+
"eval_steps_per_second": 3.111,
|
| 750 |
+
"step": 1900
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.84,
|
| 754 |
+
"grad_norm": 2.2468037605285645,
|
| 755 |
+
"learning_rate": 7.899563318777294e-05,
|
| 756 |
+
"loss": 0.2182,
|
| 757 |
+
"step": 1925
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.85,
|
| 761 |
+
"grad_norm": 0.6818110346794128,
|
| 762 |
+
"learning_rate": 7.872270742358078e-05,
|
| 763 |
+
"loss": 0.1822,
|
| 764 |
+
"step": 1950
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.86,
|
| 768 |
+
"grad_norm": 0.802448034286499,
|
| 769 |
+
"learning_rate": 7.844978165938866e-05,
|
| 770 |
+
"loss": 0.2289,
|
| 771 |
+
"step": 1975
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.87,
|
| 775 |
+
"grad_norm": 0.6907253861427307,
|
| 776 |
+
"learning_rate": 7.81768558951965e-05,
|
| 777 |
+
"loss": 0.1878,
|
| 778 |
+
"step": 2000
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.87,
|
| 782 |
+
"eval_loss": 0.22766314446926117,
|
| 783 |
+
"eval_na_accuracy": 0.8127413392066956,
|
| 784 |
+
"eval_ordinal_accuracy": 0.6492343544960022,
|
| 785 |
+
"eval_ordinal_mae": 0.4454284906387329,
|
| 786 |
+
"eval_runtime": 159.2821,
|
| 787 |
+
"eval_samples_per_second": 24.981,
|
| 788 |
+
"eval_steps_per_second": 3.127,
|
| 789 |
+
"step": 2000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.88,
|
| 793 |
+
"grad_norm": 1.1525399684906006,
|
| 794 |
+
"learning_rate": 7.790393013100437e-05,
|
| 795 |
+
"loss": 0.2146,
|
| 796 |
+
"step": 2025
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.9,
|
| 800 |
+
"grad_norm": 1.3308144807815552,
|
| 801 |
+
"learning_rate": 7.763100436681223e-05,
|
| 802 |
+
"loss": 0.2367,
|
| 803 |
+
"step": 2050
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.91,
|
| 807 |
+
"grad_norm": 1.1532173156738281,
|
| 808 |
+
"learning_rate": 7.735807860262009e-05,
|
| 809 |
+
"loss": 0.1948,
|
| 810 |
+
"step": 2075
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.92,
|
| 814 |
+
"grad_norm": 0.9184058904647827,
|
| 815 |
+
"learning_rate": 7.708515283842796e-05,
|
| 816 |
+
"loss": 0.2608,
|
| 817 |
+
"step": 2100
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.92,
|
| 821 |
+
"eval_loss": 0.23085492849349976,
|
| 822 |
+
"eval_na_accuracy": 0.8494208455085754,
|
| 823 |
+
"eval_ordinal_accuracy": 0.619185209274292,
|
| 824 |
+
"eval_ordinal_mae": 0.4517284035682678,
|
| 825 |
+
"eval_runtime": 158.9549,
|
| 826 |
+
"eval_samples_per_second": 25.032,
|
| 827 |
+
"eval_steps_per_second": 3.133,
|
| 828 |
+
"step": 2100
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.93,
|
| 832 |
+
"grad_norm": 1.0736620426177979,
|
| 833 |
+
"learning_rate": 7.681222707423581e-05,
|
| 834 |
+
"loss": 0.2409,
|
| 835 |
+
"step": 2125
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.94,
|
| 839 |
+
"grad_norm": 0.5520908832550049,
|
| 840 |
+
"learning_rate": 7.653930131004368e-05,
|
| 841 |
+
"loss": 0.1722,
|
| 842 |
+
"step": 2150
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.95,
|
| 846 |
+
"grad_norm": 1.255903720855713,
|
| 847 |
+
"learning_rate": 7.626637554585153e-05,
|
| 848 |
+
"loss": 0.1996,
|
| 849 |
+
"step": 2175
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.96,
|
| 853 |
+
"grad_norm": 1.3203591108322144,
|
| 854 |
+
"learning_rate": 7.599344978165939e-05,
|
| 855 |
+
"loss": 0.201,
|
| 856 |
+
"step": 2200
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.96,
|
| 860 |
+
"eval_loss": 0.24588599801063538,
|
| 861 |
+
"eval_na_accuracy": 0.7277992367744446,
|
| 862 |
+
"eval_ordinal_accuracy": 0.6405662894248962,
|
| 863 |
+
"eval_ordinal_mae": 0.46535709500312805,
|
| 864 |
+
"eval_runtime": 163.7913,
|
| 865 |
+
"eval_samples_per_second": 24.293,
|
| 866 |
+
"eval_steps_per_second": 3.04,
|
| 867 |
+
"step": 2200
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.97,
|
| 871 |
+
"grad_norm": 1.3525117635726929,
|
| 872 |
+
"learning_rate": 7.572052401746725e-05,
|
| 873 |
+
"loss": 0.2068,
|
| 874 |
+
"step": 2225
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.98,
|
| 878 |
+
"grad_norm": 2.916431188583374,
|
| 879 |
+
"learning_rate": 7.544759825327511e-05,
|
| 880 |
+
"loss": 0.243,
|
| 881 |
+
"step": 2250
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.99,
|
| 885 |
+
"grad_norm": 0.8391708135604858,
|
| 886 |
+
"learning_rate": 7.517467248908297e-05,
|
| 887 |
+
"loss": 0.1842,
|
| 888 |
+
"step": 2275
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 1.0,
|
| 892 |
+
"grad_norm": 0.5292081236839294,
|
| 893 |
+
"learning_rate": 7.490174672489083e-05,
|
| 894 |
+
"loss": 0.1736,
|
| 895 |
+
"step": 2300
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 1.0,
|
| 899 |
+
"eval_loss": 0.24380208551883698,
|
| 900 |
+
"eval_na_accuracy": 0.7200772166252136,
|
| 901 |
+
"eval_ordinal_accuracy": 0.6475006937980652,
|
| 902 |
+
"eval_ordinal_mae": 0.44738492369651794,
|
| 903 |
+
"eval_runtime": 161.0768,
|
| 904 |
+
"eval_samples_per_second": 24.703,
|
| 905 |
+
"eval_steps_per_second": 3.092,
|
| 906 |
+
"step": 2300
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.02,
|
| 910 |
+
"grad_norm": 0.6971523761749268,
|
| 911 |
+
"learning_rate": 7.462882096069869e-05,
|
| 912 |
+
"loss": 0.1683,
|
| 913 |
+
"step": 2325
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.03,
|
| 917 |
+
"grad_norm": 0.8325093388557434,
|
| 918 |
+
"learning_rate": 7.435589519650655e-05,
|
| 919 |
+
"loss": 0.1177,
|
| 920 |
+
"step": 2350
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.04,
|
| 924 |
+
"grad_norm": 0.8595998883247375,
|
| 925 |
+
"learning_rate": 7.408296943231441e-05,
|
| 926 |
+
"loss": 0.1626,
|
| 927 |
+
"step": 2375
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.05,
|
| 931 |
+
"grad_norm": 0.38421839475631714,
|
| 932 |
+
"learning_rate": 7.381004366812227e-05,
|
| 933 |
+
"loss": 0.1374,
|
| 934 |
+
"step": 2400
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.05,
|
| 938 |
+
"eval_loss": 0.23675759136676788,
|
| 939 |
+
"eval_na_accuracy": 0.7799227833747864,
|
| 940 |
+
"eval_ordinal_accuracy": 0.6622363328933716,
|
| 941 |
+
"eval_ordinal_mae": 0.41446253657341003,
|
| 942 |
+
"eval_runtime": 160.4437,
|
| 943 |
+
"eval_samples_per_second": 24.8,
|
| 944 |
+
"eval_steps_per_second": 3.104,
|
| 945 |
+
"step": 2400
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.06,
|
| 949 |
+
"grad_norm": 0.7025877237319946,
|
| 950 |
+
"learning_rate": 7.353711790393013e-05,
|
| 951 |
+
"loss": 0.1484,
|
| 952 |
+
"step": 2425
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 1.07,
|
| 956 |
+
"grad_norm": 1.4461692571640015,
|
| 957 |
+
"learning_rate": 7.3264192139738e-05,
|
| 958 |
+
"loss": 0.1564,
|
| 959 |
+
"step": 2450
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 1.08,
|
| 963 |
+
"grad_norm": 1.1262603998184204,
|
| 964 |
+
"learning_rate": 7.299126637554585e-05,
|
| 965 |
+
"loss": 0.1252,
|
| 966 |
+
"step": 2475
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 1.09,
|
| 970 |
+
"grad_norm": 1.1054977178573608,
|
| 971 |
+
"learning_rate": 7.271834061135371e-05,
|
| 972 |
+
"loss": 0.1334,
|
| 973 |
+
"step": 2500
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 1.09,
|
| 977 |
+
"eval_loss": 0.2424485832452774,
|
| 978 |
+
"eval_na_accuracy": 0.7509652376174927,
|
| 979 |
+
"eval_ordinal_accuracy": 0.6732158064842224,
|
| 980 |
+
"eval_ordinal_mae": 0.4105488359928131,
|
| 981 |
+
"eval_runtime": 161.6129,
|
| 982 |
+
"eval_samples_per_second": 24.621,
|
| 983 |
+
"eval_steps_per_second": 3.081,
|
| 984 |
+
"step": 2500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 1.1,
|
| 988 |
+
"grad_norm": 0.6302788257598877,
|
| 989 |
+
"learning_rate": 7.244541484716158e-05,
|
| 990 |
+
"loss": 0.1252,
|
| 991 |
+
"step": 2525
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 1.11,
|
| 995 |
+
"grad_norm": 3.8645241260528564,
|
| 996 |
+
"learning_rate": 7.217248908296944e-05,
|
| 997 |
+
"loss": 0.1444,
|
| 998 |
+
"step": 2550
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.12,
|
| 1002 |
+
"grad_norm": 0.7108765244483948,
|
| 1003 |
+
"learning_rate": 7.18995633187773e-05,
|
| 1004 |
+
"loss": 0.1273,
|
| 1005 |
+
"step": 2575
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.14,
|
| 1009 |
+
"grad_norm": 2.3784756660461426,
|
| 1010 |
+
"learning_rate": 7.162663755458516e-05,
|
| 1011 |
+
"loss": 0.1319,
|
| 1012 |
+
"step": 2600
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.14,
|
| 1016 |
+
"eval_loss": 0.23355962336063385,
|
| 1017 |
+
"eval_na_accuracy": 0.7741312980651855,
|
| 1018 |
+
"eval_ordinal_accuracy": 0.6711933016777039,
|
| 1019 |
+
"eval_ordinal_mae": 0.41552796959877014,
|
| 1020 |
+
"eval_runtime": 161.0033,
|
| 1021 |
+
"eval_samples_per_second": 24.714,
|
| 1022 |
+
"eval_steps_per_second": 3.093,
|
| 1023 |
+
"step": 2600
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 1.15,
|
| 1027 |
+
"grad_norm": 0.6569415330886841,
|
| 1028 |
+
"learning_rate": 7.135371179039302e-05,
|
| 1029 |
+
"loss": 0.1418,
|
| 1030 |
+
"step": 2625
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.16,
|
| 1034 |
+
"grad_norm": 2.9414520263671875,
|
| 1035 |
+
"learning_rate": 7.108078602620088e-05,
|
| 1036 |
+
"loss": 0.123,
|
| 1037 |
+
"step": 2650
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 1.17,
|
| 1041 |
+
"grad_norm": 0.5435983538627625,
|
| 1042 |
+
"learning_rate": 7.080786026200874e-05,
|
| 1043 |
+
"loss": 0.1458,
|
| 1044 |
+
"step": 2675
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.18,
|
| 1048 |
+
"grad_norm": 0.6094673275947571,
|
| 1049 |
+
"learning_rate": 7.05349344978166e-05,
|
| 1050 |
+
"loss": 0.1549,
|
| 1051 |
+
"step": 2700
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 1.18,
|
| 1055 |
+
"eval_loss": 0.25251126289367676,
|
| 1056 |
+
"eval_na_accuracy": 0.7586872577667236,
|
| 1057 |
+
"eval_ordinal_accuracy": 0.6625252962112427,
|
| 1058 |
+
"eval_ordinal_mae": 0.40396779775619507,
|
| 1059 |
+
"eval_runtime": 162.435,
|
| 1060 |
+
"eval_samples_per_second": 24.496,
|
| 1061 |
+
"eval_steps_per_second": 3.066,
|
| 1062 |
+
"step": 2700
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.19,
|
| 1066 |
+
"grad_norm": 0.4580962359905243,
|
| 1067 |
+
"learning_rate": 7.026200873362446e-05,
|
| 1068 |
+
"loss": 0.1382,
|
| 1069 |
+
"step": 2725
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.2,
|
| 1073 |
+
"grad_norm": 0.7736852765083313,
|
| 1074 |
+
"learning_rate": 6.998908296943232e-05,
|
| 1075 |
+
"loss": 0.1595,
|
| 1076 |
+
"step": 2750
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.21,
|
| 1080 |
+
"grad_norm": 1.1125404834747314,
|
| 1081 |
+
"learning_rate": 6.971615720524018e-05,
|
| 1082 |
+
"loss": 0.1071,
|
| 1083 |
+
"step": 2775
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 1.22,
|
| 1087 |
+
"grad_norm": 0.529449999332428,
|
| 1088 |
+
"learning_rate": 6.944323144104804e-05,
|
| 1089 |
+
"loss": 0.116,
|
| 1090 |
+
"step": 2800
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 1.22,
|
| 1094 |
+
"eval_loss": 0.25007495284080505,
|
| 1095 |
+
"eval_na_accuracy": 0.7664092779159546,
|
| 1096 |
+
"eval_ordinal_accuracy": 0.6370990872383118,
|
| 1097 |
+
"eval_ordinal_mae": 0.44249165058135986,
|
| 1098 |
+
"eval_runtime": 161.6127,
|
| 1099 |
+
"eval_samples_per_second": 24.621,
|
| 1100 |
+
"eval_steps_per_second": 3.081,
|
| 1101 |
+
"step": 2800
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.23,
|
| 1105 |
+
"grad_norm": 3.3976492881774902,
|
| 1106 |
+
"learning_rate": 6.91703056768559e-05,
|
| 1107 |
+
"loss": 0.1238,
|
| 1108 |
+
"step": 2825
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.24,
|
| 1112 |
+
"grad_norm": 0.9712594747543335,
|
| 1113 |
+
"learning_rate": 6.889737991266376e-05,
|
| 1114 |
+
"loss": 0.1313,
|
| 1115 |
+
"step": 2850
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.26,
|
| 1119 |
+
"grad_norm": 0.35930949449539185,
|
| 1120 |
+
"learning_rate": 6.862445414847162e-05,
|
| 1121 |
+
"loss": 0.1228,
|
| 1122 |
+
"step": 2875
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.27,
|
| 1126 |
+
"grad_norm": 1.873953938484192,
|
| 1127 |
+
"learning_rate": 6.835152838427948e-05,
|
| 1128 |
+
"loss": 0.1358,
|
| 1129 |
+
"step": 2900
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.27,
|
| 1133 |
+
"eval_loss": 0.23235850036144257,
|
| 1134 |
+
"eval_na_accuracy": 0.8185328245162964,
|
| 1135 |
+
"eval_ordinal_accuracy": 0.6498122215270996,
|
| 1136 |
+
"eval_ordinal_mae": 0.4136166572570801,
|
| 1137 |
+
"eval_runtime": 162.283,
|
| 1138 |
+
"eval_samples_per_second": 24.519,
|
| 1139 |
+
"eval_steps_per_second": 3.069,
|
| 1140 |
+
"step": 2900
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.28,
|
| 1144 |
+
"grad_norm": 1.8601669073104858,
|
| 1145 |
+
"learning_rate": 6.807860262008734e-05,
|
| 1146 |
+
"loss": 0.101,
|
| 1147 |
+
"step": 2925
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 1.29,
|
| 1151 |
+
"grad_norm": 0.9282914996147156,
|
| 1152 |
+
"learning_rate": 6.780567685589519e-05,
|
| 1153 |
+
"loss": 0.1435,
|
| 1154 |
+
"step": 2950
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 1.3,
|
| 1158 |
+
"grad_norm": 1.7728241682052612,
|
| 1159 |
+
"learning_rate": 6.753275109170306e-05,
|
| 1160 |
+
"loss": 0.1125,
|
| 1161 |
+
"step": 2975
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.31,
|
| 1165 |
+
"grad_norm": 0.5749986171722412,
|
| 1166 |
+
"learning_rate": 6.725982532751091e-05,
|
| 1167 |
+
"loss": 0.1614,
|
| 1168 |
+
"step": 3000
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 1.31,
|
| 1172 |
+
"eval_loss": 0.26365962624549866,
|
| 1173 |
+
"eval_na_accuracy": 0.7915058135986328,
|
| 1174 |
+
"eval_ordinal_accuracy": 0.6316093802452087,
|
| 1175 |
+
"eval_ordinal_mae": 0.43529626727104187,
|
| 1176 |
+
"eval_runtime": 161.4837,
|
| 1177 |
+
"eval_samples_per_second": 24.64,
|
| 1178 |
+
"eval_steps_per_second": 3.084,
|
| 1179 |
+
"step": 3000
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.32,
|
| 1183 |
+
"grad_norm": 0.44815096259117126,
|
| 1184 |
+
"learning_rate": 6.698689956331879e-05,
|
| 1185 |
+
"loss": 0.1436,
|
| 1186 |
+
"step": 3025
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.33,
|
| 1190 |
+
"grad_norm": 0.4672500491142273,
|
| 1191 |
+
"learning_rate": 6.671397379912665e-05,
|
| 1192 |
+
"loss": 0.0943,
|
| 1193 |
+
"step": 3050
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.34,
|
| 1197 |
+
"grad_norm": 0.8902660608291626,
|
| 1198 |
+
"learning_rate": 6.64410480349345e-05,
|
| 1199 |
+
"loss": 0.1258,
|
| 1200 |
+
"step": 3075
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.35,
|
| 1204 |
+
"grad_norm": 0.7342121005058289,
|
| 1205 |
+
"learning_rate": 6.616812227074237e-05,
|
| 1206 |
+
"loss": 0.1395,
|
| 1207 |
+
"step": 3100
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.35,
|
| 1211 |
+
"eval_loss": 0.2445780336856842,
|
| 1212 |
+
"eval_na_accuracy": 0.8011583089828491,
|
| 1213 |
+
"eval_ordinal_accuracy": 0.672637939453125,
|
| 1214 |
+
"eval_ordinal_mae": 0.4019619822502136,
|
| 1215 |
+
"eval_runtime": 161.5727,
|
| 1216 |
+
"eval_samples_per_second": 24.627,
|
| 1217 |
+
"eval_steps_per_second": 3.082,
|
| 1218 |
+
"step": 3100
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 1.36,
|
| 1222 |
+
"grad_norm": 0.7066202163696289,
|
| 1223 |
+
"learning_rate": 6.589519650655021e-05,
|
| 1224 |
+
"loss": 0.1627,
|
| 1225 |
+
"step": 3125
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 1.38,
|
| 1229 |
+
"grad_norm": 0.8218971490859985,
|
| 1230 |
+
"learning_rate": 6.562227074235809e-05,
|
| 1231 |
+
"loss": 0.1116,
|
| 1232 |
+
"step": 3150
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 1.39,
|
| 1236 |
+
"grad_norm": 2.74863600730896,
|
| 1237 |
+
"learning_rate": 6.534934497816593e-05,
|
| 1238 |
+
"loss": 0.1151,
|
| 1239 |
+
"step": 3175
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 1.4,
|
| 1243 |
+
"grad_norm": 2.341121196746826,
|
| 1244 |
+
"learning_rate": 6.507641921397381e-05,
|
| 1245 |
+
"loss": 0.1208,
|
| 1246 |
+
"step": 3200
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 1.4,
|
| 1250 |
+
"eval_loss": 0.24651078879833221,
|
| 1251 |
+
"eval_na_accuracy": 0.8243243098258972,
|
| 1252 |
+
"eval_ordinal_accuracy": 0.6763941049575806,
|
| 1253 |
+
"eval_ordinal_mae": 0.394586980342865,
|
| 1254 |
+
"eval_runtime": 160.9965,
|
| 1255 |
+
"eval_samples_per_second": 24.715,
|
| 1256 |
+
"eval_steps_per_second": 3.093,
|
| 1257 |
+
"step": 3200
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 1.41,
|
| 1261 |
+
"grad_norm": 0.610958993434906,
|
| 1262 |
+
"learning_rate": 6.480349344978166e-05,
|
| 1263 |
+
"loss": 0.1145,
|
| 1264 |
+
"step": 3225
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 1.42,
|
| 1268 |
+
"grad_norm": 0.43066203594207764,
|
| 1269 |
+
"learning_rate": 6.453056768558953e-05,
|
| 1270 |
+
"loss": 0.1322,
|
| 1271 |
+
"step": 3250
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 1.43,
|
| 1275 |
+
"grad_norm": 0.21925854682922363,
|
| 1276 |
+
"learning_rate": 6.425764192139738e-05,
|
| 1277 |
+
"loss": 0.1602,
|
| 1278 |
+
"step": 3275
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 1.44,
|
| 1282 |
+
"grad_norm": 0.34638360142707825,
|
| 1283 |
+
"learning_rate": 6.398471615720524e-05,
|
| 1284 |
+
"loss": 0.1432,
|
| 1285 |
+
"step": 3300
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 1.44,
|
| 1289 |
+
"eval_loss": 0.25519701838493347,
|
| 1290 |
+
"eval_na_accuracy": 0.8899613618850708,
|
| 1291 |
+
"eval_ordinal_accuracy": 0.6576133966445923,
|
| 1292 |
+
"eval_ordinal_mae": 0.3918676972389221,
|
| 1293 |
+
"eval_runtime": 160.3951,
|
| 1294 |
+
"eval_samples_per_second": 24.807,
|
| 1295 |
+
"eval_steps_per_second": 3.105,
|
| 1296 |
+
"step": 3300
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 1.45,
|
| 1300 |
+
"grad_norm": 0.5949413776397705,
|
| 1301 |
+
"learning_rate": 6.371179039301311e-05,
|
| 1302 |
+
"loss": 0.1249,
|
| 1303 |
+
"step": 3325
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 1.46,
|
| 1307 |
+
"grad_norm": 0.8993425965309143,
|
| 1308 |
+
"learning_rate": 6.343886462882096e-05,
|
| 1309 |
+
"loss": 0.1139,
|
| 1310 |
+
"step": 3350
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 1.47,
|
| 1314 |
+
"grad_norm": 0.7099699974060059,
|
| 1315 |
+
"learning_rate": 6.316593886462883e-05,
|
| 1316 |
+
"loss": 0.1019,
|
| 1317 |
+
"step": 3375
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 1.48,
|
| 1321 |
+
"grad_norm": 2.9975674152374268,
|
| 1322 |
+
"learning_rate": 6.289301310043668e-05,
|
| 1323 |
+
"loss": 0.1358,
|
| 1324 |
+
"step": 3400
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 1.48,
|
| 1328 |
+
"eval_loss": 0.2561098039150238,
|
| 1329 |
+
"eval_na_accuracy": 0.7895752787590027,
|
| 1330 |
+
"eval_ordinal_accuracy": 0.6795724034309387,
|
| 1331 |
+
"eval_ordinal_mae": 0.39841172099113464,
|
| 1332 |
+
"eval_runtime": 162.3278,
|
| 1333 |
+
"eval_samples_per_second": 24.512,
|
| 1334 |
+
"eval_steps_per_second": 3.068,
|
| 1335 |
+
"step": 3400
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 1.5,
|
| 1339 |
+
"grad_norm": 0.259729266166687,
|
| 1340 |
+
"learning_rate": 6.262008733624455e-05,
|
| 1341 |
+
"loss": 0.1486,
|
| 1342 |
+
"step": 3425
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 1.51,
|
| 1346 |
+
"grad_norm": 4.243904113769531,
|
| 1347 |
+
"learning_rate": 6.23471615720524e-05,
|
| 1348 |
+
"loss": 0.1652,
|
| 1349 |
+
"step": 3450
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 1.52,
|
| 1353 |
+
"grad_norm": 2.9280548095703125,
|
| 1354 |
+
"learning_rate": 6.207423580786027e-05,
|
| 1355 |
+
"loss": 0.1699,
|
| 1356 |
+
"step": 3475
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 1.53,
|
| 1360 |
+
"grad_norm": 0.5303541421890259,
|
| 1361 |
+
"learning_rate": 6.180131004366812e-05,
|
| 1362 |
+
"loss": 0.0877,
|
| 1363 |
+
"step": 3500
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 1.53,
|
| 1367 |
+
"eval_loss": 0.23811650276184082,
|
| 1368 |
+
"eval_na_accuracy": 0.7876448035240173,
|
| 1369 |
+
"eval_ordinal_accuracy": 0.6821727752685547,
|
| 1370 |
+
"eval_ordinal_mae": 0.3901168704032898,
|
| 1371 |
+
"eval_runtime": 162.0532,
|
| 1372 |
+
"eval_samples_per_second": 24.554,
|
| 1373 |
+
"eval_steps_per_second": 3.073,
|
| 1374 |
+
"step": 3500
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.54,
|
| 1378 |
+
"grad_norm": 0.42129185795783997,
|
| 1379 |
+
"learning_rate": 6.152838427947598e-05,
|
| 1380 |
+
"loss": 0.1149,
|
| 1381 |
+
"step": 3525
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.55,
|
| 1385 |
+
"grad_norm": 1.27903151512146,
|
| 1386 |
+
"learning_rate": 6.125545851528384e-05,
|
| 1387 |
+
"loss": 0.1208,
|
| 1388 |
+
"step": 3550
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.56,
|
| 1392 |
+
"grad_norm": 3.1208670139312744,
|
| 1393 |
+
"learning_rate": 6.09825327510917e-05,
|
| 1394 |
+
"loss": 0.1106,
|
| 1395 |
+
"step": 3575
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.57,
|
| 1399 |
+
"grad_norm": 3.3159916400909424,
|
| 1400 |
+
"learning_rate": 6.070960698689957e-05,
|
| 1401 |
+
"loss": 0.1212,
|
| 1402 |
+
"step": 3600
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.57,
|
| 1406 |
+
"eval_loss": 0.2600151598453522,
|
| 1407 |
+
"eval_na_accuracy": 0.7258687019348145,
|
| 1408 |
+
"eval_ordinal_accuracy": 0.6948858499526978,
|
| 1409 |
+
"eval_ordinal_mae": 0.400073766708374,
|
| 1410 |
+
"eval_runtime": 160.7378,
|
| 1411 |
+
"eval_samples_per_second": 24.755,
|
| 1412 |
+
"eval_steps_per_second": 3.098,
|
| 1413 |
+
"step": 3600
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.58,
|
| 1417 |
+
"grad_norm": 3.3880019187927246,
|
| 1418 |
+
"learning_rate": 6.043668122270742e-05,
|
| 1419 |
+
"loss": 0.1593,
|
| 1420 |
+
"step": 3625
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.59,
|
| 1424 |
+
"grad_norm": 2.641679286956787,
|
| 1425 |
+
"learning_rate": 6.016375545851529e-05,
|
| 1426 |
+
"loss": 0.1489,
|
| 1427 |
+
"step": 3650
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 1.6,
|
| 1431 |
+
"grad_norm": 1.1284505128860474,
|
| 1432 |
+
"learning_rate": 5.9890829694323144e-05,
|
| 1433 |
+
"loss": 0.1097,
|
| 1434 |
+
"step": 3675
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 1.62,
|
| 1438 |
+
"grad_norm": 1.6684277057647705,
|
| 1439 |
+
"learning_rate": 5.9617903930131005e-05,
|
| 1440 |
+
"loss": 0.1917,
|
| 1441 |
+
"step": 3700
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 1.62,
|
| 1445 |
+
"eval_loss": 0.24585247039794922,
|
| 1446 |
+
"eval_na_accuracy": 0.7818532586097717,
|
| 1447 |
+
"eval_ordinal_accuracy": 0.6893961429595947,
|
| 1448 |
+
"eval_ordinal_mae": 0.3889385461807251,
|
| 1449 |
+
"eval_runtime": 161.3514,
|
| 1450 |
+
"eval_samples_per_second": 24.66,
|
| 1451 |
+
"eval_steps_per_second": 3.086,
|
| 1452 |
+
"step": 3700
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.63,
|
| 1456 |
+
"grad_norm": 0.4128411114215851,
|
| 1457 |
+
"learning_rate": 5.934497816593887e-05,
|
| 1458 |
+
"loss": 0.1423,
|
| 1459 |
+
"step": 3725
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.64,
|
| 1463 |
+
"grad_norm": 1.0505822896957397,
|
| 1464 |
+
"learning_rate": 5.9072052401746726e-05,
|
| 1465 |
+
"loss": 0.1257,
|
| 1466 |
+
"step": 3750
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.65,
|
| 1470 |
+
"grad_norm": 0.8468612432479858,
|
| 1471 |
+
"learning_rate": 5.879912663755459e-05,
|
| 1472 |
+
"loss": 0.1296,
|
| 1473 |
+
"step": 3775
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.66,
|
| 1477 |
+
"grad_norm": 0.31584060192108154,
|
| 1478 |
+
"learning_rate": 5.852620087336245e-05,
|
| 1479 |
+
"loss": 0.1175,
|
| 1480 |
+
"step": 3800
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.66,
|
| 1484 |
+
"eval_loss": 0.2443784475326538,
|
| 1485 |
+
"eval_na_accuracy": 0.7741312980651855,
|
| 1486 |
+
"eval_ordinal_accuracy": 0.6818838715553284,
|
| 1487 |
+
"eval_ordinal_mae": 0.3937167227268219,
|
| 1488 |
+
"eval_runtime": 161.5524,
|
| 1489 |
+
"eval_samples_per_second": 24.63,
|
| 1490 |
+
"eval_steps_per_second": 3.083,
|
| 1491 |
+
"step": 3800
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 1.67,
|
| 1495 |
+
"grad_norm": 5.336325645446777,
|
| 1496 |
+
"learning_rate": 5.8253275109170314e-05,
|
| 1497 |
+
"loss": 0.1638,
|
| 1498 |
+
"step": 3825
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 1.68,
|
| 1502 |
+
"grad_norm": 1.6800111532211304,
|
| 1503 |
+
"learning_rate": 5.798034934497817e-05,
|
| 1504 |
+
"loss": 0.1314,
|
| 1505 |
+
"step": 3850
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 1.69,
|
| 1509 |
+
"grad_norm": 1.491882085800171,
|
| 1510 |
+
"learning_rate": 5.770742358078602e-05,
|
| 1511 |
+
"loss": 0.1415,
|
| 1512 |
+
"step": 3875
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 1.7,
|
| 1516 |
+
"grad_norm": 2.401737928390503,
|
| 1517 |
+
"learning_rate": 5.743449781659389e-05,
|
| 1518 |
+
"loss": 0.1522,
|
| 1519 |
+
"step": 3900
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 1.7,
|
| 1523 |
+
"eval_loss": 0.2472807914018631,
|
| 1524 |
+
"eval_na_accuracy": 0.8050193190574646,
|
| 1525 |
+
"eval_ordinal_accuracy": 0.6607916951179504,
|
| 1526 |
+
"eval_ordinal_mae": 0.40097710490226746,
|
| 1527 |
+
"eval_runtime": 160.8219,
|
| 1528 |
+
"eval_samples_per_second": 24.742,
|
| 1529 |
+
"eval_steps_per_second": 3.097,
|
| 1530 |
+
"step": 3900
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 1.71,
|
| 1534 |
+
"grad_norm": 0.6720189452171326,
|
| 1535 |
+
"learning_rate": 5.716157205240175e-05,
|
| 1536 |
+
"loss": 0.1239,
|
| 1537 |
+
"step": 3925
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 1.72,
|
| 1541 |
+
"grad_norm": 2.349804639816284,
|
| 1542 |
+
"learning_rate": 5.688864628820961e-05,
|
| 1543 |
+
"loss": 0.1318,
|
| 1544 |
+
"step": 3950
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 1.74,
|
| 1548 |
+
"grad_norm": 0.732524573802948,
|
| 1549 |
+
"learning_rate": 5.661572052401747e-05,
|
| 1550 |
+
"loss": 0.1423,
|
| 1551 |
+
"step": 3975
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 1.75,
|
| 1555 |
+
"grad_norm": 0.4833851456642151,
|
| 1556 |
+
"learning_rate": 5.634279475982534e-05,
|
| 1557 |
+
"loss": 0.1027,
|
| 1558 |
+
"step": 4000
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 1.75,
|
| 1562 |
+
"eval_loss": 0.23541530966758728,
|
| 1563 |
+
"eval_na_accuracy": 0.7837837934494019,
|
| 1564 |
+
"eval_ordinal_accuracy": 0.6477896571159363,
|
| 1565 |
+
"eval_ordinal_mae": 0.420841783285141,
|
| 1566 |
+
"eval_runtime": 155.1162,
|
| 1567 |
+
"eval_samples_per_second": 25.652,
|
| 1568 |
+
"eval_steps_per_second": 3.21,
|
| 1569 |
+
"step": 4000
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 1.76,
|
| 1573 |
+
"grad_norm": 0.5297548174858093,
|
| 1574 |
+
"learning_rate": 5.606986899563319e-05,
|
| 1575 |
+
"loss": 0.1596,
|
| 1576 |
+
"step": 4025
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 1.77,
|
| 1580 |
+
"grad_norm": 0.5475759506225586,
|
| 1581 |
+
"learning_rate": 5.5796943231441045e-05,
|
| 1582 |
+
"loss": 0.1272,
|
| 1583 |
+
"step": 4050
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 1.78,
|
| 1587 |
+
"grad_norm": 2.1666433811187744,
|
| 1588 |
+
"learning_rate": 5.552401746724891e-05,
|
| 1589 |
+
"loss": 0.1382,
|
| 1590 |
+
"step": 4075
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 1.79,
|
| 1594 |
+
"grad_norm": 3.707628011703491,
|
| 1595 |
+
"learning_rate": 5.5251091703056766e-05,
|
| 1596 |
+
"loss": 0.1343,
|
| 1597 |
+
"step": 4100
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 1.79,
|
| 1601 |
+
"eval_loss": 0.228408545255661,
|
| 1602 |
+
"eval_na_accuracy": 0.799227774143219,
|
| 1603 |
+
"eval_ordinal_accuracy": 0.6743715405464172,
|
| 1604 |
+
"eval_ordinal_mae": 0.3976960778236389,
|
| 1605 |
+
"eval_runtime": 158.2657,
|
| 1606 |
+
"eval_samples_per_second": 25.141,
|
| 1607 |
+
"eval_steps_per_second": 3.147,
|
| 1608 |
+
"step": 4100
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 1.8,
|
| 1612 |
+
"grad_norm": 0.5081536769866943,
|
| 1613 |
+
"learning_rate": 5.497816593886463e-05,
|
| 1614 |
+
"loss": 0.1381,
|
| 1615 |
+
"step": 4125
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 1.81,
|
| 1619 |
+
"grad_norm": 0.7783900499343872,
|
| 1620 |
+
"learning_rate": 5.470524017467249e-05,
|
| 1621 |
+
"loss": 0.1391,
|
| 1622 |
+
"step": 4150
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 1.82,
|
| 1626 |
+
"grad_norm": 0.6352062821388245,
|
| 1627 |
+
"learning_rate": 5.4432314410480354e-05,
|
| 1628 |
+
"loss": 0.1157,
|
| 1629 |
+
"step": 4175
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 1.83,
|
| 1633 |
+
"grad_norm": 0.6280900835990906,
|
| 1634 |
+
"learning_rate": 5.4159388646288215e-05,
|
| 1635 |
+
"loss": 0.1552,
|
| 1636 |
+
"step": 4200
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 1.83,
|
| 1640 |
+
"eval_loss": 0.2606957256793976,
|
| 1641 |
+
"eval_na_accuracy": 0.7779922485351562,
|
| 1642 |
+
"eval_ordinal_accuracy": 0.6714822053909302,
|
| 1643 |
+
"eval_ordinal_mae": 0.4044625461101532,
|
| 1644 |
+
"eval_runtime": 154.4211,
|
| 1645 |
+
"eval_samples_per_second": 25.767,
|
| 1646 |
+
"eval_steps_per_second": 3.225,
|
| 1647 |
+
"step": 4200
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.84,
|
| 1651 |
+
"grad_norm": 1.6340936422348022,
|
| 1652 |
+
"learning_rate": 5.388646288209607e-05,
|
| 1653 |
+
"loss": 0.1448,
|
| 1654 |
+
"step": 4225
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 1.86,
|
| 1658 |
+
"grad_norm": 3.3546087741851807,
|
| 1659 |
+
"learning_rate": 5.3613537117903936e-05,
|
| 1660 |
+
"loss": 0.1485,
|
| 1661 |
+
"step": 4250
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.87,
|
| 1665 |
+
"grad_norm": 0.5650043487548828,
|
| 1666 |
+
"learning_rate": 5.334061135371179e-05,
|
| 1667 |
+
"loss": 0.127,
|
| 1668 |
+
"step": 4275
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 1.88,
|
| 1672 |
+
"grad_norm": 0.8098490834236145,
|
| 1673 |
+
"learning_rate": 5.306768558951966e-05,
|
| 1674 |
+
"loss": 0.1172,
|
| 1675 |
+
"step": 4300
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 1.88,
|
| 1679 |
+
"eval_loss": 0.24209196865558624,
|
| 1680 |
+
"eval_na_accuracy": 0.8281853199005127,
|
| 1681 |
+
"eval_ordinal_accuracy": 0.6665703654289246,
|
| 1682 |
+
"eval_ordinal_mae": 0.3971348702907562,
|
| 1683 |
+
"eval_runtime": 153.4086,
|
| 1684 |
+
"eval_samples_per_second": 25.937,
|
| 1685 |
+
"eval_steps_per_second": 3.246,
|
| 1686 |
+
"step": 4300
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 1.89,
|
| 1690 |
+
"grad_norm": 1.127596378326416,
|
| 1691 |
+
"learning_rate": 5.2805676855895205e-05,
|
| 1692 |
+
"loss": 0.1808,
|
| 1693 |
+
"step": 4325
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 1.9,
|
| 1697 |
+
"grad_norm": 0.5557155609130859,
|
| 1698 |
+
"learning_rate": 5.253275109170306e-05,
|
| 1699 |
+
"loss": 0.09,
|
| 1700 |
+
"step": 4350
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 1.91,
|
| 1704 |
+
"grad_norm": 0.31405743956565857,
|
| 1705 |
+
"learning_rate": 5.2259825327510926e-05,
|
| 1706 |
+
"loss": 0.1061,
|
| 1707 |
+
"step": 4375
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 1.92,
|
| 1711 |
+
"grad_norm": 6.475078105926514,
|
| 1712 |
+
"learning_rate": 5.198689956331878e-05,
|
| 1713 |
+
"loss": 0.1381,
|
| 1714 |
+
"step": 4400
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 1.92,
|
| 1718 |
+
"eval_loss": 0.2253342866897583,
|
| 1719 |
+
"eval_na_accuracy": 0.7857142686843872,
|
| 1720 |
+
"eval_ordinal_accuracy": 0.6792834401130676,
|
| 1721 |
+
"eval_ordinal_mae": 0.3813394010066986,
|
| 1722 |
+
"eval_runtime": 156.7221,
|
| 1723 |
+
"eval_samples_per_second": 25.389,
|
| 1724 |
+
"eval_steps_per_second": 3.178,
|
| 1725 |
+
"step": 4400
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.93,
|
| 1729 |
+
"grad_norm": 0.5825577974319458,
|
| 1730 |
+
"learning_rate": 5.171397379912663e-05,
|
| 1731 |
+
"loss": 0.1524,
|
| 1732 |
+
"step": 4425
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.94,
|
| 1736 |
+
"grad_norm": 1.4979143142700195,
|
| 1737 |
+
"learning_rate": 5.14410480349345e-05,
|
| 1738 |
+
"loss": 0.142,
|
| 1739 |
+
"step": 4450
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.95,
|
| 1743 |
+
"grad_norm": 0.5638359785079956,
|
| 1744 |
+
"learning_rate": 5.116812227074236e-05,
|
| 1745 |
+
"loss": 0.1225,
|
| 1746 |
+
"step": 4475
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.97,
|
| 1750 |
+
"grad_norm": 0.44809991121292114,
|
| 1751 |
+
"learning_rate": 5.089519650655022e-05,
|
| 1752 |
+
"loss": 0.1282,
|
| 1753 |
+
"step": 4500
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.97,
|
| 1757 |
+
"eval_loss": 0.23353050649166107,
|
| 1758 |
+
"eval_na_accuracy": 0.8436293601989746,
|
| 1759 |
+
"eval_ordinal_accuracy": 0.6509679555892944,
|
| 1760 |
+
"eval_ordinal_mae": 0.41455620527267456,
|
| 1761 |
+
"eval_runtime": 154.2508,
|
| 1762 |
+
"eval_samples_per_second": 25.796,
|
| 1763 |
+
"eval_steps_per_second": 3.229,
|
| 1764 |
+
"step": 4500
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 1.98,
|
| 1768 |
+
"grad_norm": 2.9640109539031982,
|
| 1769 |
+
"learning_rate": 5.062227074235808e-05,
|
| 1770 |
+
"loss": 0.1057,
|
| 1771 |
+
"step": 4525
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 1.99,
|
| 1775 |
+
"grad_norm": 0.44117558002471924,
|
| 1776 |
+
"learning_rate": 5.034934497816595e-05,
|
| 1777 |
+
"loss": 0.13,
|
| 1778 |
+
"step": 4550
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 2.0,
|
| 1782 |
+
"grad_norm": 0.6167708039283752,
|
| 1783 |
+
"learning_rate": 5.00764192139738e-05,
|
| 1784 |
+
"loss": 0.1223,
|
| 1785 |
+
"step": 4575
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 2.01,
|
| 1789 |
+
"grad_norm": 2.0781619548797607,
|
| 1790 |
+
"learning_rate": 4.9803493449781664e-05,
|
| 1791 |
+
"loss": 0.0734,
|
| 1792 |
+
"step": 4600
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 2.01,
|
| 1796 |
+
"eval_loss": 0.23820282518863678,
|
| 1797 |
+
"eval_na_accuracy": 0.7895752787590027,
|
| 1798 |
+
"eval_ordinal_accuracy": 0.689685046672821,
|
| 1799 |
+
"eval_ordinal_mae": 0.38021621108055115,
|
| 1800 |
+
"eval_runtime": 154.7894,
|
| 1801 |
+
"eval_samples_per_second": 25.706,
|
| 1802 |
+
"eval_steps_per_second": 3.217,
|
| 1803 |
+
"step": 4600
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 2.02,
|
| 1807 |
+
"grad_norm": 3.165067195892334,
|
| 1808 |
+
"learning_rate": 4.9530567685589524e-05,
|
| 1809 |
+
"loss": 0.08,
|
| 1810 |
+
"step": 4625
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 2.03,
|
| 1814 |
+
"grad_norm": 0.43800944089889526,
|
| 1815 |
+
"learning_rate": 4.9257641921397385e-05,
|
| 1816 |
+
"loss": 0.0571,
|
| 1817 |
+
"step": 4650
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 2.04,
|
| 1821 |
+
"grad_norm": 0.45996198058128357,
|
| 1822 |
+
"learning_rate": 4.898471615720524e-05,
|
| 1823 |
+
"loss": 0.0579,
|
| 1824 |
+
"step": 4675
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 2.05,
|
| 1828 |
+
"grad_norm": 1.9151467084884644,
|
| 1829 |
+
"learning_rate": 4.87117903930131e-05,
|
| 1830 |
+
"loss": 0.1046,
|
| 1831 |
+
"step": 4700
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 2.05,
|
| 1835 |
+
"eval_loss": 0.2358408272266388,
|
| 1836 |
+
"eval_na_accuracy": 0.8011583089828491,
|
| 1837 |
+
"eval_ordinal_accuracy": 0.6873735785484314,
|
| 1838 |
+
"eval_ordinal_mae": 0.36946654319763184,
|
| 1839 |
+
"eval_runtime": 150.9459,
|
| 1840 |
+
"eval_samples_per_second": 26.36,
|
| 1841 |
+
"eval_steps_per_second": 3.299,
|
| 1842 |
+
"step": 4700
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 2.06,
|
| 1846 |
+
"grad_norm": 0.5566712021827698,
|
| 1847 |
+
"learning_rate": 4.843886462882096e-05,
|
| 1848 |
+
"loss": 0.068,
|
| 1849 |
+
"step": 4725
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 2.07,
|
| 1853 |
+
"grad_norm": 0.5846825838088989,
|
| 1854 |
+
"learning_rate": 4.8165938864628827e-05,
|
| 1855 |
+
"loss": 0.0487,
|
| 1856 |
+
"step": 4750
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 2.09,
|
| 1860 |
+
"grad_norm": 0.3993060290813446,
|
| 1861 |
+
"learning_rate": 4.789301310043669e-05,
|
| 1862 |
+
"loss": 0.0546,
|
| 1863 |
+
"step": 4775
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 2.1,
|
| 1867 |
+
"grad_norm": 0.6624791026115417,
|
| 1868 |
+
"learning_rate": 4.762008733624455e-05,
|
| 1869 |
+
"loss": 0.0529,
|
| 1870 |
+
"step": 4800
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 2.1,
|
| 1874 |
+
"eval_loss": 0.246298685669899,
|
| 1875 |
+
"eval_na_accuracy": 0.7934362888336182,
|
| 1876 |
+
"eval_ordinal_accuracy": 0.7096214890480042,
|
| 1877 |
+
"eval_ordinal_mae": 0.3595849573612213,
|
| 1878 |
+
"eval_runtime": 153.0771,
|
| 1879 |
+
"eval_samples_per_second": 25.993,
|
| 1880 |
+
"eval_steps_per_second": 3.253,
|
| 1881 |
+
"step": 4800
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 2.11,
|
| 1885 |
+
"grad_norm": 0.33810412883758545,
|
| 1886 |
+
"learning_rate": 4.734716157205241e-05,
|
| 1887 |
+
"loss": 0.0625,
|
| 1888 |
+
"step": 4825
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 2.12,
|
| 1892 |
+
"grad_norm": 3.0376217365264893,
|
| 1893 |
+
"learning_rate": 4.707423580786026e-05,
|
| 1894 |
+
"loss": 0.0749,
|
| 1895 |
+
"step": 4850
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 2.13,
|
| 1899 |
+
"grad_norm": 0.4552454352378845,
|
| 1900 |
+
"learning_rate": 4.680131004366812e-05,
|
| 1901 |
+
"loss": 0.0536,
|
| 1902 |
+
"step": 4875
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 2.14,
|
| 1906 |
+
"grad_norm": 0.6775699257850647,
|
| 1907 |
+
"learning_rate": 4.652838427947598e-05,
|
| 1908 |
+
"loss": 0.0687,
|
| 1909 |
+
"step": 4900
|
| 1910 |
+
},
|
| 1911 |
+
{
|
| 1912 |
+
"epoch": 2.14,
|
| 1913 |
+
"eval_loss": 0.26146525144577026,
|
| 1914 |
+
"eval_na_accuracy": 0.7857142686843872,
|
| 1915 |
+
"eval_ordinal_accuracy": 0.6737936735153198,
|
| 1916 |
+
"eval_ordinal_mae": 0.39211294054985046,
|
| 1917 |
+
"eval_runtime": 156.1814,
|
| 1918 |
+
"eval_samples_per_second": 25.477,
|
| 1919 |
+
"eval_steps_per_second": 3.189,
|
| 1920 |
+
"step": 4900
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 2.15,
|
| 1924 |
+
"grad_norm": 0.623523473739624,
|
| 1925 |
+
"learning_rate": 4.625545851528384e-05,
|
| 1926 |
+
"loss": 0.068,
|
| 1927 |
+
"step": 4925
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 2.16,
|
| 1931 |
+
"grad_norm": 0.5668771862983704,
|
| 1932 |
+
"learning_rate": 4.5982532751091704e-05,
|
| 1933 |
+
"loss": 0.0684,
|
| 1934 |
+
"step": 4950
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 2.17,
|
| 1938 |
+
"grad_norm": 0.16505593061447144,
|
| 1939 |
+
"learning_rate": 4.5709606986899564e-05,
|
| 1940 |
+
"loss": 0.0546,
|
| 1941 |
+
"step": 4975
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 2.18,
|
| 1945 |
+
"grad_norm": 0.5560925602912903,
|
| 1946 |
+
"learning_rate": 4.5436681222707425e-05,
|
| 1947 |
+
"loss": 0.0613,
|
| 1948 |
+
"step": 5000
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 2.18,
|
| 1952 |
+
"eval_loss": 0.2542937397956848,
|
| 1953 |
+
"eval_na_accuracy": 0.8108108043670654,
|
| 1954 |
+
"eval_ordinal_accuracy": 0.6876625418663025,
|
| 1955 |
+
"eval_ordinal_mae": 0.36514100432395935,
|
| 1956 |
+
"eval_runtime": 156.8699,
|
| 1957 |
+
"eval_samples_per_second": 25.365,
|
| 1958 |
+
"eval_steps_per_second": 3.175,
|
| 1959 |
+
"step": 5000
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 2.19,
|
| 1963 |
+
"grad_norm": 0.440731942653656,
|
| 1964 |
+
"learning_rate": 4.5163755458515285e-05,
|
| 1965 |
+
"loss": 0.0967,
|
| 1966 |
+
"step": 5025
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 2.21,
|
| 1970 |
+
"grad_norm": 0.26702314615249634,
|
| 1971 |
+
"learning_rate": 4.4890829694323146e-05,
|
| 1972 |
+
"loss": 0.0499,
|
| 1973 |
+
"step": 5050
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 2.22,
|
| 1977 |
+
"grad_norm": 0.9617776274681091,
|
| 1978 |
+
"learning_rate": 4.4617903930131006e-05,
|
| 1979 |
+
"loss": 0.0792,
|
| 1980 |
+
"step": 5075
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 2.23,
|
| 1984 |
+
"grad_norm": 3.431128740310669,
|
| 1985 |
+
"learning_rate": 4.434497816593887e-05,
|
| 1986 |
+
"loss": 0.0591,
|
| 1987 |
+
"step": 5100
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 2.23,
|
| 1991 |
+
"eval_loss": 0.25389814376831055,
|
| 1992 |
+
"eval_na_accuracy": 0.7915058135986328,
|
| 1993 |
+
"eval_ordinal_accuracy": 0.6885293126106262,
|
| 1994 |
+
"eval_ordinal_mae": 0.3693314790725708,
|
| 1995 |
+
"eval_runtime": 155.0651,
|
| 1996 |
+
"eval_samples_per_second": 25.66,
|
| 1997 |
+
"eval_steps_per_second": 3.212,
|
| 1998 |
+
"step": 5100
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 2.24,
|
| 2002 |
+
"grad_norm": 5.355819225311279,
|
| 2003 |
+
"learning_rate": 4.407205240174673e-05,
|
| 2004 |
+
"loss": 0.0611,
|
| 2005 |
+
"step": 5125
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 2.25,
|
| 2009 |
+
"grad_norm": 0.4490479528903961,
|
| 2010 |
+
"learning_rate": 4.379912663755459e-05,
|
| 2011 |
+
"loss": 0.0676,
|
| 2012 |
+
"step": 5150
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.26,
|
| 2016 |
+
"grad_norm": 0.594838559627533,
|
| 2017 |
+
"learning_rate": 4.352620087336245e-05,
|
| 2018 |
+
"loss": 0.0567,
|
| 2019 |
+
"step": 5175
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 2.27,
|
| 2023 |
+
"grad_norm": 0.2912037670612335,
|
| 2024 |
+
"learning_rate": 4.325327510917031e-05,
|
| 2025 |
+
"loss": 0.0474,
|
| 2026 |
+
"step": 5200
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 2.27,
|
| 2030 |
+
"eval_loss": 0.26495158672332764,
|
| 2031 |
+
"eval_na_accuracy": 0.799227774143219,
|
| 2032 |
+
"eval_ordinal_accuracy": 0.6836174726486206,
|
| 2033 |
+
"eval_ordinal_mae": 0.3721810579299927,
|
| 2034 |
+
"eval_runtime": 156.3533,
|
| 2035 |
+
"eval_samples_per_second": 25.449,
|
| 2036 |
+
"eval_steps_per_second": 3.185,
|
| 2037 |
+
"step": 5200
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 2.28,
|
| 2041 |
+
"grad_norm": 1.547253966331482,
|
| 2042 |
+
"learning_rate": 4.298034934497817e-05,
|
| 2043 |
+
"loss": 0.0583,
|
| 2044 |
+
"step": 5225
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 2.29,
|
| 2048 |
+
"grad_norm": 0.6619101762771606,
|
| 2049 |
+
"learning_rate": 4.270742358078603e-05,
|
| 2050 |
+
"loss": 0.0713,
|
| 2051 |
+
"step": 5250
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 2.3,
|
| 2055 |
+
"grad_norm": 0.6830999255180359,
|
| 2056 |
+
"learning_rate": 4.243449781659389e-05,
|
| 2057 |
+
"loss": 0.068,
|
| 2058 |
+
"step": 5275
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 2.31,
|
| 2062 |
+
"grad_norm": 0.6977065801620483,
|
| 2063 |
+
"learning_rate": 4.216157205240175e-05,
|
| 2064 |
+
"loss": 0.0511,
|
| 2065 |
+
"step": 5300
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 2.31,
|
| 2069 |
+
"eval_loss": 0.2630845010280609,
|
| 2070 |
+
"eval_na_accuracy": 0.8127413392066956,
|
| 2071 |
+
"eval_ordinal_accuracy": 0.686795711517334,
|
| 2072 |
+
"eval_ordinal_mae": 0.36813271045684814,
|
| 2073 |
+
"eval_runtime": 154.8738,
|
| 2074 |
+
"eval_samples_per_second": 25.692,
|
| 2075 |
+
"eval_steps_per_second": 3.216,
|
| 2076 |
+
"step": 5300
|
| 2077 |
+
},
|
| 2078 |
+
{
|
| 2079 |
+
"epoch": 2.33,
|
| 2080 |
+
"grad_norm": 0.8015338778495789,
|
| 2081 |
+
"learning_rate": 4.188864628820961e-05,
|
| 2082 |
+
"loss": 0.0511,
|
| 2083 |
+
"step": 5325
|
| 2084 |
+
},
|
| 2085 |
+
{
|
| 2086 |
+
"epoch": 2.34,
|
| 2087 |
+
"grad_norm": 2.4707908630371094,
|
| 2088 |
+
"learning_rate": 4.161572052401747e-05,
|
| 2089 |
+
"loss": 0.0704,
|
| 2090 |
+
"step": 5350
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 2.35,
|
| 2094 |
+
"grad_norm": 0.526327908039093,
|
| 2095 |
+
"learning_rate": 4.134279475982533e-05,
|
| 2096 |
+
"loss": 0.0824,
|
| 2097 |
+
"step": 5375
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 2.36,
|
| 2101 |
+
"grad_norm": 1.6800874471664429,
|
| 2102 |
+
"learning_rate": 4.1069868995633186e-05,
|
| 2103 |
+
"loss": 0.0683,
|
| 2104 |
+
"step": 5400
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"epoch": 2.36,
|
| 2108 |
+
"eval_loss": 0.271382212638855,
|
| 2109 |
+
"eval_na_accuracy": 0.7837837934494019,
|
| 2110 |
+
"eval_ordinal_accuracy": 0.6954637169837952,
|
| 2111 |
+
"eval_ordinal_mae": 0.36302649974823,
|
| 2112 |
+
"eval_runtime": 155.8769,
|
| 2113 |
+
"eval_samples_per_second": 25.527,
|
| 2114 |
+
"eval_steps_per_second": 3.195,
|
| 2115 |
+
"step": 5400
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 2.37,
|
| 2119 |
+
"grad_norm": 0.5335835814476013,
|
| 2120 |
+
"learning_rate": 4.0796943231441046e-05,
|
| 2121 |
+
"loss": 0.056,
|
| 2122 |
+
"step": 5425
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 2.38,
|
| 2126 |
+
"grad_norm": 2.2423832416534424,
|
| 2127 |
+
"learning_rate": 4.052401746724891e-05,
|
| 2128 |
+
"loss": 0.0787,
|
| 2129 |
+
"step": 5450
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 2.39,
|
| 2133 |
+
"grad_norm": 0.558754026889801,
|
| 2134 |
+
"learning_rate": 4.025109170305677e-05,
|
| 2135 |
+
"loss": 0.0481,
|
| 2136 |
+
"step": 5475
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 2.4,
|
| 2140 |
+
"grad_norm": 0.6908044815063477,
|
| 2141 |
+
"learning_rate": 3.9978165938864635e-05,
|
| 2142 |
+
"loss": 0.0654,
|
| 2143 |
+
"step": 5500
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 2.4,
|
| 2147 |
+
"eval_loss": 0.27688542008399963,
|
| 2148 |
+
"eval_na_accuracy": 0.799227774143219,
|
| 2149 |
+
"eval_ordinal_accuracy": 0.6787055730819702,
|
| 2150 |
+
"eval_ordinal_mae": 0.3673117458820343,
|
| 2151 |
+
"eval_runtime": 154.1587,
|
| 2152 |
+
"eval_samples_per_second": 25.811,
|
| 2153 |
+
"eval_steps_per_second": 3.23,
|
| 2154 |
+
"step": 5500
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 2.41,
|
| 2158 |
+
"grad_norm": 0.43695610761642456,
|
| 2159 |
+
"learning_rate": 3.9705240174672495e-05,
|
| 2160 |
+
"loss": 0.0539,
|
| 2161 |
+
"step": 5525
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 2.42,
|
| 2165 |
+
"grad_norm": 3.290745496749878,
|
| 2166 |
+
"learning_rate": 3.9432314410480356e-05,
|
| 2167 |
+
"loss": 0.0608,
|
| 2168 |
+
"step": 5550
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 2.43,
|
| 2172 |
+
"grad_norm": 0.25710350275039673,
|
| 2173 |
+
"learning_rate": 3.9159388646288216e-05,
|
| 2174 |
+
"loss": 0.0657,
|
| 2175 |
+
"step": 5575
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 2.45,
|
| 2179 |
+
"grad_norm": 0.6269412040710449,
|
| 2180 |
+
"learning_rate": 3.888646288209607e-05,
|
| 2181 |
+
"loss": 0.0581,
|
| 2182 |
+
"step": 5600
|
| 2183 |
+
},
|
| 2184 |
+
{
|
| 2185 |
+
"epoch": 2.45,
|
| 2186 |
+
"eval_loss": 0.27770209312438965,
|
| 2187 |
+
"eval_na_accuracy": 0.799227774143219,
|
| 2188 |
+
"eval_ordinal_accuracy": 0.6951748132705688,
|
| 2189 |
+
"eval_ordinal_mae": 0.3627748191356659,
|
| 2190 |
+
"eval_runtime": 157.9718,
|
| 2191 |
+
"eval_samples_per_second": 25.188,
|
| 2192 |
+
"eval_steps_per_second": 3.152,
|
| 2193 |
+
"step": 5600
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 2.46,
|
| 2197 |
+
"grad_norm": 1.5579248666763306,
|
| 2198 |
+
"learning_rate": 3.861353711790393e-05,
|
| 2199 |
+
"loss": 0.0556,
|
| 2200 |
+
"step": 5625
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 2.47,
|
| 2204 |
+
"grad_norm": 0.30162498354911804,
|
| 2205 |
+
"learning_rate": 3.834061135371179e-05,
|
| 2206 |
+
"loss": 0.0845,
|
| 2207 |
+
"step": 5650
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 2.48,
|
| 2211 |
+
"grad_norm": 0.43656259775161743,
|
| 2212 |
+
"learning_rate": 3.806768558951965e-05,
|
| 2213 |
+
"loss": 0.0616,
|
| 2214 |
+
"step": 5675
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 2.49,
|
| 2218 |
+
"grad_norm": 0.4505567252635956,
|
| 2219 |
+
"learning_rate": 3.779475982532751e-05,
|
| 2220 |
+
"loss": 0.072,
|
| 2221 |
+
"step": 5700
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 2.49,
|
| 2225 |
+
"eval_loss": 0.29192212224006653,
|
| 2226 |
+
"eval_na_accuracy": 0.7683397531509399,
|
| 2227 |
+
"eval_ordinal_accuracy": 0.6888182759284973,
|
| 2228 |
+
"eval_ordinal_mae": 0.36100971698760986,
|
| 2229 |
+
"eval_runtime": 155.17,
|
| 2230 |
+
"eval_samples_per_second": 25.643,
|
| 2231 |
+
"eval_steps_per_second": 3.209,
|
| 2232 |
+
"step": 5700
|
| 2233 |
+
},
|
| 2234 |
+
{
|
| 2235 |
+
"epoch": 2.5,
|
| 2236 |
+
"grad_norm": 0.8305689692497253,
|
| 2237 |
+
"learning_rate": 3.752183406113537e-05,
|
| 2238 |
+
"loss": 0.0489,
|
| 2239 |
+
"step": 5725
|
| 2240 |
+
},
|
| 2241 |
+
{
|
| 2242 |
+
"epoch": 2.51,
|
| 2243 |
+
"grad_norm": 0.5452491641044617,
|
| 2244 |
+
"learning_rate": 3.724890829694323e-05,
|
| 2245 |
+
"loss": 0.0584,
|
| 2246 |
+
"step": 5750
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 2.52,
|
| 2250 |
+
"grad_norm": 0.7193215489387512,
|
| 2251 |
+
"learning_rate": 3.697598253275109e-05,
|
| 2252 |
+
"loss": 0.0643,
|
| 2253 |
+
"step": 5775
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"epoch": 2.53,
|
| 2257 |
+
"grad_norm": 0.4529215693473816,
|
| 2258 |
+
"learning_rate": 3.6703056768558954e-05,
|
| 2259 |
+
"loss": 0.0737,
|
| 2260 |
+
"step": 5800
|
| 2261 |
+
},
|
| 2262 |
+
{
|
| 2263 |
+
"epoch": 2.53,
|
| 2264 |
+
"eval_loss": 0.2807420790195465,
|
| 2265 |
+
"eval_na_accuracy": 0.7837837934494019,
|
| 2266 |
+
"eval_ordinal_accuracy": 0.6983530521392822,
|
| 2267 |
+
"eval_ordinal_mae": 0.3611612617969513,
|
| 2268 |
+
"eval_runtime": 154.656,
|
| 2269 |
+
"eval_samples_per_second": 25.728,
|
| 2270 |
+
"eval_steps_per_second": 3.22,
|
| 2271 |
+
"step": 5800
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 2.54,
|
| 2275 |
+
"grad_norm": 0.4110221564769745,
|
| 2276 |
+
"learning_rate": 3.6430131004366814e-05,
|
| 2277 |
+
"loss": 0.0548,
|
| 2278 |
+
"step": 5825
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 2.55,
|
| 2282 |
+
"grad_norm": 0.7328541278839111,
|
| 2283 |
+
"learning_rate": 3.6157205240174675e-05,
|
| 2284 |
+
"loss": 0.0728,
|
| 2285 |
+
"step": 5850
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 2.57,
|
| 2289 |
+
"grad_norm": 0.2497873455286026,
|
| 2290 |
+
"learning_rate": 3.5884279475982535e-05,
|
| 2291 |
+
"loss": 0.0608,
|
| 2292 |
+
"step": 5875
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 2.58,
|
| 2296 |
+
"grad_norm": 6.07706880569458,
|
| 2297 |
+
"learning_rate": 3.5611353711790396e-05,
|
| 2298 |
+
"loss": 0.0667,
|
| 2299 |
+
"step": 5900
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 2.58,
|
| 2303 |
+
"eval_loss": 0.292630672454834,
|
| 2304 |
+
"eval_na_accuracy": 0.7509652376174927,
|
| 2305 |
+
"eval_ordinal_accuracy": 0.7000866532325745,
|
| 2306 |
+
"eval_ordinal_mae": 0.36070069670677185,
|
| 2307 |
+
"eval_runtime": 156.6494,
|
| 2308 |
+
"eval_samples_per_second": 25.401,
|
| 2309 |
+
"eval_steps_per_second": 3.179,
|
| 2310 |
+
"step": 5900
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 2.59,
|
| 2314 |
+
"grad_norm": 2.6040148735046387,
|
| 2315 |
+
"learning_rate": 3.5338427947598256e-05,
|
| 2316 |
+
"loss": 0.0745,
|
| 2317 |
+
"step": 5925
|
| 2318 |
+
},
|
| 2319 |
+
{
|
| 2320 |
+
"epoch": 2.6,
|
| 2321 |
+
"grad_norm": 0.428023099899292,
|
| 2322 |
+
"learning_rate": 3.506550218340611e-05,
|
| 2323 |
+
"loss": 0.0455,
|
| 2324 |
+
"step": 5950
|
| 2325 |
+
},
|
| 2326 |
+
{
|
| 2327 |
+
"epoch": 2.61,
|
| 2328 |
+
"grad_norm": 0.24350808560848236,
|
| 2329 |
+
"learning_rate": 3.479257641921397e-05,
|
| 2330 |
+
"loss": 0.067,
|
| 2331 |
+
"step": 5975
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 2.62,
|
| 2335 |
+
"grad_norm": 0.6879482865333557,
|
| 2336 |
+
"learning_rate": 3.451965065502184e-05,
|
| 2337 |
+
"loss": 0.0669,
|
| 2338 |
+
"step": 6000
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 2.62,
|
| 2342 |
+
"eval_loss": 0.2874707579612732,
|
| 2343 |
+
"eval_na_accuracy": 0.799227774143219,
|
| 2344 |
+
"eval_ordinal_accuracy": 0.6891071796417236,
|
| 2345 |
+
"eval_ordinal_mae": 0.36164331436157227,
|
| 2346 |
+
"eval_runtime": 155.7575,
|
| 2347 |
+
"eval_samples_per_second": 25.546,
|
| 2348 |
+
"eval_steps_per_second": 3.197,
|
| 2349 |
+
"step": 6000
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 2.63,
|
| 2353 |
+
"grad_norm": 0.786054790019989,
|
| 2354 |
+
"learning_rate": 3.42467248908297e-05,
|
| 2355 |
+
"loss": 0.0736,
|
| 2356 |
+
"step": 6025
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 2.64,
|
| 2360 |
+
"grad_norm": 0.7047861218452454,
|
| 2361 |
+
"learning_rate": 3.397379912663756e-05,
|
| 2362 |
+
"loss": 0.0551,
|
| 2363 |
+
"step": 6050
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 2.65,
|
| 2367 |
+
"grad_norm": 0.6863640546798706,
|
| 2368 |
+
"learning_rate": 3.370087336244542e-05,
|
| 2369 |
+
"loss": 0.0643,
|
| 2370 |
+
"step": 6075
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 2.66,
|
| 2374 |
+
"grad_norm": 0.6037794947624207,
|
| 2375 |
+
"learning_rate": 3.342794759825328e-05,
|
| 2376 |
+
"loss": 0.0535,
|
| 2377 |
+
"step": 6100
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 2.66,
|
| 2381 |
+
"eval_loss": 0.2853965759277344,
|
| 2382 |
+
"eval_na_accuracy": 0.7683397531509399,
|
| 2383 |
+
"eval_ordinal_accuracy": 0.6960415840148926,
|
| 2384 |
+
"eval_ordinal_mae": 0.35648074746131897,
|
| 2385 |
+
"eval_runtime": 156.7027,
|
| 2386 |
+
"eval_samples_per_second": 25.392,
|
| 2387 |
+
"eval_steps_per_second": 3.178,
|
| 2388 |
+
"step": 6100
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 2.67,
|
| 2392 |
+
"grad_norm": 0.30565348267555237,
|
| 2393 |
+
"learning_rate": 3.315502183406114e-05,
|
| 2394 |
+
"loss": 0.0412,
|
| 2395 |
+
"step": 6125
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 2.69,
|
| 2399 |
+
"grad_norm": 0.3631564974784851,
|
| 2400 |
+
"learning_rate": 3.2882096069868994e-05,
|
| 2401 |
+
"loss": 0.0584,
|
| 2402 |
+
"step": 6150
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 2.7,
|
| 2406 |
+
"grad_norm": 0.6103675365447998,
|
| 2407 |
+
"learning_rate": 3.2609170305676854e-05,
|
| 2408 |
+
"loss": 0.0481,
|
| 2409 |
+
"step": 6175
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 2.71,
|
| 2413 |
+
"grad_norm": 10.306925773620605,
|
| 2414 |
+
"learning_rate": 3.2336244541484715e-05,
|
| 2415 |
+
"loss": 0.06,
|
| 2416 |
+
"step": 6200
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 2.71,
|
| 2420 |
+
"eval_loss": 0.28473392128944397,
|
| 2421 |
+
"eval_na_accuracy": 0.7741312980651855,
|
| 2422 |
+
"eval_ordinal_accuracy": 0.7015313506126404,
|
| 2423 |
+
"eval_ordinal_mae": 0.3500910997390747,
|
| 2424 |
+
"eval_runtime": 154.8993,
|
| 2425 |
+
"eval_samples_per_second": 25.688,
|
| 2426 |
+
"eval_steps_per_second": 3.215,
|
| 2427 |
+
"step": 6200
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 2.72,
|
| 2431 |
+
"grad_norm": 0.5145313143730164,
|
| 2432 |
+
"learning_rate": 3.2063318777292575e-05,
|
| 2433 |
+
"loss": 0.0586,
|
| 2434 |
+
"step": 6225
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"epoch": 2.73,
|
| 2438 |
+
"grad_norm": 0.9967983365058899,
|
| 2439 |
+
"learning_rate": 3.1790393013100436e-05,
|
| 2440 |
+
"loss": 0.0736,
|
| 2441 |
+
"step": 6250
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 2.74,
|
| 2445 |
+
"grad_norm": 0.652100682258606,
|
| 2446 |
+
"learning_rate": 3.15174672489083e-05,
|
| 2447 |
+
"loss": 0.057,
|
| 2448 |
+
"step": 6275
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 2.75,
|
| 2452 |
+
"grad_norm": 0.64205402135849,
|
| 2453 |
+
"learning_rate": 3.1244541484716164e-05,
|
| 2454 |
+
"loss": 0.0534,
|
| 2455 |
+
"step": 6300
|
| 2456 |
+
},
|
| 2457 |
+
{
|
| 2458 |
+
"epoch": 2.75,
|
| 2459 |
+
"eval_loss": 0.28205522894859314,
|
| 2460 |
+
"eval_na_accuracy": 0.7625482678413391,
|
| 2461 |
+
"eval_ordinal_accuracy": 0.7006645202636719,
|
| 2462 |
+
"eval_ordinal_mae": 0.34947505593299866,
|
| 2463 |
+
"eval_runtime": 155.841,
|
| 2464 |
+
"eval_samples_per_second": 25.532,
|
| 2465 |
+
"eval_steps_per_second": 3.196,
|
| 2466 |
+
"step": 6300
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 2.76,
|
| 2470 |
+
"grad_norm": 1.2284494638442993,
|
| 2471 |
+
"learning_rate": 3.097161572052402e-05,
|
| 2472 |
+
"loss": 0.0517,
|
| 2473 |
+
"step": 6325
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 2.77,
|
| 2477 |
+
"grad_norm": 0.4024920165538788,
|
| 2478 |
+
"learning_rate": 3.069868995633188e-05,
|
| 2479 |
+
"loss": 0.0857,
|
| 2480 |
+
"step": 6350
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 2.78,
|
| 2484 |
+
"grad_norm": 0.5288224816322327,
|
| 2485 |
+
"learning_rate": 3.0425764192139738e-05,
|
| 2486 |
+
"loss": 0.051,
|
| 2487 |
+
"step": 6375
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 2.79,
|
| 2491 |
+
"grad_norm": 0.6519297957420349,
|
| 2492 |
+
"learning_rate": 3.01528384279476e-05,
|
| 2493 |
+
"loss": 0.0526,
|
| 2494 |
+
"step": 6400
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 2.79,
|
| 2498 |
+
"eval_loss": 0.28344523906707764,
|
| 2499 |
+
"eval_na_accuracy": 0.7625482678413391,
|
| 2500 |
+
"eval_ordinal_accuracy": 0.670037567615509,
|
| 2501 |
+
"eval_ordinal_mae": 0.385305792093277,
|
| 2502 |
+
"eval_runtime": 154.7606,
|
| 2503 |
+
"eval_samples_per_second": 25.711,
|
| 2504 |
+
"eval_steps_per_second": 3.218,
|
| 2505 |
+
"step": 6400
|
| 2506 |
+
},
|
| 2507 |
+
{
|
| 2508 |
+
"epoch": 2.81,
|
| 2509 |
+
"grad_norm": 0.7009943723678589,
|
| 2510 |
+
"learning_rate": 2.987991266375546e-05,
|
| 2511 |
+
"loss": 0.0624,
|
| 2512 |
+
"step": 6425
|
| 2513 |
+
},
|
| 2514 |
+
{
|
| 2515 |
+
"epoch": 2.82,
|
| 2516 |
+
"grad_norm": 0.6731958389282227,
|
| 2517 |
+
"learning_rate": 2.9606986899563323e-05,
|
| 2518 |
+
"loss": 0.068,
|
| 2519 |
+
"step": 6450
|
| 2520 |
+
},
|
| 2521 |
+
{
|
| 2522 |
+
"epoch": 2.83,
|
| 2523 |
+
"grad_norm": 0.3764704763889313,
|
| 2524 |
+
"learning_rate": 2.9334061135371184e-05,
|
| 2525 |
+
"loss": 0.0677,
|
| 2526 |
+
"step": 6475
|
| 2527 |
+
},
|
| 2528 |
+
{
|
| 2529 |
+
"epoch": 2.84,
|
| 2530 |
+
"grad_norm": 0.5906457901000977,
|
| 2531 |
+
"learning_rate": 2.9061135371179037e-05,
|
| 2532 |
+
"loss": 0.0841,
|
| 2533 |
+
"step": 6500
|
| 2534 |
+
},
|
| 2535 |
+
{
|
| 2536 |
+
"epoch": 2.84,
|
| 2537 |
+
"eval_loss": 0.28385940194129944,
|
| 2538 |
+
"eval_na_accuracy": 0.7490347623825073,
|
| 2539 |
+
"eval_ordinal_accuracy": 0.7044206857681274,
|
| 2540 |
+
"eval_ordinal_mae": 0.35039493441581726,
|
| 2541 |
+
"eval_runtime": 156.3169,
|
| 2542 |
+
"eval_samples_per_second": 25.455,
|
| 2543 |
+
"eval_steps_per_second": 3.186,
|
| 2544 |
+
"step": 6500
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 2.85,
|
| 2548 |
+
"grad_norm": 0.3305709958076477,
|
| 2549 |
+
"learning_rate": 2.8788209606986898e-05,
|
| 2550 |
+
"loss": 0.0652,
|
| 2551 |
+
"step": 6525
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 2.86,
|
| 2555 |
+
"grad_norm": 0.4257774353027344,
|
| 2556 |
+
"learning_rate": 2.8526200873362446e-05,
|
| 2557 |
+
"loss": 0.0608,
|
| 2558 |
+
"step": 6550
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 2.87,
|
| 2562 |
+
"grad_norm": 0.9447629451751709,
|
| 2563 |
+
"learning_rate": 2.8253275109170307e-05,
|
| 2564 |
+
"loss": 0.0527,
|
| 2565 |
+
"step": 6575
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 2.88,
|
| 2569 |
+
"grad_norm": 0.8275176882743835,
|
| 2570 |
+
"learning_rate": 2.7980349344978167e-05,
|
| 2571 |
+
"loss": 0.0529,
|
| 2572 |
+
"step": 6600
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 2.88,
|
| 2576 |
+
"eval_loss": 0.2857762575149536,
|
| 2577 |
+
"eval_na_accuracy": 0.7818532586097717,
|
| 2578 |
+
"eval_ordinal_accuracy": 0.689685046672821,
|
| 2579 |
+
"eval_ordinal_mae": 0.35951367020606995,
|
| 2580 |
+
"eval_runtime": 156.4554,
|
| 2581 |
+
"eval_samples_per_second": 25.432,
|
| 2582 |
+
"eval_steps_per_second": 3.183,
|
| 2583 |
+
"step": 6600
|
| 2584 |
+
},
|
| 2585 |
+
{
|
| 2586 |
+
"epoch": 2.89,
|
| 2587 |
+
"grad_norm": 0.5894487500190735,
|
| 2588 |
+
"learning_rate": 2.770742358078603e-05,
|
| 2589 |
+
"loss": 0.0643,
|
| 2590 |
+
"step": 6625
|
| 2591 |
+
},
|
| 2592 |
+
{
|
| 2593 |
+
"epoch": 2.9,
|
| 2594 |
+
"grad_norm": 0.8872036933898926,
|
| 2595 |
+
"learning_rate": 2.743449781659389e-05,
|
| 2596 |
+
"loss": 0.0578,
|
| 2597 |
+
"step": 6650
|
| 2598 |
+
},
|
| 2599 |
+
{
|
| 2600 |
+
"epoch": 2.91,
|
| 2601 |
+
"grad_norm": 0.511169970035553,
|
| 2602 |
+
"learning_rate": 2.7161572052401745e-05,
|
| 2603 |
+
"loss": 0.0393,
|
| 2604 |
+
"step": 6675
|
| 2605 |
+
},
|
| 2606 |
+
{
|
| 2607 |
+
"epoch": 2.93,
|
| 2608 |
+
"grad_norm": 0.5537564754486084,
|
| 2609 |
+
"learning_rate": 2.6888646288209606e-05,
|
| 2610 |
+
"loss": 0.0811,
|
| 2611 |
+
"step": 6700
|
| 2612 |
+
},
|
| 2613 |
+
{
|
| 2614 |
+
"epoch": 2.93,
|
| 2615 |
+
"eval_loss": 0.28430891036987305,
|
| 2616 |
+
"eval_na_accuracy": 0.7799227833747864,
|
| 2617 |
+
"eval_ordinal_accuracy": 0.7047096490859985,
|
| 2618 |
+
"eval_ordinal_mae": 0.34795093536376953,
|
| 2619 |
+
"eval_runtime": 156.7138,
|
| 2620 |
+
"eval_samples_per_second": 25.39,
|
| 2621 |
+
"eval_steps_per_second": 3.178,
|
| 2622 |
+
"step": 6700
|
| 2623 |
+
},
|
| 2624 |
+
{
|
| 2625 |
+
"epoch": 2.94,
|
| 2626 |
+
"grad_norm": 1.6618189811706543,
|
| 2627 |
+
"learning_rate": 2.661572052401747e-05,
|
| 2628 |
+
"loss": 0.0705,
|
| 2629 |
+
"step": 6725
|
| 2630 |
+
},
|
| 2631 |
+
{
|
| 2632 |
+
"epoch": 2.95,
|
| 2633 |
+
"grad_norm": 0.4913439154624939,
|
| 2634 |
+
"learning_rate": 2.634279475982533e-05,
|
| 2635 |
+
"loss": 0.0875,
|
| 2636 |
+
"step": 6750
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 2.96,
|
| 2640 |
+
"grad_norm": 0.5068143010139465,
|
| 2641 |
+
"learning_rate": 2.606986899563319e-05,
|
| 2642 |
+
"loss": 0.0557,
|
| 2643 |
+
"step": 6775
|
| 2644 |
+
},
|
| 2645 |
+
{
|
| 2646 |
+
"epoch": 2.97,
|
| 2647 |
+
"grad_norm": 0.23857353627681732,
|
| 2648 |
+
"learning_rate": 2.579694323144105e-05,
|
| 2649 |
+
"loss": 0.0502,
|
| 2650 |
+
"step": 6800
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"epoch": 2.97,
|
| 2654 |
+
"eval_loss": 0.28915783762931824,
|
| 2655 |
+
"eval_na_accuracy": 0.7818532586097717,
|
| 2656 |
+
"eval_ordinal_accuracy": 0.700953483581543,
|
| 2657 |
+
"eval_ordinal_mae": 0.34830236434936523,
|
| 2658 |
+
"eval_runtime": 155.6303,
|
| 2659 |
+
"eval_samples_per_second": 25.567,
|
| 2660 |
+
"eval_steps_per_second": 3.2,
|
| 2661 |
+
"step": 6800
|
| 2662 |
+
},
|
| 2663 |
+
{
|
| 2664 |
+
"epoch": 2.98,
|
| 2665 |
+
"grad_norm": 0.9183345437049866,
|
| 2666 |
+
"learning_rate": 2.552401746724891e-05,
|
| 2667 |
+
"loss": 0.0514,
|
| 2668 |
+
"step": 6825
|
| 2669 |
+
},
|
| 2670 |
+
{
|
| 2671 |
+
"epoch": 2.99,
|
| 2672 |
+
"grad_norm": 0.6839514374732971,
|
| 2673 |
+
"learning_rate": 2.525109170305677e-05,
|
| 2674 |
+
"loss": 0.0682,
|
| 2675 |
+
"step": 6850
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 3.0,
|
| 2679 |
+
"grad_norm": 2.4068310260772705,
|
| 2680 |
+
"learning_rate": 2.4978165938864632e-05,
|
| 2681 |
+
"loss": 0.0709,
|
| 2682 |
+
"step": 6875
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 3.01,
|
| 2686 |
+
"grad_norm": 0.04599028080701828,
|
| 2687 |
+
"learning_rate": 2.470524017467249e-05,
|
| 2688 |
+
"loss": 0.0273,
|
| 2689 |
+
"step": 6900
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 3.01,
|
| 2693 |
+
"eval_loss": 0.2801385819911957,
|
| 2694 |
+
"eval_na_accuracy": 0.8108108043670654,
|
| 2695 |
+
"eval_ordinal_accuracy": 0.6957526803016663,
|
| 2696 |
+
"eval_ordinal_mae": 0.34536227583885193,
|
| 2697 |
+
"eval_runtime": 156.2048,
|
| 2698 |
+
"eval_samples_per_second": 25.473,
|
| 2699 |
+
"eval_steps_per_second": 3.188,
|
| 2700 |
+
"step": 6900
|
| 2701 |
+
},
|
| 2702 |
+
{
|
| 2703 |
+
"epoch": 3.02,
|
| 2704 |
+
"grad_norm": 0.5234570503234863,
|
| 2705 |
+
"learning_rate": 2.443231441048035e-05,
|
| 2706 |
+
"loss": 0.0273,
|
| 2707 |
+
"step": 6925
|
| 2708 |
+
},
|
| 2709 |
+
{
|
| 2710 |
+
"epoch": 3.03,
|
| 2711 |
+
"grad_norm": 0.4756307601928711,
|
| 2712 |
+
"learning_rate": 2.415938864628821e-05,
|
| 2713 |
+
"loss": 0.0338,
|
| 2714 |
+
"step": 6950
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 3.05,
|
| 2718 |
+
"grad_norm": 0.40528589487075806,
|
| 2719 |
+
"learning_rate": 2.388646288209607e-05,
|
| 2720 |
+
"loss": 0.0391,
|
| 2721 |
+
"step": 6975
|
| 2722 |
+
},
|
| 2723 |
+
{
|
| 2724 |
+
"epoch": 3.06,
|
| 2725 |
+
"grad_norm": 0.4284062385559082,
|
| 2726 |
+
"learning_rate": 2.361353711790393e-05,
|
| 2727 |
+
"loss": 0.0306,
|
| 2728 |
+
"step": 7000
|
| 2729 |
+
},
|
| 2730 |
+
{
|
| 2731 |
+
"epoch": 3.06,
|
| 2732 |
+
"eval_loss": 0.2782219350337982,
|
| 2733 |
+
"eval_na_accuracy": 0.8030887842178345,
|
| 2734 |
+
"eval_ordinal_accuracy": 0.7023981213569641,
|
| 2735 |
+
"eval_ordinal_mae": 0.3443802297115326,
|
| 2736 |
+
"eval_runtime": 155.0659,
|
| 2737 |
+
"eval_samples_per_second": 25.66,
|
| 2738 |
+
"eval_steps_per_second": 3.212,
|
| 2739 |
+
"step": 7000
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 3.07,
|
| 2743 |
+
"grad_norm": 0.420832097530365,
|
| 2744 |
+
"learning_rate": 2.3340611353711792e-05,
|
| 2745 |
+
"loss": 0.0308,
|
| 2746 |
+
"step": 7025
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 3.08,
|
| 2750 |
+
"grad_norm": 0.12627224624156952,
|
| 2751 |
+
"learning_rate": 2.3067685589519653e-05,
|
| 2752 |
+
"loss": 0.0219,
|
| 2753 |
+
"step": 7050
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 3.09,
|
| 2757 |
+
"grad_norm": 0.6852111220359802,
|
| 2758 |
+
"learning_rate": 2.279475982532751e-05,
|
| 2759 |
+
"loss": 0.0289,
|
| 2760 |
+
"step": 7075
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 3.1,
|
| 2764 |
+
"grad_norm": 0.4591895043849945,
|
| 2765 |
+
"learning_rate": 2.252183406113537e-05,
|
| 2766 |
+
"loss": 0.0257,
|
| 2767 |
+
"step": 7100
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 3.1,
|
| 2771 |
+
"eval_loss": 0.2796567380428314,
|
| 2772 |
+
"eval_na_accuracy": 0.7934362888336182,
|
| 2773 |
+
"eval_ordinal_accuracy": 0.7084657549858093,
|
| 2774 |
+
"eval_ordinal_mae": 0.33523455262184143,
|
| 2775 |
+
"eval_runtime": 155.6618,
|
| 2776 |
+
"eval_samples_per_second": 25.562,
|
| 2777 |
+
"eval_steps_per_second": 3.199,
|
| 2778 |
+
"step": 7100
|
| 2779 |
+
},
|
| 2780 |
+
{
|
| 2781 |
+
"epoch": 3.11,
|
| 2782 |
+
"grad_norm": 7.793858051300049,
|
| 2783 |
+
"learning_rate": 2.2248908296943234e-05,
|
| 2784 |
+
"loss": 0.0323,
|
| 2785 |
+
"step": 7125
|
| 2786 |
+
},
|
| 2787 |
+
{
|
| 2788 |
+
"epoch": 3.12,
|
| 2789 |
+
"grad_norm": 0.4730852246284485,
|
| 2790 |
+
"learning_rate": 2.1975982532751095e-05,
|
| 2791 |
+
"loss": 0.0432,
|
| 2792 |
+
"step": 7150
|
| 2793 |
+
},
|
| 2794 |
+
{
|
| 2795 |
+
"epoch": 3.13,
|
| 2796 |
+
"grad_norm": 0.9067665338516235,
|
| 2797 |
+
"learning_rate": 2.170305676855895e-05,
|
| 2798 |
+
"loss": 0.0324,
|
| 2799 |
+
"step": 7175
|
| 2800 |
+
},
|
| 2801 |
+
{
|
| 2802 |
+
"epoch": 3.14,
|
| 2803 |
+
"grad_norm": 0.23400144279003143,
|
| 2804 |
+
"learning_rate": 2.1430131004366812e-05,
|
| 2805 |
+
"loss": 0.0241,
|
| 2806 |
+
"step": 7200
|
| 2807 |
+
},
|
| 2808 |
+
{
|
| 2809 |
+
"epoch": 3.14,
|
| 2810 |
+
"eval_loss": 0.2827575206756592,
|
| 2811 |
+
"eval_na_accuracy": 0.7953668236732483,
|
| 2812 |
+
"eval_ordinal_accuracy": 0.7058653831481934,
|
| 2813 |
+
"eval_ordinal_mae": 0.33425432443618774,
|
| 2814 |
+
"eval_runtime": 157.3972,
|
| 2815 |
+
"eval_samples_per_second": 25.28,
|
| 2816 |
+
"eval_steps_per_second": 3.164,
|
| 2817 |
+
"step": 7200
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 3.16,
|
| 2821 |
+
"grad_norm": 0.6540936231613159,
|
| 2822 |
+
"learning_rate": 2.1157205240174673e-05,
|
| 2823 |
+
"loss": 0.0266,
|
| 2824 |
+
"step": 7225
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 3.17,
|
| 2828 |
+
"grad_norm": 0.3661313056945801,
|
| 2829 |
+
"learning_rate": 2.0884279475982536e-05,
|
| 2830 |
+
"loss": 0.03,
|
| 2831 |
+
"step": 7250
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 3.18,
|
| 2835 |
+
"grad_norm": 0.48538270592689514,
|
| 2836 |
+
"learning_rate": 2.0611353711790394e-05,
|
| 2837 |
+
"loss": 0.0268,
|
| 2838 |
+
"step": 7275
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 3.19,
|
| 2842 |
+
"grad_norm": 0.12903234362602234,
|
| 2843 |
+
"learning_rate": 2.0338427947598254e-05,
|
| 2844 |
+
"loss": 0.0255,
|
| 2845 |
+
"step": 7300
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 3.19,
|
| 2849 |
+
"eval_loss": 0.28903913497924805,
|
| 2850 |
+
"eval_na_accuracy": 0.8050193190574646,
|
| 2851 |
+
"eval_ordinal_accuracy": 0.6980641484260559,
|
| 2852 |
+
"eval_ordinal_mae": 0.3364236354827881,
|
| 2853 |
+
"eval_runtime": 155.705,
|
| 2854 |
+
"eval_samples_per_second": 25.555,
|
| 2855 |
+
"eval_steps_per_second": 3.198,
|
| 2856 |
+
"step": 7300
|
| 2857 |
+
},
|
| 2858 |
+
{
|
| 2859 |
+
"epoch": 3.2,
|
| 2860 |
+
"grad_norm": 0.6427123546600342,
|
| 2861 |
+
"learning_rate": 2.0065502183406115e-05,
|
| 2862 |
+
"loss": 0.0256,
|
| 2863 |
+
"step": 7325
|
| 2864 |
+
},
|
| 2865 |
+
{
|
| 2866 |
+
"epoch": 3.21,
|
| 2867 |
+
"grad_norm": 0.9630228281021118,
|
| 2868 |
+
"learning_rate": 1.9792576419213975e-05,
|
| 2869 |
+
"loss": 0.0261,
|
| 2870 |
+
"step": 7350
|
| 2871 |
+
},
|
| 2872 |
+
{
|
| 2873 |
+
"epoch": 3.22,
|
| 2874 |
+
"grad_norm": 0.4561873972415924,
|
| 2875 |
+
"learning_rate": 1.9519650655021836e-05,
|
| 2876 |
+
"loss": 0.0337,
|
| 2877 |
+
"step": 7375
|
| 2878 |
+
},
|
| 2879 |
+
{
|
| 2880 |
+
"epoch": 3.23,
|
| 2881 |
+
"grad_norm": 0.40141957998275757,
|
| 2882 |
+
"learning_rate": 1.9246724890829696e-05,
|
| 2883 |
+
"loss": 0.0245,
|
| 2884 |
+
"step": 7400
|
| 2885 |
+
},
|
| 2886 |
+
{
|
| 2887 |
+
"epoch": 3.23,
|
| 2888 |
+
"eval_loss": 0.29058343172073364,
|
| 2889 |
+
"eval_na_accuracy": 0.799227774143219,
|
| 2890 |
+
"eval_ordinal_accuracy": 0.7044206857681274,
|
| 2891 |
+
"eval_ordinal_mae": 0.3391839265823364,
|
| 2892 |
+
"eval_runtime": 156.6469,
|
| 2893 |
+
"eval_samples_per_second": 25.401,
|
| 2894 |
+
"eval_steps_per_second": 3.179,
|
| 2895 |
+
"step": 7400
|
| 2896 |
+
},
|
| 2897 |
+
{
|
| 2898 |
+
"epoch": 3.24,
|
| 2899 |
+
"grad_norm": 0.04360814392566681,
|
| 2900 |
+
"learning_rate": 1.8973799126637557e-05,
|
| 2901 |
+
"loss": 0.0271,
|
| 2902 |
+
"step": 7425
|
| 2903 |
+
},
|
| 2904 |
+
{
|
| 2905 |
+
"epoch": 3.25,
|
| 2906 |
+
"grad_norm": 0.2782489061355591,
|
| 2907 |
+
"learning_rate": 1.8700873362445414e-05,
|
| 2908 |
+
"loss": 0.0345,
|
| 2909 |
+
"step": 7450
|
| 2910 |
+
},
|
| 2911 |
+
{
|
| 2912 |
+
"epoch": 3.26,
|
| 2913 |
+
"grad_norm": 0.4086083769798279,
|
| 2914 |
+
"learning_rate": 1.8427947598253274e-05,
|
| 2915 |
+
"loss": 0.0519,
|
| 2916 |
+
"step": 7475
|
| 2917 |
+
},
|
| 2918 |
+
{
|
| 2919 |
+
"epoch": 3.28,
|
| 2920 |
+
"grad_norm": 0.37691470980644226,
|
| 2921 |
+
"learning_rate": 1.8155021834061138e-05,
|
| 2922 |
+
"loss": 0.0232,
|
| 2923 |
+
"step": 7500
|
| 2924 |
+
},
|
| 2925 |
+
{
|
| 2926 |
+
"epoch": 3.28,
|
| 2927 |
+
"eval_loss": 0.28911489248275757,
|
| 2928 |
+
"eval_na_accuracy": 0.7857142686843872,
|
| 2929 |
+
"eval_ordinal_accuracy": 0.7035539150238037,
|
| 2930 |
+
"eval_ordinal_mae": 0.3337612450122833,
|
| 2931 |
+
"eval_runtime": 155.5823,
|
| 2932 |
+
"eval_samples_per_second": 25.575,
|
| 2933 |
+
"eval_steps_per_second": 3.201,
|
| 2934 |
+
"step": 7500
|
| 2935 |
+
},
|
| 2936 |
+
{
|
| 2937 |
+
"epoch": 3.29,
|
| 2938 |
+
"grad_norm": 0.220824733376503,
|
| 2939 |
+
"learning_rate": 1.7882096069869e-05,
|
| 2940 |
+
"loss": 0.0274,
|
| 2941 |
+
"step": 7525
|
| 2942 |
+
},
|
| 2943 |
+
{
|
| 2944 |
+
"epoch": 3.3,
|
| 2945 |
+
"grad_norm": 0.38171643018722534,
|
| 2946 |
+
"learning_rate": 1.7609170305676856e-05,
|
| 2947 |
+
"loss": 0.0257,
|
| 2948 |
+
"step": 7550
|
| 2949 |
+
},
|
| 2950 |
+
{
|
| 2951 |
+
"epoch": 3.31,
|
| 2952 |
+
"grad_norm": 0.6748324632644653,
|
| 2953 |
+
"learning_rate": 1.7336244541484716e-05,
|
| 2954 |
+
"loss": 0.0212,
|
| 2955 |
+
"step": 7575
|
| 2956 |
+
},
|
| 2957 |
+
{
|
| 2958 |
+
"epoch": 3.32,
|
| 2959 |
+
"grad_norm": 0.42487770318984985,
|
| 2960 |
+
"learning_rate": 1.7063318777292577e-05,
|
| 2961 |
+
"loss": 0.0352,
|
| 2962 |
+
"step": 7600
|
| 2963 |
+
},
|
| 2964 |
+
{
|
| 2965 |
+
"epoch": 3.32,
|
| 2966 |
+
"eval_loss": 0.2908113896846771,
|
| 2967 |
+
"eval_na_accuracy": 0.7895752787590027,
|
| 2968 |
+
"eval_ordinal_accuracy": 0.6925743818283081,
|
| 2969 |
+
"eval_ordinal_mae": 0.34433993697166443,
|
| 2970 |
+
"eval_runtime": 154.4772,
|
| 2971 |
+
"eval_samples_per_second": 25.758,
|
| 2972 |
+
"eval_steps_per_second": 3.224,
|
| 2973 |
+
"step": 7600
|
| 2974 |
+
},
|
| 2975 |
+
{
|
| 2976 |
+
"epoch": 3.33,
|
| 2977 |
+
"grad_norm": 0.6813647747039795,
|
| 2978 |
+
"learning_rate": 1.6790393013100437e-05,
|
| 2979 |
+
"loss": 0.0405,
|
| 2980 |
+
"step": 7625
|
| 2981 |
+
},
|
| 2982 |
+
{
|
| 2983 |
+
"epoch": 3.34,
|
| 2984 |
+
"grad_norm": 0.46545034646987915,
|
| 2985 |
+
"learning_rate": 1.6517467248908298e-05,
|
| 2986 |
+
"loss": 0.0252,
|
| 2987 |
+
"step": 7650
|
| 2988 |
+
},
|
| 2989 |
+
{
|
| 2990 |
+
"epoch": 3.35,
|
| 2991 |
+
"grad_norm": 0.32561665773391724,
|
| 2992 |
+
"learning_rate": 1.6244541484716158e-05,
|
| 2993 |
+
"loss": 0.0287,
|
| 2994 |
+
"step": 7675
|
| 2995 |
+
},
|
| 2996 |
+
{
|
| 2997 |
+
"epoch": 3.36,
|
| 2998 |
+
"grad_norm": 0.38751569390296936,
|
| 2999 |
+
"learning_rate": 1.597161572052402e-05,
|
| 3000 |
+
"loss": 0.0376,
|
| 3001 |
+
"step": 7700
|
| 3002 |
+
},
|
| 3003 |
+
{
|
| 3004 |
+
"epoch": 3.36,
|
| 3005 |
+
"eval_loss": 0.2876608371734619,
|
| 3006 |
+
"eval_na_accuracy": 0.7915058135986328,
|
| 3007 |
+
"eval_ordinal_accuracy": 0.7049985527992249,
|
| 3008 |
+
"eval_ordinal_mae": 0.331503301858902,
|
| 3009 |
+
"eval_runtime": 155.51,
|
| 3010 |
+
"eval_samples_per_second": 25.587,
|
| 3011 |
+
"eval_steps_per_second": 3.202,
|
| 3012 |
+
"step": 7700
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 3.37,
|
| 3016 |
+
"grad_norm": 0.317843496799469,
|
| 3017 |
+
"learning_rate": 1.5698689956331876e-05,
|
| 3018 |
+
"loss": 0.0346,
|
| 3019 |
+
"step": 7725
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 3.38,
|
| 3023 |
+
"grad_norm": 0.09346043318510056,
|
| 3024 |
+
"learning_rate": 1.542576419213974e-05,
|
| 3025 |
+
"loss": 0.0187,
|
| 3026 |
+
"step": 7750
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 3.4,
|
| 3030 |
+
"grad_norm": 0.508102536201477,
|
| 3031 |
+
"learning_rate": 1.51528384279476e-05,
|
| 3032 |
+
"loss": 0.0208,
|
| 3033 |
+
"step": 7775
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 3.41,
|
| 3037 |
+
"grad_norm": 0.3914332687854767,
|
| 3038 |
+
"learning_rate": 1.487991266375546e-05,
|
| 3039 |
+
"loss": 0.025,
|
| 3040 |
+
"step": 7800
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 3.41,
|
| 3044 |
+
"eval_loss": 0.2889249920845032,
|
| 3045 |
+
"eval_na_accuracy": 0.7895752787590027,
|
| 3046 |
+
"eval_ordinal_accuracy": 0.7075989842414856,
|
| 3047 |
+
"eval_ordinal_mae": 0.33163872361183167,
|
| 3048 |
+
"eval_runtime": 156.7804,
|
| 3049 |
+
"eval_samples_per_second": 25.379,
|
| 3050 |
+
"eval_steps_per_second": 3.176,
|
| 3051 |
+
"step": 7800
|
| 3052 |
+
},
|
| 3053 |
+
{
|
| 3054 |
+
"epoch": 3.42,
|
| 3055 |
+
"grad_norm": 0.6848337054252625,
|
| 3056 |
+
"learning_rate": 1.460698689956332e-05,
|
| 3057 |
+
"loss": 0.0259,
|
| 3058 |
+
"step": 7825
|
| 3059 |
+
},
|
| 3060 |
+
{
|
| 3061 |
+
"epoch": 3.43,
|
| 3062 |
+
"grad_norm": 0.5732501149177551,
|
| 3063 |
+
"learning_rate": 1.433406113537118e-05,
|
| 3064 |
+
"loss": 0.0222,
|
| 3065 |
+
"step": 7850
|
| 3066 |
+
},
|
| 3067 |
+
{
|
| 3068 |
+
"epoch": 3.44,
|
| 3069 |
+
"grad_norm": 0.638590931892395,
|
| 3070 |
+
"learning_rate": 1.406113537117904e-05,
|
| 3071 |
+
"loss": 0.0237,
|
| 3072 |
+
"step": 7875
|
| 3073 |
+
},
|
| 3074 |
+
{
|
| 3075 |
+
"epoch": 3.45,
|
| 3076 |
+
"grad_norm": 0.7879953980445862,
|
| 3077 |
+
"learning_rate": 1.37882096069869e-05,
|
| 3078 |
+
"loss": 0.0225,
|
| 3079 |
+
"step": 7900
|
| 3080 |
+
},
|
| 3081 |
+
{
|
| 3082 |
+
"epoch": 3.45,
|
| 3083 |
+
"eval_loss": 0.2901510000228882,
|
| 3084 |
+
"eval_na_accuracy": 0.7818532586097717,
|
| 3085 |
+
"eval_ordinal_accuracy": 0.7070211172103882,
|
| 3086 |
+
"eval_ordinal_mae": 0.32855790853500366,
|
| 3087 |
+
"eval_runtime": 157.7082,
|
| 3088 |
+
"eval_samples_per_second": 25.23,
|
| 3089 |
+
"eval_steps_per_second": 3.158,
|
| 3090 |
+
"step": 7900
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 3.46,
|
| 3094 |
+
"grad_norm": 0.45826223492622375,
|
| 3095 |
+
"learning_rate": 1.351528384279476e-05,
|
| 3096 |
+
"loss": 0.03,
|
| 3097 |
+
"step": 7925
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 3.47,
|
| 3101 |
+
"grad_norm": 0.5093744993209839,
|
| 3102 |
+
"learning_rate": 1.324235807860262e-05,
|
| 3103 |
+
"loss": 0.023,
|
| 3104 |
+
"step": 7950
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 3.48,
|
| 3108 |
+
"grad_norm": 0.39197513461112976,
|
| 3109 |
+
"learning_rate": 1.2969432314410482e-05,
|
| 3110 |
+
"loss": 0.0263,
|
| 3111 |
+
"step": 7975
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 3.49,
|
| 3115 |
+
"grad_norm": 0.4618348777294159,
|
| 3116 |
+
"learning_rate": 1.269650655021834e-05,
|
| 3117 |
+
"loss": 0.024,
|
| 3118 |
+
"step": 8000
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 3.49,
|
| 3122 |
+
"eval_loss": 0.29018646478652954,
|
| 3123 |
+
"eval_na_accuracy": 0.7953668236732483,
|
| 3124 |
+
"eval_ordinal_accuracy": 0.7101993560791016,
|
| 3125 |
+
"eval_ordinal_mae": 0.3269650340080261,
|
| 3126 |
+
"eval_runtime": 155.3244,
|
| 3127 |
+
"eval_samples_per_second": 25.617,
|
| 3128 |
+
"eval_steps_per_second": 3.206,
|
| 3129 |
+
"step": 8000
|
| 3130 |
+
},
|
| 3131 |
+
{
|
| 3132 |
+
"epoch": 3.5,
|
| 3133 |
+
"grad_norm": 0.5933849811553955,
|
| 3134 |
+
"learning_rate": 1.2423580786026202e-05,
|
| 3135 |
+
"loss": 0.0225,
|
| 3136 |
+
"step": 8025
|
| 3137 |
+
},
|
| 3138 |
+
{
|
| 3139 |
+
"epoch": 3.52,
|
| 3140 |
+
"grad_norm": 0.04294763505458832,
|
| 3141 |
+
"learning_rate": 1.2150655021834062e-05,
|
| 3142 |
+
"loss": 0.0228,
|
| 3143 |
+
"step": 8050
|
| 3144 |
+
},
|
| 3145 |
+
{
|
| 3146 |
+
"epoch": 3.53,
|
| 3147 |
+
"grad_norm": 0.5286312699317932,
|
| 3148 |
+
"learning_rate": 1.1877729257641921e-05,
|
| 3149 |
+
"loss": 0.03,
|
| 3150 |
+
"step": 8075
|
| 3151 |
+
},
|
| 3152 |
+
{
|
| 3153 |
+
"epoch": 3.54,
|
| 3154 |
+
"grad_norm": 0.09194879978895187,
|
| 3155 |
+
"learning_rate": 1.1604803493449783e-05,
|
| 3156 |
+
"loss": 0.0404,
|
| 3157 |
+
"step": 8100
|
| 3158 |
+
},
|
| 3159 |
+
{
|
| 3160 |
+
"epoch": 3.54,
|
| 3161 |
+
"eval_loss": 0.29498282074928284,
|
| 3162 |
+
"eval_na_accuracy": 0.7895752787590027,
|
| 3163 |
+
"eval_ordinal_accuracy": 0.705287516117096,
|
| 3164 |
+
"eval_ordinal_mae": 0.32936587929725647,
|
| 3165 |
+
"eval_runtime": 156.3299,
|
| 3166 |
+
"eval_samples_per_second": 25.453,
|
| 3167 |
+
"eval_steps_per_second": 3.186,
|
| 3168 |
+
"step": 8100
|
| 3169 |
+
},
|
| 3170 |
+
{
|
| 3171 |
+
"epoch": 3.55,
|
| 3172 |
+
"grad_norm": 0.3700167238712311,
|
| 3173 |
+
"learning_rate": 1.1331877729257642e-05,
|
| 3174 |
+
"loss": 0.0293,
|
| 3175 |
+
"step": 8125
|
| 3176 |
+
},
|
| 3177 |
+
{
|
| 3178 |
+
"epoch": 3.56,
|
| 3179 |
+
"grad_norm": 0.10644713789224625,
|
| 3180 |
+
"learning_rate": 1.1058951965065504e-05,
|
| 3181 |
+
"loss": 0.0265,
|
| 3182 |
+
"step": 8150
|
| 3183 |
+
},
|
| 3184 |
+
{
|
| 3185 |
+
"epoch": 3.57,
|
| 3186 |
+
"grad_norm": 0.4384317994117737,
|
| 3187 |
+
"learning_rate": 1.0786026200873363e-05,
|
| 3188 |
+
"loss": 0.0274,
|
| 3189 |
+
"step": 8175
|
| 3190 |
+
},
|
| 3191 |
+
{
|
| 3192 |
+
"epoch": 3.58,
|
| 3193 |
+
"grad_norm": 0.4964589774608612,
|
| 3194 |
+
"learning_rate": 1.0513100436681223e-05,
|
| 3195 |
+
"loss": 0.0221,
|
| 3196 |
+
"step": 8200
|
| 3197 |
+
},
|
| 3198 |
+
{
|
| 3199 |
+
"epoch": 3.58,
|
| 3200 |
+
"eval_loss": 0.2923668920993805,
|
| 3201 |
+
"eval_na_accuracy": 0.7934362888336182,
|
| 3202 |
+
"eval_ordinal_accuracy": 0.7093325853347778,
|
| 3203 |
+
"eval_ordinal_mae": 0.3270767033100128,
|
| 3204 |
+
"eval_runtime": 156.0459,
|
| 3205 |
+
"eval_samples_per_second": 25.499,
|
| 3206 |
+
"eval_steps_per_second": 3.191,
|
| 3207 |
+
"step": 8200
|
| 3208 |
+
},
|
| 3209 |
+
{
|
| 3210 |
+
"epoch": 3.59,
|
| 3211 |
+
"grad_norm": 0.20232300460338593,
|
| 3212 |
+
"learning_rate": 1.0240174672489084e-05,
|
| 3213 |
+
"loss": 0.0253,
|
| 3214 |
+
"step": 8225
|
| 3215 |
+
},
|
| 3216 |
+
{
|
| 3217 |
+
"epoch": 3.6,
|
| 3218 |
+
"grad_norm": 0.19642572104930878,
|
| 3219 |
+
"learning_rate": 9.967248908296943e-06,
|
| 3220 |
+
"loss": 0.0309,
|
| 3221 |
+
"step": 8250
|
| 3222 |
+
},
|
| 3223 |
+
{
|
| 3224 |
+
"epoch": 3.61,
|
| 3225 |
+
"grad_norm": 0.12435351312160492,
|
| 3226 |
+
"learning_rate": 9.694323144104805e-06,
|
| 3227 |
+
"loss": 0.0275,
|
| 3228 |
+
"step": 8275
|
| 3229 |
+
},
|
| 3230 |
+
{
|
| 3231 |
+
"epoch": 3.62,
|
| 3232 |
+
"grad_norm": 0.3429054915904999,
|
| 3233 |
+
"learning_rate": 9.421397379912664e-06,
|
| 3234 |
+
"loss": 0.0182,
|
| 3235 |
+
"step": 8300
|
| 3236 |
+
},
|
| 3237 |
+
{
|
| 3238 |
+
"epoch": 3.62,
|
| 3239 |
+
"eval_loss": 0.29207319021224976,
|
| 3240 |
+
"eval_na_accuracy": 0.7934362888336182,
|
| 3241 |
+
"eval_ordinal_accuracy": 0.7104883193969727,
|
| 3242 |
+
"eval_ordinal_mae": 0.32371771335601807,
|
| 3243 |
+
"eval_runtime": 157.1157,
|
| 3244 |
+
"eval_samples_per_second": 25.325,
|
| 3245 |
+
"eval_steps_per_second": 3.17,
|
| 3246 |
+
"step": 8300
|
| 3247 |
+
},
|
| 3248 |
+
{
|
| 3249 |
+
"epoch": 3.64,
|
| 3250 |
+
"grad_norm": 0.11734936386346817,
|
| 3251 |
+
"learning_rate": 9.148471615720524e-06,
|
| 3252 |
+
"loss": 0.0341,
|
| 3253 |
+
"step": 8325
|
| 3254 |
+
},
|
| 3255 |
+
{
|
| 3256 |
+
"epoch": 3.65,
|
| 3257 |
+
"grad_norm": 0.18671230971813202,
|
| 3258 |
+
"learning_rate": 8.875545851528385e-06,
|
| 3259 |
+
"loss": 0.0257,
|
| 3260 |
+
"step": 8350
|
| 3261 |
+
},
|
| 3262 |
+
{
|
| 3263 |
+
"epoch": 3.66,
|
| 3264 |
+
"grad_norm": 0.1754232794046402,
|
| 3265 |
+
"learning_rate": 8.602620087336245e-06,
|
| 3266 |
+
"loss": 0.0306,
|
| 3267 |
+
"step": 8375
|
| 3268 |
+
},
|
| 3269 |
+
{
|
| 3270 |
+
"epoch": 3.67,
|
| 3271 |
+
"grad_norm": 0.2011016607284546,
|
| 3272 |
+
"learning_rate": 8.329694323144106e-06,
|
| 3273 |
+
"loss": 0.0304,
|
| 3274 |
+
"step": 8400
|
| 3275 |
+
},
|
| 3276 |
+
{
|
| 3277 |
+
"epoch": 3.67,
|
| 3278 |
+
"eval_loss": 0.29112711548805237,
|
| 3279 |
+
"eval_na_accuracy": 0.7857142686843872,
|
| 3280 |
+
"eval_ordinal_accuracy": 0.7133776545524597,
|
| 3281 |
+
"eval_ordinal_mae": 0.3231416344642639,
|
| 3282 |
+
"eval_runtime": 155.6543,
|
| 3283 |
+
"eval_samples_per_second": 25.563,
|
| 3284 |
+
"eval_steps_per_second": 3.199,
|
| 3285 |
+
"step": 8400
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"epoch": 3.68,
|
| 3289 |
+
"grad_norm": 1.1286529302597046,
|
| 3290 |
+
"learning_rate": 8.056768558951966e-06,
|
| 3291 |
+
"loss": 0.0285,
|
| 3292 |
+
"step": 8425
|
| 3293 |
+
},
|
| 3294 |
+
{
|
| 3295 |
+
"epoch": 3.69,
|
| 3296 |
+
"grad_norm": 0.4878416359424591,
|
| 3297 |
+
"learning_rate": 7.783842794759825e-06,
|
| 3298 |
+
"loss": 0.0163,
|
| 3299 |
+
"step": 8450
|
| 3300 |
+
},
|
| 3301 |
+
{
|
| 3302 |
+
"epoch": 3.7,
|
| 3303 |
+
"grad_norm": 0.5879720449447632,
|
| 3304 |
+
"learning_rate": 7.510917030567686e-06,
|
| 3305 |
+
"loss": 0.0433,
|
| 3306 |
+
"step": 8475
|
| 3307 |
+
},
|
| 3308 |
+
{
|
| 3309 |
+
"epoch": 3.71,
|
| 3310 |
+
"grad_norm": 0.8792235255241394,
|
| 3311 |
+
"learning_rate": 7.237991266375546e-06,
|
| 3312 |
+
"loss": 0.0193,
|
| 3313 |
+
"step": 8500
|
| 3314 |
+
},
|
| 3315 |
+
{
|
| 3316 |
+
"epoch": 3.71,
|
| 3317 |
+
"eval_loss": 0.2914559841156006,
|
| 3318 |
+
"eval_na_accuracy": 0.7837837934494019,
|
| 3319 |
+
"eval_ordinal_accuracy": 0.7165558934211731,
|
| 3320 |
+
"eval_ordinal_mae": 0.32214629650115967,
|
| 3321 |
+
"eval_runtime": 155.1881,
|
| 3322 |
+
"eval_samples_per_second": 25.64,
|
| 3323 |
+
"eval_steps_per_second": 3.209,
|
| 3324 |
+
"step": 8500
|
| 3325 |
+
},
|
| 3326 |
+
{
|
| 3327 |
+
"epoch": 3.72,
|
| 3328 |
+
"grad_norm": 0.2179727405309677,
|
| 3329 |
+
"learning_rate": 6.9650655021834055e-06,
|
| 3330 |
+
"loss": 0.0237,
|
| 3331 |
+
"step": 8525
|
| 3332 |
+
},
|
| 3333 |
+
{
|
| 3334 |
+
"epoch": 3.73,
|
| 3335 |
+
"grad_norm": 0.7128644585609436,
|
| 3336 |
+
"learning_rate": 6.692139737991267e-06,
|
| 3337 |
+
"loss": 0.0306,
|
| 3338 |
+
"step": 8550
|
| 3339 |
+
},
|
| 3340 |
+
{
|
| 3341 |
+
"epoch": 3.74,
|
| 3342 |
+
"grad_norm": 0.2546403110027313,
|
| 3343 |
+
"learning_rate": 6.4192139737991265e-06,
|
| 3344 |
+
"loss": 0.0215,
|
| 3345 |
+
"step": 8575
|
| 3346 |
+
},
|
| 3347 |
+
{
|
| 3348 |
+
"epoch": 3.76,
|
| 3349 |
+
"grad_norm": 0.39975956082344055,
|
| 3350 |
+
"learning_rate": 6.146288209606987e-06,
|
| 3351 |
+
"loss": 0.0223,
|
| 3352 |
+
"step": 8600
|
| 3353 |
+
},
|
| 3354 |
+
{
|
| 3355 |
+
"epoch": 3.76,
|
| 3356 |
+
"eval_loss": 0.29310527443885803,
|
| 3357 |
+
"eval_na_accuracy": 0.7895752787590027,
|
| 3358 |
+
"eval_ordinal_accuracy": 0.7122219204902649,
|
| 3359 |
+
"eval_ordinal_mae": 0.32349658012390137,
|
| 3360 |
+
"eval_runtime": 154.5645,
|
| 3361 |
+
"eval_samples_per_second": 25.743,
|
| 3362 |
+
"eval_steps_per_second": 3.222,
|
| 3363 |
+
"step": 8600
|
| 3364 |
+
},
|
| 3365 |
+
{
|
| 3366 |
+
"epoch": 3.77,
|
| 3367 |
+
"grad_norm": 0.34678587317466736,
|
| 3368 |
+
"learning_rate": 5.884279475982533e-06,
|
| 3369 |
+
"loss": 0.0203,
|
| 3370 |
+
"step": 8625
|
| 3371 |
+
},
|
| 3372 |
+
{
|
| 3373 |
+
"epoch": 3.78,
|
| 3374 |
+
"grad_norm": 0.46029233932495117,
|
| 3375 |
+
"learning_rate": 5.611353711790393e-06,
|
| 3376 |
+
"loss": 0.0252,
|
| 3377 |
+
"step": 8650
|
| 3378 |
+
},
|
| 3379 |
+
{
|
| 3380 |
+
"epoch": 3.79,
|
| 3381 |
+
"grad_norm": 0.3514462113380432,
|
| 3382 |
+
"learning_rate": 5.338427947598254e-06,
|
| 3383 |
+
"loss": 0.0182,
|
| 3384 |
+
"step": 8675
|
| 3385 |
+
},
|
| 3386 |
+
{
|
| 3387 |
+
"epoch": 3.8,
|
| 3388 |
+
"grad_norm": 0.9231175184249878,
|
| 3389 |
+
"learning_rate": 5.065502183406113e-06,
|
| 3390 |
+
"loss": 0.0254,
|
| 3391 |
+
"step": 8700
|
| 3392 |
+
},
|
| 3393 |
+
{
|
| 3394 |
+
"epoch": 3.8,
|
| 3395 |
+
"eval_loss": 0.2946593761444092,
|
| 3396 |
+
"eval_na_accuracy": 0.7876448035240173,
|
| 3397 |
+
"eval_ordinal_accuracy": 0.7174227237701416,
|
| 3398 |
+
"eval_ordinal_mae": 0.32142174243927,
|
| 3399 |
+
"eval_runtime": 155.717,
|
| 3400 |
+
"eval_samples_per_second": 25.553,
|
| 3401 |
+
"eval_steps_per_second": 3.198,
|
| 3402 |
+
"step": 8700
|
| 3403 |
+
},
|
| 3404 |
+
{
|
| 3405 |
+
"epoch": 3.81,
|
| 3406 |
+
"grad_norm": 0.659959614276886,
|
| 3407 |
+
"learning_rate": 4.792576419213974e-06,
|
| 3408 |
+
"loss": 0.0277,
|
| 3409 |
+
"step": 8725
|
| 3410 |
+
},
|
| 3411 |
+
{
|
| 3412 |
+
"epoch": 3.82,
|
| 3413 |
+
"grad_norm": 1.0919593572616577,
|
| 3414 |
+
"learning_rate": 4.519650655021834e-06,
|
| 3415 |
+
"loss": 0.0306,
|
| 3416 |
+
"step": 8750
|
| 3417 |
+
},
|
| 3418 |
+
{
|
| 3419 |
+
"epoch": 3.83,
|
| 3420 |
+
"grad_norm": 0.9325423836708069,
|
| 3421 |
+
"learning_rate": 4.246724890829695e-06,
|
| 3422 |
+
"loss": 0.0331,
|
| 3423 |
+
"step": 8775
|
| 3424 |
+
},
|
| 3425 |
+
{
|
| 3426 |
+
"epoch": 3.84,
|
| 3427 |
+
"grad_norm": 0.21544720232486725,
|
| 3428 |
+
"learning_rate": 3.9737991266375545e-06,
|
| 3429 |
+
"loss": 0.0215,
|
| 3430 |
+
"step": 8800
|
| 3431 |
+
},
|
| 3432 |
+
{
|
| 3433 |
+
"epoch": 3.84,
|
| 3434 |
+
"eval_loss": 0.293580025434494,
|
| 3435 |
+
"eval_na_accuracy": 0.7857142686843872,
|
| 3436 |
+
"eval_ordinal_accuracy": 0.7127997875213623,
|
| 3437 |
+
"eval_ordinal_mae": 0.3201707899570465,
|
| 3438 |
+
"eval_runtime": 157.8828,
|
| 3439 |
+
"eval_samples_per_second": 25.202,
|
| 3440 |
+
"eval_steps_per_second": 3.154,
|
| 3441 |
+
"step": 8800
|
| 3442 |
+
},
|
| 3443 |
+
{
|
| 3444 |
+
"epoch": 3.85,
|
| 3445 |
+
"grad_norm": 0.43472805619239807,
|
| 3446 |
+
"learning_rate": 3.7008733624454154e-06,
|
| 3447 |
+
"loss": 0.0345,
|
| 3448 |
+
"step": 8825
|
| 3449 |
+
},
|
| 3450 |
+
{
|
| 3451 |
+
"epoch": 3.86,
|
| 3452 |
+
"grad_norm": 0.18415190279483795,
|
| 3453 |
+
"learning_rate": 3.4279475982532755e-06,
|
| 3454 |
+
"loss": 0.0268,
|
| 3455 |
+
"step": 8850
|
| 3456 |
+
},
|
| 3457 |
+
{
|
| 3458 |
+
"epoch": 3.88,
|
| 3459 |
+
"grad_norm": 0.8721256852149963,
|
| 3460 |
+
"learning_rate": 3.155021834061136e-06,
|
| 3461 |
+
"loss": 0.0258,
|
| 3462 |
+
"step": 8875
|
| 3463 |
+
},
|
| 3464 |
+
{
|
| 3465 |
+
"epoch": 3.89,
|
| 3466 |
+
"grad_norm": 0.1487792730331421,
|
| 3467 |
+
"learning_rate": 2.8820960698689956e-06,
|
| 3468 |
+
"loss": 0.0312,
|
| 3469 |
+
"step": 8900
|
| 3470 |
+
},
|
| 3471 |
+
{
|
| 3472 |
+
"epoch": 3.89,
|
| 3473 |
+
"eval_loss": 0.295600026845932,
|
| 3474 |
+
"eval_na_accuracy": 0.7857142686843872,
|
| 3475 |
+
"eval_ordinal_accuracy": 0.7133776545524597,
|
| 3476 |
+
"eval_ordinal_mae": 0.32104432582855225,
|
| 3477 |
+
"eval_runtime": 158.1112,
|
| 3478 |
+
"eval_samples_per_second": 25.166,
|
| 3479 |
+
"eval_steps_per_second": 3.15,
|
| 3480 |
+
"step": 8900
|
| 3481 |
+
},
|
| 3482 |
+
{
|
| 3483 |
+
"epoch": 3.9,
|
| 3484 |
+
"grad_norm": 0.6491901278495789,
|
| 3485 |
+
"learning_rate": 2.609170305676856e-06,
|
| 3486 |
+
"loss": 0.0526,
|
| 3487 |
+
"step": 8925
|
| 3488 |
+
},
|
| 3489 |
+
{
|
| 3490 |
+
"epoch": 3.91,
|
| 3491 |
+
"grad_norm": 0.40534159541130066,
|
| 3492 |
+
"learning_rate": 2.336244541484716e-06,
|
| 3493 |
+
"loss": 0.0227,
|
| 3494 |
+
"step": 8950
|
| 3495 |
+
},
|
| 3496 |
+
{
|
| 3497 |
+
"epoch": 3.92,
|
| 3498 |
+
"grad_norm": 0.06649890542030334,
|
| 3499 |
+
"learning_rate": 2.0633187772925767e-06,
|
| 3500 |
+
"loss": 0.0157,
|
| 3501 |
+
"step": 8975
|
| 3502 |
+
},
|
| 3503 |
+
{
|
| 3504 |
+
"epoch": 3.93,
|
| 3505 |
+
"grad_norm": 0.2696411609649658,
|
| 3506 |
+
"learning_rate": 1.7903930131004367e-06,
|
| 3507 |
+
"loss": 0.0189,
|
| 3508 |
+
"step": 9000
|
| 3509 |
+
},
|
| 3510 |
+
{
|
| 3511 |
+
"epoch": 3.93,
|
| 3512 |
+
"eval_loss": 0.2945779263973236,
|
| 3513 |
+
"eval_na_accuracy": 0.7876448035240173,
|
| 3514 |
+
"eval_ordinal_accuracy": 0.7125108242034912,
|
| 3515 |
+
"eval_ordinal_mae": 0.3210395574569702,
|
| 3516 |
+
"eval_runtime": 157.9016,
|
| 3517 |
+
"eval_samples_per_second": 25.199,
|
| 3518 |
+
"eval_steps_per_second": 3.154,
|
| 3519 |
+
"step": 9000
|
| 3520 |
+
},
|
| 3521 |
+
{
|
| 3522 |
+
"epoch": 3.94,
|
| 3523 |
+
"grad_norm": 0.16493447124958038,
|
| 3524 |
+
"learning_rate": 1.517467248908297e-06,
|
| 3525 |
+
"loss": 0.0204,
|
| 3526 |
+
"step": 9025
|
| 3527 |
+
},
|
| 3528 |
+
{
|
| 3529 |
+
"epoch": 3.95,
|
| 3530 |
+
"grad_norm": 0.5132766366004944,
|
| 3531 |
+
"learning_rate": 1.2445414847161573e-06,
|
| 3532 |
+
"loss": 0.0182,
|
| 3533 |
+
"step": 9050
|
| 3534 |
+
},
|
| 3535 |
+
{
|
| 3536 |
+
"epoch": 3.96,
|
| 3537 |
+
"grad_norm": 0.06899993121623993,
|
| 3538 |
+
"learning_rate": 9.716157205240176e-07,
|
| 3539 |
+
"loss": 0.0194,
|
| 3540 |
+
"step": 9075
|
| 3541 |
+
},
|
| 3542 |
+
{
|
| 3543 |
+
"epoch": 3.97,
|
| 3544 |
+
"grad_norm": 0.09663155674934387,
|
| 3545 |
+
"learning_rate": 6.986899563318777e-07,
|
| 3546 |
+
"loss": 0.021,
|
| 3547 |
+
"step": 9100
|
| 3548 |
+
},
|
| 3549 |
+
{
|
| 3550 |
+
"epoch": 3.97,
|
| 3551 |
+
"eval_loss": 0.2948993146419525,
|
| 3552 |
+
"eval_na_accuracy": 0.7876448035240173,
|
| 3553 |
+
"eval_ordinal_accuracy": 0.7145333886146545,
|
| 3554 |
+
"eval_ordinal_mae": 0.31944769620895386,
|
| 3555 |
+
"eval_runtime": 157.4833,
|
| 3556 |
+
"eval_samples_per_second": 25.266,
|
| 3557 |
+
"eval_steps_per_second": 3.162,
|
| 3558 |
+
"step": 9100
|
| 3559 |
+
},
|
| 3560 |
+
{
|
| 3561 |
+
"epoch": 3.98,
|
| 3562 |
+
"grad_norm": 0.4333021342754364,
|
| 3563 |
+
"learning_rate": 4.2576419213973797e-07,
|
| 3564 |
+
"loss": 0.0262,
|
| 3565 |
+
"step": 9125
|
| 3566 |
+
},
|
| 3567 |
+
{
|
| 3568 |
+
"epoch": 4.0,
|
| 3569 |
+
"grad_norm": 0.39392733573913574,
|
| 3570 |
+
"learning_rate": 1.5283842794759825e-07,
|
| 3571 |
+
"loss": 0.0247,
|
| 3572 |
+
"step": 9150
|
| 3573 |
+
},
|
| 3574 |
+
{
|
| 3575 |
+
"epoch": 4.0,
|
| 3576 |
+
"step": 9160,
|
| 3577 |
+
"total_flos": 1.1353293455817277e+19,
|
| 3578 |
+
"train_loss": 0.11642740544208273,
|
| 3579 |
+
"train_runtime": 27830.4973,
|
| 3580 |
+
"train_samples_per_second": 5.264,
|
| 3581 |
+
"train_steps_per_second": 0.329
|
| 3582 |
+
}
|
| 3583 |
+
],
|
| 3584 |
+
"logging_steps": 25,
|
| 3585 |
+
"max_steps": 9160,
|
| 3586 |
+
"num_input_tokens_seen": 0,
|
| 3587 |
+
"num_train_epochs": 4,
|
| 3588 |
+
"save_steps": 100,
|
| 3589 |
+
"total_flos": 1.1353293455817277e+19,
|
| 3590 |
+
"train_batch_size": 16,
|
| 3591 |
+
"trial_name": null,
|
| 3592 |
+
"trial_params": null
|
| 3593 |
+
}
|