🍻 cheers
Browse files- README.md +6 -5
- all_results.json +14 -0
- eval_results.json +10 -0
- runs/Mar30_19-49-55_ryanserver/events.out.tfevents.1711869903.ryanserver.6566.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +3267 -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: ryan03302024
|
|
@@ -13,12 +14,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# ryan03302024
|
| 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: ryan03302024
|
|
|
|
| 14 |
|
| 15 |
# ryan03302024
|
| 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: 0.2044
|
| 20 |
+
- Ordinal Mae: 0.4324
|
| 21 |
+
- Ordinal Accuracy: 0.6648
|
| 22 |
+
- Na Accuracy: 0.8333
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.20436730980873108,
|
| 4 |
+
"eval_na_accuracy": 0.8333333134651184,
|
| 5 |
+
"eval_ordinal_accuracy": 0.6647829413414001,
|
| 6 |
+
"eval_ordinal_mae": 0.4324062764644623,
|
| 7 |
+
"eval_runtime": 186.5896,
|
| 8 |
+
"eval_samples_per_second": 23.983,
|
| 9 |
+
"eval_steps_per_second": 3.001,
|
| 10 |
+
"train_loss": 0.13915026724546314,
|
| 11 |
+
"train_runtime": 27077.9759,
|
| 12 |
+
"train_samples_per_second": 4.916,
|
| 13 |
+
"train_steps_per_second": 0.307
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.20436730980873108,
|
| 4 |
+
"eval_na_accuracy": 0.8333333134651184,
|
| 5 |
+
"eval_ordinal_accuracy": 0.6647829413414001,
|
| 6 |
+
"eval_ordinal_mae": 0.4324062764644623,
|
| 7 |
+
"eval_runtime": 186.5896,
|
| 8 |
+
"eval_samples_per_second": 23.983,
|
| 9 |
+
"eval_steps_per_second": 3.001
|
| 10 |
+
}
|
runs/Mar30_19-49-55_ryanserver/events.out.tfevents.1711869903.ryanserver.6566.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccc3d7fc01fcf87fcb8169c4396f44c003495bee72670fa00d8911172e0535e3
|
| 3 |
+
size 529
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.13915026724546314,
|
| 4 |
+
"train_runtime": 27077.9759,
|
| 5 |
+
"train_samples_per_second": 4.916,
|
| 6 |
+
"train_steps_per_second": 0.307
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3267 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.20436730980873108,
|
| 3 |
+
"best_model_checkpoint": "./ryan03302024/checkpoint-2700",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 8319,
|
| 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": 0.9509561657905579,
|
| 14 |
+
"learning_rate": 9.969948311095084e-05,
|
| 15 |
+
"loss": 0.5096,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02,
|
| 20 |
+
"grad_norm": 0.5529997944831848,
|
| 21 |
+
"learning_rate": 9.939896622190168e-05,
|
| 22 |
+
"loss": 0.3519,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"grad_norm": 1.6374471187591553,
|
| 28 |
+
"learning_rate": 9.909844933285252e-05,
|
| 29 |
+
"loss": 0.3431,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.04,
|
| 34 |
+
"grad_norm": 1.235526204109192,
|
| 35 |
+
"learning_rate": 9.879793244380335e-05,
|
| 36 |
+
"loss": 0.3617,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04,
|
| 41 |
+
"eval_loss": 0.3133379817008972,
|
| 42 |
+
"eval_na_accuracy": 0.876288652420044,
|
| 43 |
+
"eval_ordinal_accuracy": 0.41741588711738586,
|
| 44 |
+
"eval_ordinal_mae": 0.8465587496757507,
|
| 45 |
+
"eval_runtime": 338.0185,
|
| 46 |
+
"eval_samples_per_second": 13.239,
|
| 47 |
+
"eval_steps_per_second": 1.657,
|
| 48 |
+
"step": 100
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.05,
|
| 52 |
+
"grad_norm": 1.0370614528656006,
|
| 53 |
+
"learning_rate": 9.849741555475418e-05,
|
| 54 |
+
"loss": 0.3721,
|
| 55 |
+
"step": 125
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.05,
|
| 59 |
+
"grad_norm": 1.619168996810913,
|
| 60 |
+
"learning_rate": 9.819689866570502e-05,
|
| 61 |
+
"loss": 0.3498,
|
| 62 |
+
"step": 150
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.06,
|
| 66 |
+
"grad_norm": 0.6790041923522949,
|
| 67 |
+
"learning_rate": 9.789638177665586e-05,
|
| 68 |
+
"loss": 0.3633,
|
| 69 |
+
"step": 175
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.07,
|
| 73 |
+
"grad_norm": 0.47009700536727905,
|
| 74 |
+
"learning_rate": 9.759586488760669e-05,
|
| 75 |
+
"loss": 0.2891,
|
| 76 |
+
"step": 200
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.07,
|
| 80 |
+
"eval_loss": 0.3022407293319702,
|
| 81 |
+
"eval_na_accuracy": 0.699312686920166,
|
| 82 |
+
"eval_ordinal_accuracy": 0.5044952630996704,
|
| 83 |
+
"eval_ordinal_mae": 0.7738743424415588,
|
| 84 |
+
"eval_runtime": 195.8973,
|
| 85 |
+
"eval_samples_per_second": 22.844,
|
| 86 |
+
"eval_steps_per_second": 2.859,
|
| 87 |
+
"step": 200
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.08,
|
| 91 |
+
"grad_norm": 1.6545381546020508,
|
| 92 |
+
"learning_rate": 9.73073686741195e-05,
|
| 93 |
+
"loss": 0.3277,
|
| 94 |
+
"step": 225
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.09,
|
| 98 |
+
"grad_norm": 0.2690508961677551,
|
| 99 |
+
"learning_rate": 9.700685178507033e-05,
|
| 100 |
+
"loss": 0.3505,
|
| 101 |
+
"step": 250
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.1,
|
| 105 |
+
"grad_norm": 2.571977138519287,
|
| 106 |
+
"learning_rate": 9.670633489602116e-05,
|
| 107 |
+
"loss": 0.2819,
|
| 108 |
+
"step": 275
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.11,
|
| 112 |
+
"grad_norm": 1.7339119911193848,
|
| 113 |
+
"learning_rate": 9.6405818006972e-05,
|
| 114 |
+
"loss": 0.3163,
|
| 115 |
+
"step": 300
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.11,
|
| 119 |
+
"eval_loss": 0.26153865456581116,
|
| 120 |
+
"eval_na_accuracy": 0.7903780341148376,
|
| 121 |
+
"eval_ordinal_accuracy": 0.5597226023674011,
|
| 122 |
+
"eval_ordinal_mae": 0.6166509985923767,
|
| 123 |
+
"eval_runtime": 200.5643,
|
| 124 |
+
"eval_samples_per_second": 22.312,
|
| 125 |
+
"eval_steps_per_second": 2.792,
|
| 126 |
+
"step": 300
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.12,
|
| 130 |
+
"grad_norm": 0.86951744556427,
|
| 131 |
+
"learning_rate": 9.610530111792283e-05,
|
| 132 |
+
"loss": 0.2707,
|
| 133 |
+
"step": 325
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.13,
|
| 137 |
+
"grad_norm": 0.3769865036010742,
|
| 138 |
+
"learning_rate": 9.580478422887367e-05,
|
| 139 |
+
"loss": 0.2917,
|
| 140 |
+
"step": 350
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.14,
|
| 144 |
+
"grad_norm": 0.39000704884529114,
|
| 145 |
+
"learning_rate": 9.55042673398245e-05,
|
| 146 |
+
"loss": 0.2765,
|
| 147 |
+
"step": 375
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.14,
|
| 151 |
+
"grad_norm": 0.7430490255355835,
|
| 152 |
+
"learning_rate": 9.520375045077534e-05,
|
| 153 |
+
"loss": 0.2781,
|
| 154 |
+
"step": 400
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.14,
|
| 158 |
+
"eval_loss": 0.2597866952419281,
|
| 159 |
+
"eval_na_accuracy": 0.8298969268798828,
|
| 160 |
+
"eval_ordinal_accuracy": 0.5936295986175537,
|
| 161 |
+
"eval_ordinal_mae": 0.5432500839233398,
|
| 162 |
+
"eval_runtime": 199.7937,
|
| 163 |
+
"eval_samples_per_second": 22.398,
|
| 164 |
+
"eval_steps_per_second": 2.803,
|
| 165 |
+
"step": 400
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.15,
|
| 169 |
+
"grad_norm": 1.8847980499267578,
|
| 170 |
+
"learning_rate": 9.490323356172616e-05,
|
| 171 |
+
"loss": 0.2643,
|
| 172 |
+
"step": 425
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.16,
|
| 176 |
+
"grad_norm": 1.0712331533432007,
|
| 177 |
+
"learning_rate": 9.461473734823898e-05,
|
| 178 |
+
"loss": 0.2747,
|
| 179 |
+
"step": 450
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.17,
|
| 183 |
+
"grad_norm": 0.9433643221855164,
|
| 184 |
+
"learning_rate": 9.431422045918981e-05,
|
| 185 |
+
"loss": 0.295,
|
| 186 |
+
"step": 475
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.18,
|
| 190 |
+
"grad_norm": 1.2171131372451782,
|
| 191 |
+
"learning_rate": 9.401370357014065e-05,
|
| 192 |
+
"loss": 0.2731,
|
| 193 |
+
"step": 500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.18,
|
| 197 |
+
"eval_loss": 0.26127612590789795,
|
| 198 |
+
"eval_na_accuracy": 0.8453608155250549,
|
| 199 |
+
"eval_ordinal_accuracy": 0.5566401481628418,
|
| 200 |
+
"eval_ordinal_mae": 0.5651282668113708,
|
| 201 |
+
"eval_runtime": 199.6257,
|
| 202 |
+
"eval_samples_per_second": 22.417,
|
| 203 |
+
"eval_steps_per_second": 2.805,
|
| 204 |
+
"step": 500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.19,
|
| 208 |
+
"grad_norm": 1.1272056102752686,
|
| 209 |
+
"learning_rate": 9.371318668109149e-05,
|
| 210 |
+
"loss": 0.2878,
|
| 211 |
+
"step": 525
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.2,
|
| 215 |
+
"grad_norm": 0.4902811348438263,
|
| 216 |
+
"learning_rate": 9.341266979204232e-05,
|
| 217 |
+
"loss": 0.2426,
|
| 218 |
+
"step": 550
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.21,
|
| 222 |
+
"grad_norm": 0.5631658434867859,
|
| 223 |
+
"learning_rate": 9.311215290299315e-05,
|
| 224 |
+
"loss": 0.2487,
|
| 225 |
+
"step": 575
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.22,
|
| 229 |
+
"grad_norm": 0.6327888369560242,
|
| 230 |
+
"learning_rate": 9.281163601394399e-05,
|
| 231 |
+
"loss": 0.2926,
|
| 232 |
+
"step": 600
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.22,
|
| 236 |
+
"eval_loss": 0.2734401226043701,
|
| 237 |
+
"eval_na_accuracy": 0.9089347124099731,
|
| 238 |
+
"eval_ordinal_accuracy": 0.5494477152824402,
|
| 239 |
+
"eval_ordinal_mae": 0.5305272340774536,
|
| 240 |
+
"eval_runtime": 196.452,
|
| 241 |
+
"eval_samples_per_second": 22.779,
|
| 242 |
+
"eval_steps_per_second": 2.851,
|
| 243 |
+
"step": 600
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.23,
|
| 247 |
+
"grad_norm": 0.6612924337387085,
|
| 248 |
+
"learning_rate": 9.251111912489481e-05,
|
| 249 |
+
"loss": 0.2871,
|
| 250 |
+
"step": 625
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.23,
|
| 254 |
+
"grad_norm": 1.513719081878662,
|
| 255 |
+
"learning_rate": 9.221060223584565e-05,
|
| 256 |
+
"loss": 0.2538,
|
| 257 |
+
"step": 650
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.24,
|
| 261 |
+
"grad_norm": 1.1069471836090088,
|
| 262 |
+
"learning_rate": 9.191008534679649e-05,
|
| 263 |
+
"loss": 0.21,
|
| 264 |
+
"step": 675
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.25,
|
| 268 |
+
"grad_norm": 2.458164691925049,
|
| 269 |
+
"learning_rate": 9.160956845774733e-05,
|
| 270 |
+
"loss": 0.2686,
|
| 271 |
+
"step": 700
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.25,
|
| 275 |
+
"eval_loss": 0.23620270192623138,
|
| 276 |
+
"eval_na_accuracy": 0.7886598110198975,
|
| 277 |
+
"eval_ordinal_accuracy": 0.6249678730964661,
|
| 278 |
+
"eval_ordinal_mae": 0.485275000333786,
|
| 279 |
+
"eval_runtime": 190.0791,
|
| 280 |
+
"eval_samples_per_second": 23.543,
|
| 281 |
+
"eval_steps_per_second": 2.946,
|
| 282 |
+
"step": 700
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.26,
|
| 286 |
+
"grad_norm": 0.5598509907722473,
|
| 287 |
+
"learning_rate": 9.130905156869817e-05,
|
| 288 |
+
"loss": 0.2525,
|
| 289 |
+
"step": 725
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.27,
|
| 293 |
+
"grad_norm": 1.2617449760437012,
|
| 294 |
+
"learning_rate": 9.1008534679649e-05,
|
| 295 |
+
"loss": 0.2453,
|
| 296 |
+
"step": 750
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.28,
|
| 300 |
+
"grad_norm": 1.5153591632843018,
|
| 301 |
+
"learning_rate": 9.070801779059983e-05,
|
| 302 |
+
"loss": 0.225,
|
| 303 |
+
"step": 775
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.29,
|
| 307 |
+
"grad_norm": 1.562745451927185,
|
| 308 |
+
"learning_rate": 9.040750090155067e-05,
|
| 309 |
+
"loss": 0.2715,
|
| 310 |
+
"step": 800
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.29,
|
| 314 |
+
"eval_loss": 0.24541285634040833,
|
| 315 |
+
"eval_na_accuracy": 0.7714776396751404,
|
| 316 |
+
"eval_ordinal_accuracy": 0.6254816055297852,
|
| 317 |
+
"eval_ordinal_mae": 0.49135151505470276,
|
| 318 |
+
"eval_runtime": 193.3675,
|
| 319 |
+
"eval_samples_per_second": 23.142,
|
| 320 |
+
"eval_steps_per_second": 2.896,
|
| 321 |
+
"step": 800
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.3,
|
| 325 |
+
"grad_norm": 1.5192123651504517,
|
| 326 |
+
"learning_rate": 9.010698401250151e-05,
|
| 327 |
+
"loss": 0.2424,
|
| 328 |
+
"step": 825
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.31,
|
| 332 |
+
"grad_norm": 0.8706183433532715,
|
| 333 |
+
"learning_rate": 8.980646712345235e-05,
|
| 334 |
+
"loss": 0.2341,
|
| 335 |
+
"step": 850
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.32,
|
| 339 |
+
"grad_norm": 1.0854986906051636,
|
| 340 |
+
"learning_rate": 8.950595023440318e-05,
|
| 341 |
+
"loss": 0.2694,
|
| 342 |
+
"step": 875
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.32,
|
| 346 |
+
"grad_norm": 2.208933115005493,
|
| 347 |
+
"learning_rate": 8.920543334535402e-05,
|
| 348 |
+
"loss": 0.2459,
|
| 349 |
+
"step": 900
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.32,
|
| 353 |
+
"eval_loss": 0.2451752871274948,
|
| 354 |
+
"eval_na_accuracy": 0.7800687551498413,
|
| 355 |
+
"eval_ordinal_accuracy": 0.6072437763214111,
|
| 356 |
+
"eval_ordinal_mae": 0.47625866532325745,
|
| 357 |
+
"eval_runtime": 192.5483,
|
| 358 |
+
"eval_samples_per_second": 23.241,
|
| 359 |
+
"eval_steps_per_second": 2.908,
|
| 360 |
+
"step": 900
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.33,
|
| 364 |
+
"grad_norm": 0.8433920741081238,
|
| 365 |
+
"learning_rate": 8.890491645630485e-05,
|
| 366 |
+
"loss": 0.2375,
|
| 367 |
+
"step": 925
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.34,
|
| 371 |
+
"grad_norm": 2.9415366649627686,
|
| 372 |
+
"learning_rate": 8.860439956725569e-05,
|
| 373 |
+
"loss": 0.2918,
|
| 374 |
+
"step": 950
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.35,
|
| 378 |
+
"grad_norm": 1.6653732061386108,
|
| 379 |
+
"learning_rate": 8.830388267820651e-05,
|
| 380 |
+
"loss": 0.2615,
|
| 381 |
+
"step": 975
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.36,
|
| 385 |
+
"grad_norm": 0.47592782974243164,
|
| 386 |
+
"learning_rate": 8.800336578915735e-05,
|
| 387 |
+
"loss": 0.2033,
|
| 388 |
+
"step": 1000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.36,
|
| 392 |
+
"eval_loss": 0.23654678463935852,
|
| 393 |
+
"eval_na_accuracy": 0.7663230299949646,
|
| 394 |
+
"eval_ordinal_accuracy": 0.6105831265449524,
|
| 395 |
+
"eval_ordinal_mae": 0.4967080354690552,
|
| 396 |
+
"eval_runtime": 192.911,
|
| 397 |
+
"eval_samples_per_second": 23.197,
|
| 398 |
+
"eval_steps_per_second": 2.903,
|
| 399 |
+
"step": 1000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.37,
|
| 403 |
+
"grad_norm": 0.8534409403800964,
|
| 404 |
+
"learning_rate": 8.770284890010819e-05,
|
| 405 |
+
"loss": 0.2082,
|
| 406 |
+
"step": 1025
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.38,
|
| 410 |
+
"grad_norm": 0.6388253569602966,
|
| 411 |
+
"learning_rate": 8.740233201105903e-05,
|
| 412 |
+
"loss": 0.2238,
|
| 413 |
+
"step": 1050
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.39,
|
| 417 |
+
"grad_norm": 1.5685051679611206,
|
| 418 |
+
"learning_rate": 8.710181512200987e-05,
|
| 419 |
+
"loss": 0.2775,
|
| 420 |
+
"step": 1075
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.4,
|
| 424 |
+
"grad_norm": 0.9940025806427002,
|
| 425 |
+
"learning_rate": 8.680129823296069e-05,
|
| 426 |
+
"loss": 0.2234,
|
| 427 |
+
"step": 1100
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.4,
|
| 431 |
+
"eval_loss": 0.22986453771591187,
|
| 432 |
+
"eval_na_accuracy": 0.8676975965499878,
|
| 433 |
+
"eval_ordinal_accuracy": 0.6180323362350464,
|
| 434 |
+
"eval_ordinal_mae": 0.49474066495895386,
|
| 435 |
+
"eval_runtime": 191.9691,
|
| 436 |
+
"eval_samples_per_second": 23.311,
|
| 437 |
+
"eval_steps_per_second": 2.917,
|
| 438 |
+
"step": 1100
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.41,
|
| 442 |
+
"grad_norm": 0.6706956624984741,
|
| 443 |
+
"learning_rate": 8.650078134391153e-05,
|
| 444 |
+
"loss": 0.2027,
|
| 445 |
+
"step": 1125
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.41,
|
| 449 |
+
"grad_norm": 0.4717120826244354,
|
| 450 |
+
"learning_rate": 8.620026445486237e-05,
|
| 451 |
+
"loss": 0.2072,
|
| 452 |
+
"step": 1150
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.42,
|
| 456 |
+
"grad_norm": 1.5387229919433594,
|
| 457 |
+
"learning_rate": 8.58997475658132e-05,
|
| 458 |
+
"loss": 0.2328,
|
| 459 |
+
"step": 1175
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.43,
|
| 463 |
+
"grad_norm": 1.0794016122817993,
|
| 464 |
+
"learning_rate": 8.559923067676405e-05,
|
| 465 |
+
"loss": 0.2035,
|
| 466 |
+
"step": 1200
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.43,
|
| 470 |
+
"eval_loss": 0.2313634753227234,
|
| 471 |
+
"eval_na_accuracy": 0.7835051417350769,
|
| 472 |
+
"eval_ordinal_accuracy": 0.6308759450912476,
|
| 473 |
+
"eval_ordinal_mae": 0.4743907153606415,
|
| 474 |
+
"eval_runtime": 191.4648,
|
| 475 |
+
"eval_samples_per_second": 23.372,
|
| 476 |
+
"eval_steps_per_second": 2.925,
|
| 477 |
+
"step": 1200
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.44,
|
| 481 |
+
"grad_norm": 1.2199459075927734,
|
| 482 |
+
"learning_rate": 8.529871378771488e-05,
|
| 483 |
+
"loss": 0.2769,
|
| 484 |
+
"step": 1225
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.45,
|
| 488 |
+
"grad_norm": 0.5869888067245483,
|
| 489 |
+
"learning_rate": 8.499819689866571e-05,
|
| 490 |
+
"loss": 0.2194,
|
| 491 |
+
"step": 1250
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.46,
|
| 495 |
+
"grad_norm": 1.1209378242492676,
|
| 496 |
+
"learning_rate": 8.469768000961655e-05,
|
| 497 |
+
"loss": 0.2536,
|
| 498 |
+
"step": 1275
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.47,
|
| 502 |
+
"grad_norm": 0.4376941919326782,
|
| 503 |
+
"learning_rate": 8.439716312056739e-05,
|
| 504 |
+
"loss": 0.2277,
|
| 505 |
+
"step": 1300
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.47,
|
| 509 |
+
"eval_loss": 0.23891955614089966,
|
| 510 |
+
"eval_na_accuracy": 0.730240523815155,
|
| 511 |
+
"eval_ordinal_accuracy": 0.643462598323822,
|
| 512 |
+
"eval_ordinal_mae": 0.46490678191185,
|
| 513 |
+
"eval_runtime": 193.3761,
|
| 514 |
+
"eval_samples_per_second": 23.141,
|
| 515 |
+
"eval_steps_per_second": 2.896,
|
| 516 |
+
"step": 1300
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.48,
|
| 520 |
+
"grad_norm": 1.8051934242248535,
|
| 521 |
+
"learning_rate": 8.409664623151821e-05,
|
| 522 |
+
"loss": 0.2007,
|
| 523 |
+
"step": 1325
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.49,
|
| 527 |
+
"grad_norm": 1.5033048391342163,
|
| 528 |
+
"learning_rate": 8.379612934246905e-05,
|
| 529 |
+
"loss": 0.1993,
|
| 530 |
+
"step": 1350
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.5,
|
| 534 |
+
"grad_norm": 0.577111542224884,
|
| 535 |
+
"learning_rate": 8.349561245341989e-05,
|
| 536 |
+
"loss": 0.2337,
|
| 537 |
+
"step": 1375
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.5,
|
| 541 |
+
"grad_norm": 0.8847935795783997,
|
| 542 |
+
"learning_rate": 8.319509556437071e-05,
|
| 543 |
+
"loss": 0.2535,
|
| 544 |
+
"step": 1400
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.5,
|
| 548 |
+
"eval_loss": 0.22593823075294495,
|
| 549 |
+
"eval_na_accuracy": 0.8247422575950623,
|
| 550 |
+
"eval_ordinal_accuracy": 0.6021063327789307,
|
| 551 |
+
"eval_ordinal_mae": 0.45086583495140076,
|
| 552 |
+
"eval_runtime": 192.5485,
|
| 553 |
+
"eval_samples_per_second": 23.241,
|
| 554 |
+
"eval_steps_per_second": 2.908,
|
| 555 |
+
"step": 1400
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.51,
|
| 559 |
+
"grad_norm": 1.888088345527649,
|
| 560 |
+
"learning_rate": 8.289457867532155e-05,
|
| 561 |
+
"loss": 0.2162,
|
| 562 |
+
"step": 1425
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.52,
|
| 566 |
+
"grad_norm": 0.9532464146614075,
|
| 567 |
+
"learning_rate": 8.259406178627239e-05,
|
| 568 |
+
"loss": 0.2632,
|
| 569 |
+
"step": 1450
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.53,
|
| 573 |
+
"grad_norm": 2.7865819931030273,
|
| 574 |
+
"learning_rate": 8.229354489722323e-05,
|
| 575 |
+
"loss": 0.2005,
|
| 576 |
+
"step": 1475
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.54,
|
| 580 |
+
"grad_norm": 1.0594526529312134,
|
| 581 |
+
"learning_rate": 8.199302800817407e-05,
|
| 582 |
+
"loss": 0.2209,
|
| 583 |
+
"step": 1500
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.54,
|
| 587 |
+
"eval_loss": 0.23685050010681152,
|
| 588 |
+
"eval_na_accuracy": 0.7577319741249084,
|
| 589 |
+
"eval_ordinal_accuracy": 0.6362702250480652,
|
| 590 |
+
"eval_ordinal_mae": 0.45073509216308594,
|
| 591 |
+
"eval_runtime": 192.1913,
|
| 592 |
+
"eval_samples_per_second": 23.284,
|
| 593 |
+
"eval_steps_per_second": 2.914,
|
| 594 |
+
"step": 1500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.55,
|
| 598 |
+
"grad_norm": 0.9557788372039795,
|
| 599 |
+
"learning_rate": 8.16925111191249e-05,
|
| 600 |
+
"loss": 0.2009,
|
| 601 |
+
"step": 1525
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.56,
|
| 605 |
+
"grad_norm": 0.7707318067550659,
|
| 606 |
+
"learning_rate": 8.139199423007573e-05,
|
| 607 |
+
"loss": 0.2172,
|
| 608 |
+
"step": 1550
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.57,
|
| 612 |
+
"grad_norm": 1.569989562034607,
|
| 613 |
+
"learning_rate": 8.109147734102657e-05,
|
| 614 |
+
"loss": 0.2229,
|
| 615 |
+
"step": 1575
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.58,
|
| 619 |
+
"grad_norm": 1.5089187622070312,
|
| 620 |
+
"learning_rate": 8.079096045197741e-05,
|
| 621 |
+
"loss": 0.2007,
|
| 622 |
+
"step": 1600
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.58,
|
| 626 |
+
"eval_loss": 0.21611952781677246,
|
| 627 |
+
"eval_na_accuracy": 0.831615149974823,
|
| 628 |
+
"eval_ordinal_accuracy": 0.6539943218231201,
|
| 629 |
+
"eval_ordinal_mae": 0.427180677652359,
|
| 630 |
+
"eval_runtime": 190.3474,
|
| 631 |
+
"eval_samples_per_second": 23.51,
|
| 632 |
+
"eval_steps_per_second": 2.942,
|
| 633 |
+
"step": 1600
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.59,
|
| 637 |
+
"grad_norm": 1.9716092348098755,
|
| 638 |
+
"learning_rate": 8.049044356292825e-05,
|
| 639 |
+
"loss": 0.2375,
|
| 640 |
+
"step": 1625
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.6,
|
| 644 |
+
"grad_norm": 2.04927659034729,
|
| 645 |
+
"learning_rate": 8.018992667387908e-05,
|
| 646 |
+
"loss": 0.2548,
|
| 647 |
+
"step": 1650
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.6,
|
| 651 |
+
"grad_norm": 1.1613515615463257,
|
| 652 |
+
"learning_rate": 7.988940978482991e-05,
|
| 653 |
+
"loss": 0.3238,
|
| 654 |
+
"step": 1675
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.61,
|
| 658 |
+
"grad_norm": 1.4977881908416748,
|
| 659 |
+
"learning_rate": 7.958889289578075e-05,
|
| 660 |
+
"loss": 0.2013,
|
| 661 |
+
"step": 1700
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.61,
|
| 665 |
+
"eval_loss": 0.24333100020885468,
|
| 666 |
+
"eval_na_accuracy": 0.7731958627700806,
|
| 667 |
+
"eval_ordinal_accuracy": 0.6128949522972107,
|
| 668 |
+
"eval_ordinal_mae": 0.43257907032966614,
|
| 669 |
+
"eval_runtime": 193.154,
|
| 670 |
+
"eval_samples_per_second": 23.168,
|
| 671 |
+
"eval_steps_per_second": 2.899,
|
| 672 |
+
"step": 1700
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.62,
|
| 676 |
+
"grad_norm": 0.6059219837188721,
|
| 677 |
+
"learning_rate": 7.928837600673157e-05,
|
| 678 |
+
"loss": 0.273,
|
| 679 |
+
"step": 1725
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 0.63,
|
| 683 |
+
"grad_norm": 1.3245080709457397,
|
| 684 |
+
"learning_rate": 7.898785911768241e-05,
|
| 685 |
+
"loss": 0.2148,
|
| 686 |
+
"step": 1750
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.64,
|
| 690 |
+
"grad_norm": 0.5151876211166382,
|
| 691 |
+
"learning_rate": 7.868734222863325e-05,
|
| 692 |
+
"loss": 0.1901,
|
| 693 |
+
"step": 1775
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.65,
|
| 697 |
+
"grad_norm": 0.37926343083381653,
|
| 698 |
+
"learning_rate": 7.838682533958409e-05,
|
| 699 |
+
"loss": 0.1999,
|
| 700 |
+
"step": 1800
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 0.65,
|
| 704 |
+
"eval_loss": 0.22266778349876404,
|
| 705 |
+
"eval_na_accuracy": 0.8247422575950623,
|
| 706 |
+
"eval_ordinal_accuracy": 0.6552786827087402,
|
| 707 |
+
"eval_ordinal_mae": 0.4460422396659851,
|
| 708 |
+
"eval_runtime": 193.6404,
|
| 709 |
+
"eval_samples_per_second": 23.11,
|
| 710 |
+
"eval_steps_per_second": 2.892,
|
| 711 |
+
"step": 1800
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.66,
|
| 715 |
+
"grad_norm": 4.746518611907959,
|
| 716 |
+
"learning_rate": 7.808630845053493e-05,
|
| 717 |
+
"loss": 0.2169,
|
| 718 |
+
"step": 1825
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.67,
|
| 722 |
+
"grad_norm": 0.3521455228328705,
|
| 723 |
+
"learning_rate": 7.778579156148575e-05,
|
| 724 |
+
"loss": 0.228,
|
| 725 |
+
"step": 1850
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.68,
|
| 729 |
+
"grad_norm": 1.3322985172271729,
|
| 730 |
+
"learning_rate": 7.748527467243659e-05,
|
| 731 |
+
"loss": 0.2047,
|
| 732 |
+
"step": 1875
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.69,
|
| 736 |
+
"grad_norm": 0.6390167474746704,
|
| 737 |
+
"learning_rate": 7.718475778338743e-05,
|
| 738 |
+
"loss": 0.2157,
|
| 739 |
+
"step": 1900
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.69,
|
| 743 |
+
"eval_loss": 0.2134324014186859,
|
| 744 |
+
"eval_na_accuracy": 0.8161512017250061,
|
| 745 |
+
"eval_ordinal_accuracy": 0.6362702250480652,
|
| 746 |
+
"eval_ordinal_mae": 0.4728001058101654,
|
| 747 |
+
"eval_runtime": 191.9038,
|
| 748 |
+
"eval_samples_per_second": 23.319,
|
| 749 |
+
"eval_steps_per_second": 2.918,
|
| 750 |
+
"step": 1900
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.69,
|
| 754 |
+
"grad_norm": 2.581801176071167,
|
| 755 |
+
"learning_rate": 7.688424089433827e-05,
|
| 756 |
+
"loss": 0.2335,
|
| 757 |
+
"step": 1925
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.7,
|
| 761 |
+
"grad_norm": 1.3418828248977661,
|
| 762 |
+
"learning_rate": 7.65837240052891e-05,
|
| 763 |
+
"loss": 0.2446,
|
| 764 |
+
"step": 1950
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.71,
|
| 768 |
+
"grad_norm": 0.605707585811615,
|
| 769 |
+
"learning_rate": 7.628320711623994e-05,
|
| 770 |
+
"loss": 0.2144,
|
| 771 |
+
"step": 1975
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.72,
|
| 775 |
+
"grad_norm": 0.6443113088607788,
|
| 776 |
+
"learning_rate": 7.598269022719077e-05,
|
| 777 |
+
"loss": 0.2154,
|
| 778 |
+
"step": 2000
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.72,
|
| 782 |
+
"eval_loss": 0.2238776683807373,
|
| 783 |
+
"eval_na_accuracy": 0.8573883175849915,
|
| 784 |
+
"eval_ordinal_accuracy": 0.5787310600280762,
|
| 785 |
+
"eval_ordinal_mae": 0.4734483063220978,
|
| 786 |
+
"eval_runtime": 192.57,
|
| 787 |
+
"eval_samples_per_second": 23.238,
|
| 788 |
+
"eval_steps_per_second": 2.908,
|
| 789 |
+
"step": 2000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.73,
|
| 793 |
+
"grad_norm": 1.4812798500061035,
|
| 794 |
+
"learning_rate": 7.568217333814161e-05,
|
| 795 |
+
"loss": 0.2172,
|
| 796 |
+
"step": 2025
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.74,
|
| 800 |
+
"grad_norm": 1.5400125980377197,
|
| 801 |
+
"learning_rate": 7.538165644909245e-05,
|
| 802 |
+
"loss": 0.1907,
|
| 803 |
+
"step": 2050
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.75,
|
| 807 |
+
"grad_norm": 0.6313005685806274,
|
| 808 |
+
"learning_rate": 7.508113956004327e-05,
|
| 809 |
+
"loss": 0.2078,
|
| 810 |
+
"step": 2075
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.76,
|
| 814 |
+
"grad_norm": 1.3446621894836426,
|
| 815 |
+
"learning_rate": 7.478062267099411e-05,
|
| 816 |
+
"loss": 0.2169,
|
| 817 |
+
"step": 2100
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.76,
|
| 821 |
+
"eval_loss": 0.23939213156700134,
|
| 822 |
+
"eval_na_accuracy": 0.8848797082901001,
|
| 823 |
+
"eval_ordinal_accuracy": 0.6254816055297852,
|
| 824 |
+
"eval_ordinal_mae": 0.4392252564430237,
|
| 825 |
+
"eval_runtime": 194.2506,
|
| 826 |
+
"eval_samples_per_second": 23.037,
|
| 827 |
+
"eval_steps_per_second": 2.883,
|
| 828 |
+
"step": 2100
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.77,
|
| 832 |
+
"grad_norm": 0.5709229111671448,
|
| 833 |
+
"learning_rate": 7.448010578194495e-05,
|
| 834 |
+
"loss": 0.2155,
|
| 835 |
+
"step": 2125
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.78,
|
| 839 |
+
"grad_norm": 2.9002838134765625,
|
| 840 |
+
"learning_rate": 7.417958889289577e-05,
|
| 841 |
+
"loss": 0.2534,
|
| 842 |
+
"step": 2150
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.78,
|
| 846 |
+
"grad_norm": 1.3746689558029175,
|
| 847 |
+
"learning_rate": 7.387907200384661e-05,
|
| 848 |
+
"loss": 0.2489,
|
| 849 |
+
"step": 2175
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.79,
|
| 853 |
+
"grad_norm": 1.1106956005096436,
|
| 854 |
+
"learning_rate": 7.357855511479745e-05,
|
| 855 |
+
"loss": 0.2719,
|
| 856 |
+
"step": 2200
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.79,
|
| 860 |
+
"eval_loss": 0.2283402532339096,
|
| 861 |
+
"eval_na_accuracy": 0.8780068755149841,
|
| 862 |
+
"eval_ordinal_accuracy": 0.6229129433631897,
|
| 863 |
+
"eval_ordinal_mae": 0.4323791265487671,
|
| 864 |
+
"eval_runtime": 193.3183,
|
| 865 |
+
"eval_samples_per_second": 23.148,
|
| 866 |
+
"eval_steps_per_second": 2.897,
|
| 867 |
+
"step": 2200
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.8,
|
| 871 |
+
"grad_norm": 1.5689876079559326,
|
| 872 |
+
"learning_rate": 7.327803822574829e-05,
|
| 873 |
+
"loss": 0.2054,
|
| 874 |
+
"step": 2225
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.81,
|
| 878 |
+
"grad_norm": 2.14363694190979,
|
| 879 |
+
"learning_rate": 7.297752133669913e-05,
|
| 880 |
+
"loss": 0.213,
|
| 881 |
+
"step": 2250
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 0.82,
|
| 885 |
+
"grad_norm": 1.4198272228240967,
|
| 886 |
+
"learning_rate": 7.267700444764997e-05,
|
| 887 |
+
"loss": 0.1729,
|
| 888 |
+
"step": 2275
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 0.83,
|
| 892 |
+
"grad_norm": 0.5297597646713257,
|
| 893 |
+
"learning_rate": 7.237648755860079e-05,
|
| 894 |
+
"loss": 0.2244,
|
| 895 |
+
"step": 2300
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 0.83,
|
| 899 |
+
"eval_loss": 0.2139568328857422,
|
| 900 |
+
"eval_na_accuracy": 0.8728522062301636,
|
| 901 |
+
"eval_ordinal_accuracy": 0.6313896775245667,
|
| 902 |
+
"eval_ordinal_mae": 0.4482755959033966,
|
| 903 |
+
"eval_runtime": 193.8188,
|
| 904 |
+
"eval_samples_per_second": 23.089,
|
| 905 |
+
"eval_steps_per_second": 2.889,
|
| 906 |
+
"step": 2300
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.84,
|
| 910 |
+
"grad_norm": 0.4800972044467926,
|
| 911 |
+
"learning_rate": 7.207597066955163e-05,
|
| 912 |
+
"loss": 0.231,
|
| 913 |
+
"step": 2325
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.85,
|
| 917 |
+
"grad_norm": 2.125603199005127,
|
| 918 |
+
"learning_rate": 7.177545378050247e-05,
|
| 919 |
+
"loss": 0.2371,
|
| 920 |
+
"step": 2350
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.86,
|
| 924 |
+
"grad_norm": 1.553396224975586,
|
| 925 |
+
"learning_rate": 7.147493689145331e-05,
|
| 926 |
+
"loss": 0.217,
|
| 927 |
+
"step": 2375
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.87,
|
| 931 |
+
"grad_norm": 1.5980515480041504,
|
| 932 |
+
"learning_rate": 7.117442000240415e-05,
|
| 933 |
+
"loss": 0.2072,
|
| 934 |
+
"step": 2400
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.87,
|
| 938 |
+
"eval_loss": 0.2198052555322647,
|
| 939 |
+
"eval_na_accuracy": 0.8213058710098267,
|
| 940 |
+
"eval_ordinal_accuracy": 0.6439763903617859,
|
| 941 |
+
"eval_ordinal_mae": 0.4330386817455292,
|
| 942 |
+
"eval_runtime": 193.8423,
|
| 943 |
+
"eval_samples_per_second": 23.086,
|
| 944 |
+
"eval_steps_per_second": 2.889,
|
| 945 |
+
"step": 2400
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.87,
|
| 949 |
+
"grad_norm": 1.0013697147369385,
|
| 950 |
+
"learning_rate": 7.087390311335498e-05,
|
| 951 |
+
"loss": 0.2141,
|
| 952 |
+
"step": 2425
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 0.88,
|
| 956 |
+
"grad_norm": 2.5208072662353516,
|
| 957 |
+
"learning_rate": 7.057338622430581e-05,
|
| 958 |
+
"loss": 0.2109,
|
| 959 |
+
"step": 2450
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 0.89,
|
| 963 |
+
"grad_norm": 0.3612011969089508,
|
| 964 |
+
"learning_rate": 7.027286933525665e-05,
|
| 965 |
+
"loss": 0.1701,
|
| 966 |
+
"step": 2475
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 0.9,
|
| 970 |
+
"grad_norm": 0.6919033527374268,
|
| 971 |
+
"learning_rate": 6.997235244620747e-05,
|
| 972 |
+
"loss": 0.1754,
|
| 973 |
+
"step": 2500
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 0.9,
|
| 977 |
+
"eval_loss": 0.20990537106990814,
|
| 978 |
+
"eval_na_accuracy": 0.8419243693351746,
|
| 979 |
+
"eval_ordinal_accuracy": 0.6712047457695007,
|
| 980 |
+
"eval_ordinal_mae": 0.41983720660209656,
|
| 981 |
+
"eval_runtime": 193.4285,
|
| 982 |
+
"eval_samples_per_second": 23.135,
|
| 983 |
+
"eval_steps_per_second": 2.895,
|
| 984 |
+
"step": 2500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.91,
|
| 988 |
+
"grad_norm": 2.494234323501587,
|
| 989 |
+
"learning_rate": 6.967183555715831e-05,
|
| 990 |
+
"loss": 0.2547,
|
| 991 |
+
"step": 2525
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.92,
|
| 995 |
+
"grad_norm": 1.2194478511810303,
|
| 996 |
+
"learning_rate": 6.937131866810915e-05,
|
| 997 |
+
"loss": 0.2105,
|
| 998 |
+
"step": 2550
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.93,
|
| 1002 |
+
"grad_norm": 0.8242117166519165,
|
| 1003 |
+
"learning_rate": 6.907080177905999e-05,
|
| 1004 |
+
"loss": 0.185,
|
| 1005 |
+
"step": 2575
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.94,
|
| 1009 |
+
"grad_norm": 2.185267210006714,
|
| 1010 |
+
"learning_rate": 6.877028489001081e-05,
|
| 1011 |
+
"loss": 0.1773,
|
| 1012 |
+
"step": 2600
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.94,
|
| 1016 |
+
"eval_loss": 0.20526131987571716,
|
| 1017 |
+
"eval_na_accuracy": 0.8642611503601074,
|
| 1018 |
+
"eval_ordinal_accuracy": 0.6586180329322815,
|
| 1019 |
+
"eval_ordinal_mae": 0.4104856550693512,
|
| 1020 |
+
"eval_runtime": 191.4771,
|
| 1021 |
+
"eval_samples_per_second": 23.371,
|
| 1022 |
+
"eval_steps_per_second": 2.925,
|
| 1023 |
+
"step": 2600
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.95,
|
| 1027 |
+
"grad_norm": 1.5727041959762573,
|
| 1028 |
+
"learning_rate": 6.846976800096165e-05,
|
| 1029 |
+
"loss": 0.1994,
|
| 1030 |
+
"step": 2625
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 0.96,
|
| 1034 |
+
"grad_norm": 1.3567266464233398,
|
| 1035 |
+
"learning_rate": 6.816925111191249e-05,
|
| 1036 |
+
"loss": 0.2087,
|
| 1037 |
+
"step": 2650
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.96,
|
| 1041 |
+
"grad_norm": 0.43862801790237427,
|
| 1042 |
+
"learning_rate": 6.786873422286333e-05,
|
| 1043 |
+
"loss": 0.2394,
|
| 1044 |
+
"step": 2675
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.97,
|
| 1048 |
+
"grad_norm": 0.7140023708343506,
|
| 1049 |
+
"learning_rate": 6.756821733381417e-05,
|
| 1050 |
+
"loss": 0.2378,
|
| 1051 |
+
"step": 2700
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.97,
|
| 1055 |
+
"eval_loss": 0.20436730980873108,
|
| 1056 |
+
"eval_na_accuracy": 0.8333333134651184,
|
| 1057 |
+
"eval_ordinal_accuracy": 0.6647829413414001,
|
| 1058 |
+
"eval_ordinal_mae": 0.4324062764644623,
|
| 1059 |
+
"eval_runtime": 193.6819,
|
| 1060 |
+
"eval_samples_per_second": 23.105,
|
| 1061 |
+
"eval_steps_per_second": 2.891,
|
| 1062 |
+
"step": 2700
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.98,
|
| 1066 |
+
"grad_norm": 0.44048529863357544,
|
| 1067 |
+
"learning_rate": 6.7267700444765e-05,
|
| 1068 |
+
"loss": 0.172,
|
| 1069 |
+
"step": 2725
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.99,
|
| 1073 |
+
"grad_norm": 2.4433631896972656,
|
| 1074 |
+
"learning_rate": 6.696718355571583e-05,
|
| 1075 |
+
"loss": 0.1666,
|
| 1076 |
+
"step": 2750
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.0,
|
| 1080 |
+
"grad_norm": 0.6148251891136169,
|
| 1081 |
+
"learning_rate": 6.666666666666667e-05,
|
| 1082 |
+
"loss": 0.2,
|
| 1083 |
+
"step": 2775
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 1.01,
|
| 1087 |
+
"grad_norm": 0.5114859342575073,
|
| 1088 |
+
"learning_rate": 6.636614977761751e-05,
|
| 1089 |
+
"loss": 0.1295,
|
| 1090 |
+
"step": 2800
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 1.01,
|
| 1094 |
+
"eval_loss": 0.20437294244766235,
|
| 1095 |
+
"eval_na_accuracy": 0.8247422575950623,
|
| 1096 |
+
"eval_ordinal_accuracy": 0.6843051910400391,
|
| 1097 |
+
"eval_ordinal_mae": 0.4015503525733948,
|
| 1098 |
+
"eval_runtime": 191.7797,
|
| 1099 |
+
"eval_samples_per_second": 23.334,
|
| 1100 |
+
"eval_steps_per_second": 2.92,
|
| 1101 |
+
"step": 2800
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.02,
|
| 1105 |
+
"grad_norm": 0.5778698921203613,
|
| 1106 |
+
"learning_rate": 6.606563288856835e-05,
|
| 1107 |
+
"loss": 0.1506,
|
| 1108 |
+
"step": 2825
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.03,
|
| 1112 |
+
"grad_norm": 0.3983612358570099,
|
| 1113 |
+
"learning_rate": 6.576511599951917e-05,
|
| 1114 |
+
"loss": 0.1358,
|
| 1115 |
+
"step": 2850
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.04,
|
| 1119 |
+
"grad_norm": 0.8497461080551147,
|
| 1120 |
+
"learning_rate": 6.546459911047001e-05,
|
| 1121 |
+
"loss": 0.1288,
|
| 1122 |
+
"step": 2875
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.05,
|
| 1126 |
+
"grad_norm": 1.2482887506484985,
|
| 1127 |
+
"learning_rate": 6.516408222142085e-05,
|
| 1128 |
+
"loss": 0.1126,
|
| 1129 |
+
"step": 2900
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.05,
|
| 1133 |
+
"eval_loss": 0.2301819771528244,
|
| 1134 |
+
"eval_na_accuracy": 0.7577319741249084,
|
| 1135 |
+
"eval_ordinal_accuracy": 0.6804521083831787,
|
| 1136 |
+
"eval_ordinal_mae": 0.402468740940094,
|
| 1137 |
+
"eval_runtime": 195.9356,
|
| 1138 |
+
"eval_samples_per_second": 22.839,
|
| 1139 |
+
"eval_steps_per_second": 2.858,
|
| 1140 |
+
"step": 2900
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.05,
|
| 1144 |
+
"grad_norm": 12.926443099975586,
|
| 1145 |
+
"learning_rate": 6.486356533237167e-05,
|
| 1146 |
+
"loss": 0.1244,
|
| 1147 |
+
"step": 2925
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 1.06,
|
| 1151 |
+
"grad_norm": 0.5321182012557983,
|
| 1152 |
+
"learning_rate": 6.456304844332251e-05,
|
| 1153 |
+
"loss": 0.1368,
|
| 1154 |
+
"step": 2950
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 1.07,
|
| 1158 |
+
"grad_norm": 0.4846901297569275,
|
| 1159 |
+
"learning_rate": 6.426253155427335e-05,
|
| 1160 |
+
"loss": 0.1837,
|
| 1161 |
+
"step": 2975
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.08,
|
| 1165 |
+
"grad_norm": 0.6585441827774048,
|
| 1166 |
+
"learning_rate": 6.396201466522419e-05,
|
| 1167 |
+
"loss": 0.1262,
|
| 1168 |
+
"step": 3000
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 1.08,
|
| 1172 |
+
"eval_loss": 0.22050338983535767,
|
| 1173 |
+
"eval_na_accuracy": 0.8092783689498901,
|
| 1174 |
+
"eval_ordinal_accuracy": 0.6516824960708618,
|
| 1175 |
+
"eval_ordinal_mae": 0.4016842246055603,
|
| 1176 |
+
"eval_runtime": 191.162,
|
| 1177 |
+
"eval_samples_per_second": 23.409,
|
| 1178 |
+
"eval_steps_per_second": 2.929,
|
| 1179 |
+
"step": 3000
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.09,
|
| 1183 |
+
"grad_norm": 0.30136457085609436,
|
| 1184 |
+
"learning_rate": 6.366149777617503e-05,
|
| 1185 |
+
"loss": 0.1417,
|
| 1186 |
+
"step": 3025
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.1,
|
| 1190 |
+
"grad_norm": 2.017369508743286,
|
| 1191 |
+
"learning_rate": 6.336098088712587e-05,
|
| 1192 |
+
"loss": 0.1155,
|
| 1193 |
+
"step": 3050
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.11,
|
| 1197 |
+
"grad_norm": 0.6489114165306091,
|
| 1198 |
+
"learning_rate": 6.306046399807669e-05,
|
| 1199 |
+
"loss": 0.1074,
|
| 1200 |
+
"step": 3075
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.12,
|
| 1204 |
+
"grad_norm": 0.5059970617294312,
|
| 1205 |
+
"learning_rate": 6.275994710902753e-05,
|
| 1206 |
+
"loss": 0.1104,
|
| 1207 |
+
"step": 3100
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.12,
|
| 1211 |
+
"eval_loss": 0.21169866621494293,
|
| 1212 |
+
"eval_na_accuracy": 0.8453608155250549,
|
| 1213 |
+
"eval_ordinal_accuracy": 0.6778833866119385,
|
| 1214 |
+
"eval_ordinal_mae": 0.39305010437965393,
|
| 1215 |
+
"eval_runtime": 189.5391,
|
| 1216 |
+
"eval_samples_per_second": 23.61,
|
| 1217 |
+
"eval_steps_per_second": 2.955,
|
| 1218 |
+
"step": 3100
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 1.13,
|
| 1222 |
+
"grad_norm": 1.127930998802185,
|
| 1223 |
+
"learning_rate": 6.245943021997837e-05,
|
| 1224 |
+
"loss": 0.1353,
|
| 1225 |
+
"step": 3125
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 1.14,
|
| 1229 |
+
"grad_norm": 1.9614742994308472,
|
| 1230 |
+
"learning_rate": 6.215891333092921e-05,
|
| 1231 |
+
"loss": 0.1069,
|
| 1232 |
+
"step": 3150
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 1.14,
|
| 1236 |
+
"grad_norm": 0.5779272317886353,
|
| 1237 |
+
"learning_rate": 6.185839644188005e-05,
|
| 1238 |
+
"loss": 0.1161,
|
| 1239 |
+
"step": 3175
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 1.15,
|
| 1243 |
+
"grad_norm": 0.6223546266555786,
|
| 1244 |
+
"learning_rate": 6.155787955283087e-05,
|
| 1245 |
+
"loss": 0.1657,
|
| 1246 |
+
"step": 3200
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 1.15,
|
| 1250 |
+
"eval_loss": 0.21738822758197784,
|
| 1251 |
+
"eval_na_accuracy": 0.8591065406799316,
|
| 1252 |
+
"eval_ordinal_accuracy": 0.6665810346603394,
|
| 1253 |
+
"eval_ordinal_mae": 0.38904985785484314,
|
| 1254 |
+
"eval_runtime": 193.8286,
|
| 1255 |
+
"eval_samples_per_second": 23.087,
|
| 1256 |
+
"eval_steps_per_second": 2.889,
|
| 1257 |
+
"step": 3200
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 1.16,
|
| 1261 |
+
"grad_norm": 1.1987367868423462,
|
| 1262 |
+
"learning_rate": 6.125736266378171e-05,
|
| 1263 |
+
"loss": 0.1139,
|
| 1264 |
+
"step": 3225
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 1.17,
|
| 1268 |
+
"grad_norm": 0.510863184928894,
|
| 1269 |
+
"learning_rate": 6.095684577473254e-05,
|
| 1270 |
+
"loss": 0.1286,
|
| 1271 |
+
"step": 3250
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 1.18,
|
| 1275 |
+
"grad_norm": 0.7094324827194214,
|
| 1276 |
+
"learning_rate": 6.065632888568338e-05,
|
| 1277 |
+
"loss": 0.1231,
|
| 1278 |
+
"step": 3275
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 1.19,
|
| 1282 |
+
"grad_norm": 2.9405245780944824,
|
| 1283 |
+
"learning_rate": 6.035581199663422e-05,
|
| 1284 |
+
"loss": 0.1186,
|
| 1285 |
+
"step": 3300
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 1.19,
|
| 1289 |
+
"eval_loss": 0.22988717257976532,
|
| 1290 |
+
"eval_na_accuracy": 0.8058419227600098,
|
| 1291 |
+
"eval_ordinal_accuracy": 0.6622142195701599,
|
| 1292 |
+
"eval_ordinal_mae": 0.40129175782203674,
|
| 1293 |
+
"eval_runtime": 191.4373,
|
| 1294 |
+
"eval_samples_per_second": 23.376,
|
| 1295 |
+
"eval_steps_per_second": 2.925,
|
| 1296 |
+
"step": 3300
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 1.2,
|
| 1300 |
+
"grad_norm": 1.9970686435699463,
|
| 1301 |
+
"learning_rate": 6.005529510758505e-05,
|
| 1302 |
+
"loss": 0.1492,
|
| 1303 |
+
"step": 3325
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 1.21,
|
| 1307 |
+
"grad_norm": 0.4853156805038452,
|
| 1308 |
+
"learning_rate": 5.975477821853589e-05,
|
| 1309 |
+
"loss": 0.0923,
|
| 1310 |
+
"step": 3350
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 1.22,
|
| 1314 |
+
"grad_norm": 3.004967451095581,
|
| 1315 |
+
"learning_rate": 5.9454261329486714e-05,
|
| 1316 |
+
"loss": 0.1395,
|
| 1317 |
+
"step": 3375
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 1.23,
|
| 1321 |
+
"grad_norm": 2.5411417484283447,
|
| 1322 |
+
"learning_rate": 5.915374444043755e-05,
|
| 1323 |
+
"loss": 0.1304,
|
| 1324 |
+
"step": 3400
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 1.23,
|
| 1328 |
+
"eval_loss": 0.21757462620735168,
|
| 1329 |
+
"eval_na_accuracy": 0.8109965920448303,
|
| 1330 |
+
"eval_ordinal_accuracy": 0.6902132034301758,
|
| 1331 |
+
"eval_ordinal_mae": 0.3801174759864807,
|
| 1332 |
+
"eval_runtime": 191.9938,
|
| 1333 |
+
"eval_samples_per_second": 23.308,
|
| 1334 |
+
"eval_steps_per_second": 2.917,
|
| 1335 |
+
"step": 3400
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 1.24,
|
| 1339 |
+
"grad_norm": 2.031360626220703,
|
| 1340 |
+
"learning_rate": 5.885322755138839e-05,
|
| 1341 |
+
"loss": 0.161,
|
| 1342 |
+
"step": 3425
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 1.24,
|
| 1346 |
+
"grad_norm": 0.9166708588600159,
|
| 1347 |
+
"learning_rate": 5.855271066233923e-05,
|
| 1348 |
+
"loss": 0.1062,
|
| 1349 |
+
"step": 3450
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 1.25,
|
| 1353 |
+
"grad_norm": 2.4028913974761963,
|
| 1354 |
+
"learning_rate": 5.825219377329007e-05,
|
| 1355 |
+
"loss": 0.1085,
|
| 1356 |
+
"step": 3475
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 1.26,
|
| 1360 |
+
"grad_norm": 0.99100261926651,
|
| 1361 |
+
"learning_rate": 5.79516768842409e-05,
|
| 1362 |
+
"loss": 0.1081,
|
| 1363 |
+
"step": 3500
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 1.26,
|
| 1367 |
+
"eval_loss": 0.23295216262340546,
|
| 1368 |
+
"eval_na_accuracy": 0.831615149974823,
|
| 1369 |
+
"eval_ordinal_accuracy": 0.664269208908081,
|
| 1370 |
+
"eval_ordinal_mae": 0.3867188096046448,
|
| 1371 |
+
"eval_runtime": 194.3732,
|
| 1372 |
+
"eval_samples_per_second": 23.023,
|
| 1373 |
+
"eval_steps_per_second": 2.881,
|
| 1374 |
+
"step": 3500
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.27,
|
| 1378 |
+
"grad_norm": 0.6745060682296753,
|
| 1379 |
+
"learning_rate": 5.765115999519173e-05,
|
| 1380 |
+
"loss": 0.1079,
|
| 1381 |
+
"step": 3525
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.28,
|
| 1385 |
+
"grad_norm": 0.5718048810958862,
|
| 1386 |
+
"learning_rate": 5.735064310614256e-05,
|
| 1387 |
+
"loss": 0.1353,
|
| 1388 |
+
"step": 3550
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.29,
|
| 1392 |
+
"grad_norm": 0.4868764579296112,
|
| 1393 |
+
"learning_rate": 5.70501262170934e-05,
|
| 1394 |
+
"loss": 0.1872,
|
| 1395 |
+
"step": 3575
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.3,
|
| 1399 |
+
"grad_norm": 1.2596338987350464,
|
| 1400 |
+
"learning_rate": 5.674960932804424e-05,
|
| 1401 |
+
"loss": 0.1281,
|
| 1402 |
+
"step": 3600
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.3,
|
| 1406 |
+
"eval_loss": 0.23198525607585907,
|
| 1407 |
+
"eval_na_accuracy": 0.7680412530899048,
|
| 1408 |
+
"eval_ordinal_accuracy": 0.6902132034301758,
|
| 1409 |
+
"eval_ordinal_mae": 0.3953803777694702,
|
| 1410 |
+
"eval_runtime": 193.0669,
|
| 1411 |
+
"eval_samples_per_second": 23.178,
|
| 1412 |
+
"eval_steps_per_second": 2.901,
|
| 1413 |
+
"step": 3600
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.31,
|
| 1417 |
+
"grad_norm": 0.5509974360466003,
|
| 1418 |
+
"learning_rate": 5.644909243899508e-05,
|
| 1419 |
+
"loss": 0.1085,
|
| 1420 |
+
"step": 3625
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.32,
|
| 1424 |
+
"grad_norm": 1.8018646240234375,
|
| 1425 |
+
"learning_rate": 5.614857554994592e-05,
|
| 1426 |
+
"loss": 0.1134,
|
| 1427 |
+
"step": 3650
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 1.33,
|
| 1431 |
+
"grad_norm": 0.46525055170059204,
|
| 1432 |
+
"learning_rate": 5.584805866089674e-05,
|
| 1433 |
+
"loss": 0.1789,
|
| 1434 |
+
"step": 3675
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 1.33,
|
| 1438 |
+
"grad_norm": 0.4697776734828949,
|
| 1439 |
+
"learning_rate": 5.554754177184758e-05,
|
| 1440 |
+
"loss": 0.1192,
|
| 1441 |
+
"step": 3700
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 1.33,
|
| 1445 |
+
"eval_loss": 0.231234610080719,
|
| 1446 |
+
"eval_na_accuracy": 0.7989690899848938,
|
| 1447 |
+
"eval_ordinal_accuracy": 0.6768559217453003,
|
| 1448 |
+
"eval_ordinal_mae": 0.4108929932117462,
|
| 1449 |
+
"eval_runtime": 192.9099,
|
| 1450 |
+
"eval_samples_per_second": 23.197,
|
| 1451 |
+
"eval_steps_per_second": 2.903,
|
| 1452 |
+
"step": 3700
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.34,
|
| 1456 |
+
"grad_norm": 1.9536067247390747,
|
| 1457 |
+
"learning_rate": 5.524702488279841e-05,
|
| 1458 |
+
"loss": 0.1531,
|
| 1459 |
+
"step": 3725
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.35,
|
| 1463 |
+
"grad_norm": 0.6636119484901428,
|
| 1464 |
+
"learning_rate": 5.494650799374925e-05,
|
| 1465 |
+
"loss": 0.1152,
|
| 1466 |
+
"step": 3750
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.36,
|
| 1470 |
+
"grad_norm": 3.2403175830841064,
|
| 1471 |
+
"learning_rate": 5.464599110470009e-05,
|
| 1472 |
+
"loss": 0.133,
|
| 1473 |
+
"step": 3775
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.37,
|
| 1477 |
+
"grad_norm": 0.7575627565383911,
|
| 1478 |
+
"learning_rate": 5.434547421565093e-05,
|
| 1479 |
+
"loss": 0.1029,
|
| 1480 |
+
"step": 3800
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.37,
|
| 1484 |
+
"eval_loss": 0.21953611075878143,
|
| 1485 |
+
"eval_na_accuracy": 0.8024054765701294,
|
| 1486 |
+
"eval_ordinal_accuracy": 0.681993305683136,
|
| 1487 |
+
"eval_ordinal_mae": 0.38697296380996704,
|
| 1488 |
+
"eval_runtime": 192.4936,
|
| 1489 |
+
"eval_samples_per_second": 23.248,
|
| 1490 |
+
"eval_steps_per_second": 2.909,
|
| 1491 |
+
"step": 3800
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 1.38,
|
| 1495 |
+
"grad_norm": 0.6479007601737976,
|
| 1496 |
+
"learning_rate": 5.404495732660175e-05,
|
| 1497 |
+
"loss": 0.1174,
|
| 1498 |
+
"step": 3825
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 1.39,
|
| 1502 |
+
"grad_norm": 2.8630564212799072,
|
| 1503 |
+
"learning_rate": 5.374444043755259e-05,
|
| 1504 |
+
"loss": 0.1398,
|
| 1505 |
+
"step": 3850
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 1.4,
|
| 1509 |
+
"grad_norm": 0.6482840180397034,
|
| 1510 |
+
"learning_rate": 5.344392354850343e-05,
|
| 1511 |
+
"loss": 0.1144,
|
| 1512 |
+
"step": 3875
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 1.41,
|
| 1516 |
+
"grad_norm": 0.39722609519958496,
|
| 1517 |
+
"learning_rate": 5.314340665945426e-05,
|
| 1518 |
+
"loss": 0.1159,
|
| 1519 |
+
"step": 3900
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 1.41,
|
| 1523 |
+
"eval_loss": 0.22003380954265594,
|
| 1524 |
+
"eval_na_accuracy": 0.7903780341148376,
|
| 1525 |
+
"eval_ordinal_accuracy": 0.6812227368354797,
|
| 1526 |
+
"eval_ordinal_mae": 0.3859783113002777,
|
| 1527 |
+
"eval_runtime": 193.9688,
|
| 1528 |
+
"eval_samples_per_second": 23.071,
|
| 1529 |
+
"eval_steps_per_second": 2.887,
|
| 1530 |
+
"step": 3900
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 1.42,
|
| 1534 |
+
"grad_norm": 0.7128223776817322,
|
| 1535 |
+
"learning_rate": 5.28428897704051e-05,
|
| 1536 |
+
"loss": 0.1437,
|
| 1537 |
+
"step": 3925
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 1.42,
|
| 1541 |
+
"grad_norm": 2.3041298389434814,
|
| 1542 |
+
"learning_rate": 5.254237288135594e-05,
|
| 1543 |
+
"loss": 0.1413,
|
| 1544 |
+
"step": 3950
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 1.43,
|
| 1548 |
+
"grad_norm": 0.9336991310119629,
|
| 1549 |
+
"learning_rate": 5.2241855992306764e-05,
|
| 1550 |
+
"loss": 0.1112,
|
| 1551 |
+
"step": 3975
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 1.44,
|
| 1555 |
+
"grad_norm": 3.5301501750946045,
|
| 1556 |
+
"learning_rate": 5.19413391032576e-05,
|
| 1557 |
+
"loss": 0.1159,
|
| 1558 |
+
"step": 4000
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 1.44,
|
| 1562 |
+
"eval_loss": 0.21585588157176971,
|
| 1563 |
+
"eval_na_accuracy": 0.7989690899848938,
|
| 1564 |
+
"eval_ordinal_accuracy": 0.6981762051582336,
|
| 1565 |
+
"eval_ordinal_mae": 0.3712264895439148,
|
| 1566 |
+
"eval_runtime": 191.7494,
|
| 1567 |
+
"eval_samples_per_second": 23.338,
|
| 1568 |
+
"eval_steps_per_second": 2.92,
|
| 1569 |
+
"step": 4000
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 1.45,
|
| 1573 |
+
"grad_norm": 0.8215810060501099,
|
| 1574 |
+
"learning_rate": 5.164082221420844e-05,
|
| 1575 |
+
"loss": 0.0948,
|
| 1576 |
+
"step": 4025
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 1.46,
|
| 1580 |
+
"grad_norm": 0.8609411716461182,
|
| 1581 |
+
"learning_rate": 5.134030532515928e-05,
|
| 1582 |
+
"loss": 0.0936,
|
| 1583 |
+
"step": 4050
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 1.47,
|
| 1587 |
+
"grad_norm": 0.7595614790916443,
|
| 1588 |
+
"learning_rate": 5.103978843611011e-05,
|
| 1589 |
+
"loss": 0.1181,
|
| 1590 |
+
"step": 4075
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 1.48,
|
| 1594 |
+
"grad_norm": 0.7951629757881165,
|
| 1595 |
+
"learning_rate": 5.073927154706095e-05,
|
| 1596 |
+
"loss": 0.107,
|
| 1597 |
+
"step": 4100
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 1.48,
|
| 1601 |
+
"eval_loss": 0.22618594765663147,
|
| 1602 |
+
"eval_na_accuracy": 0.8213058710098267,
|
| 1603 |
+
"eval_ordinal_accuracy": 0.6904700994491577,
|
| 1604 |
+
"eval_ordinal_mae": 0.37572237849235535,
|
| 1605 |
+
"eval_runtime": 193.8218,
|
| 1606 |
+
"eval_samples_per_second": 23.088,
|
| 1607 |
+
"eval_steps_per_second": 2.889,
|
| 1608 |
+
"step": 4100
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 1.49,
|
| 1612 |
+
"grad_norm": 1.809657096862793,
|
| 1613 |
+
"learning_rate": 5.0438754658011775e-05,
|
| 1614 |
+
"loss": 0.1275,
|
| 1615 |
+
"step": 4125
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 1.5,
|
| 1619 |
+
"grad_norm": 0.6124809384346008,
|
| 1620 |
+
"learning_rate": 5.0138237768962613e-05,
|
| 1621 |
+
"loss": 0.0975,
|
| 1622 |
+
"step": 4150
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 1.51,
|
| 1626 |
+
"grad_norm": 0.5735268592834473,
|
| 1627 |
+
"learning_rate": 4.983772087991345e-05,
|
| 1628 |
+
"loss": 0.1267,
|
| 1629 |
+
"step": 4175
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 1.51,
|
| 1633 |
+
"grad_norm": 0.2053624987602234,
|
| 1634 |
+
"learning_rate": 4.953720399086429e-05,
|
| 1635 |
+
"loss": 0.1262,
|
| 1636 |
+
"step": 4200
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 1.51,
|
| 1640 |
+
"eval_loss": 0.22913989424705505,
|
| 1641 |
+
"eval_na_accuracy": 0.8247422575950623,
|
| 1642 |
+
"eval_ordinal_accuracy": 0.683534562587738,
|
| 1643 |
+
"eval_ordinal_mae": 0.3841015100479126,
|
| 1644 |
+
"eval_runtime": 192.0713,
|
| 1645 |
+
"eval_samples_per_second": 23.299,
|
| 1646 |
+
"eval_steps_per_second": 2.916,
|
| 1647 |
+
"step": 4200
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.52,
|
| 1651 |
+
"grad_norm": 1.163071632385254,
|
| 1652 |
+
"learning_rate": 4.923668710181513e-05,
|
| 1653 |
+
"loss": 0.112,
|
| 1654 |
+
"step": 4225
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 1.53,
|
| 1658 |
+
"grad_norm": 0.48347094655036926,
|
| 1659 |
+
"learning_rate": 4.893617021276596e-05,
|
| 1660 |
+
"loss": 0.1312,
|
| 1661 |
+
"step": 4250
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.54,
|
| 1665 |
+
"grad_norm": 2.0154635906219482,
|
| 1666 |
+
"learning_rate": 4.863565332371679e-05,
|
| 1667 |
+
"loss": 0.1057,
|
| 1668 |
+
"step": 4275
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 1.55,
|
| 1672 |
+
"grad_norm": 2.7999942302703857,
|
| 1673 |
+
"learning_rate": 4.833513643466763e-05,
|
| 1674 |
+
"loss": 0.1437,
|
| 1675 |
+
"step": 4300
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 1.55,
|
| 1679 |
+
"eval_loss": 0.23114901781082153,
|
| 1680 |
+
"eval_na_accuracy": 0.800687313079834,
|
| 1681 |
+
"eval_ordinal_accuracy": 0.6922681927680969,
|
| 1682 |
+
"eval_ordinal_mae": 0.3750612139701843,
|
| 1683 |
+
"eval_runtime": 193.0261,
|
| 1684 |
+
"eval_samples_per_second": 23.183,
|
| 1685 |
+
"eval_steps_per_second": 2.901,
|
| 1686 |
+
"step": 4300
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 1.56,
|
| 1690 |
+
"grad_norm": 0.7880312204360962,
|
| 1691 |
+
"learning_rate": 4.803461954561846e-05,
|
| 1692 |
+
"loss": 0.1099,
|
| 1693 |
+
"step": 4325
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 1.57,
|
| 1697 |
+
"grad_norm": 0.5259920954704285,
|
| 1698 |
+
"learning_rate": 4.77341026565693e-05,
|
| 1699 |
+
"loss": 0.1355,
|
| 1700 |
+
"step": 4350
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 1.58,
|
| 1704 |
+
"grad_norm": 0.49388599395751953,
|
| 1705 |
+
"learning_rate": 4.743358576752014e-05,
|
| 1706 |
+
"loss": 0.1331,
|
| 1707 |
+
"step": 4375
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 1.59,
|
| 1711 |
+
"grad_norm": 0.7215922474861145,
|
| 1712 |
+
"learning_rate": 4.714508955403294e-05,
|
| 1713 |
+
"loss": 0.0916,
|
| 1714 |
+
"step": 4400
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 1.59,
|
| 1718 |
+
"eval_loss": 0.23432399332523346,
|
| 1719 |
+
"eval_na_accuracy": 0.8659793734550476,
|
| 1720 |
+
"eval_ordinal_accuracy": 0.6791677474975586,
|
| 1721 |
+
"eval_ordinal_mae": 0.37433725595474243,
|
| 1722 |
+
"eval_runtime": 191.7082,
|
| 1723 |
+
"eval_samples_per_second": 23.343,
|
| 1724 |
+
"eval_steps_per_second": 2.921,
|
| 1725 |
+
"step": 4400
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.6,
|
| 1729 |
+
"grad_norm": 0.4619504511356354,
|
| 1730 |
+
"learning_rate": 4.684457266498378e-05,
|
| 1731 |
+
"loss": 0.11,
|
| 1732 |
+
"step": 4425
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.6,
|
| 1736 |
+
"grad_norm": 2.470409393310547,
|
| 1737 |
+
"learning_rate": 4.654405577593461e-05,
|
| 1738 |
+
"loss": 0.138,
|
| 1739 |
+
"step": 4450
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.61,
|
| 1743 |
+
"grad_norm": 0.46536511182785034,
|
| 1744 |
+
"learning_rate": 4.6243538886885443e-05,
|
| 1745 |
+
"loss": 0.1233,
|
| 1746 |
+
"step": 4475
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.62,
|
| 1750 |
+
"grad_norm": 0.4539566934108734,
|
| 1751 |
+
"learning_rate": 4.594302199783628e-05,
|
| 1752 |
+
"loss": 0.1266,
|
| 1753 |
+
"step": 4500
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.62,
|
| 1757 |
+
"eval_loss": 0.22511447966098785,
|
| 1758 |
+
"eval_na_accuracy": 0.8505154848098755,
|
| 1759 |
+
"eval_ordinal_accuracy": 0.6861032843589783,
|
| 1760 |
+
"eval_ordinal_mae": 0.37239742279052734,
|
| 1761 |
+
"eval_runtime": 185.8881,
|
| 1762 |
+
"eval_samples_per_second": 24.074,
|
| 1763 |
+
"eval_steps_per_second": 3.013,
|
| 1764 |
+
"step": 4500
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 1.63,
|
| 1768 |
+
"grad_norm": 0.497732013463974,
|
| 1769 |
+
"learning_rate": 4.5642505108787114e-05,
|
| 1770 |
+
"loss": 0.109,
|
| 1771 |
+
"step": 4525
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 1.64,
|
| 1775 |
+
"grad_norm": 2.833667278289795,
|
| 1776 |
+
"learning_rate": 4.534198821973795e-05,
|
| 1777 |
+
"loss": 0.1342,
|
| 1778 |
+
"step": 4550
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 1.65,
|
| 1782 |
+
"grad_norm": 0.6105310320854187,
|
| 1783 |
+
"learning_rate": 4.504147133068879e-05,
|
| 1784 |
+
"loss": 0.125,
|
| 1785 |
+
"step": 4575
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 1.66,
|
| 1789 |
+
"grad_norm": 0.5035513639450073,
|
| 1790 |
+
"learning_rate": 4.474095444163962e-05,
|
| 1791 |
+
"loss": 0.1185,
|
| 1792 |
+
"step": 4600
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 1.66,
|
| 1796 |
+
"eval_loss": 0.22424614429473877,
|
| 1797 |
+
"eval_na_accuracy": 0.8264604806900024,
|
| 1798 |
+
"eval_ordinal_accuracy": 0.6902132034301758,
|
| 1799 |
+
"eval_ordinal_mae": 0.36660563945770264,
|
| 1800 |
+
"eval_runtime": 188.1827,
|
| 1801 |
+
"eval_samples_per_second": 23.78,
|
| 1802 |
+
"eval_steps_per_second": 2.976,
|
| 1803 |
+
"step": 4600
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 1.67,
|
| 1807 |
+
"grad_norm": 0.6165774464607239,
|
| 1808 |
+
"learning_rate": 4.444043755259046e-05,
|
| 1809 |
+
"loss": 0.1273,
|
| 1810 |
+
"step": 4625
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 1.68,
|
| 1814 |
+
"grad_norm": 2.2787024974823,
|
| 1815 |
+
"learning_rate": 4.413992066354129e-05,
|
| 1816 |
+
"loss": 0.1537,
|
| 1817 |
+
"step": 4650
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 1.69,
|
| 1821 |
+
"grad_norm": 1.2412303686141968,
|
| 1822 |
+
"learning_rate": 4.3839403774492125e-05,
|
| 1823 |
+
"loss": 0.1197,
|
| 1824 |
+
"step": 4675
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 1.69,
|
| 1828 |
+
"grad_norm": 2.671398162841797,
|
| 1829 |
+
"learning_rate": 4.353888688544296e-05,
|
| 1830 |
+
"loss": 0.1037,
|
| 1831 |
+
"step": 4700
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 1.69,
|
| 1835 |
+
"eval_loss": 0.22189220786094666,
|
| 1836 |
+
"eval_na_accuracy": 0.8522336483001709,
|
| 1837 |
+
"eval_ordinal_accuracy": 0.6845620274543762,
|
| 1838 |
+
"eval_ordinal_mae": 0.3699798583984375,
|
| 1839 |
+
"eval_runtime": 185.1462,
|
| 1840 |
+
"eval_samples_per_second": 24.17,
|
| 1841 |
+
"eval_steps_per_second": 3.025,
|
| 1842 |
+
"step": 4700
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 1.7,
|
| 1846 |
+
"grad_norm": 0.7951823472976685,
|
| 1847 |
+
"learning_rate": 4.32383699963938e-05,
|
| 1848 |
+
"loss": 0.1335,
|
| 1849 |
+
"step": 4725
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 1.71,
|
| 1853 |
+
"grad_norm": 0.5750038027763367,
|
| 1854 |
+
"learning_rate": 4.2937853107344634e-05,
|
| 1855 |
+
"loss": 0.1225,
|
| 1856 |
+
"step": 4750
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 1.72,
|
| 1860 |
+
"grad_norm": 0.599660336971283,
|
| 1861 |
+
"learning_rate": 4.263733621829547e-05,
|
| 1862 |
+
"loss": 0.1153,
|
| 1863 |
+
"step": 4775
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 1.73,
|
| 1867 |
+
"grad_norm": 0.5971084237098694,
|
| 1868 |
+
"learning_rate": 4.233681932924631e-05,
|
| 1869 |
+
"loss": 0.1264,
|
| 1870 |
+
"step": 4800
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 1.73,
|
| 1874 |
+
"eval_loss": 0.22111621499061584,
|
| 1875 |
+
"eval_na_accuracy": 0.8350515365600586,
|
| 1876 |
+
"eval_ordinal_accuracy": 0.6891857385635376,
|
| 1877 |
+
"eval_ordinal_mae": 0.36766940355300903,
|
| 1878 |
+
"eval_runtime": 187.791,
|
| 1879 |
+
"eval_samples_per_second": 23.83,
|
| 1880 |
+
"eval_steps_per_second": 2.982,
|
| 1881 |
+
"step": 4800
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 1.74,
|
| 1885 |
+
"grad_norm": 0.6335272789001465,
|
| 1886 |
+
"learning_rate": 4.203630244019714e-05,
|
| 1887 |
+
"loss": 0.1309,
|
| 1888 |
+
"step": 4825
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 1.75,
|
| 1892 |
+
"grad_norm": 1.4906469583511353,
|
| 1893 |
+
"learning_rate": 4.1735785551147974e-05,
|
| 1894 |
+
"loss": 0.1481,
|
| 1895 |
+
"step": 4850
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 1.76,
|
| 1899 |
+
"grad_norm": 0.5834776163101196,
|
| 1900 |
+
"learning_rate": 4.143526866209881e-05,
|
| 1901 |
+
"loss": 0.1082,
|
| 1902 |
+
"step": 4875
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 1.77,
|
| 1906 |
+
"grad_norm": 0.3094954788684845,
|
| 1907 |
+
"learning_rate": 4.1134751773049644e-05,
|
| 1908 |
+
"loss": 0.1404,
|
| 1909 |
+
"step": 4900
|
| 1910 |
+
},
|
| 1911 |
+
{
|
| 1912 |
+
"epoch": 1.77,
|
| 1913 |
+
"eval_loss": 0.22064529359340668,
|
| 1914 |
+
"eval_na_accuracy": 0.7938144207000732,
|
| 1915 |
+
"eval_ordinal_accuracy": 0.6945800185203552,
|
| 1916 |
+
"eval_ordinal_mae": 0.371782511472702,
|
| 1917 |
+
"eval_runtime": 187.3419,
|
| 1918 |
+
"eval_samples_per_second": 23.887,
|
| 1919 |
+
"eval_steps_per_second": 2.989,
|
| 1920 |
+
"step": 4900
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 1.78,
|
| 1924 |
+
"grad_norm": 0.43263766169548035,
|
| 1925 |
+
"learning_rate": 4.083423488400048e-05,
|
| 1926 |
+
"loss": 0.0901,
|
| 1927 |
+
"step": 4925
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 1.79,
|
| 1931 |
+
"grad_norm": 1.0660347938537598,
|
| 1932 |
+
"learning_rate": 4.053371799495132e-05,
|
| 1933 |
+
"loss": 0.1197,
|
| 1934 |
+
"step": 4950
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 1.79,
|
| 1938 |
+
"grad_norm": 0.7330833077430725,
|
| 1939 |
+
"learning_rate": 4.023320110590215e-05,
|
| 1940 |
+
"loss": 0.1052,
|
| 1941 |
+
"step": 4975
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 1.8,
|
| 1945 |
+
"grad_norm": 2.152076005935669,
|
| 1946 |
+
"learning_rate": 3.993268421685299e-05,
|
| 1947 |
+
"loss": 0.1238,
|
| 1948 |
+
"step": 5000
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 1.8,
|
| 1952 |
+
"eval_loss": 0.20976723730564117,
|
| 1953 |
+
"eval_na_accuracy": 0.8264604806900024,
|
| 1954 |
+
"eval_ordinal_accuracy": 0.6948369145393372,
|
| 1955 |
+
"eval_ordinal_mae": 0.37225744128227234,
|
| 1956 |
+
"eval_runtime": 186.1293,
|
| 1957 |
+
"eval_samples_per_second": 24.042,
|
| 1958 |
+
"eval_steps_per_second": 3.009,
|
| 1959 |
+
"step": 5000
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 1.81,
|
| 1963 |
+
"grad_norm": 0.28938254714012146,
|
| 1964 |
+
"learning_rate": 3.9632167327803824e-05,
|
| 1965 |
+
"loss": 0.1089,
|
| 1966 |
+
"step": 5025
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 1.82,
|
| 1970 |
+
"grad_norm": 0.5542977452278137,
|
| 1971 |
+
"learning_rate": 3.9331650438754655e-05,
|
| 1972 |
+
"loss": 0.1034,
|
| 1973 |
+
"step": 5050
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 1.83,
|
| 1977 |
+
"grad_norm": 3.0670604705810547,
|
| 1978 |
+
"learning_rate": 3.9031133549705494e-05,
|
| 1979 |
+
"loss": 0.1207,
|
| 1980 |
+
"step": 5075
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 1.84,
|
| 1984 |
+
"grad_norm": 1.1476399898529053,
|
| 1985 |
+
"learning_rate": 3.873061666065633e-05,
|
| 1986 |
+
"loss": 0.0868,
|
| 1987 |
+
"step": 5100
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 1.84,
|
| 1991 |
+
"eval_loss": 0.2088630199432373,
|
| 1992 |
+
"eval_na_accuracy": 0.8144329786300659,
|
| 1993 |
+
"eval_ordinal_accuracy": 0.7025430202484131,
|
| 1994 |
+
"eval_ordinal_mae": 0.3573513329029083,
|
| 1995 |
+
"eval_runtime": 186.6283,
|
| 1996 |
+
"eval_samples_per_second": 23.978,
|
| 1997 |
+
"eval_steps_per_second": 3.001,
|
| 1998 |
+
"step": 5100
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 1.85,
|
| 2002 |
+
"grad_norm": 1.155088186264038,
|
| 2003 |
+
"learning_rate": 3.8430099771607164e-05,
|
| 2004 |
+
"loss": 0.1285,
|
| 2005 |
+
"step": 5125
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 1.86,
|
| 2009 |
+
"grad_norm": 5.079723358154297,
|
| 2010 |
+
"learning_rate": 3.8129582882558e-05,
|
| 2011 |
+
"loss": 0.1503,
|
| 2012 |
+
"step": 5150
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 1.87,
|
| 2016 |
+
"grad_norm": 1.3054969310760498,
|
| 2017 |
+
"learning_rate": 3.782906599350884e-05,
|
| 2018 |
+
"loss": 0.1117,
|
| 2019 |
+
"step": 5175
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 1.88,
|
| 2023 |
+
"grad_norm": 0.676068902015686,
|
| 2024 |
+
"learning_rate": 3.752854910445967e-05,
|
| 2025 |
+
"loss": 0.0828,
|
| 2026 |
+
"step": 5200
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 1.88,
|
| 2030 |
+
"eval_loss": 0.2203822135925293,
|
| 2031 |
+
"eval_na_accuracy": 0.7817869186401367,
|
| 2032 |
+
"eval_ordinal_accuracy": 0.7030567526817322,
|
| 2033 |
+
"eval_ordinal_mae": 0.3679908215999603,
|
| 2034 |
+
"eval_runtime": 186.9501,
|
| 2035 |
+
"eval_samples_per_second": 23.937,
|
| 2036 |
+
"eval_steps_per_second": 2.995,
|
| 2037 |
+
"step": 5200
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 1.88,
|
| 2041 |
+
"grad_norm": 0.5627509355545044,
|
| 2042 |
+
"learning_rate": 3.7228032215410505e-05,
|
| 2043 |
+
"loss": 0.1013,
|
| 2044 |
+
"step": 5225
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 1.89,
|
| 2048 |
+
"grad_norm": 0.74530029296875,
|
| 2049 |
+
"learning_rate": 3.6927515326361343e-05,
|
| 2050 |
+
"loss": 0.1163,
|
| 2051 |
+
"step": 5250
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 1.9,
|
| 2055 |
+
"grad_norm": 0.4432946741580963,
|
| 2056 |
+
"learning_rate": 3.6626998437312175e-05,
|
| 2057 |
+
"loss": 0.1076,
|
| 2058 |
+
"step": 5275
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 1.91,
|
| 2062 |
+
"grad_norm": 0.8598417639732361,
|
| 2063 |
+
"learning_rate": 3.6326481548263014e-05,
|
| 2064 |
+
"loss": 0.0986,
|
| 2065 |
+
"step": 5300
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 1.91,
|
| 2069 |
+
"eval_loss": 0.21255970001220703,
|
| 2070 |
+
"eval_na_accuracy": 0.8127147555351257,
|
| 2071 |
+
"eval_ordinal_accuracy": 0.6981762051582336,
|
| 2072 |
+
"eval_ordinal_mae": 0.35426145792007446,
|
| 2073 |
+
"eval_runtime": 188.2634,
|
| 2074 |
+
"eval_samples_per_second": 23.77,
|
| 2075 |
+
"eval_steps_per_second": 2.975,
|
| 2076 |
+
"step": 5300
|
| 2077 |
+
},
|
| 2078 |
+
{
|
| 2079 |
+
"epoch": 1.92,
|
| 2080 |
+
"grad_norm": 0.5436437726020813,
|
| 2081 |
+
"learning_rate": 3.602596465921385e-05,
|
| 2082 |
+
"loss": 0.1368,
|
| 2083 |
+
"step": 5325
|
| 2084 |
+
},
|
| 2085 |
+
{
|
| 2086 |
+
"epoch": 1.93,
|
| 2087 |
+
"grad_norm": 0.3918437063694,
|
| 2088 |
+
"learning_rate": 3.5725447770164684e-05,
|
| 2089 |
+
"loss": 0.1062,
|
| 2090 |
+
"step": 5350
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 1.94,
|
| 2094 |
+
"grad_norm": 3.4165215492248535,
|
| 2095 |
+
"learning_rate": 3.542493088111552e-05,
|
| 2096 |
+
"loss": 0.1394,
|
| 2097 |
+
"step": 5375
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 1.95,
|
| 2101 |
+
"grad_norm": 0.5507489442825317,
|
| 2102 |
+
"learning_rate": 3.5124413992066354e-05,
|
| 2103 |
+
"loss": 0.0869,
|
| 2104 |
+
"step": 5400
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"epoch": 1.95,
|
| 2108 |
+
"eval_loss": 0.2247212827205658,
|
| 2109 |
+
"eval_na_accuracy": 0.80756014585495,
|
| 2110 |
+
"eval_ordinal_accuracy": 0.7107629179954529,
|
| 2111 |
+
"eval_ordinal_mae": 0.35320159792900085,
|
| 2112 |
+
"eval_runtime": 186.4594,
|
| 2113 |
+
"eval_samples_per_second": 24.0,
|
| 2114 |
+
"eval_steps_per_second": 3.003,
|
| 2115 |
+
"step": 5400
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 1.96,
|
| 2119 |
+
"grad_norm": 0.36401164531707764,
|
| 2120 |
+
"learning_rate": 3.4823897103017186e-05,
|
| 2121 |
+
"loss": 0.1216,
|
| 2122 |
+
"step": 5425
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 1.97,
|
| 2126 |
+
"grad_norm": 0.5114885568618774,
|
| 2127 |
+
"learning_rate": 3.4523380213968025e-05,
|
| 2128 |
+
"loss": 0.1034,
|
| 2129 |
+
"step": 5450
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 1.97,
|
| 2133 |
+
"grad_norm": 0.5193465352058411,
|
| 2134 |
+
"learning_rate": 3.422286332491886e-05,
|
| 2135 |
+
"loss": 0.095,
|
| 2136 |
+
"step": 5475
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 1.98,
|
| 2140 |
+
"grad_norm": 0.3319372236728668,
|
| 2141 |
+
"learning_rate": 3.3922346435869695e-05,
|
| 2142 |
+
"loss": 0.1006,
|
| 2143 |
+
"step": 5500
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 1.98,
|
| 2147 |
+
"eval_loss": 0.22681304812431335,
|
| 2148 |
+
"eval_na_accuracy": 0.8161512017250061,
|
| 2149 |
+
"eval_ordinal_accuracy": 0.702799916267395,
|
| 2150 |
+
"eval_ordinal_mae": 0.3637341260910034,
|
| 2151 |
+
"eval_runtime": 187.993,
|
| 2152 |
+
"eval_samples_per_second": 23.804,
|
| 2153 |
+
"eval_steps_per_second": 2.979,
|
| 2154 |
+
"step": 5500
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 1.99,
|
| 2158 |
+
"grad_norm": 0.6313589215278625,
|
| 2159 |
+
"learning_rate": 3.3621829546820533e-05,
|
| 2160 |
+
"loss": 0.1265,
|
| 2161 |
+
"step": 5525
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 2.0,
|
| 2165 |
+
"grad_norm": 0.3126126825809479,
|
| 2166 |
+
"learning_rate": 3.332131265777137e-05,
|
| 2167 |
+
"loss": 0.1002,
|
| 2168 |
+
"step": 5550
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 2.01,
|
| 2172 |
+
"grad_norm": 0.7703510522842407,
|
| 2173 |
+
"learning_rate": 3.3020795768722204e-05,
|
| 2174 |
+
"loss": 0.065,
|
| 2175 |
+
"step": 5575
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 2.02,
|
| 2179 |
+
"grad_norm": 0.5371888875961304,
|
| 2180 |
+
"learning_rate": 3.2720278879673036e-05,
|
| 2181 |
+
"loss": 0.0639,
|
| 2182 |
+
"step": 5600
|
| 2183 |
+
},
|
| 2184 |
+
{
|
| 2185 |
+
"epoch": 2.02,
|
| 2186 |
+
"eval_loss": 0.22521378099918365,
|
| 2187 |
+
"eval_na_accuracy": 0.8109965920448303,
|
| 2188 |
+
"eval_ordinal_accuracy": 0.7069098353385925,
|
| 2189 |
+
"eval_ordinal_mae": 0.3478536903858185,
|
| 2190 |
+
"eval_runtime": 186.1883,
|
| 2191 |
+
"eval_samples_per_second": 24.035,
|
| 2192 |
+
"eval_steps_per_second": 3.008,
|
| 2193 |
+
"step": 5600
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 2.03,
|
| 2197 |
+
"grad_norm": 0.3779759109020233,
|
| 2198 |
+
"learning_rate": 3.2419761990623874e-05,
|
| 2199 |
+
"loss": 0.0491,
|
| 2200 |
+
"step": 5625
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 2.04,
|
| 2204 |
+
"grad_norm": 0.3881787657737732,
|
| 2205 |
+
"learning_rate": 3.2119245101574706e-05,
|
| 2206 |
+
"loss": 0.0475,
|
| 2207 |
+
"step": 5650
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 2.05,
|
| 2211 |
+
"grad_norm": 0.2288794368505478,
|
| 2212 |
+
"learning_rate": 3.1818728212525544e-05,
|
| 2213 |
+
"loss": 0.062,
|
| 2214 |
+
"step": 5675
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 2.06,
|
| 2218 |
+
"grad_norm": 0.4537404477596283,
|
| 2219 |
+
"learning_rate": 3.151821132347638e-05,
|
| 2220 |
+
"loss": 0.0569,
|
| 2221 |
+
"step": 5700
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 2.06,
|
| 2225 |
+
"eval_loss": 0.23154324293136597,
|
| 2226 |
+
"eval_na_accuracy": 0.80756014585495,
|
| 2227 |
+
"eval_ordinal_accuracy": 0.7166709303855896,
|
| 2228 |
+
"eval_ordinal_mae": 0.3399028480052948,
|
| 2229 |
+
"eval_runtime": 188.0319,
|
| 2230 |
+
"eval_samples_per_second": 23.799,
|
| 2231 |
+
"eval_steps_per_second": 2.978,
|
| 2232 |
+
"step": 5700
|
| 2233 |
+
},
|
| 2234 |
+
{
|
| 2235 |
+
"epoch": 2.06,
|
| 2236 |
+
"grad_norm": 0.4112221300601959,
|
| 2237 |
+
"learning_rate": 3.1217694434427215e-05,
|
| 2238 |
+
"loss": 0.0513,
|
| 2239 |
+
"step": 5725
|
| 2240 |
+
},
|
| 2241 |
+
{
|
| 2242 |
+
"epoch": 2.07,
|
| 2243 |
+
"grad_norm": 0.4015844166278839,
|
| 2244 |
+
"learning_rate": 3.091717754537805e-05,
|
| 2245 |
+
"loss": 0.0608,
|
| 2246 |
+
"step": 5750
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 2.08,
|
| 2250 |
+
"grad_norm": 0.43563222885131836,
|
| 2251 |
+
"learning_rate": 3.0616660656328885e-05,
|
| 2252 |
+
"loss": 0.0463,
|
| 2253 |
+
"step": 5775
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"epoch": 2.09,
|
| 2257 |
+
"grad_norm": 2.328296422958374,
|
| 2258 |
+
"learning_rate": 3.031614376727972e-05,
|
| 2259 |
+
"loss": 0.0626,
|
| 2260 |
+
"step": 5800
|
| 2261 |
+
},
|
| 2262 |
+
{
|
| 2263 |
+
"epoch": 2.09,
|
| 2264 |
+
"eval_loss": 0.2304299920797348,
|
| 2265 |
+
"eval_na_accuracy": 0.8127147555351257,
|
| 2266 |
+
"eval_ordinal_accuracy": 0.702799916267395,
|
| 2267 |
+
"eval_ordinal_mae": 0.34806403517723083,
|
| 2268 |
+
"eval_runtime": 186.3734,
|
| 2269 |
+
"eval_samples_per_second": 24.011,
|
| 2270 |
+
"eval_steps_per_second": 3.005,
|
| 2271 |
+
"step": 5800
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 2.1,
|
| 2275 |
+
"grad_norm": 0.5192309021949768,
|
| 2276 |
+
"learning_rate": 3.001562687823056e-05,
|
| 2277 |
+
"loss": 0.0506,
|
| 2278 |
+
"step": 5825
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 2.11,
|
| 2282 |
+
"grad_norm": 0.7943512201309204,
|
| 2283 |
+
"learning_rate": 2.9715109989181394e-05,
|
| 2284 |
+
"loss": 0.0612,
|
| 2285 |
+
"step": 5850
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 2.12,
|
| 2289 |
+
"grad_norm": 0.5543213486671448,
|
| 2290 |
+
"learning_rate": 2.9414593100132226e-05,
|
| 2291 |
+
"loss": 0.0571,
|
| 2292 |
+
"step": 5875
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 2.13,
|
| 2296 |
+
"grad_norm": 0.32637158036231995,
|
| 2297 |
+
"learning_rate": 2.9114076211083064e-05,
|
| 2298 |
+
"loss": 0.0502,
|
| 2299 |
+
"step": 5900
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 2.13,
|
| 2303 |
+
"eval_loss": 0.23814311623573303,
|
| 2304 |
+
"eval_na_accuracy": 0.8092783689498901,
|
| 2305 |
+
"eval_ordinal_accuracy": 0.6953506469726562,
|
| 2306 |
+
"eval_ordinal_mae": 0.3623509407043457,
|
| 2307 |
+
"eval_runtime": 185.1929,
|
| 2308 |
+
"eval_samples_per_second": 24.164,
|
| 2309 |
+
"eval_steps_per_second": 3.024,
|
| 2310 |
+
"step": 5900
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 2.14,
|
| 2314 |
+
"grad_norm": 0.4265578091144562,
|
| 2315 |
+
"learning_rate": 2.88135593220339e-05,
|
| 2316 |
+
"loss": 0.0529,
|
| 2317 |
+
"step": 5925
|
| 2318 |
+
},
|
| 2319 |
+
{
|
| 2320 |
+
"epoch": 2.15,
|
| 2321 |
+
"grad_norm": 0.5854742527008057,
|
| 2322 |
+
"learning_rate": 2.8513042432984738e-05,
|
| 2323 |
+
"loss": 0.0458,
|
| 2324 |
+
"step": 5950
|
| 2325 |
+
},
|
| 2326 |
+
{
|
| 2327 |
+
"epoch": 2.15,
|
| 2328 |
+
"grad_norm": 0.6325811147689819,
|
| 2329 |
+
"learning_rate": 2.821252554393557e-05,
|
| 2330 |
+
"loss": 0.0422,
|
| 2331 |
+
"step": 5975
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 2.16,
|
| 2335 |
+
"grad_norm": 0.3043919503688812,
|
| 2336 |
+
"learning_rate": 2.7912008654886408e-05,
|
| 2337 |
+
"loss": 0.0541,
|
| 2338 |
+
"step": 6000
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 2.16,
|
| 2342 |
+
"eval_loss": 0.2298140674829483,
|
| 2343 |
+
"eval_na_accuracy": 0.8109965920448303,
|
| 2344 |
+
"eval_ordinal_accuracy": 0.7159003615379333,
|
| 2345 |
+
"eval_ordinal_mae": 0.34048062562942505,
|
| 2346 |
+
"eval_runtime": 188.0938,
|
| 2347 |
+
"eval_samples_per_second": 23.791,
|
| 2348 |
+
"eval_steps_per_second": 2.977,
|
| 2349 |
+
"step": 6000
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 2.17,
|
| 2353 |
+
"grad_norm": 0.5921896696090698,
|
| 2354 |
+
"learning_rate": 2.7611491765837243e-05,
|
| 2355 |
+
"loss": 0.0441,
|
| 2356 |
+
"step": 6025
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 2.18,
|
| 2360 |
+
"grad_norm": 0.5739880204200745,
|
| 2361 |
+
"learning_rate": 2.7310974876788075e-05,
|
| 2362 |
+
"loss": 0.0399,
|
| 2363 |
+
"step": 6050
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 2.19,
|
| 2367 |
+
"grad_norm": 0.6747081279754639,
|
| 2368 |
+
"learning_rate": 2.7010457987738914e-05,
|
| 2369 |
+
"loss": 0.0467,
|
| 2370 |
+
"step": 6075
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 2.2,
|
| 2374 |
+
"grad_norm": 0.5710461139678955,
|
| 2375 |
+
"learning_rate": 2.670994109868975e-05,
|
| 2376 |
+
"loss": 0.0671,
|
| 2377 |
+
"step": 6100
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 2.2,
|
| 2381 |
+
"eval_loss": 0.24321676790714264,
|
| 2382 |
+
"eval_na_accuracy": 0.7989690899848938,
|
| 2383 |
+
"eval_ordinal_accuracy": 0.7030567526817322,
|
| 2384 |
+
"eval_ordinal_mae": 0.3529086709022522,
|
| 2385 |
+
"eval_runtime": 188.2916,
|
| 2386 |
+
"eval_samples_per_second": 23.766,
|
| 2387 |
+
"eval_steps_per_second": 2.974,
|
| 2388 |
+
"step": 6100
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 2.21,
|
| 2392 |
+
"grad_norm": 0.3675624430179596,
|
| 2393 |
+
"learning_rate": 2.640942420964058e-05,
|
| 2394 |
+
"loss": 0.0466,
|
| 2395 |
+
"step": 6125
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 2.22,
|
| 2399 |
+
"grad_norm": 0.31548529863357544,
|
| 2400 |
+
"learning_rate": 2.610890732059142e-05,
|
| 2401 |
+
"loss": 0.0764,
|
| 2402 |
+
"step": 6150
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 2.23,
|
| 2406 |
+
"grad_norm": 0.43977534770965576,
|
| 2407 |
+
"learning_rate": 2.5808390431542258e-05,
|
| 2408 |
+
"loss": 0.0475,
|
| 2409 |
+
"step": 6175
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 2.24,
|
| 2413 |
+
"grad_norm": 0.6533438563346863,
|
| 2414 |
+
"learning_rate": 2.550787354249309e-05,
|
| 2415 |
+
"loss": 0.0672,
|
| 2416 |
+
"step": 6200
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 2.24,
|
| 2420 |
+
"eval_loss": 0.2430579513311386,
|
| 2421 |
+
"eval_na_accuracy": 0.7714776396751404,
|
| 2422 |
+
"eval_ordinal_accuracy": 0.7194965481758118,
|
| 2423 |
+
"eval_ordinal_mae": 0.3360508680343628,
|
| 2424 |
+
"eval_runtime": 186.7478,
|
| 2425 |
+
"eval_samples_per_second": 23.963,
|
| 2426 |
+
"eval_steps_per_second": 2.999,
|
| 2427 |
+
"step": 6200
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 2.24,
|
| 2431 |
+
"grad_norm": 0.2441914677619934,
|
| 2432 |
+
"learning_rate": 2.5207356653443925e-05,
|
| 2433 |
+
"loss": 0.0503,
|
| 2434 |
+
"step": 6225
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"epoch": 2.25,
|
| 2438 |
+
"grad_norm": 0.3184777796268463,
|
| 2439 |
+
"learning_rate": 2.490683976439476e-05,
|
| 2440 |
+
"loss": 0.0641,
|
| 2441 |
+
"step": 6250
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 2.26,
|
| 2445 |
+
"grad_norm": 0.5295473337173462,
|
| 2446 |
+
"learning_rate": 2.4606322875345595e-05,
|
| 2447 |
+
"loss": 0.0453,
|
| 2448 |
+
"step": 6275
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 2.27,
|
| 2452 |
+
"grad_norm": 0.6061444282531738,
|
| 2453 |
+
"learning_rate": 2.430580598629643e-05,
|
| 2454 |
+
"loss": 0.0446,
|
| 2455 |
+
"step": 6300
|
| 2456 |
+
},
|
| 2457 |
+
{
|
| 2458 |
+
"epoch": 2.27,
|
| 2459 |
+
"eval_loss": 0.24466152489185333,
|
| 2460 |
+
"eval_na_accuracy": 0.7938144207000732,
|
| 2461 |
+
"eval_ordinal_accuracy": 0.7141022086143494,
|
| 2462 |
+
"eval_ordinal_mae": 0.34008586406707764,
|
| 2463 |
+
"eval_runtime": 184.0098,
|
| 2464 |
+
"eval_samples_per_second": 24.319,
|
| 2465 |
+
"eval_steps_per_second": 3.043,
|
| 2466 |
+
"step": 6300
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 2.28,
|
| 2470 |
+
"grad_norm": 0.7771974802017212,
|
| 2471 |
+
"learning_rate": 2.4005289097247265e-05,
|
| 2472 |
+
"loss": 0.0506,
|
| 2473 |
+
"step": 6325
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 2.29,
|
| 2477 |
+
"grad_norm": 0.48779726028442383,
|
| 2478 |
+
"learning_rate": 2.37047722081981e-05,
|
| 2479 |
+
"loss": 0.0625,
|
| 2480 |
+
"step": 6350
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 2.3,
|
| 2484 |
+
"grad_norm": 0.5689972639083862,
|
| 2485 |
+
"learning_rate": 2.340425531914894e-05,
|
| 2486 |
+
"loss": 0.0504,
|
| 2487 |
+
"step": 6375
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 2.31,
|
| 2491 |
+
"grad_norm": 0.35768938064575195,
|
| 2492 |
+
"learning_rate": 2.310373843009977e-05,
|
| 2493 |
+
"loss": 0.0424,
|
| 2494 |
+
"step": 6400
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 2.31,
|
| 2498 |
+
"eval_loss": 0.24263423681259155,
|
| 2499 |
+
"eval_na_accuracy": 0.8161512017250061,
|
| 2500 |
+
"eval_ordinal_accuracy": 0.7017723917961121,
|
| 2501 |
+
"eval_ordinal_mae": 0.34848281741142273,
|
| 2502 |
+
"eval_runtime": 184.8006,
|
| 2503 |
+
"eval_samples_per_second": 24.215,
|
| 2504 |
+
"eval_steps_per_second": 3.03,
|
| 2505 |
+
"step": 6400
|
| 2506 |
+
},
|
| 2507 |
+
{
|
| 2508 |
+
"epoch": 2.32,
|
| 2509 |
+
"grad_norm": 0.28792133927345276,
|
| 2510 |
+
"learning_rate": 2.280322154105061e-05,
|
| 2511 |
+
"loss": 0.0444,
|
| 2512 |
+
"step": 6425
|
| 2513 |
+
},
|
| 2514 |
+
{
|
| 2515 |
+
"epoch": 2.33,
|
| 2516 |
+
"grad_norm": 0.5131263136863708,
|
| 2517 |
+
"learning_rate": 2.2502704652001444e-05,
|
| 2518 |
+
"loss": 0.0494,
|
| 2519 |
+
"step": 6450
|
| 2520 |
+
},
|
| 2521 |
+
{
|
| 2522 |
+
"epoch": 2.34,
|
| 2523 |
+
"grad_norm": 0.4703335464000702,
|
| 2524 |
+
"learning_rate": 2.220218776295228e-05,
|
| 2525 |
+
"loss": 0.0568,
|
| 2526 |
+
"step": 6475
|
| 2527 |
+
},
|
| 2528 |
+
{
|
| 2529 |
+
"epoch": 2.34,
|
| 2530 |
+
"grad_norm": 0.48926159739494324,
|
| 2531 |
+
"learning_rate": 2.1901670873903115e-05,
|
| 2532 |
+
"loss": 0.0386,
|
| 2533 |
+
"step": 6500
|
| 2534 |
+
},
|
| 2535 |
+
{
|
| 2536 |
+
"epoch": 2.34,
|
| 2537 |
+
"eval_loss": 0.24884438514709473,
|
| 2538 |
+
"eval_na_accuracy": 0.8127147555351257,
|
| 2539 |
+
"eval_ordinal_accuracy": 0.7123041152954102,
|
| 2540 |
+
"eval_ordinal_mae": 0.33866390585899353,
|
| 2541 |
+
"eval_runtime": 182.7756,
|
| 2542 |
+
"eval_samples_per_second": 24.484,
|
| 2543 |
+
"eval_steps_per_second": 3.064,
|
| 2544 |
+
"step": 6500
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 2.35,
|
| 2548 |
+
"grad_norm": 0.7936327457427979,
|
| 2549 |
+
"learning_rate": 2.160115398485395e-05,
|
| 2550 |
+
"loss": 0.0553,
|
| 2551 |
+
"step": 6525
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 2.36,
|
| 2555 |
+
"grad_norm": 0.41186073422431946,
|
| 2556 |
+
"learning_rate": 2.1300637095804785e-05,
|
| 2557 |
+
"loss": 0.0441,
|
| 2558 |
+
"step": 6550
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 2.37,
|
| 2562 |
+
"grad_norm": 0.7716944813728333,
|
| 2563 |
+
"learning_rate": 2.1000120206755623e-05,
|
| 2564 |
+
"loss": 0.0562,
|
| 2565 |
+
"step": 6575
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 2.38,
|
| 2569 |
+
"grad_norm": 0.40576568245887756,
|
| 2570 |
+
"learning_rate": 2.0699603317706455e-05,
|
| 2571 |
+
"loss": 0.0736,
|
| 2572 |
+
"step": 6600
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 2.38,
|
| 2576 |
+
"eval_loss": 0.24542821943759918,
|
| 2577 |
+
"eval_na_accuracy": 0.831615149974823,
|
| 2578 |
+
"eval_ordinal_accuracy": 0.7053686380386353,
|
| 2579 |
+
"eval_ordinal_mae": 0.3381500244140625,
|
| 2580 |
+
"eval_runtime": 188.0054,
|
| 2581 |
+
"eval_samples_per_second": 23.803,
|
| 2582 |
+
"eval_steps_per_second": 2.979,
|
| 2583 |
+
"step": 6600
|
| 2584 |
+
},
|
| 2585 |
+
{
|
| 2586 |
+
"epoch": 2.39,
|
| 2587 |
+
"grad_norm": 2.147202968597412,
|
| 2588 |
+
"learning_rate": 2.039908642865729e-05,
|
| 2589 |
+
"loss": 0.0552,
|
| 2590 |
+
"step": 6625
|
| 2591 |
+
},
|
| 2592 |
+
{
|
| 2593 |
+
"epoch": 2.4,
|
| 2594 |
+
"grad_norm": 1.0888266563415527,
|
| 2595 |
+
"learning_rate": 2.009856953960813e-05,
|
| 2596 |
+
"loss": 0.0598,
|
| 2597 |
+
"step": 6650
|
| 2598 |
+
},
|
| 2599 |
+
{
|
| 2600 |
+
"epoch": 2.41,
|
| 2601 |
+
"grad_norm": 0.6044988036155701,
|
| 2602 |
+
"learning_rate": 1.9798052650558964e-05,
|
| 2603 |
+
"loss": 0.039,
|
| 2604 |
+
"step": 6675
|
| 2605 |
+
},
|
| 2606 |
+
{
|
| 2607 |
+
"epoch": 2.42,
|
| 2608 |
+
"grad_norm": 0.5873610973358154,
|
| 2609 |
+
"learning_rate": 1.9497535761509796e-05,
|
| 2610 |
+
"loss": 0.0421,
|
| 2611 |
+
"step": 6700
|
| 2612 |
+
},
|
| 2613 |
+
{
|
| 2614 |
+
"epoch": 2.42,
|
| 2615 |
+
"eval_loss": 0.25130367279052734,
|
| 2616 |
+
"eval_na_accuracy": 0.831615149974823,
|
| 2617 |
+
"eval_ordinal_accuracy": 0.712047278881073,
|
| 2618 |
+
"eval_ordinal_mae": 0.3393591046333313,
|
| 2619 |
+
"eval_runtime": 185.2317,
|
| 2620 |
+
"eval_samples_per_second": 24.159,
|
| 2621 |
+
"eval_steps_per_second": 3.023,
|
| 2622 |
+
"step": 6700
|
| 2623 |
+
},
|
| 2624 |
+
{
|
| 2625 |
+
"epoch": 2.43,
|
| 2626 |
+
"grad_norm": 0.5890676975250244,
|
| 2627 |
+
"learning_rate": 1.9197018872460634e-05,
|
| 2628 |
+
"loss": 0.0717,
|
| 2629 |
+
"step": 6725
|
| 2630 |
+
},
|
| 2631 |
+
{
|
| 2632 |
+
"epoch": 2.43,
|
| 2633 |
+
"grad_norm": 0.3779636025428772,
|
| 2634 |
+
"learning_rate": 1.889650198341147e-05,
|
| 2635 |
+
"loss": 0.0559,
|
| 2636 |
+
"step": 6750
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 2.44,
|
| 2640 |
+
"grad_norm": 0.38733378052711487,
|
| 2641 |
+
"learning_rate": 1.8595985094362305e-05,
|
| 2642 |
+
"loss": 0.0458,
|
| 2643 |
+
"step": 6775
|
| 2644 |
+
},
|
| 2645 |
+
{
|
| 2646 |
+
"epoch": 2.45,
|
| 2647 |
+
"grad_norm": 0.6435078978538513,
|
| 2648 |
+
"learning_rate": 1.829546820531314e-05,
|
| 2649 |
+
"loss": 0.0607,
|
| 2650 |
+
"step": 6800
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"epoch": 2.45,
|
| 2654 |
+
"eval_loss": 0.2546432614326477,
|
| 2655 |
+
"eval_na_accuracy": 0.8264604806900024,
|
| 2656 |
+
"eval_ordinal_accuracy": 0.7092216610908508,
|
| 2657 |
+
"eval_ordinal_mae": 0.33696386218070984,
|
| 2658 |
+
"eval_runtime": 185.2223,
|
| 2659 |
+
"eval_samples_per_second": 24.16,
|
| 2660 |
+
"eval_steps_per_second": 3.023,
|
| 2661 |
+
"step": 6800
|
| 2662 |
+
},
|
| 2663 |
+
{
|
| 2664 |
+
"epoch": 2.46,
|
| 2665 |
+
"grad_norm": 0.34649285674095154,
|
| 2666 |
+
"learning_rate": 1.7994951316263975e-05,
|
| 2667 |
+
"loss": 0.0459,
|
| 2668 |
+
"step": 6825
|
| 2669 |
+
},
|
| 2670 |
+
{
|
| 2671 |
+
"epoch": 2.47,
|
| 2672 |
+
"grad_norm": 0.7860547304153442,
|
| 2673 |
+
"learning_rate": 1.769443442721481e-05,
|
| 2674 |
+
"loss": 0.0483,
|
| 2675 |
+
"step": 6850
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 2.48,
|
| 2679 |
+
"grad_norm": 0.4681091904640198,
|
| 2680 |
+
"learning_rate": 1.7393917538165645e-05,
|
| 2681 |
+
"loss": 0.0481,
|
| 2682 |
+
"step": 6875
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 2.49,
|
| 2686 |
+
"grad_norm": 1.788452386856079,
|
| 2687 |
+
"learning_rate": 1.709340064911648e-05,
|
| 2688 |
+
"loss": 0.0517,
|
| 2689 |
+
"step": 6900
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 2.49,
|
| 2693 |
+
"eval_loss": 0.25944724678993225,
|
| 2694 |
+
"eval_na_accuracy": 0.8298969268798828,
|
| 2695 |
+
"eval_ordinal_accuracy": 0.7081941962242126,
|
| 2696 |
+
"eval_ordinal_mae": 0.3375920057296753,
|
| 2697 |
+
"eval_runtime": 187.8946,
|
| 2698 |
+
"eval_samples_per_second": 23.817,
|
| 2699 |
+
"eval_steps_per_second": 2.98,
|
| 2700 |
+
"step": 6900
|
| 2701 |
+
},
|
| 2702 |
+
{
|
| 2703 |
+
"epoch": 2.5,
|
| 2704 |
+
"grad_norm": 0.35276201367378235,
|
| 2705 |
+
"learning_rate": 1.6792883760067316e-05,
|
| 2706 |
+
"loss": 0.0602,
|
| 2707 |
+
"step": 6925
|
| 2708 |
+
},
|
| 2709 |
+
{
|
| 2710 |
+
"epoch": 2.51,
|
| 2711 |
+
"grad_norm": 0.607291042804718,
|
| 2712 |
+
"learning_rate": 1.6492366871018154e-05,
|
| 2713 |
+
"loss": 0.0426,
|
| 2714 |
+
"step": 6950
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 2.52,
|
| 2718 |
+
"grad_norm": 0.29660192131996155,
|
| 2719 |
+
"learning_rate": 1.6191849981968986e-05,
|
| 2720 |
+
"loss": 0.0499,
|
| 2721 |
+
"step": 6975
|
| 2722 |
+
},
|
| 2723 |
+
{
|
| 2724 |
+
"epoch": 2.52,
|
| 2725 |
+
"grad_norm": 0.6227554082870483,
|
| 2726 |
+
"learning_rate": 1.589133309291982e-05,
|
| 2727 |
+
"loss": 0.062,
|
| 2728 |
+
"step": 7000
|
| 2729 |
+
},
|
| 2730 |
+
{
|
| 2731 |
+
"epoch": 2.52,
|
| 2732 |
+
"eval_loss": 0.2532944679260254,
|
| 2733 |
+
"eval_na_accuracy": 0.8109965920448303,
|
| 2734 |
+
"eval_ordinal_accuracy": 0.710506021976471,
|
| 2735 |
+
"eval_ordinal_mae": 0.33686304092407227,
|
| 2736 |
+
"eval_runtime": 184.4841,
|
| 2737 |
+
"eval_samples_per_second": 24.257,
|
| 2738 |
+
"eval_steps_per_second": 3.035,
|
| 2739 |
+
"step": 7000
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 2.53,
|
| 2743 |
+
"grad_norm": 0.37592121958732605,
|
| 2744 |
+
"learning_rate": 1.559081620387066e-05,
|
| 2745 |
+
"loss": 0.0529,
|
| 2746 |
+
"step": 7025
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 2.54,
|
| 2750 |
+
"grad_norm": 0.7044575810432434,
|
| 2751 |
+
"learning_rate": 1.5290299314821495e-05,
|
| 2752 |
+
"loss": 0.0555,
|
| 2753 |
+
"step": 7050
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 2.55,
|
| 2757 |
+
"grad_norm": 0.47716042399406433,
|
| 2758 |
+
"learning_rate": 1.4989782425772328e-05,
|
| 2759 |
+
"loss": 0.0424,
|
| 2760 |
+
"step": 7075
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 2.56,
|
| 2764 |
+
"grad_norm": 0.6846262812614441,
|
| 2765 |
+
"learning_rate": 1.4689265536723165e-05,
|
| 2766 |
+
"loss": 0.0664,
|
| 2767 |
+
"step": 7100
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 2.56,
|
| 2771 |
+
"eval_loss": 0.2534230649471283,
|
| 2772 |
+
"eval_na_accuracy": 0.8024054765701294,
|
| 2773 |
+
"eval_ordinal_accuracy": 0.7184690237045288,
|
| 2774 |
+
"eval_ordinal_mae": 0.33289140462875366,
|
| 2775 |
+
"eval_runtime": 185.2999,
|
| 2776 |
+
"eval_samples_per_second": 24.15,
|
| 2777 |
+
"eval_steps_per_second": 3.022,
|
| 2778 |
+
"step": 7100
|
| 2779 |
+
},
|
| 2780 |
+
{
|
| 2781 |
+
"epoch": 2.57,
|
| 2782 |
+
"grad_norm": 0.8216082453727722,
|
| 2783 |
+
"learning_rate": 1.4388748647674e-05,
|
| 2784 |
+
"loss": 0.0481,
|
| 2785 |
+
"step": 7125
|
| 2786 |
+
},
|
| 2787 |
+
{
|
| 2788 |
+
"epoch": 2.58,
|
| 2789 |
+
"grad_norm": 0.8088984489440918,
|
| 2790 |
+
"learning_rate": 1.4088231758624834e-05,
|
| 2791 |
+
"loss": 0.0575,
|
| 2792 |
+
"step": 7150
|
| 2793 |
+
},
|
| 2794 |
+
{
|
| 2795 |
+
"epoch": 2.59,
|
| 2796 |
+
"grad_norm": 0.7712150812149048,
|
| 2797 |
+
"learning_rate": 1.3787714869575672e-05,
|
| 2798 |
+
"loss": 0.0464,
|
| 2799 |
+
"step": 7175
|
| 2800 |
+
},
|
| 2801 |
+
{
|
| 2802 |
+
"epoch": 2.6,
|
| 2803 |
+
"grad_norm": 0.2501738369464874,
|
| 2804 |
+
"learning_rate": 1.3487197980526506e-05,
|
| 2805 |
+
"loss": 0.0389,
|
| 2806 |
+
"step": 7200
|
| 2807 |
+
},
|
| 2808 |
+
{
|
| 2809 |
+
"epoch": 2.6,
|
| 2810 |
+
"eval_loss": 0.246970534324646,
|
| 2811 |
+
"eval_na_accuracy": 0.8092783689498901,
|
| 2812 |
+
"eval_ordinal_accuracy": 0.7259182929992676,
|
| 2813 |
+
"eval_ordinal_mae": 0.328827440738678,
|
| 2814 |
+
"eval_runtime": 185.0735,
|
| 2815 |
+
"eval_samples_per_second": 24.18,
|
| 2816 |
+
"eval_steps_per_second": 3.026,
|
| 2817 |
+
"step": 7200
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 2.61,
|
| 2821 |
+
"grad_norm": 0.6835588216781616,
|
| 2822 |
+
"learning_rate": 1.318668109147734e-05,
|
| 2823 |
+
"loss": 0.0475,
|
| 2824 |
+
"step": 7225
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 2.61,
|
| 2828 |
+
"grad_norm": 0.5996441841125488,
|
| 2829 |
+
"learning_rate": 1.2886164202428178e-05,
|
| 2830 |
+
"loss": 0.0443,
|
| 2831 |
+
"step": 7250
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 2.62,
|
| 2835 |
+
"grad_norm": 2.0018677711486816,
|
| 2836 |
+
"learning_rate": 1.2585647313379013e-05,
|
| 2837 |
+
"loss": 0.0425,
|
| 2838 |
+
"step": 7275
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 2.63,
|
| 2842 |
+
"grad_norm": 0.300843209028244,
|
| 2843 |
+
"learning_rate": 1.2285130424329848e-05,
|
| 2844 |
+
"loss": 0.0671,
|
| 2845 |
+
"step": 7300
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 2.63,
|
| 2849 |
+
"eval_loss": 0.25160375237464905,
|
| 2850 |
+
"eval_na_accuracy": 0.8041236996650696,
|
| 2851 |
+
"eval_ordinal_accuracy": 0.7159003615379333,
|
| 2852 |
+
"eval_ordinal_mae": 0.3293640613555908,
|
| 2853 |
+
"eval_runtime": 186.9929,
|
| 2854 |
+
"eval_samples_per_second": 23.931,
|
| 2855 |
+
"eval_steps_per_second": 2.995,
|
| 2856 |
+
"step": 7300
|
| 2857 |
+
},
|
| 2858 |
+
{
|
| 2859 |
+
"epoch": 2.64,
|
| 2860 |
+
"grad_norm": 0.677975058555603,
|
| 2861 |
+
"learning_rate": 1.1984613535280683e-05,
|
| 2862 |
+
"loss": 0.0438,
|
| 2863 |
+
"step": 7325
|
| 2864 |
+
},
|
| 2865 |
+
{
|
| 2866 |
+
"epoch": 2.65,
|
| 2867 |
+
"grad_norm": 0.45172086358070374,
|
| 2868 |
+
"learning_rate": 1.1684096646231518e-05,
|
| 2869 |
+
"loss": 0.0503,
|
| 2870 |
+
"step": 7350
|
| 2871 |
+
},
|
| 2872 |
+
{
|
| 2873 |
+
"epoch": 2.66,
|
| 2874 |
+
"grad_norm": 0.8617995381355286,
|
| 2875 |
+
"learning_rate": 1.1383579757182353e-05,
|
| 2876 |
+
"loss": 0.0426,
|
| 2877 |
+
"step": 7375
|
| 2878 |
+
},
|
| 2879 |
+
{
|
| 2880 |
+
"epoch": 2.67,
|
| 2881 |
+
"grad_norm": 0.47193852066993713,
|
| 2882 |
+
"learning_rate": 1.108306286813319e-05,
|
| 2883 |
+
"loss": 0.0416,
|
| 2884 |
+
"step": 7400
|
| 2885 |
+
},
|
| 2886 |
+
{
|
| 2887 |
+
"epoch": 2.67,
|
| 2888 |
+
"eval_loss": 0.25071558356285095,
|
| 2889 |
+
"eval_na_accuracy": 0.8058419227600098,
|
| 2890 |
+
"eval_ordinal_accuracy": 0.7133316397666931,
|
| 2891 |
+
"eval_ordinal_mae": 0.33067333698272705,
|
| 2892 |
+
"eval_runtime": 187.7549,
|
| 2893 |
+
"eval_samples_per_second": 23.834,
|
| 2894 |
+
"eval_steps_per_second": 2.983,
|
| 2895 |
+
"step": 7400
|
| 2896 |
+
},
|
| 2897 |
+
{
|
| 2898 |
+
"epoch": 2.68,
|
| 2899 |
+
"grad_norm": 1.0205371379852295,
|
| 2900 |
+
"learning_rate": 1.0782545979084024e-05,
|
| 2901 |
+
"loss": 0.0495,
|
| 2902 |
+
"step": 7425
|
| 2903 |
+
},
|
| 2904 |
+
{
|
| 2905 |
+
"epoch": 2.69,
|
| 2906 |
+
"grad_norm": 0.8885800838470459,
|
| 2907 |
+
"learning_rate": 1.048202909003486e-05,
|
| 2908 |
+
"loss": 0.0407,
|
| 2909 |
+
"step": 7450
|
| 2910 |
+
},
|
| 2911 |
+
{
|
| 2912 |
+
"epoch": 2.7,
|
| 2913 |
+
"grad_norm": 0.6127232313156128,
|
| 2914 |
+
"learning_rate": 1.0181512200985696e-05,
|
| 2915 |
+
"loss": 0.0611,
|
| 2916 |
+
"step": 7475
|
| 2917 |
+
},
|
| 2918 |
+
{
|
| 2919 |
+
"epoch": 2.7,
|
| 2920 |
+
"grad_norm": 0.7351526021957397,
|
| 2921 |
+
"learning_rate": 9.880995311936533e-06,
|
| 2922 |
+
"loss": 0.0541,
|
| 2923 |
+
"step": 7500
|
| 2924 |
+
},
|
| 2925 |
+
{
|
| 2926 |
+
"epoch": 2.7,
|
| 2927 |
+
"eval_loss": 0.25292566418647766,
|
| 2928 |
+
"eval_na_accuracy": 0.8058419227600098,
|
| 2929 |
+
"eval_ordinal_accuracy": 0.71101975440979,
|
| 2930 |
+
"eval_ordinal_mae": 0.335502564907074,
|
| 2931 |
+
"eval_runtime": 185.7438,
|
| 2932 |
+
"eval_samples_per_second": 24.092,
|
| 2933 |
+
"eval_steps_per_second": 3.015,
|
| 2934 |
+
"step": 7500
|
| 2935 |
+
},
|
| 2936 |
+
{
|
| 2937 |
+
"epoch": 2.71,
|
| 2938 |
+
"grad_norm": 0.715017557144165,
|
| 2939 |
+
"learning_rate": 9.580478422887366e-06,
|
| 2940 |
+
"loss": 0.0581,
|
| 2941 |
+
"step": 7525
|
| 2942 |
+
},
|
| 2943 |
+
{
|
| 2944 |
+
"epoch": 2.72,
|
| 2945 |
+
"grad_norm": 0.2852751910686493,
|
| 2946 |
+
"learning_rate": 9.279961533838203e-06,
|
| 2947 |
+
"loss": 0.0507,
|
| 2948 |
+
"step": 7550
|
| 2949 |
+
},
|
| 2950 |
+
{
|
| 2951 |
+
"epoch": 2.73,
|
| 2952 |
+
"grad_norm": 0.5301045775413513,
|
| 2953 |
+
"learning_rate": 8.979444644789038e-06,
|
| 2954 |
+
"loss": 0.0427,
|
| 2955 |
+
"step": 7575
|
| 2956 |
+
},
|
| 2957 |
+
{
|
| 2958 |
+
"epoch": 2.74,
|
| 2959 |
+
"grad_norm": 0.3962666094303131,
|
| 2960 |
+
"learning_rate": 8.678927755739873e-06,
|
| 2961 |
+
"loss": 0.0374,
|
| 2962 |
+
"step": 7600
|
| 2963 |
+
},
|
| 2964 |
+
{
|
| 2965 |
+
"epoch": 2.74,
|
| 2966 |
+
"eval_loss": 0.2529982626438141,
|
| 2967 |
+
"eval_na_accuracy": 0.8109965920448303,
|
| 2968 |
+
"eval_ordinal_accuracy": 0.7148728370666504,
|
| 2969 |
+
"eval_ordinal_mae": 0.33152100443840027,
|
| 2970 |
+
"eval_runtime": 184.9088,
|
| 2971 |
+
"eval_samples_per_second": 24.201,
|
| 2972 |
+
"eval_steps_per_second": 3.029,
|
| 2973 |
+
"step": 7600
|
| 2974 |
+
},
|
| 2975 |
+
{
|
| 2976 |
+
"epoch": 2.75,
|
| 2977 |
+
"grad_norm": 0.5724599957466125,
|
| 2978 |
+
"learning_rate": 8.378410866690708e-06,
|
| 2979 |
+
"loss": 0.0383,
|
| 2980 |
+
"step": 7625
|
| 2981 |
+
},
|
| 2982 |
+
{
|
| 2983 |
+
"epoch": 2.76,
|
| 2984 |
+
"grad_norm": 0.6337906718254089,
|
| 2985 |
+
"learning_rate": 8.077893977641545e-06,
|
| 2986 |
+
"loss": 0.0339,
|
| 2987 |
+
"step": 7650
|
| 2988 |
+
},
|
| 2989 |
+
{
|
| 2990 |
+
"epoch": 2.77,
|
| 2991 |
+
"grad_norm": 0.645459771156311,
|
| 2992 |
+
"learning_rate": 7.777377088592379e-06,
|
| 2993 |
+
"loss": 0.0485,
|
| 2994 |
+
"step": 7675
|
| 2995 |
+
},
|
| 2996 |
+
{
|
| 2997 |
+
"epoch": 2.78,
|
| 2998 |
+
"grad_norm": 5.039384841918945,
|
| 2999 |
+
"learning_rate": 7.476860199543215e-06,
|
| 3000 |
+
"loss": 0.04,
|
| 3001 |
+
"step": 7700
|
| 3002 |
+
},
|
| 3003 |
+
{
|
| 3004 |
+
"epoch": 2.78,
|
| 3005 |
+
"eval_loss": 0.2519625723361969,
|
| 3006 |
+
"eval_na_accuracy": 0.80756014585495,
|
| 3007 |
+
"eval_ordinal_accuracy": 0.7166709303855896,
|
| 3008 |
+
"eval_ordinal_mae": 0.32904064655303955,
|
| 3009 |
+
"eval_runtime": 188.802,
|
| 3010 |
+
"eval_samples_per_second": 23.702,
|
| 3011 |
+
"eval_steps_per_second": 2.966,
|
| 3012 |
+
"step": 7700
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 2.79,
|
| 3016 |
+
"grad_norm": 0.30601269006729126,
|
| 3017 |
+
"learning_rate": 7.176343310494051e-06,
|
| 3018 |
+
"loss": 0.053,
|
| 3019 |
+
"step": 7725
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 2.79,
|
| 3023 |
+
"grad_norm": 0.6143732070922852,
|
| 3024 |
+
"learning_rate": 6.875826421444885e-06,
|
| 3025 |
+
"loss": 0.0433,
|
| 3026 |
+
"step": 7750
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 2.8,
|
| 3030 |
+
"grad_norm": 0.5583890080451965,
|
| 3031 |
+
"learning_rate": 6.575309532395721e-06,
|
| 3032 |
+
"loss": 0.0534,
|
| 3033 |
+
"step": 7775
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 2.81,
|
| 3037 |
+
"grad_norm": 0.5204710960388184,
|
| 3038 |
+
"learning_rate": 6.274792643346557e-06,
|
| 3039 |
+
"loss": 0.0507,
|
| 3040 |
+
"step": 7800
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 2.81,
|
| 3044 |
+
"eval_loss": 0.2555212676525116,
|
| 3045 |
+
"eval_na_accuracy": 0.8127147555351257,
|
| 3046 |
+
"eval_ordinal_accuracy": 0.710506021976471,
|
| 3047 |
+
"eval_ordinal_mae": 0.3297020196914673,
|
| 3048 |
+
"eval_runtime": 185.0982,
|
| 3049 |
+
"eval_samples_per_second": 24.176,
|
| 3050 |
+
"eval_steps_per_second": 3.025,
|
| 3051 |
+
"step": 7800
|
| 3052 |
+
},
|
| 3053 |
+
{
|
| 3054 |
+
"epoch": 2.82,
|
| 3055 |
+
"grad_norm": 0.11941999197006226,
|
| 3056 |
+
"learning_rate": 5.974275754297392e-06,
|
| 3057 |
+
"loss": 0.0392,
|
| 3058 |
+
"step": 7825
|
| 3059 |
+
},
|
| 3060 |
+
{
|
| 3061 |
+
"epoch": 2.83,
|
| 3062 |
+
"grad_norm": 0.20734691619873047,
|
| 3063 |
+
"learning_rate": 5.673758865248227e-06,
|
| 3064 |
+
"loss": 0.06,
|
| 3065 |
+
"step": 7850
|
| 3066 |
+
},
|
| 3067 |
+
{
|
| 3068 |
+
"epoch": 2.84,
|
| 3069 |
+
"grad_norm": 0.48085981607437134,
|
| 3070 |
+
"learning_rate": 5.373241976199063e-06,
|
| 3071 |
+
"loss": 0.0502,
|
| 3072 |
+
"step": 7875
|
| 3073 |
+
},
|
| 3074 |
+
{
|
| 3075 |
+
"epoch": 2.85,
|
| 3076 |
+
"grad_norm": 0.5097972750663757,
|
| 3077 |
+
"learning_rate": 5.072725087149898e-06,
|
| 3078 |
+
"loss": 0.0379,
|
| 3079 |
+
"step": 7900
|
| 3080 |
+
},
|
| 3081 |
+
{
|
| 3082 |
+
"epoch": 2.85,
|
| 3083 |
+
"eval_loss": 0.2531285285949707,
|
| 3084 |
+
"eval_na_accuracy": 0.8127147555351257,
|
| 3085 |
+
"eval_ordinal_accuracy": 0.7161571979522705,
|
| 3086 |
+
"eval_ordinal_mae": 0.3273853659629822,
|
| 3087 |
+
"eval_runtime": 183.7697,
|
| 3088 |
+
"eval_samples_per_second": 24.351,
|
| 3089 |
+
"eval_steps_per_second": 3.047,
|
| 3090 |
+
"step": 7900
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 2.86,
|
| 3094 |
+
"grad_norm": 0.1783066987991333,
|
| 3095 |
+
"learning_rate": 4.7722081981007335e-06,
|
| 3096 |
+
"loss": 0.0455,
|
| 3097 |
+
"step": 7925
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 2.87,
|
| 3101 |
+
"grad_norm": 0.6303412318229675,
|
| 3102 |
+
"learning_rate": 4.4716913090515695e-06,
|
| 3103 |
+
"loss": 0.0639,
|
| 3104 |
+
"step": 7950
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 2.88,
|
| 3108 |
+
"grad_norm": 0.7201049327850342,
|
| 3109 |
+
"learning_rate": 4.171174420002405e-06,
|
| 3110 |
+
"loss": 0.0373,
|
| 3111 |
+
"step": 7975
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 2.88,
|
| 3115 |
+
"grad_norm": 0.31524857878685,
|
| 3116 |
+
"learning_rate": 3.87065753095324e-06,
|
| 3117 |
+
"loss": 0.0736,
|
| 3118 |
+
"step": 8000
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 2.88,
|
| 3122 |
+
"eval_loss": 0.25256654620170593,
|
| 3123 |
+
"eval_na_accuracy": 0.8195876479148865,
|
| 3124 |
+
"eval_ordinal_accuracy": 0.7164140939712524,
|
| 3125 |
+
"eval_ordinal_mae": 0.3279343843460083,
|
| 3126 |
+
"eval_runtime": 187.2067,
|
| 3127 |
+
"eval_samples_per_second": 23.904,
|
| 3128 |
+
"eval_steps_per_second": 2.991,
|
| 3129 |
+
"step": 8000
|
| 3130 |
+
},
|
| 3131 |
+
{
|
| 3132 |
+
"epoch": 2.89,
|
| 3133 |
+
"grad_norm": 0.1482267528772354,
|
| 3134 |
+
"learning_rate": 3.5701406419040754e-06,
|
| 3135 |
+
"loss": 0.0363,
|
| 3136 |
+
"step": 8025
|
| 3137 |
+
},
|
| 3138 |
+
{
|
| 3139 |
+
"epoch": 2.9,
|
| 3140 |
+
"grad_norm": 0.6438891887664795,
|
| 3141 |
+
"learning_rate": 3.2696237528549105e-06,
|
| 3142 |
+
"loss": 0.043,
|
| 3143 |
+
"step": 8050
|
| 3144 |
+
},
|
| 3145 |
+
{
|
| 3146 |
+
"epoch": 2.91,
|
| 3147 |
+
"grad_norm": 0.5657501816749573,
|
| 3148 |
+
"learning_rate": 2.969106863805746e-06,
|
| 3149 |
+
"loss": 0.0351,
|
| 3150 |
+
"step": 8075
|
| 3151 |
+
},
|
| 3152 |
+
{
|
| 3153 |
+
"epoch": 2.92,
|
| 3154 |
+
"grad_norm": 0.35640329122543335,
|
| 3155 |
+
"learning_rate": 2.6685899747565817e-06,
|
| 3156 |
+
"loss": 0.0589,
|
| 3157 |
+
"step": 8100
|
| 3158 |
+
},
|
| 3159 |
+
{
|
| 3160 |
+
"epoch": 2.92,
|
| 3161 |
+
"eval_loss": 0.2521790862083435,
|
| 3162 |
+
"eval_na_accuracy": 0.8161512017250061,
|
| 3163 |
+
"eval_ordinal_accuracy": 0.7143591046333313,
|
| 3164 |
+
"eval_ordinal_mae": 0.3267035186290741,
|
| 3165 |
+
"eval_runtime": 185.6368,
|
| 3166 |
+
"eval_samples_per_second": 24.106,
|
| 3167 |
+
"eval_steps_per_second": 3.017,
|
| 3168 |
+
"step": 8100
|
| 3169 |
+
},
|
| 3170 |
+
{
|
| 3171 |
+
"epoch": 2.93,
|
| 3172 |
+
"grad_norm": 0.6037762761116028,
|
| 3173 |
+
"learning_rate": 2.368073085707417e-06,
|
| 3174 |
+
"loss": 0.052,
|
| 3175 |
+
"step": 8125
|
| 3176 |
+
},
|
| 3177 |
+
{
|
| 3178 |
+
"epoch": 2.94,
|
| 3179 |
+
"grad_norm": 0.5858399868011475,
|
| 3180 |
+
"learning_rate": 2.067556196658252e-06,
|
| 3181 |
+
"loss": 0.043,
|
| 3182 |
+
"step": 8150
|
| 3183 |
+
},
|
| 3184 |
+
{
|
| 3185 |
+
"epoch": 2.95,
|
| 3186 |
+
"grad_norm": 0.9954311847686768,
|
| 3187 |
+
"learning_rate": 1.7670393076090878e-06,
|
| 3188 |
+
"loss": 0.0708,
|
| 3189 |
+
"step": 8175
|
| 3190 |
+
},
|
| 3191 |
+
{
|
| 3192 |
+
"epoch": 2.96,
|
| 3193 |
+
"grad_norm": 0.448538601398468,
|
| 3194 |
+
"learning_rate": 1.4665224185599232e-06,
|
| 3195 |
+
"loss": 0.0449,
|
| 3196 |
+
"step": 8200
|
| 3197 |
+
},
|
| 3198 |
+
{
|
| 3199 |
+
"epoch": 2.96,
|
| 3200 |
+
"eval_loss": 0.252143532037735,
|
| 3201 |
+
"eval_na_accuracy": 0.8161512017250061,
|
| 3202 |
+
"eval_ordinal_accuracy": 0.7148728370666504,
|
| 3203 |
+
"eval_ordinal_mae": 0.3271646499633789,
|
| 3204 |
+
"eval_runtime": 188.3236,
|
| 3205 |
+
"eval_samples_per_second": 23.762,
|
| 3206 |
+
"eval_steps_per_second": 2.974,
|
| 3207 |
+
"step": 8200
|
| 3208 |
+
},
|
| 3209 |
+
{
|
| 3210 |
+
"epoch": 2.97,
|
| 3211 |
+
"grad_norm": 0.3916318416595459,
|
| 3212 |
+
"learning_rate": 1.1660055295107585e-06,
|
| 3213 |
+
"loss": 0.0519,
|
| 3214 |
+
"step": 8225
|
| 3215 |
+
},
|
| 3216 |
+
{
|
| 3217 |
+
"epoch": 2.98,
|
| 3218 |
+
"grad_norm": 0.7591487765312195,
|
| 3219 |
+
"learning_rate": 8.654886404615941e-07,
|
| 3220 |
+
"loss": 0.0447,
|
| 3221 |
+
"step": 8250
|
| 3222 |
+
},
|
| 3223 |
+
{
|
| 3224 |
+
"epoch": 2.98,
|
| 3225 |
+
"grad_norm": 0.33720019459724426,
|
| 3226 |
+
"learning_rate": 5.649717514124295e-07,
|
| 3227 |
+
"loss": 0.0486,
|
| 3228 |
+
"step": 8275
|
| 3229 |
+
},
|
| 3230 |
+
{
|
| 3231 |
+
"epoch": 2.99,
|
| 3232 |
+
"grad_norm": 0.5342977046966553,
|
| 3233 |
+
"learning_rate": 2.644548623632648e-07,
|
| 3234 |
+
"loss": 0.0498,
|
| 3235 |
+
"step": 8300
|
| 3236 |
+
},
|
| 3237 |
+
{
|
| 3238 |
+
"epoch": 2.99,
|
| 3239 |
+
"eval_loss": 0.2520281970500946,
|
| 3240 |
+
"eval_na_accuracy": 0.8144329786300659,
|
| 3241 |
+
"eval_ordinal_accuracy": 0.7166709303855896,
|
| 3242 |
+
"eval_ordinal_mae": 0.3264659643173218,
|
| 3243 |
+
"eval_runtime": 186.96,
|
| 3244 |
+
"eval_samples_per_second": 23.936,
|
| 3245 |
+
"eval_steps_per_second": 2.995,
|
| 3246 |
+
"step": 8300
|
| 3247 |
+
},
|
| 3248 |
+
{
|
| 3249 |
+
"epoch": 3.0,
|
| 3250 |
+
"step": 8319,
|
| 3251 |
+
"total_flos": 1.0314863567841853e+19,
|
| 3252 |
+
"train_loss": 0.13915026724546314,
|
| 3253 |
+
"train_runtime": 27077.9759,
|
| 3254 |
+
"train_samples_per_second": 4.916,
|
| 3255 |
+
"train_steps_per_second": 0.307
|
| 3256 |
+
}
|
| 3257 |
+
],
|
| 3258 |
+
"logging_steps": 25,
|
| 3259 |
+
"max_steps": 8319,
|
| 3260 |
+
"num_input_tokens_seen": 0,
|
| 3261 |
+
"num_train_epochs": 3,
|
| 3262 |
+
"save_steps": 100,
|
| 3263 |
+
"total_flos": 1.0314863567841853e+19,
|
| 3264 |
+
"train_batch_size": 16,
|
| 3265 |
+
"trial_name": null,
|
| 3266 |
+
"trial_params": null
|
| 3267 |
+
}
|