End of training
Browse files- README.md +4 -3
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Jun19_19-59-24_ml6.hpc.uio.no/events.out.tfevents.1718824779.ml6.hpc.uio.no.3789351.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +3093 -0
README.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
---
|
| 2 |
base_model: anderloh/Hugginhface-master-wav2vec-pretreined-5-class-train-test
|
| 3 |
tags:
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
metrics:
|
| 6 |
- accuracy
|
|
@@ -14,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# HuggingfaceTest
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [anderloh/Hugginhface-master-wav2vec-pretreined-5-class-train-test](https://huggingface.co/anderloh/Hugginhface-master-wav2vec-pretreined-5-class-train-test) on
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
-
- Accuracy: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 1 |
---
|
| 2 |
base_model: anderloh/Hugginhface-master-wav2vec-pretreined-5-class-train-test
|
| 3 |
tags:
|
| 4 |
+
- audio-classification
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
|
|
|
| 15 |
|
| 16 |
# HuggingfaceTest
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [anderloh/Hugginhface-master-wav2vec-pretreined-5-class-train-test](https://huggingface.co/anderloh/Hugginhface-master-wav2vec-pretreined-5-class-train-test) on the anderloh/Master5Class dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.8156
|
| 21 |
+
- Accuracy: 0.7028
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 323.08,
|
| 3 |
+
"eval_accuracy": 0.7027972027972028,
|
| 4 |
+
"eval_loss": 0.8156144022941589,
|
| 5 |
+
"eval_runtime": 5.0661,
|
| 6 |
+
"eval_samples_per_second": 56.453,
|
| 7 |
+
"eval_steps_per_second": 0.592,
|
| 8 |
+
"train_loss": 0.8143934268043155,
|
| 9 |
+
"train_runtime": 4784.9132,
|
| 10 |
+
"train_samples_per_second": 113.231,
|
| 11 |
+
"train_steps_per_second": 0.219
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 323.08,
|
| 3 |
+
"eval_accuracy": 0.7027972027972028,
|
| 4 |
+
"eval_loss": 0.8156144022941589,
|
| 5 |
+
"eval_runtime": 5.0661,
|
| 6 |
+
"eval_samples_per_second": 56.453,
|
| 7 |
+
"eval_steps_per_second": 0.592
|
| 8 |
+
}
|
runs/Jun19_19-59-24_ml6.hpc.uio.no/events.out.tfevents.1718824779.ml6.hpc.uio.no.3789351.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd383e2a0a632cc9427727b4a52ff49d1d73ffca3a4750f2874b621fb4e917fa
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 323.08,
|
| 3 |
+
"train_loss": 0.8143934268043155,
|
| 4 |
+
"train_runtime": 4784.9132,
|
| 5 |
+
"train_samples_per_second": 113.231,
|
| 6 |
+
"train_steps_per_second": 0.219
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3093 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7027972027972028,
|
| 3 |
+
"best_model_checkpoint": "wav2vec2-5Class-train-test-finetune/checkpoint-721",
|
| 4 |
+
"epoch": 323.0769230769231,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1050,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.92,
|
| 13 |
+
"eval_accuracy": 0.34265734265734266,
|
| 14 |
+
"eval_loss": 1.59893798828125,
|
| 15 |
+
"eval_runtime": 4.2802,
|
| 16 |
+
"eval_samples_per_second": 66.819,
|
| 17 |
+
"eval_steps_per_second": 0.701,
|
| 18 |
+
"step": 3
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.85,
|
| 22 |
+
"eval_accuracy": 0.34265734265734266,
|
| 23 |
+
"eval_loss": 1.5987956523895264,
|
| 24 |
+
"eval_runtime": 4.8166,
|
| 25 |
+
"eval_samples_per_second": 59.378,
|
| 26 |
+
"eval_steps_per_second": 0.623,
|
| 27 |
+
"step": 6
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.77,
|
| 31 |
+
"eval_accuracy": 0.34265734265734266,
|
| 32 |
+
"eval_loss": 1.598555326461792,
|
| 33 |
+
"eval_runtime": 3.989,
|
| 34 |
+
"eval_samples_per_second": 71.697,
|
| 35 |
+
"eval_steps_per_second": 0.752,
|
| 36 |
+
"step": 9
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 4.0,
|
| 40 |
+
"eval_accuracy": 0.34265734265734266,
|
| 41 |
+
"eval_loss": 1.598075270652771,
|
| 42 |
+
"eval_runtime": 4.3871,
|
| 43 |
+
"eval_samples_per_second": 65.191,
|
| 44 |
+
"eval_steps_per_second": 0.684,
|
| 45 |
+
"step": 13
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 4.92,
|
| 49 |
+
"eval_accuracy": 0.3356643356643357,
|
| 50 |
+
"eval_loss": 1.5975924730300903,
|
| 51 |
+
"eval_runtime": 4.7955,
|
| 52 |
+
"eval_samples_per_second": 59.639,
|
| 53 |
+
"eval_steps_per_second": 0.626,
|
| 54 |
+
"step": 16
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 5.85,
|
| 58 |
+
"eval_accuracy": 0.34265734265734266,
|
| 59 |
+
"eval_loss": 1.5970256328582764,
|
| 60 |
+
"eval_runtime": 4.4665,
|
| 61 |
+
"eval_samples_per_second": 64.032,
|
| 62 |
+
"eval_steps_per_second": 0.672,
|
| 63 |
+
"step": 19
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 6.77,
|
| 67 |
+
"eval_accuracy": 0.33916083916083917,
|
| 68 |
+
"eval_loss": 1.5963499546051025,
|
| 69 |
+
"eval_runtime": 4.3016,
|
| 70 |
+
"eval_samples_per_second": 66.488,
|
| 71 |
+
"eval_steps_per_second": 0.697,
|
| 72 |
+
"step": 22
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 8.0,
|
| 76 |
+
"eval_accuracy": 0.3356643356643357,
|
| 77 |
+
"eval_loss": 1.5952636003494263,
|
| 78 |
+
"eval_runtime": 3.9531,
|
| 79 |
+
"eval_samples_per_second": 72.347,
|
| 80 |
+
"eval_steps_per_second": 0.759,
|
| 81 |
+
"step": 26
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 8.92,
|
| 85 |
+
"eval_accuracy": 0.32867132867132864,
|
| 86 |
+
"eval_loss": 1.594333291053772,
|
| 87 |
+
"eval_runtime": 5.6915,
|
| 88 |
+
"eval_samples_per_second": 50.25,
|
| 89 |
+
"eval_steps_per_second": 0.527,
|
| 90 |
+
"step": 29
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 9.85,
|
| 94 |
+
"eval_accuracy": 0.32867132867132864,
|
| 95 |
+
"eval_loss": 1.5933252573013306,
|
| 96 |
+
"eval_runtime": 4.4236,
|
| 97 |
+
"eval_samples_per_second": 64.653,
|
| 98 |
+
"eval_steps_per_second": 0.678,
|
| 99 |
+
"step": 32
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 10.77,
|
| 103 |
+
"eval_accuracy": 0.32167832167832167,
|
| 104 |
+
"eval_loss": 1.592211365699768,
|
| 105 |
+
"eval_runtime": 4.9541,
|
| 106 |
+
"eval_samples_per_second": 57.73,
|
| 107 |
+
"eval_steps_per_second": 0.606,
|
| 108 |
+
"step": 35
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 12.0,
|
| 112 |
+
"eval_accuracy": 0.3181818181818182,
|
| 113 |
+
"eval_loss": 1.5905568599700928,
|
| 114 |
+
"eval_runtime": 5.1955,
|
| 115 |
+
"eval_samples_per_second": 55.047,
|
| 116 |
+
"eval_steps_per_second": 0.577,
|
| 117 |
+
"step": 39
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 12.92,
|
| 121 |
+
"eval_accuracy": 0.3146853146853147,
|
| 122 |
+
"eval_loss": 1.58920156955719,
|
| 123 |
+
"eval_runtime": 3.6236,
|
| 124 |
+
"eval_samples_per_second": 78.926,
|
| 125 |
+
"eval_steps_per_second": 0.828,
|
| 126 |
+
"step": 42
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 13.85,
|
| 130 |
+
"eval_accuracy": 0.3006993006993007,
|
| 131 |
+
"eval_loss": 1.5877453088760376,
|
| 132 |
+
"eval_runtime": 4.348,
|
| 133 |
+
"eval_samples_per_second": 65.778,
|
| 134 |
+
"eval_steps_per_second": 0.69,
|
| 135 |
+
"step": 45
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 14.77,
|
| 139 |
+
"eval_accuracy": 0.2937062937062937,
|
| 140 |
+
"eval_loss": 1.5862104892730713,
|
| 141 |
+
"eval_runtime": 4.6902,
|
| 142 |
+
"eval_samples_per_second": 60.978,
|
| 143 |
+
"eval_steps_per_second": 0.64,
|
| 144 |
+
"step": 48
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 15.38,
|
| 148 |
+
"grad_norm": 65952.0234375,
|
| 149 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 150 |
+
"loss": 1.5907,
|
| 151 |
+
"step": 50
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 16.0,
|
| 155 |
+
"eval_accuracy": 0.2972027972027972,
|
| 156 |
+
"eval_loss": 1.5840750932693481,
|
| 157 |
+
"eval_runtime": 4.547,
|
| 158 |
+
"eval_samples_per_second": 62.899,
|
| 159 |
+
"eval_steps_per_second": 0.66,
|
| 160 |
+
"step": 52
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 16.92,
|
| 164 |
+
"eval_accuracy": 0.28321678321678323,
|
| 165 |
+
"eval_loss": 1.5823713541030884,
|
| 166 |
+
"eval_runtime": 5.3625,
|
| 167 |
+
"eval_samples_per_second": 53.334,
|
| 168 |
+
"eval_steps_per_second": 0.559,
|
| 169 |
+
"step": 55
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 17.85,
|
| 173 |
+
"eval_accuracy": 0.27972027972027974,
|
| 174 |
+
"eval_loss": 1.5806101560592651,
|
| 175 |
+
"eval_runtime": 4.7671,
|
| 176 |
+
"eval_samples_per_second": 59.995,
|
| 177 |
+
"eval_steps_per_second": 0.629,
|
| 178 |
+
"step": 58
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 18.77,
|
| 182 |
+
"eval_accuracy": 0.2692307692307692,
|
| 183 |
+
"eval_loss": 1.5787912607192993,
|
| 184 |
+
"eval_runtime": 4.3086,
|
| 185 |
+
"eval_samples_per_second": 66.378,
|
| 186 |
+
"eval_steps_per_second": 0.696,
|
| 187 |
+
"step": 61
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 20.0,
|
| 191 |
+
"eval_accuracy": 0.2692307692307692,
|
| 192 |
+
"eval_loss": 1.576175332069397,
|
| 193 |
+
"eval_runtime": 5.3175,
|
| 194 |
+
"eval_samples_per_second": 53.784,
|
| 195 |
+
"eval_steps_per_second": 0.564,
|
| 196 |
+
"step": 65
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 20.92,
|
| 200 |
+
"eval_accuracy": 0.26573426573426573,
|
| 201 |
+
"eval_loss": 1.5740149021148682,
|
| 202 |
+
"eval_runtime": 4.5172,
|
| 203 |
+
"eval_samples_per_second": 63.314,
|
| 204 |
+
"eval_steps_per_second": 0.664,
|
| 205 |
+
"step": 68
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 21.85,
|
| 209 |
+
"eval_accuracy": 0.25524475524475526,
|
| 210 |
+
"eval_loss": 1.5717105865478516,
|
| 211 |
+
"eval_runtime": 3.9011,
|
| 212 |
+
"eval_samples_per_second": 73.312,
|
| 213 |
+
"eval_steps_per_second": 0.769,
|
| 214 |
+
"step": 71
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 22.77,
|
| 218 |
+
"eval_accuracy": 0.2517482517482518,
|
| 219 |
+
"eval_loss": 1.5693939924240112,
|
| 220 |
+
"eval_runtime": 3.9307,
|
| 221 |
+
"eval_samples_per_second": 72.76,
|
| 222 |
+
"eval_steps_per_second": 0.763,
|
| 223 |
+
"step": 74
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 24.0,
|
| 227 |
+
"eval_accuracy": 0.23776223776223776,
|
| 228 |
+
"eval_loss": 1.566083312034607,
|
| 229 |
+
"eval_runtime": 3.7134,
|
| 230 |
+
"eval_samples_per_second": 77.019,
|
| 231 |
+
"eval_steps_per_second": 0.808,
|
| 232 |
+
"step": 78
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 24.92,
|
| 236 |
+
"eval_accuracy": 0.23426573426573427,
|
| 237 |
+
"eval_loss": 1.5634570121765137,
|
| 238 |
+
"eval_runtime": 4.5234,
|
| 239 |
+
"eval_samples_per_second": 63.226,
|
| 240 |
+
"eval_steps_per_second": 0.663,
|
| 241 |
+
"step": 81
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 25.85,
|
| 245 |
+
"eval_accuracy": 0.22377622377622378,
|
| 246 |
+
"eval_loss": 1.5608404874801636,
|
| 247 |
+
"eval_runtime": 4.4129,
|
| 248 |
+
"eval_samples_per_second": 64.81,
|
| 249 |
+
"eval_steps_per_second": 0.68,
|
| 250 |
+
"step": 84
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 26.77,
|
| 254 |
+
"eval_accuracy": 0.22377622377622378,
|
| 255 |
+
"eval_loss": 1.5581375360488892,
|
| 256 |
+
"eval_runtime": 4.7168,
|
| 257 |
+
"eval_samples_per_second": 60.635,
|
| 258 |
+
"eval_steps_per_second": 0.636,
|
| 259 |
+
"step": 87
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 28.0,
|
| 263 |
+
"eval_accuracy": 0.22727272727272727,
|
| 264 |
+
"eval_loss": 1.5542311668395996,
|
| 265 |
+
"eval_runtime": 5.4736,
|
| 266 |
+
"eval_samples_per_second": 52.251,
|
| 267 |
+
"eval_steps_per_second": 0.548,
|
| 268 |
+
"step": 91
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 28.92,
|
| 272 |
+
"eval_accuracy": 0.22727272727272727,
|
| 273 |
+
"eval_loss": 1.5511480569839478,
|
| 274 |
+
"eval_runtime": 5.6532,
|
| 275 |
+
"eval_samples_per_second": 50.591,
|
| 276 |
+
"eval_steps_per_second": 0.531,
|
| 277 |
+
"step": 94
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 29.85,
|
| 281 |
+
"eval_accuracy": 0.22727272727272727,
|
| 282 |
+
"eval_loss": 1.5479341745376587,
|
| 283 |
+
"eval_runtime": 5.2852,
|
| 284 |
+
"eval_samples_per_second": 54.113,
|
| 285 |
+
"eval_steps_per_second": 0.568,
|
| 286 |
+
"step": 97
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 30.77,
|
| 290 |
+
"grad_norm": 68930.8125,
|
| 291 |
+
"learning_rate": 2.857142857142857e-05,
|
| 292 |
+
"loss": 1.5431,
|
| 293 |
+
"step": 100
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 30.77,
|
| 297 |
+
"eval_accuracy": 0.22727272727272727,
|
| 298 |
+
"eval_loss": 1.5448040962219238,
|
| 299 |
+
"eval_runtime": 4.6157,
|
| 300 |
+
"eval_samples_per_second": 61.962,
|
| 301 |
+
"eval_steps_per_second": 0.65,
|
| 302 |
+
"step": 100
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 32.0,
|
| 306 |
+
"eval_accuracy": 0.22727272727272727,
|
| 307 |
+
"eval_loss": 1.5407565832138062,
|
| 308 |
+
"eval_runtime": 6.2131,
|
| 309 |
+
"eval_samples_per_second": 46.032,
|
| 310 |
+
"eval_steps_per_second": 0.483,
|
| 311 |
+
"step": 104
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 32.92,
|
| 315 |
+
"eval_accuracy": 0.22727272727272727,
|
| 316 |
+
"eval_loss": 1.5379865169525146,
|
| 317 |
+
"eval_runtime": 4.645,
|
| 318 |
+
"eval_samples_per_second": 61.571,
|
| 319 |
+
"eval_steps_per_second": 0.646,
|
| 320 |
+
"step": 107
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 33.85,
|
| 324 |
+
"eval_accuracy": 0.22727272727272727,
|
| 325 |
+
"eval_loss": 1.5359200239181519,
|
| 326 |
+
"eval_runtime": 5.5884,
|
| 327 |
+
"eval_samples_per_second": 51.178,
|
| 328 |
+
"eval_steps_per_second": 0.537,
|
| 329 |
+
"step": 110
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 34.77,
|
| 333 |
+
"eval_accuracy": 0.22727272727272727,
|
| 334 |
+
"eval_loss": 1.5345218181610107,
|
| 335 |
+
"eval_runtime": 4.5718,
|
| 336 |
+
"eval_samples_per_second": 62.557,
|
| 337 |
+
"eval_steps_per_second": 0.656,
|
| 338 |
+
"step": 113
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 36.0,
|
| 342 |
+
"eval_accuracy": 0.22727272727272727,
|
| 343 |
+
"eval_loss": 1.5334985256195068,
|
| 344 |
+
"eval_runtime": 5.3526,
|
| 345 |
+
"eval_samples_per_second": 53.432,
|
| 346 |
+
"eval_steps_per_second": 0.56,
|
| 347 |
+
"step": 117
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 36.92,
|
| 351 |
+
"eval_accuracy": 0.22727272727272727,
|
| 352 |
+
"eval_loss": 1.5340909957885742,
|
| 353 |
+
"eval_runtime": 4.471,
|
| 354 |
+
"eval_samples_per_second": 63.967,
|
| 355 |
+
"eval_steps_per_second": 0.671,
|
| 356 |
+
"step": 120
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 37.85,
|
| 360 |
+
"eval_accuracy": 0.22727272727272727,
|
| 361 |
+
"eval_loss": 1.5361381769180298,
|
| 362 |
+
"eval_runtime": 3.5623,
|
| 363 |
+
"eval_samples_per_second": 80.286,
|
| 364 |
+
"eval_steps_per_second": 0.842,
|
| 365 |
+
"step": 123
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 38.77,
|
| 369 |
+
"eval_accuracy": 0.22727272727272727,
|
| 370 |
+
"eval_loss": 1.5397439002990723,
|
| 371 |
+
"eval_runtime": 4.9023,
|
| 372 |
+
"eval_samples_per_second": 58.34,
|
| 373 |
+
"eval_steps_per_second": 0.612,
|
| 374 |
+
"step": 126
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 40.0,
|
| 378 |
+
"eval_accuracy": 0.22727272727272727,
|
| 379 |
+
"eval_loss": 1.5478534698486328,
|
| 380 |
+
"eval_runtime": 3.7352,
|
| 381 |
+
"eval_samples_per_second": 76.569,
|
| 382 |
+
"eval_steps_per_second": 0.803,
|
| 383 |
+
"step": 130
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 40.92,
|
| 387 |
+
"eval_accuracy": 0.22727272727272727,
|
| 388 |
+
"eval_loss": 1.5564229488372803,
|
| 389 |
+
"eval_runtime": 4.3225,
|
| 390 |
+
"eval_samples_per_second": 66.166,
|
| 391 |
+
"eval_steps_per_second": 0.694,
|
| 392 |
+
"step": 133
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 41.85,
|
| 396 |
+
"eval_accuracy": 0.22727272727272727,
|
| 397 |
+
"eval_loss": 1.5678777694702148,
|
| 398 |
+
"eval_runtime": 4.6076,
|
| 399 |
+
"eval_samples_per_second": 62.072,
|
| 400 |
+
"eval_steps_per_second": 0.651,
|
| 401 |
+
"step": 136
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 42.77,
|
| 405 |
+
"eval_accuracy": 0.22727272727272727,
|
| 406 |
+
"eval_loss": 1.5821971893310547,
|
| 407 |
+
"eval_runtime": 4.2697,
|
| 408 |
+
"eval_samples_per_second": 66.983,
|
| 409 |
+
"eval_steps_per_second": 0.703,
|
| 410 |
+
"step": 139
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 44.0,
|
| 414 |
+
"eval_accuracy": 0.22727272727272727,
|
| 415 |
+
"eval_loss": 1.6002099514007568,
|
| 416 |
+
"eval_runtime": 4.533,
|
| 417 |
+
"eval_samples_per_second": 63.094,
|
| 418 |
+
"eval_steps_per_second": 0.662,
|
| 419 |
+
"step": 143
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 44.92,
|
| 423 |
+
"eval_accuracy": 0.22727272727272727,
|
| 424 |
+
"eval_loss": 1.6109449863433838,
|
| 425 |
+
"eval_runtime": 3.9799,
|
| 426 |
+
"eval_samples_per_second": 71.861,
|
| 427 |
+
"eval_steps_per_second": 0.754,
|
| 428 |
+
"step": 146
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 45.85,
|
| 432 |
+
"eval_accuracy": 0.22727272727272727,
|
| 433 |
+
"eval_loss": 1.6145771741867065,
|
| 434 |
+
"eval_runtime": 4.3613,
|
| 435 |
+
"eval_samples_per_second": 65.576,
|
| 436 |
+
"eval_steps_per_second": 0.688,
|
| 437 |
+
"step": 149
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 46.15,
|
| 441 |
+
"grad_norm": 45833.69921875,
|
| 442 |
+
"learning_rate": 2.857142857142857e-05,
|
| 443 |
+
"loss": 1.4033,
|
| 444 |
+
"step": 150
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 46.77,
|
| 448 |
+
"eval_accuracy": 0.22727272727272727,
|
| 449 |
+
"eval_loss": 1.6130825281143188,
|
| 450 |
+
"eval_runtime": 4.2963,
|
| 451 |
+
"eval_samples_per_second": 66.568,
|
| 452 |
+
"eval_steps_per_second": 0.698,
|
| 453 |
+
"step": 152
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 48.0,
|
| 457 |
+
"eval_accuracy": 0.22727272727272727,
|
| 458 |
+
"eval_loss": 1.6008453369140625,
|
| 459 |
+
"eval_runtime": 4.063,
|
| 460 |
+
"eval_samples_per_second": 70.391,
|
| 461 |
+
"eval_steps_per_second": 0.738,
|
| 462 |
+
"step": 156
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 48.92,
|
| 466 |
+
"eval_accuracy": 0.24125874125874125,
|
| 467 |
+
"eval_loss": 1.586226224899292,
|
| 468 |
+
"eval_runtime": 4.5029,
|
| 469 |
+
"eval_samples_per_second": 63.515,
|
| 470 |
+
"eval_steps_per_second": 0.666,
|
| 471 |
+
"step": 159
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 49.85,
|
| 475 |
+
"eval_accuracy": 0.2692307692307692,
|
| 476 |
+
"eval_loss": 1.572645902633667,
|
| 477 |
+
"eval_runtime": 5.0597,
|
| 478 |
+
"eval_samples_per_second": 56.525,
|
| 479 |
+
"eval_steps_per_second": 0.593,
|
| 480 |
+
"step": 162
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 50.77,
|
| 484 |
+
"eval_accuracy": 0.2692307692307692,
|
| 485 |
+
"eval_loss": 1.559901237487793,
|
| 486 |
+
"eval_runtime": 4.4174,
|
| 487 |
+
"eval_samples_per_second": 64.744,
|
| 488 |
+
"eval_steps_per_second": 0.679,
|
| 489 |
+
"step": 165
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 52.0,
|
| 493 |
+
"eval_accuracy": 0.2867132867132867,
|
| 494 |
+
"eval_loss": 1.5458828210830688,
|
| 495 |
+
"eval_runtime": 4.357,
|
| 496 |
+
"eval_samples_per_second": 65.642,
|
| 497 |
+
"eval_steps_per_second": 0.689,
|
| 498 |
+
"step": 169
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 52.92,
|
| 502 |
+
"eval_accuracy": 0.2937062937062937,
|
| 503 |
+
"eval_loss": 1.5382803678512573,
|
| 504 |
+
"eval_runtime": 5.6394,
|
| 505 |
+
"eval_samples_per_second": 50.714,
|
| 506 |
+
"eval_steps_per_second": 0.532,
|
| 507 |
+
"step": 172
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 53.85,
|
| 511 |
+
"eval_accuracy": 0.3146853146853147,
|
| 512 |
+
"eval_loss": 1.5310516357421875,
|
| 513 |
+
"eval_runtime": 4.4695,
|
| 514 |
+
"eval_samples_per_second": 63.989,
|
| 515 |
+
"eval_steps_per_second": 0.671,
|
| 516 |
+
"step": 175
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 54.77,
|
| 520 |
+
"eval_accuracy": 0.32517482517482516,
|
| 521 |
+
"eval_loss": 1.5242317914962769,
|
| 522 |
+
"eval_runtime": 3.8554,
|
| 523 |
+
"eval_samples_per_second": 74.181,
|
| 524 |
+
"eval_steps_per_second": 0.778,
|
| 525 |
+
"step": 178
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 56.0,
|
| 529 |
+
"eval_accuracy": 0.3356643356643357,
|
| 530 |
+
"eval_loss": 1.5169461965560913,
|
| 531 |
+
"eval_runtime": 3.9817,
|
| 532 |
+
"eval_samples_per_second": 71.828,
|
| 533 |
+
"eval_steps_per_second": 0.753,
|
| 534 |
+
"step": 182
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 56.92,
|
| 538 |
+
"eval_accuracy": 0.34265734265734266,
|
| 539 |
+
"eval_loss": 1.5103094577789307,
|
| 540 |
+
"eval_runtime": 3.9287,
|
| 541 |
+
"eval_samples_per_second": 72.797,
|
| 542 |
+
"eval_steps_per_second": 0.764,
|
| 543 |
+
"step": 185
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 57.85,
|
| 547 |
+
"eval_accuracy": 0.34615384615384615,
|
| 548 |
+
"eval_loss": 1.5055506229400635,
|
| 549 |
+
"eval_runtime": 4.3922,
|
| 550 |
+
"eval_samples_per_second": 65.115,
|
| 551 |
+
"eval_steps_per_second": 0.683,
|
| 552 |
+
"step": 188
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 58.77,
|
| 556 |
+
"eval_accuracy": 0.34615384615384615,
|
| 557 |
+
"eval_loss": 1.4995349645614624,
|
| 558 |
+
"eval_runtime": 4.2261,
|
| 559 |
+
"eval_samples_per_second": 67.675,
|
| 560 |
+
"eval_steps_per_second": 0.71,
|
| 561 |
+
"step": 191
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 60.0,
|
| 565 |
+
"eval_accuracy": 0.34965034965034963,
|
| 566 |
+
"eval_loss": 1.4939184188842773,
|
| 567 |
+
"eval_runtime": 3.9946,
|
| 568 |
+
"eval_samples_per_second": 71.597,
|
| 569 |
+
"eval_steps_per_second": 0.751,
|
| 570 |
+
"step": 195
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 60.92,
|
| 574 |
+
"eval_accuracy": 0.36013986013986016,
|
| 575 |
+
"eval_loss": 1.4870301485061646,
|
| 576 |
+
"eval_runtime": 4.7123,
|
| 577 |
+
"eval_samples_per_second": 60.693,
|
| 578 |
+
"eval_steps_per_second": 0.637,
|
| 579 |
+
"step": 198
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 61.54,
|
| 583 |
+
"grad_norm": 27324.4609375,
|
| 584 |
+
"learning_rate": 2.6984126984126984e-05,
|
| 585 |
+
"loss": 1.2485,
|
| 586 |
+
"step": 200
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 61.85,
|
| 590 |
+
"eval_accuracy": 0.36713286713286714,
|
| 591 |
+
"eval_loss": 1.4828742742538452,
|
| 592 |
+
"eval_runtime": 4.8484,
|
| 593 |
+
"eval_samples_per_second": 58.989,
|
| 594 |
+
"eval_steps_per_second": 0.619,
|
| 595 |
+
"step": 201
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 62.77,
|
| 599 |
+
"eval_accuracy": 0.3741258741258741,
|
| 600 |
+
"eval_loss": 1.4735387563705444,
|
| 601 |
+
"eval_runtime": 4.203,
|
| 602 |
+
"eval_samples_per_second": 68.047,
|
| 603 |
+
"eval_steps_per_second": 0.714,
|
| 604 |
+
"step": 204
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 64.0,
|
| 608 |
+
"eval_accuracy": 0.3811188811188811,
|
| 609 |
+
"eval_loss": 1.4612373113632202,
|
| 610 |
+
"eval_runtime": 4.6341,
|
| 611 |
+
"eval_samples_per_second": 61.716,
|
| 612 |
+
"eval_steps_per_second": 0.647,
|
| 613 |
+
"step": 208
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 64.92,
|
| 617 |
+
"eval_accuracy": 0.3986013986013986,
|
| 618 |
+
"eval_loss": 1.4491915702819824,
|
| 619 |
+
"eval_runtime": 3.9863,
|
| 620 |
+
"eval_samples_per_second": 71.745,
|
| 621 |
+
"eval_steps_per_second": 0.753,
|
| 622 |
+
"step": 211
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 65.85,
|
| 626 |
+
"eval_accuracy": 0.4125874125874126,
|
| 627 |
+
"eval_loss": 1.4364999532699585,
|
| 628 |
+
"eval_runtime": 4.1321,
|
| 629 |
+
"eval_samples_per_second": 69.214,
|
| 630 |
+
"eval_steps_per_second": 0.726,
|
| 631 |
+
"step": 214
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 66.77,
|
| 635 |
+
"eval_accuracy": 0.4230769230769231,
|
| 636 |
+
"eval_loss": 1.4226809740066528,
|
| 637 |
+
"eval_runtime": 4.2397,
|
| 638 |
+
"eval_samples_per_second": 67.458,
|
| 639 |
+
"eval_steps_per_second": 0.708,
|
| 640 |
+
"step": 217
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 68.0,
|
| 644 |
+
"eval_accuracy": 0.43356643356643354,
|
| 645 |
+
"eval_loss": 1.4095807075500488,
|
| 646 |
+
"eval_runtime": 3.8645,
|
| 647 |
+
"eval_samples_per_second": 74.007,
|
| 648 |
+
"eval_steps_per_second": 0.776,
|
| 649 |
+
"step": 221
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 68.92,
|
| 653 |
+
"eval_accuracy": 0.4370629370629371,
|
| 654 |
+
"eval_loss": 1.4010183811187744,
|
| 655 |
+
"eval_runtime": 4.5348,
|
| 656 |
+
"eval_samples_per_second": 63.068,
|
| 657 |
+
"eval_steps_per_second": 0.662,
|
| 658 |
+
"step": 224
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 69.85,
|
| 662 |
+
"eval_accuracy": 0.4405594405594406,
|
| 663 |
+
"eval_loss": 1.3949679136276245,
|
| 664 |
+
"eval_runtime": 4.4414,
|
| 665 |
+
"eval_samples_per_second": 64.394,
|
| 666 |
+
"eval_steps_per_second": 0.675,
|
| 667 |
+
"step": 227
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 70.77,
|
| 671 |
+
"eval_accuracy": 0.4370629370629371,
|
| 672 |
+
"eval_loss": 1.3919552564620972,
|
| 673 |
+
"eval_runtime": 4.3028,
|
| 674 |
+
"eval_samples_per_second": 66.468,
|
| 675 |
+
"eval_steps_per_second": 0.697,
|
| 676 |
+
"step": 230
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 72.0,
|
| 680 |
+
"eval_accuracy": 0.4405594405594406,
|
| 681 |
+
"eval_loss": 1.3798925876617432,
|
| 682 |
+
"eval_runtime": 3.4387,
|
| 683 |
+
"eval_samples_per_second": 83.17,
|
| 684 |
+
"eval_steps_per_second": 0.872,
|
| 685 |
+
"step": 234
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 72.92,
|
| 689 |
+
"eval_accuracy": 0.44755244755244755,
|
| 690 |
+
"eval_loss": 1.366864800453186,
|
| 691 |
+
"eval_runtime": 4.6503,
|
| 692 |
+
"eval_samples_per_second": 61.502,
|
| 693 |
+
"eval_steps_per_second": 0.645,
|
| 694 |
+
"step": 237
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 73.85,
|
| 698 |
+
"eval_accuracy": 0.45454545454545453,
|
| 699 |
+
"eval_loss": 1.3514918088912964,
|
| 700 |
+
"eval_runtime": 4.5609,
|
| 701 |
+
"eval_samples_per_second": 62.707,
|
| 702 |
+
"eval_steps_per_second": 0.658,
|
| 703 |
+
"step": 240
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 74.77,
|
| 707 |
+
"eval_accuracy": 0.47202797202797203,
|
| 708 |
+
"eval_loss": 1.3400850296020508,
|
| 709 |
+
"eval_runtime": 3.8017,
|
| 710 |
+
"eval_samples_per_second": 75.229,
|
| 711 |
+
"eval_steps_per_second": 0.789,
|
| 712 |
+
"step": 243
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 76.0,
|
| 716 |
+
"eval_accuracy": 0.4825174825174825,
|
| 717 |
+
"eval_loss": 1.3286209106445312,
|
| 718 |
+
"eval_runtime": 5.7477,
|
| 719 |
+
"eval_samples_per_second": 49.759,
|
| 720 |
+
"eval_steps_per_second": 0.522,
|
| 721 |
+
"step": 247
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 76.92,
|
| 725 |
+
"grad_norm": 23198.236328125,
|
| 726 |
+
"learning_rate": 2.5396825396825397e-05,
|
| 727 |
+
"loss": 1.1198,
|
| 728 |
+
"step": 250
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 76.92,
|
| 732 |
+
"eval_accuracy": 0.486013986013986,
|
| 733 |
+
"eval_loss": 1.317462682723999,
|
| 734 |
+
"eval_runtime": 4.5266,
|
| 735 |
+
"eval_samples_per_second": 63.182,
|
| 736 |
+
"eval_steps_per_second": 0.663,
|
| 737 |
+
"step": 250
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 77.85,
|
| 741 |
+
"eval_accuracy": 0.48951048951048953,
|
| 742 |
+
"eval_loss": 1.3067171573638916,
|
| 743 |
+
"eval_runtime": 3.882,
|
| 744 |
+
"eval_samples_per_second": 73.673,
|
| 745 |
+
"eval_steps_per_second": 0.773,
|
| 746 |
+
"step": 253
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 78.77,
|
| 750 |
+
"eval_accuracy": 0.4825174825174825,
|
| 751 |
+
"eval_loss": 1.3013015985488892,
|
| 752 |
+
"eval_runtime": 4.0902,
|
| 753 |
+
"eval_samples_per_second": 69.923,
|
| 754 |
+
"eval_steps_per_second": 0.733,
|
| 755 |
+
"step": 256
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 80.0,
|
| 759 |
+
"eval_accuracy": 0.479020979020979,
|
| 760 |
+
"eval_loss": 1.2954434156417847,
|
| 761 |
+
"eval_runtime": 5.4081,
|
| 762 |
+
"eval_samples_per_second": 52.884,
|
| 763 |
+
"eval_steps_per_second": 0.555,
|
| 764 |
+
"step": 260
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 80.92,
|
| 768 |
+
"eval_accuracy": 0.486013986013986,
|
| 769 |
+
"eval_loss": 1.289677381515503,
|
| 770 |
+
"eval_runtime": 4.384,
|
| 771 |
+
"eval_samples_per_second": 65.238,
|
| 772 |
+
"eval_steps_per_second": 0.684,
|
| 773 |
+
"step": 263
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 81.85,
|
| 777 |
+
"eval_accuracy": 0.486013986013986,
|
| 778 |
+
"eval_loss": 1.283199667930603,
|
| 779 |
+
"eval_runtime": 4.3325,
|
| 780 |
+
"eval_samples_per_second": 66.013,
|
| 781 |
+
"eval_steps_per_second": 0.692,
|
| 782 |
+
"step": 266
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 82.77,
|
| 786 |
+
"eval_accuracy": 0.4825174825174825,
|
| 787 |
+
"eval_loss": 1.2712346315383911,
|
| 788 |
+
"eval_runtime": 4.6039,
|
| 789 |
+
"eval_samples_per_second": 62.121,
|
| 790 |
+
"eval_steps_per_second": 0.652,
|
| 791 |
+
"step": 269
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 84.0,
|
| 795 |
+
"eval_accuracy": 0.493006993006993,
|
| 796 |
+
"eval_loss": 1.2584125995635986,
|
| 797 |
+
"eval_runtime": 4.5791,
|
| 798 |
+
"eval_samples_per_second": 62.458,
|
| 799 |
+
"eval_steps_per_second": 0.655,
|
| 800 |
+
"step": 273
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 84.92,
|
| 804 |
+
"eval_accuracy": 0.4965034965034965,
|
| 805 |
+
"eval_loss": 1.2516244649887085,
|
| 806 |
+
"eval_runtime": 4.8825,
|
| 807 |
+
"eval_samples_per_second": 58.577,
|
| 808 |
+
"eval_steps_per_second": 0.614,
|
| 809 |
+
"step": 276
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 85.85,
|
| 813 |
+
"eval_accuracy": 0.5,
|
| 814 |
+
"eval_loss": 1.2455971240997314,
|
| 815 |
+
"eval_runtime": 3.9744,
|
| 816 |
+
"eval_samples_per_second": 71.96,
|
| 817 |
+
"eval_steps_per_second": 0.755,
|
| 818 |
+
"step": 279
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 86.77,
|
| 822 |
+
"eval_accuracy": 0.5104895104895105,
|
| 823 |
+
"eval_loss": 1.2443982362747192,
|
| 824 |
+
"eval_runtime": 4.5207,
|
| 825 |
+
"eval_samples_per_second": 63.265,
|
| 826 |
+
"eval_steps_per_second": 0.664,
|
| 827 |
+
"step": 282
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 88.0,
|
| 831 |
+
"eval_accuracy": 0.5104895104895105,
|
| 832 |
+
"eval_loss": 1.2373132705688477,
|
| 833 |
+
"eval_runtime": 5.6152,
|
| 834 |
+
"eval_samples_per_second": 50.933,
|
| 835 |
+
"eval_steps_per_second": 0.534,
|
| 836 |
+
"step": 286
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 88.92,
|
| 840 |
+
"eval_accuracy": 0.513986013986014,
|
| 841 |
+
"eval_loss": 1.2309471368789673,
|
| 842 |
+
"eval_runtime": 4.7969,
|
| 843 |
+
"eval_samples_per_second": 59.622,
|
| 844 |
+
"eval_steps_per_second": 0.625,
|
| 845 |
+
"step": 289
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 89.85,
|
| 849 |
+
"eval_accuracy": 0.5209790209790209,
|
| 850 |
+
"eval_loss": 1.2219436168670654,
|
| 851 |
+
"eval_runtime": 4.2518,
|
| 852 |
+
"eval_samples_per_second": 67.266,
|
| 853 |
+
"eval_steps_per_second": 0.706,
|
| 854 |
+
"step": 292
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 90.77,
|
| 858 |
+
"eval_accuracy": 0.5209790209790209,
|
| 859 |
+
"eval_loss": 1.2145464420318604,
|
| 860 |
+
"eval_runtime": 4.6368,
|
| 861 |
+
"eval_samples_per_second": 61.68,
|
| 862 |
+
"eval_steps_per_second": 0.647,
|
| 863 |
+
"step": 295
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 92.0,
|
| 867 |
+
"eval_accuracy": 0.527972027972028,
|
| 868 |
+
"eval_loss": 1.2054263353347778,
|
| 869 |
+
"eval_runtime": 4.2071,
|
| 870 |
+
"eval_samples_per_second": 67.98,
|
| 871 |
+
"eval_steps_per_second": 0.713,
|
| 872 |
+
"step": 299
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 92.31,
|
| 876 |
+
"grad_norm": 29195.7578125,
|
| 877 |
+
"learning_rate": 2.380952380952381e-05,
|
| 878 |
+
"loss": 0.9915,
|
| 879 |
+
"step": 300
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 92.92,
|
| 883 |
+
"eval_accuracy": 0.534965034965035,
|
| 884 |
+
"eval_loss": 1.1981616020202637,
|
| 885 |
+
"eval_runtime": 4.3609,
|
| 886 |
+
"eval_samples_per_second": 65.583,
|
| 887 |
+
"eval_steps_per_second": 0.688,
|
| 888 |
+
"step": 302
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 93.85,
|
| 892 |
+
"eval_accuracy": 0.5384615384615384,
|
| 893 |
+
"eval_loss": 1.1913262605667114,
|
| 894 |
+
"eval_runtime": 3.9073,
|
| 895 |
+
"eval_samples_per_second": 73.197,
|
| 896 |
+
"eval_steps_per_second": 0.768,
|
| 897 |
+
"step": 305
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 94.77,
|
| 901 |
+
"eval_accuracy": 0.5454545454545454,
|
| 902 |
+
"eval_loss": 1.185881495475769,
|
| 903 |
+
"eval_runtime": 3.928,
|
| 904 |
+
"eval_samples_per_second": 72.811,
|
| 905 |
+
"eval_steps_per_second": 0.764,
|
| 906 |
+
"step": 308
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 96.0,
|
| 910 |
+
"eval_accuracy": 0.548951048951049,
|
| 911 |
+
"eval_loss": 1.179394006729126,
|
| 912 |
+
"eval_runtime": 4.1933,
|
| 913 |
+
"eval_samples_per_second": 68.204,
|
| 914 |
+
"eval_steps_per_second": 0.715,
|
| 915 |
+
"step": 312
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 96.92,
|
| 919 |
+
"eval_accuracy": 0.5454545454545454,
|
| 920 |
+
"eval_loss": 1.1733678579330444,
|
| 921 |
+
"eval_runtime": 5.0205,
|
| 922 |
+
"eval_samples_per_second": 56.967,
|
| 923 |
+
"eval_steps_per_second": 0.598,
|
| 924 |
+
"step": 315
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 97.85,
|
| 928 |
+
"eval_accuracy": 0.5524475524475524,
|
| 929 |
+
"eval_loss": 1.1637603044509888,
|
| 930 |
+
"eval_runtime": 4.8886,
|
| 931 |
+
"eval_samples_per_second": 58.503,
|
| 932 |
+
"eval_steps_per_second": 0.614,
|
| 933 |
+
"step": 318
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 98.77,
|
| 937 |
+
"eval_accuracy": 0.5524475524475524,
|
| 938 |
+
"eval_loss": 1.1549575328826904,
|
| 939 |
+
"eval_runtime": 4.9266,
|
| 940 |
+
"eval_samples_per_second": 58.052,
|
| 941 |
+
"eval_steps_per_second": 0.609,
|
| 942 |
+
"step": 321
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 100.0,
|
| 946 |
+
"eval_accuracy": 0.548951048951049,
|
| 947 |
+
"eval_loss": 1.1464989185333252,
|
| 948 |
+
"eval_runtime": 4.7642,
|
| 949 |
+
"eval_samples_per_second": 60.032,
|
| 950 |
+
"eval_steps_per_second": 0.63,
|
| 951 |
+
"step": 325
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 100.92,
|
| 955 |
+
"eval_accuracy": 0.5594405594405595,
|
| 956 |
+
"eval_loss": 1.1443748474121094,
|
| 957 |
+
"eval_runtime": 4.7025,
|
| 958 |
+
"eval_samples_per_second": 60.819,
|
| 959 |
+
"eval_steps_per_second": 0.638,
|
| 960 |
+
"step": 328
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 101.85,
|
| 964 |
+
"eval_accuracy": 0.5629370629370629,
|
| 965 |
+
"eval_loss": 1.1359333992004395,
|
| 966 |
+
"eval_runtime": 4.6342,
|
| 967 |
+
"eval_samples_per_second": 61.715,
|
| 968 |
+
"eval_steps_per_second": 0.647,
|
| 969 |
+
"step": 331
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 102.77,
|
| 973 |
+
"eval_accuracy": 0.5664335664335665,
|
| 974 |
+
"eval_loss": 1.1271060705184937,
|
| 975 |
+
"eval_runtime": 4.4245,
|
| 976 |
+
"eval_samples_per_second": 64.639,
|
| 977 |
+
"eval_steps_per_second": 0.678,
|
| 978 |
+
"step": 334
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 104.0,
|
| 982 |
+
"eval_accuracy": 0.5769230769230769,
|
| 983 |
+
"eval_loss": 1.109040379524231,
|
| 984 |
+
"eval_runtime": 4.9047,
|
| 985 |
+
"eval_samples_per_second": 58.311,
|
| 986 |
+
"eval_steps_per_second": 0.612,
|
| 987 |
+
"step": 338
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 104.92,
|
| 991 |
+
"eval_accuracy": 0.5944055944055944,
|
| 992 |
+
"eval_loss": 1.0972033739089966,
|
| 993 |
+
"eval_runtime": 4.5473,
|
| 994 |
+
"eval_samples_per_second": 62.895,
|
| 995 |
+
"eval_steps_per_second": 0.66,
|
| 996 |
+
"step": 341
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 105.85,
|
| 1000 |
+
"eval_accuracy": 0.6013986013986014,
|
| 1001 |
+
"eval_loss": 1.090105414390564,
|
| 1002 |
+
"eval_runtime": 3.7875,
|
| 1003 |
+
"eval_samples_per_second": 75.511,
|
| 1004 |
+
"eval_steps_per_second": 0.792,
|
| 1005 |
+
"step": 344
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 106.77,
|
| 1009 |
+
"eval_accuracy": 0.6083916083916084,
|
| 1010 |
+
"eval_loss": 1.0809463262557983,
|
| 1011 |
+
"eval_runtime": 4.7656,
|
| 1012 |
+
"eval_samples_per_second": 60.014,
|
| 1013 |
+
"eval_steps_per_second": 0.63,
|
| 1014 |
+
"step": 347
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 107.69,
|
| 1018 |
+
"grad_norm": 32308.33984375,
|
| 1019 |
+
"learning_rate": 2.222222222222222e-05,
|
| 1020 |
+
"loss": 0.8834,
|
| 1021 |
+
"step": 350
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 108.0,
|
| 1025 |
+
"eval_accuracy": 0.6118881118881119,
|
| 1026 |
+
"eval_loss": 1.0683268308639526,
|
| 1027 |
+
"eval_runtime": 4.3145,
|
| 1028 |
+
"eval_samples_per_second": 66.288,
|
| 1029 |
+
"eval_steps_per_second": 0.695,
|
| 1030 |
+
"step": 351
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 108.92,
|
| 1034 |
+
"eval_accuracy": 0.6223776223776224,
|
| 1035 |
+
"eval_loss": 1.0605404376983643,
|
| 1036 |
+
"eval_runtime": 4.6097,
|
| 1037 |
+
"eval_samples_per_second": 62.043,
|
| 1038 |
+
"eval_steps_per_second": 0.651,
|
| 1039 |
+
"step": 354
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 109.85,
|
| 1043 |
+
"eval_accuracy": 0.6258741258741258,
|
| 1044 |
+
"eval_loss": 1.0562984943389893,
|
| 1045 |
+
"eval_runtime": 4.859,
|
| 1046 |
+
"eval_samples_per_second": 58.86,
|
| 1047 |
+
"eval_steps_per_second": 0.617,
|
| 1048 |
+
"step": 357
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 110.77,
|
| 1052 |
+
"eval_accuracy": 0.6223776223776224,
|
| 1053 |
+
"eval_loss": 1.0537959337234497,
|
| 1054 |
+
"eval_runtime": 4.948,
|
| 1055 |
+
"eval_samples_per_second": 57.801,
|
| 1056 |
+
"eval_steps_per_second": 0.606,
|
| 1057 |
+
"step": 360
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 112.0,
|
| 1061 |
+
"eval_accuracy": 0.6153846153846154,
|
| 1062 |
+
"eval_loss": 1.0491102933883667,
|
| 1063 |
+
"eval_runtime": 4.1434,
|
| 1064 |
+
"eval_samples_per_second": 69.026,
|
| 1065 |
+
"eval_steps_per_second": 0.724,
|
| 1066 |
+
"step": 364
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 112.92,
|
| 1070 |
+
"eval_accuracy": 0.6118881118881119,
|
| 1071 |
+
"eval_loss": 1.044057011604309,
|
| 1072 |
+
"eval_runtime": 4.3774,
|
| 1073 |
+
"eval_samples_per_second": 65.336,
|
| 1074 |
+
"eval_steps_per_second": 0.685,
|
| 1075 |
+
"step": 367
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 113.85,
|
| 1079 |
+
"eval_accuracy": 0.6118881118881119,
|
| 1080 |
+
"eval_loss": 1.0357924699783325,
|
| 1081 |
+
"eval_runtime": 4.7038,
|
| 1082 |
+
"eval_samples_per_second": 60.801,
|
| 1083 |
+
"eval_steps_per_second": 0.638,
|
| 1084 |
+
"step": 370
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 114.77,
|
| 1088 |
+
"eval_accuracy": 0.6223776223776224,
|
| 1089 |
+
"eval_loss": 1.0194157361984253,
|
| 1090 |
+
"eval_runtime": 5.0902,
|
| 1091 |
+
"eval_samples_per_second": 56.187,
|
| 1092 |
+
"eval_steps_per_second": 0.589,
|
| 1093 |
+
"step": 373
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 116.0,
|
| 1097 |
+
"eval_accuracy": 0.6293706293706294,
|
| 1098 |
+
"eval_loss": 1.0034115314483643,
|
| 1099 |
+
"eval_runtime": 4.386,
|
| 1100 |
+
"eval_samples_per_second": 65.208,
|
| 1101 |
+
"eval_steps_per_second": 0.684,
|
| 1102 |
+
"step": 377
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 116.92,
|
| 1106 |
+
"eval_accuracy": 0.6258741258741258,
|
| 1107 |
+
"eval_loss": 0.9991269707679749,
|
| 1108 |
+
"eval_runtime": 5.2708,
|
| 1109 |
+
"eval_samples_per_second": 54.261,
|
| 1110 |
+
"eval_steps_per_second": 0.569,
|
| 1111 |
+
"step": 380
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 117.85,
|
| 1115 |
+
"eval_accuracy": 0.6258741258741258,
|
| 1116 |
+
"eval_loss": 0.9959561824798584,
|
| 1117 |
+
"eval_runtime": 4.7556,
|
| 1118 |
+
"eval_samples_per_second": 60.139,
|
| 1119 |
+
"eval_steps_per_second": 0.631,
|
| 1120 |
+
"step": 383
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 118.77,
|
| 1124 |
+
"eval_accuracy": 0.6293706293706294,
|
| 1125 |
+
"eval_loss": 0.9911425113677979,
|
| 1126 |
+
"eval_runtime": 4.0817,
|
| 1127 |
+
"eval_samples_per_second": 70.068,
|
| 1128 |
+
"eval_steps_per_second": 0.735,
|
| 1129 |
+
"step": 386
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 120.0,
|
| 1133 |
+
"eval_accuracy": 0.6433566433566433,
|
| 1134 |
+
"eval_loss": 0.9834115505218506,
|
| 1135 |
+
"eval_runtime": 4.0058,
|
| 1136 |
+
"eval_samples_per_second": 71.396,
|
| 1137 |
+
"eval_steps_per_second": 0.749,
|
| 1138 |
+
"step": 390
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 120.92,
|
| 1142 |
+
"eval_accuracy": 0.6433566433566433,
|
| 1143 |
+
"eval_loss": 0.9775691628456116,
|
| 1144 |
+
"eval_runtime": 4.3856,
|
| 1145 |
+
"eval_samples_per_second": 65.214,
|
| 1146 |
+
"eval_steps_per_second": 0.684,
|
| 1147 |
+
"step": 393
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 121.85,
|
| 1151 |
+
"eval_accuracy": 0.6433566433566433,
|
| 1152 |
+
"eval_loss": 0.9772741198539734,
|
| 1153 |
+
"eval_runtime": 4.6976,
|
| 1154 |
+
"eval_samples_per_second": 60.882,
|
| 1155 |
+
"eval_steps_per_second": 0.639,
|
| 1156 |
+
"step": 396
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 122.77,
|
| 1160 |
+
"eval_accuracy": 0.6433566433566433,
|
| 1161 |
+
"eval_loss": 0.9734641909599304,
|
| 1162 |
+
"eval_runtime": 4.6506,
|
| 1163 |
+
"eval_samples_per_second": 61.498,
|
| 1164 |
+
"eval_steps_per_second": 0.645,
|
| 1165 |
+
"step": 399
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 123.08,
|
| 1169 |
+
"grad_norm": 27630.990234375,
|
| 1170 |
+
"learning_rate": 2.0634920634920633e-05,
|
| 1171 |
+
"loss": 0.7786,
|
| 1172 |
+
"step": 400
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 124.0,
|
| 1176 |
+
"eval_accuracy": 0.6398601398601399,
|
| 1177 |
+
"eval_loss": 0.9730696082115173,
|
| 1178 |
+
"eval_runtime": 3.9976,
|
| 1179 |
+
"eval_samples_per_second": 71.542,
|
| 1180 |
+
"eval_steps_per_second": 0.75,
|
| 1181 |
+
"step": 403
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 124.92,
|
| 1185 |
+
"eval_accuracy": 0.6433566433566433,
|
| 1186 |
+
"eval_loss": 0.9727755188941956,
|
| 1187 |
+
"eval_runtime": 4.0553,
|
| 1188 |
+
"eval_samples_per_second": 70.525,
|
| 1189 |
+
"eval_steps_per_second": 0.74,
|
| 1190 |
+
"step": 406
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 125.85,
|
| 1194 |
+
"eval_accuracy": 0.6573426573426573,
|
| 1195 |
+
"eval_loss": 0.9657326936721802,
|
| 1196 |
+
"eval_runtime": 4.4666,
|
| 1197 |
+
"eval_samples_per_second": 64.031,
|
| 1198 |
+
"eval_steps_per_second": 0.672,
|
| 1199 |
+
"step": 409
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 126.77,
|
| 1203 |
+
"eval_accuracy": 0.6573426573426573,
|
| 1204 |
+
"eval_loss": 0.9547586441040039,
|
| 1205 |
+
"eval_runtime": 4.6999,
|
| 1206 |
+
"eval_samples_per_second": 60.852,
|
| 1207 |
+
"eval_steps_per_second": 0.638,
|
| 1208 |
+
"step": 412
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 128.0,
|
| 1212 |
+
"eval_accuracy": 0.6643356643356644,
|
| 1213 |
+
"eval_loss": 0.942358136177063,
|
| 1214 |
+
"eval_runtime": 4.8438,
|
| 1215 |
+
"eval_samples_per_second": 59.045,
|
| 1216 |
+
"eval_steps_per_second": 0.619,
|
| 1217 |
+
"step": 416
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 128.92,
|
| 1221 |
+
"eval_accuracy": 0.6678321678321678,
|
| 1222 |
+
"eval_loss": 0.9391436576843262,
|
| 1223 |
+
"eval_runtime": 4.4506,
|
| 1224 |
+
"eval_samples_per_second": 64.261,
|
| 1225 |
+
"eval_steps_per_second": 0.674,
|
| 1226 |
+
"step": 419
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 129.85,
|
| 1230 |
+
"eval_accuracy": 0.6678321678321678,
|
| 1231 |
+
"eval_loss": 0.9418392777442932,
|
| 1232 |
+
"eval_runtime": 4.2912,
|
| 1233 |
+
"eval_samples_per_second": 66.648,
|
| 1234 |
+
"eval_steps_per_second": 0.699,
|
| 1235 |
+
"step": 422
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 130.77,
|
| 1239 |
+
"eval_accuracy": 0.6608391608391608,
|
| 1240 |
+
"eval_loss": 0.9476207494735718,
|
| 1241 |
+
"eval_runtime": 4.7281,
|
| 1242 |
+
"eval_samples_per_second": 60.49,
|
| 1243 |
+
"eval_steps_per_second": 0.635,
|
| 1244 |
+
"step": 425
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 132.0,
|
| 1248 |
+
"eval_accuracy": 0.6643356643356644,
|
| 1249 |
+
"eval_loss": 0.9457269310951233,
|
| 1250 |
+
"eval_runtime": 4.314,
|
| 1251 |
+
"eval_samples_per_second": 66.295,
|
| 1252 |
+
"eval_steps_per_second": 0.695,
|
| 1253 |
+
"step": 429
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 132.92,
|
| 1257 |
+
"eval_accuracy": 0.6643356643356644,
|
| 1258 |
+
"eval_loss": 0.941338062286377,
|
| 1259 |
+
"eval_runtime": 3.916,
|
| 1260 |
+
"eval_samples_per_second": 73.033,
|
| 1261 |
+
"eval_steps_per_second": 0.766,
|
| 1262 |
+
"step": 432
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 133.85,
|
| 1266 |
+
"eval_accuracy": 0.6678321678321678,
|
| 1267 |
+
"eval_loss": 0.9334166049957275,
|
| 1268 |
+
"eval_runtime": 4.5886,
|
| 1269 |
+
"eval_samples_per_second": 62.329,
|
| 1270 |
+
"eval_steps_per_second": 0.654,
|
| 1271 |
+
"step": 435
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 134.77,
|
| 1275 |
+
"eval_accuracy": 0.6678321678321678,
|
| 1276 |
+
"eval_loss": 0.9328890442848206,
|
| 1277 |
+
"eval_runtime": 4.1417,
|
| 1278 |
+
"eval_samples_per_second": 69.054,
|
| 1279 |
+
"eval_steps_per_second": 0.724,
|
| 1280 |
+
"step": 438
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 136.0,
|
| 1284 |
+
"eval_accuracy": 0.6713286713286714,
|
| 1285 |
+
"eval_loss": 0.9333996772766113,
|
| 1286 |
+
"eval_runtime": 4.538,
|
| 1287 |
+
"eval_samples_per_second": 63.023,
|
| 1288 |
+
"eval_steps_per_second": 0.661,
|
| 1289 |
+
"step": 442
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 136.92,
|
| 1293 |
+
"eval_accuracy": 0.6713286713286714,
|
| 1294 |
+
"eval_loss": 0.9264596700668335,
|
| 1295 |
+
"eval_runtime": 4.6642,
|
| 1296 |
+
"eval_samples_per_second": 61.318,
|
| 1297 |
+
"eval_steps_per_second": 0.643,
|
| 1298 |
+
"step": 445
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 137.85,
|
| 1302 |
+
"eval_accuracy": 0.6713286713286714,
|
| 1303 |
+
"eval_loss": 0.9186587929725647,
|
| 1304 |
+
"eval_runtime": 4.5978,
|
| 1305 |
+
"eval_samples_per_second": 62.204,
|
| 1306 |
+
"eval_steps_per_second": 0.652,
|
| 1307 |
+
"step": 448
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 138.46,
|
| 1311 |
+
"grad_norm": 34684.0078125,
|
| 1312 |
+
"learning_rate": 1.9047619047619046e-05,
|
| 1313 |
+
"loss": 0.7133,
|
| 1314 |
+
"step": 450
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 138.77,
|
| 1318 |
+
"eval_accuracy": 0.6678321678321678,
|
| 1319 |
+
"eval_loss": 0.916916012763977,
|
| 1320 |
+
"eval_runtime": 4.1718,
|
| 1321 |
+
"eval_samples_per_second": 68.556,
|
| 1322 |
+
"eval_steps_per_second": 0.719,
|
| 1323 |
+
"step": 451
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 140.0,
|
| 1327 |
+
"eval_accuracy": 0.6713286713286714,
|
| 1328 |
+
"eval_loss": 0.9141567349433899,
|
| 1329 |
+
"eval_runtime": 4.8158,
|
| 1330 |
+
"eval_samples_per_second": 59.388,
|
| 1331 |
+
"eval_steps_per_second": 0.623,
|
| 1332 |
+
"step": 455
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 140.92,
|
| 1336 |
+
"eval_accuracy": 0.6713286713286714,
|
| 1337 |
+
"eval_loss": 0.9131244421005249,
|
| 1338 |
+
"eval_runtime": 4.3984,
|
| 1339 |
+
"eval_samples_per_second": 65.024,
|
| 1340 |
+
"eval_steps_per_second": 0.682,
|
| 1341 |
+
"step": 458
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 141.85,
|
| 1345 |
+
"eval_accuracy": 0.6783216783216783,
|
| 1346 |
+
"eval_loss": 0.9160958528518677,
|
| 1347 |
+
"eval_runtime": 3.9738,
|
| 1348 |
+
"eval_samples_per_second": 71.971,
|
| 1349 |
+
"eval_steps_per_second": 0.755,
|
| 1350 |
+
"step": 461
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 142.77,
|
| 1354 |
+
"eval_accuracy": 0.6678321678321678,
|
| 1355 |
+
"eval_loss": 0.9223662614822388,
|
| 1356 |
+
"eval_runtime": 3.7836,
|
| 1357 |
+
"eval_samples_per_second": 75.589,
|
| 1358 |
+
"eval_steps_per_second": 0.793,
|
| 1359 |
+
"step": 464
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 144.0,
|
| 1363 |
+
"eval_accuracy": 0.6748251748251748,
|
| 1364 |
+
"eval_loss": 0.9139449000358582,
|
| 1365 |
+
"eval_runtime": 4.0554,
|
| 1366 |
+
"eval_samples_per_second": 70.522,
|
| 1367 |
+
"eval_steps_per_second": 0.74,
|
| 1368 |
+
"step": 468
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 144.92,
|
| 1372 |
+
"eval_accuracy": 0.6748251748251748,
|
| 1373 |
+
"eval_loss": 0.9089756608009338,
|
| 1374 |
+
"eval_runtime": 4.4989,
|
| 1375 |
+
"eval_samples_per_second": 63.571,
|
| 1376 |
+
"eval_steps_per_second": 0.667,
|
| 1377 |
+
"step": 471
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 145.85,
|
| 1381 |
+
"eval_accuracy": 0.6713286713286714,
|
| 1382 |
+
"eval_loss": 0.9072948694229126,
|
| 1383 |
+
"eval_runtime": 3.984,
|
| 1384 |
+
"eval_samples_per_second": 71.788,
|
| 1385 |
+
"eval_steps_per_second": 0.753,
|
| 1386 |
+
"step": 474
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 146.77,
|
| 1390 |
+
"eval_accuracy": 0.6608391608391608,
|
| 1391 |
+
"eval_loss": 0.9110231995582581,
|
| 1392 |
+
"eval_runtime": 4.596,
|
| 1393 |
+
"eval_samples_per_second": 62.228,
|
| 1394 |
+
"eval_steps_per_second": 0.653,
|
| 1395 |
+
"step": 477
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 148.0,
|
| 1399 |
+
"eval_accuracy": 0.6573426573426573,
|
| 1400 |
+
"eval_loss": 0.9167369604110718,
|
| 1401 |
+
"eval_runtime": 4.7051,
|
| 1402 |
+
"eval_samples_per_second": 60.785,
|
| 1403 |
+
"eval_steps_per_second": 0.638,
|
| 1404 |
+
"step": 481
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 148.92,
|
| 1408 |
+
"eval_accuracy": 0.6643356643356644,
|
| 1409 |
+
"eval_loss": 0.9118071794509888,
|
| 1410 |
+
"eval_runtime": 3.9295,
|
| 1411 |
+
"eval_samples_per_second": 72.783,
|
| 1412 |
+
"eval_steps_per_second": 0.763,
|
| 1413 |
+
"step": 484
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 149.85,
|
| 1417 |
+
"eval_accuracy": 0.6713286713286714,
|
| 1418 |
+
"eval_loss": 0.8996461629867554,
|
| 1419 |
+
"eval_runtime": 4.5063,
|
| 1420 |
+
"eval_samples_per_second": 63.466,
|
| 1421 |
+
"eval_steps_per_second": 0.666,
|
| 1422 |
+
"step": 487
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 150.77,
|
| 1426 |
+
"eval_accuracy": 0.6748251748251748,
|
| 1427 |
+
"eval_loss": 0.8903929591178894,
|
| 1428 |
+
"eval_runtime": 4.0074,
|
| 1429 |
+
"eval_samples_per_second": 71.369,
|
| 1430 |
+
"eval_steps_per_second": 0.749,
|
| 1431 |
+
"step": 490
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 152.0,
|
| 1435 |
+
"eval_accuracy": 0.6748251748251748,
|
| 1436 |
+
"eval_loss": 0.8889052867889404,
|
| 1437 |
+
"eval_runtime": 4.2482,
|
| 1438 |
+
"eval_samples_per_second": 67.323,
|
| 1439 |
+
"eval_steps_per_second": 0.706,
|
| 1440 |
+
"step": 494
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 152.92,
|
| 1444 |
+
"eval_accuracy": 0.6713286713286714,
|
| 1445 |
+
"eval_loss": 0.889894425868988,
|
| 1446 |
+
"eval_runtime": 4.7658,
|
| 1447 |
+
"eval_samples_per_second": 60.011,
|
| 1448 |
+
"eval_steps_per_second": 0.629,
|
| 1449 |
+
"step": 497
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 153.85,
|
| 1453 |
+
"grad_norm": 27670.865234375,
|
| 1454 |
+
"learning_rate": 1.746031746031746e-05,
|
| 1455 |
+
"loss": 0.6674,
|
| 1456 |
+
"step": 500
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 153.85,
|
| 1460 |
+
"eval_accuracy": 0.6748251748251748,
|
| 1461 |
+
"eval_loss": 0.887377917766571,
|
| 1462 |
+
"eval_runtime": 4.6951,
|
| 1463 |
+
"eval_samples_per_second": 60.915,
|
| 1464 |
+
"eval_steps_per_second": 0.639,
|
| 1465 |
+
"step": 500
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 154.77,
|
| 1469 |
+
"eval_accuracy": 0.6748251748251748,
|
| 1470 |
+
"eval_loss": 0.8873924016952515,
|
| 1471 |
+
"eval_runtime": 3.8042,
|
| 1472 |
+
"eval_samples_per_second": 75.181,
|
| 1473 |
+
"eval_steps_per_second": 0.789,
|
| 1474 |
+
"step": 503
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 156.0,
|
| 1478 |
+
"eval_accuracy": 0.6748251748251748,
|
| 1479 |
+
"eval_loss": 0.8905075788497925,
|
| 1480 |
+
"eval_runtime": 3.9282,
|
| 1481 |
+
"eval_samples_per_second": 72.806,
|
| 1482 |
+
"eval_steps_per_second": 0.764,
|
| 1483 |
+
"step": 507
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 156.92,
|
| 1487 |
+
"eval_accuracy": 0.6783216783216783,
|
| 1488 |
+
"eval_loss": 0.8881194591522217,
|
| 1489 |
+
"eval_runtime": 4.2085,
|
| 1490 |
+
"eval_samples_per_second": 67.957,
|
| 1491 |
+
"eval_steps_per_second": 0.713,
|
| 1492 |
+
"step": 510
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 157.85,
|
| 1496 |
+
"eval_accuracy": 0.6748251748251748,
|
| 1497 |
+
"eval_loss": 0.882903516292572,
|
| 1498 |
+
"eval_runtime": 5.345,
|
| 1499 |
+
"eval_samples_per_second": 53.508,
|
| 1500 |
+
"eval_steps_per_second": 0.561,
|
| 1501 |
+
"step": 513
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 158.77,
|
| 1505 |
+
"eval_accuracy": 0.6783216783216783,
|
| 1506 |
+
"eval_loss": 0.8809071183204651,
|
| 1507 |
+
"eval_runtime": 4.4142,
|
| 1508 |
+
"eval_samples_per_second": 64.791,
|
| 1509 |
+
"eval_steps_per_second": 0.68,
|
| 1510 |
+
"step": 516
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 160.0,
|
| 1514 |
+
"eval_accuracy": 0.6783216783216783,
|
| 1515 |
+
"eval_loss": 0.8780828714370728,
|
| 1516 |
+
"eval_runtime": 3.6498,
|
| 1517 |
+
"eval_samples_per_second": 78.361,
|
| 1518 |
+
"eval_steps_per_second": 0.822,
|
| 1519 |
+
"step": 520
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 160.92,
|
| 1523 |
+
"eval_accuracy": 0.6818181818181818,
|
| 1524 |
+
"eval_loss": 0.8776365518569946,
|
| 1525 |
+
"eval_runtime": 3.4668,
|
| 1526 |
+
"eval_samples_per_second": 82.497,
|
| 1527 |
+
"eval_steps_per_second": 0.865,
|
| 1528 |
+
"step": 523
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 161.85,
|
| 1532 |
+
"eval_accuracy": 0.6783216783216783,
|
| 1533 |
+
"eval_loss": 0.8795685768127441,
|
| 1534 |
+
"eval_runtime": 3.8004,
|
| 1535 |
+
"eval_samples_per_second": 75.256,
|
| 1536 |
+
"eval_steps_per_second": 0.789,
|
| 1537 |
+
"step": 526
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 162.77,
|
| 1541 |
+
"eval_accuracy": 0.6818181818181818,
|
| 1542 |
+
"eval_loss": 0.8795468807220459,
|
| 1543 |
+
"eval_runtime": 3.8694,
|
| 1544 |
+
"eval_samples_per_second": 73.913,
|
| 1545 |
+
"eval_steps_per_second": 0.775,
|
| 1546 |
+
"step": 529
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 164.0,
|
| 1550 |
+
"eval_accuracy": 0.6783216783216783,
|
| 1551 |
+
"eval_loss": 0.8797011971473694,
|
| 1552 |
+
"eval_runtime": 4.1348,
|
| 1553 |
+
"eval_samples_per_second": 69.169,
|
| 1554 |
+
"eval_steps_per_second": 0.726,
|
| 1555 |
+
"step": 533
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 164.92,
|
| 1559 |
+
"eval_accuracy": 0.6783216783216783,
|
| 1560 |
+
"eval_loss": 0.8706856966018677,
|
| 1561 |
+
"eval_runtime": 4.5762,
|
| 1562 |
+
"eval_samples_per_second": 62.498,
|
| 1563 |
+
"eval_steps_per_second": 0.656,
|
| 1564 |
+
"step": 536
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 165.85,
|
| 1568 |
+
"eval_accuracy": 0.6783216783216783,
|
| 1569 |
+
"eval_loss": 0.8697258830070496,
|
| 1570 |
+
"eval_runtime": 3.5794,
|
| 1571 |
+
"eval_samples_per_second": 79.901,
|
| 1572 |
+
"eval_steps_per_second": 0.838,
|
| 1573 |
+
"step": 539
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 166.77,
|
| 1577 |
+
"eval_accuracy": 0.6783216783216783,
|
| 1578 |
+
"eval_loss": 0.8723975419998169,
|
| 1579 |
+
"eval_runtime": 5.761,
|
| 1580 |
+
"eval_samples_per_second": 49.644,
|
| 1581 |
+
"eval_steps_per_second": 0.521,
|
| 1582 |
+
"step": 542
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 168.0,
|
| 1586 |
+
"eval_accuracy": 0.6748251748251748,
|
| 1587 |
+
"eval_loss": 0.870445966720581,
|
| 1588 |
+
"eval_runtime": 4.2907,
|
| 1589 |
+
"eval_samples_per_second": 66.656,
|
| 1590 |
+
"eval_steps_per_second": 0.699,
|
| 1591 |
+
"step": 546
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 168.92,
|
| 1595 |
+
"eval_accuracy": 0.6748251748251748,
|
| 1596 |
+
"eval_loss": 0.8693636655807495,
|
| 1597 |
+
"eval_runtime": 4.5637,
|
| 1598 |
+
"eval_samples_per_second": 62.668,
|
| 1599 |
+
"eval_steps_per_second": 0.657,
|
| 1600 |
+
"step": 549
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 169.23,
|
| 1604 |
+
"grad_norm": 67537.203125,
|
| 1605 |
+
"learning_rate": 1.5873015873015872e-05,
|
| 1606 |
+
"loss": 0.6305,
|
| 1607 |
+
"step": 550
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 169.85,
|
| 1611 |
+
"eval_accuracy": 0.6748251748251748,
|
| 1612 |
+
"eval_loss": 0.8739539980888367,
|
| 1613 |
+
"eval_runtime": 4.5496,
|
| 1614 |
+
"eval_samples_per_second": 62.862,
|
| 1615 |
+
"eval_steps_per_second": 0.659,
|
| 1616 |
+
"step": 552
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 170.77,
|
| 1620 |
+
"eval_accuracy": 0.6748251748251748,
|
| 1621 |
+
"eval_loss": 0.8713040947914124,
|
| 1622 |
+
"eval_runtime": 4.3907,
|
| 1623 |
+
"eval_samples_per_second": 65.138,
|
| 1624 |
+
"eval_steps_per_second": 0.683,
|
| 1625 |
+
"step": 555
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 172.0,
|
| 1629 |
+
"eval_accuracy": 0.6783216783216783,
|
| 1630 |
+
"eval_loss": 0.8682331442832947,
|
| 1631 |
+
"eval_runtime": 4.1777,
|
| 1632 |
+
"eval_samples_per_second": 68.459,
|
| 1633 |
+
"eval_steps_per_second": 0.718,
|
| 1634 |
+
"step": 559
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 172.92,
|
| 1638 |
+
"eval_accuracy": 0.6783216783216783,
|
| 1639 |
+
"eval_loss": 0.868798553943634,
|
| 1640 |
+
"eval_runtime": 3.5218,
|
| 1641 |
+
"eval_samples_per_second": 81.207,
|
| 1642 |
+
"eval_steps_per_second": 0.852,
|
| 1643 |
+
"step": 562
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 173.85,
|
| 1647 |
+
"eval_accuracy": 0.6818181818181818,
|
| 1648 |
+
"eval_loss": 0.8692768216133118,
|
| 1649 |
+
"eval_runtime": 5.0064,
|
| 1650 |
+
"eval_samples_per_second": 57.127,
|
| 1651 |
+
"eval_steps_per_second": 0.599,
|
| 1652 |
+
"step": 565
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 174.77,
|
| 1656 |
+
"eval_accuracy": 0.6783216783216783,
|
| 1657 |
+
"eval_loss": 0.874369204044342,
|
| 1658 |
+
"eval_runtime": 4.1257,
|
| 1659 |
+
"eval_samples_per_second": 69.322,
|
| 1660 |
+
"eval_steps_per_second": 0.727,
|
| 1661 |
+
"step": 568
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 176.0,
|
| 1665 |
+
"eval_accuracy": 0.6783216783216783,
|
| 1666 |
+
"eval_loss": 0.8759630918502808,
|
| 1667 |
+
"eval_runtime": 4.4848,
|
| 1668 |
+
"eval_samples_per_second": 63.771,
|
| 1669 |
+
"eval_steps_per_second": 0.669,
|
| 1670 |
+
"step": 572
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 176.92,
|
| 1674 |
+
"eval_accuracy": 0.6853146853146853,
|
| 1675 |
+
"eval_loss": 0.8696449398994446,
|
| 1676 |
+
"eval_runtime": 4.1683,
|
| 1677 |
+
"eval_samples_per_second": 68.613,
|
| 1678 |
+
"eval_steps_per_second": 0.72,
|
| 1679 |
+
"step": 575
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 177.85,
|
| 1683 |
+
"eval_accuracy": 0.6853146853146853,
|
| 1684 |
+
"eval_loss": 0.8668593764305115,
|
| 1685 |
+
"eval_runtime": 4.3889,
|
| 1686 |
+
"eval_samples_per_second": 65.165,
|
| 1687 |
+
"eval_steps_per_second": 0.684,
|
| 1688 |
+
"step": 578
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 178.77,
|
| 1692 |
+
"eval_accuracy": 0.6853146853146853,
|
| 1693 |
+
"eval_loss": 0.8641146421432495,
|
| 1694 |
+
"eval_runtime": 4.0742,
|
| 1695 |
+
"eval_samples_per_second": 70.197,
|
| 1696 |
+
"eval_steps_per_second": 0.736,
|
| 1697 |
+
"step": 581
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 180.0,
|
| 1701 |
+
"eval_accuracy": 0.6713286713286714,
|
| 1702 |
+
"eval_loss": 0.8696537613868713,
|
| 1703 |
+
"eval_runtime": 4.1345,
|
| 1704 |
+
"eval_samples_per_second": 69.173,
|
| 1705 |
+
"eval_steps_per_second": 0.726,
|
| 1706 |
+
"step": 585
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 180.92,
|
| 1710 |
+
"eval_accuracy": 0.6748251748251748,
|
| 1711 |
+
"eval_loss": 0.8678367733955383,
|
| 1712 |
+
"eval_runtime": 3.994,
|
| 1713 |
+
"eval_samples_per_second": 71.607,
|
| 1714 |
+
"eval_steps_per_second": 0.751,
|
| 1715 |
+
"step": 588
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 181.85,
|
| 1719 |
+
"eval_accuracy": 0.6818181818181818,
|
| 1720 |
+
"eval_loss": 0.8620542287826538,
|
| 1721 |
+
"eval_runtime": 4.32,
|
| 1722 |
+
"eval_samples_per_second": 66.204,
|
| 1723 |
+
"eval_steps_per_second": 0.694,
|
| 1724 |
+
"step": 591
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 182.77,
|
| 1728 |
+
"eval_accuracy": 0.6888111888111889,
|
| 1729 |
+
"eval_loss": 0.8557011485099792,
|
| 1730 |
+
"eval_runtime": 4.7717,
|
| 1731 |
+
"eval_samples_per_second": 59.937,
|
| 1732 |
+
"eval_steps_per_second": 0.629,
|
| 1733 |
+
"step": 594
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 184.0,
|
| 1737 |
+
"eval_accuracy": 0.6888111888111889,
|
| 1738 |
+
"eval_loss": 0.848114013671875,
|
| 1739 |
+
"eval_runtime": 4.0948,
|
| 1740 |
+
"eval_samples_per_second": 69.845,
|
| 1741 |
+
"eval_steps_per_second": 0.733,
|
| 1742 |
+
"step": 598
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 184.62,
|
| 1746 |
+
"grad_norm": 36502.2421875,
|
| 1747 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 1748 |
+
"loss": 0.6095,
|
| 1749 |
+
"step": 600
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 184.92,
|
| 1753 |
+
"eval_accuracy": 0.6888111888111889,
|
| 1754 |
+
"eval_loss": 0.8428906798362732,
|
| 1755 |
+
"eval_runtime": 4.6887,
|
| 1756 |
+
"eval_samples_per_second": 60.997,
|
| 1757 |
+
"eval_steps_per_second": 0.64,
|
| 1758 |
+
"step": 601
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 185.85,
|
| 1762 |
+
"eval_accuracy": 0.6888111888111889,
|
| 1763 |
+
"eval_loss": 0.8413122892379761,
|
| 1764 |
+
"eval_runtime": 3.8998,
|
| 1765 |
+
"eval_samples_per_second": 73.337,
|
| 1766 |
+
"eval_steps_per_second": 0.769,
|
| 1767 |
+
"step": 604
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 186.77,
|
| 1771 |
+
"eval_accuracy": 0.6923076923076923,
|
| 1772 |
+
"eval_loss": 0.8402045965194702,
|
| 1773 |
+
"eval_runtime": 4.1508,
|
| 1774 |
+
"eval_samples_per_second": 68.903,
|
| 1775 |
+
"eval_steps_per_second": 0.723,
|
| 1776 |
+
"step": 607
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 188.0,
|
| 1780 |
+
"eval_accuracy": 0.6888111888111889,
|
| 1781 |
+
"eval_loss": 0.8415275812149048,
|
| 1782 |
+
"eval_runtime": 4.4966,
|
| 1783 |
+
"eval_samples_per_second": 63.603,
|
| 1784 |
+
"eval_steps_per_second": 0.667,
|
| 1785 |
+
"step": 611
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 188.92,
|
| 1789 |
+
"eval_accuracy": 0.6923076923076923,
|
| 1790 |
+
"eval_loss": 0.8409523963928223,
|
| 1791 |
+
"eval_runtime": 4.0007,
|
| 1792 |
+
"eval_samples_per_second": 71.488,
|
| 1793 |
+
"eval_steps_per_second": 0.75,
|
| 1794 |
+
"step": 614
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 189.85,
|
| 1798 |
+
"eval_accuracy": 0.6853146853146853,
|
| 1799 |
+
"eval_loss": 0.8388563394546509,
|
| 1800 |
+
"eval_runtime": 4.5212,
|
| 1801 |
+
"eval_samples_per_second": 63.257,
|
| 1802 |
+
"eval_steps_per_second": 0.664,
|
| 1803 |
+
"step": 617
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 190.77,
|
| 1807 |
+
"eval_accuracy": 0.6853146853146853,
|
| 1808 |
+
"eval_loss": 0.8353860378265381,
|
| 1809 |
+
"eval_runtime": 4.6112,
|
| 1810 |
+
"eval_samples_per_second": 62.023,
|
| 1811 |
+
"eval_steps_per_second": 0.651,
|
| 1812 |
+
"step": 620
|
| 1813 |
+
},
|
| 1814 |
+
{
|
| 1815 |
+
"epoch": 192.0,
|
| 1816 |
+
"eval_accuracy": 0.6888111888111889,
|
| 1817 |
+
"eval_loss": 0.8356983661651611,
|
| 1818 |
+
"eval_runtime": 4.6563,
|
| 1819 |
+
"eval_samples_per_second": 61.422,
|
| 1820 |
+
"eval_steps_per_second": 0.644,
|
| 1821 |
+
"step": 624
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 192.92,
|
| 1825 |
+
"eval_accuracy": 0.6958041958041958,
|
| 1826 |
+
"eval_loss": 0.8400572538375854,
|
| 1827 |
+
"eval_runtime": 5.369,
|
| 1828 |
+
"eval_samples_per_second": 53.269,
|
| 1829 |
+
"eval_steps_per_second": 0.559,
|
| 1830 |
+
"step": 627
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 193.85,
|
| 1834 |
+
"eval_accuracy": 0.6958041958041958,
|
| 1835 |
+
"eval_loss": 0.844892144203186,
|
| 1836 |
+
"eval_runtime": 4.0956,
|
| 1837 |
+
"eval_samples_per_second": 69.831,
|
| 1838 |
+
"eval_steps_per_second": 0.732,
|
| 1839 |
+
"step": 630
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 194.77,
|
| 1843 |
+
"eval_accuracy": 0.6958041958041958,
|
| 1844 |
+
"eval_loss": 0.8478845357894897,
|
| 1845 |
+
"eval_runtime": 4.6385,
|
| 1846 |
+
"eval_samples_per_second": 61.658,
|
| 1847 |
+
"eval_steps_per_second": 0.647,
|
| 1848 |
+
"step": 633
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 196.0,
|
| 1852 |
+
"eval_accuracy": 0.6923076923076923,
|
| 1853 |
+
"eval_loss": 0.8454630374908447,
|
| 1854 |
+
"eval_runtime": 4.4423,
|
| 1855 |
+
"eval_samples_per_second": 64.381,
|
| 1856 |
+
"eval_steps_per_second": 0.675,
|
| 1857 |
+
"step": 637
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 196.92,
|
| 1861 |
+
"eval_accuracy": 0.6923076923076923,
|
| 1862 |
+
"eval_loss": 0.8421822190284729,
|
| 1863 |
+
"eval_runtime": 3.8632,
|
| 1864 |
+
"eval_samples_per_second": 74.032,
|
| 1865 |
+
"eval_steps_per_second": 0.777,
|
| 1866 |
+
"step": 640
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 197.85,
|
| 1870 |
+
"eval_accuracy": 0.6923076923076923,
|
| 1871 |
+
"eval_loss": 0.8425044417381287,
|
| 1872 |
+
"eval_runtime": 5.1031,
|
| 1873 |
+
"eval_samples_per_second": 56.044,
|
| 1874 |
+
"eval_steps_per_second": 0.588,
|
| 1875 |
+
"step": 643
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 198.77,
|
| 1879 |
+
"eval_accuracy": 0.6923076923076923,
|
| 1880 |
+
"eval_loss": 0.8436546325683594,
|
| 1881 |
+
"eval_runtime": 4.9685,
|
| 1882 |
+
"eval_samples_per_second": 57.562,
|
| 1883 |
+
"eval_steps_per_second": 0.604,
|
| 1884 |
+
"step": 646
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 200.0,
|
| 1888 |
+
"grad_norm": 66285.84375,
|
| 1889 |
+
"learning_rate": 1.2698412698412699e-05,
|
| 1890 |
+
"loss": 0.5908,
|
| 1891 |
+
"step": 650
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 200.0,
|
| 1895 |
+
"eval_accuracy": 0.6958041958041958,
|
| 1896 |
+
"eval_loss": 0.8366544246673584,
|
| 1897 |
+
"eval_runtime": 4.3292,
|
| 1898 |
+
"eval_samples_per_second": 66.063,
|
| 1899 |
+
"eval_steps_per_second": 0.693,
|
| 1900 |
+
"step": 650
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 200.92,
|
| 1904 |
+
"eval_accuracy": 0.6993006993006993,
|
| 1905 |
+
"eval_loss": 0.834704577922821,
|
| 1906 |
+
"eval_runtime": 4.7887,
|
| 1907 |
+
"eval_samples_per_second": 59.724,
|
| 1908 |
+
"eval_steps_per_second": 0.626,
|
| 1909 |
+
"step": 653
|
| 1910 |
+
},
|
| 1911 |
+
{
|
| 1912 |
+
"epoch": 201.85,
|
| 1913 |
+
"eval_accuracy": 0.6958041958041958,
|
| 1914 |
+
"eval_loss": 0.8286824226379395,
|
| 1915 |
+
"eval_runtime": 4.388,
|
| 1916 |
+
"eval_samples_per_second": 65.178,
|
| 1917 |
+
"eval_steps_per_second": 0.684,
|
| 1918 |
+
"step": 656
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 202.77,
|
| 1922 |
+
"eval_accuracy": 0.6923076923076923,
|
| 1923 |
+
"eval_loss": 0.8259890079498291,
|
| 1924 |
+
"eval_runtime": 3.7365,
|
| 1925 |
+
"eval_samples_per_second": 76.543,
|
| 1926 |
+
"eval_steps_per_second": 0.803,
|
| 1927 |
+
"step": 659
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 204.0,
|
| 1931 |
+
"eval_accuracy": 0.6958041958041958,
|
| 1932 |
+
"eval_loss": 0.8263576626777649,
|
| 1933 |
+
"eval_runtime": 4.9175,
|
| 1934 |
+
"eval_samples_per_second": 58.159,
|
| 1935 |
+
"eval_steps_per_second": 0.61,
|
| 1936 |
+
"step": 663
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 204.92,
|
| 1940 |
+
"eval_accuracy": 0.6958041958041958,
|
| 1941 |
+
"eval_loss": 0.8295235633850098,
|
| 1942 |
+
"eval_runtime": 4.3071,
|
| 1943 |
+
"eval_samples_per_second": 66.401,
|
| 1944 |
+
"eval_steps_per_second": 0.697,
|
| 1945 |
+
"step": 666
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 205.85,
|
| 1949 |
+
"eval_accuracy": 0.6923076923076923,
|
| 1950 |
+
"eval_loss": 0.8301726579666138,
|
| 1951 |
+
"eval_runtime": 3.7499,
|
| 1952 |
+
"eval_samples_per_second": 76.268,
|
| 1953 |
+
"eval_steps_per_second": 0.8,
|
| 1954 |
+
"step": 669
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 206.77,
|
| 1958 |
+
"eval_accuracy": 0.6923076923076923,
|
| 1959 |
+
"eval_loss": 0.828461766242981,
|
| 1960 |
+
"eval_runtime": 3.8022,
|
| 1961 |
+
"eval_samples_per_second": 75.219,
|
| 1962 |
+
"eval_steps_per_second": 0.789,
|
| 1963 |
+
"step": 672
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 208.0,
|
| 1967 |
+
"eval_accuracy": 0.6923076923076923,
|
| 1968 |
+
"eval_loss": 0.831078052520752,
|
| 1969 |
+
"eval_runtime": 4.2868,
|
| 1970 |
+
"eval_samples_per_second": 66.716,
|
| 1971 |
+
"eval_steps_per_second": 0.7,
|
| 1972 |
+
"step": 676
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 208.92,
|
| 1976 |
+
"eval_accuracy": 0.6923076923076923,
|
| 1977 |
+
"eval_loss": 0.8320910334587097,
|
| 1978 |
+
"eval_runtime": 4.474,
|
| 1979 |
+
"eval_samples_per_second": 63.925,
|
| 1980 |
+
"eval_steps_per_second": 0.671,
|
| 1981 |
+
"step": 679
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 209.85,
|
| 1985 |
+
"eval_accuracy": 0.6923076923076923,
|
| 1986 |
+
"eval_loss": 0.8305550813674927,
|
| 1987 |
+
"eval_runtime": 4.1246,
|
| 1988 |
+
"eval_samples_per_second": 69.341,
|
| 1989 |
+
"eval_steps_per_second": 0.727,
|
| 1990 |
+
"step": 682
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 210.77,
|
| 1994 |
+
"eval_accuracy": 0.6923076923076923,
|
| 1995 |
+
"eval_loss": 0.8302868604660034,
|
| 1996 |
+
"eval_runtime": 4.9131,
|
| 1997 |
+
"eval_samples_per_second": 58.212,
|
| 1998 |
+
"eval_steps_per_second": 0.611,
|
| 1999 |
+
"step": 685
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 212.0,
|
| 2003 |
+
"eval_accuracy": 0.6993006993006993,
|
| 2004 |
+
"eval_loss": 0.8256182670593262,
|
| 2005 |
+
"eval_runtime": 4.5542,
|
| 2006 |
+
"eval_samples_per_second": 62.8,
|
| 2007 |
+
"eval_steps_per_second": 0.659,
|
| 2008 |
+
"step": 689
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 212.92,
|
| 2012 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2013 |
+
"eval_loss": 0.8230299353599548,
|
| 2014 |
+
"eval_runtime": 4.2845,
|
| 2015 |
+
"eval_samples_per_second": 66.752,
|
| 2016 |
+
"eval_steps_per_second": 0.7,
|
| 2017 |
+
"step": 692
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 213.85,
|
| 2021 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2022 |
+
"eval_loss": 0.819442868232727,
|
| 2023 |
+
"eval_runtime": 4.4153,
|
| 2024 |
+
"eval_samples_per_second": 64.775,
|
| 2025 |
+
"eval_steps_per_second": 0.679,
|
| 2026 |
+
"step": 695
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 214.77,
|
| 2030 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2031 |
+
"eval_loss": 0.8183168768882751,
|
| 2032 |
+
"eval_runtime": 4.9672,
|
| 2033 |
+
"eval_samples_per_second": 57.577,
|
| 2034 |
+
"eval_steps_per_second": 0.604,
|
| 2035 |
+
"step": 698
|
| 2036 |
+
},
|
| 2037 |
+
{
|
| 2038 |
+
"epoch": 215.38,
|
| 2039 |
+
"grad_norm": 29832.03125,
|
| 2040 |
+
"learning_rate": 1.111111111111111e-05,
|
| 2041 |
+
"loss": 0.5763,
|
| 2042 |
+
"step": 700
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 216.0,
|
| 2046 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2047 |
+
"eval_loss": 0.8231977224349976,
|
| 2048 |
+
"eval_runtime": 4.6354,
|
| 2049 |
+
"eval_samples_per_second": 61.699,
|
| 2050 |
+
"eval_steps_per_second": 0.647,
|
| 2051 |
+
"step": 702
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 216.92,
|
| 2055 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2056 |
+
"eval_loss": 0.8236932158470154,
|
| 2057 |
+
"eval_runtime": 3.7182,
|
| 2058 |
+
"eval_samples_per_second": 76.92,
|
| 2059 |
+
"eval_steps_per_second": 0.807,
|
| 2060 |
+
"step": 705
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 217.85,
|
| 2064 |
+
"eval_accuracy": 0.6993006993006993,
|
| 2065 |
+
"eval_loss": 0.8195610642433167,
|
| 2066 |
+
"eval_runtime": 3.5502,
|
| 2067 |
+
"eval_samples_per_second": 80.56,
|
| 2068 |
+
"eval_steps_per_second": 0.845,
|
| 2069 |
+
"step": 708
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 218.77,
|
| 2073 |
+
"eval_accuracy": 0.6993006993006993,
|
| 2074 |
+
"eval_loss": 0.8142436742782593,
|
| 2075 |
+
"eval_runtime": 4.9155,
|
| 2076 |
+
"eval_samples_per_second": 58.184,
|
| 2077 |
+
"eval_steps_per_second": 0.61,
|
| 2078 |
+
"step": 711
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 220.0,
|
| 2082 |
+
"eval_accuracy": 0.6993006993006993,
|
| 2083 |
+
"eval_loss": 0.8115321397781372,
|
| 2084 |
+
"eval_runtime": 4.0939,
|
| 2085 |
+
"eval_samples_per_second": 69.86,
|
| 2086 |
+
"eval_steps_per_second": 0.733,
|
| 2087 |
+
"step": 715
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 220.92,
|
| 2091 |
+
"eval_accuracy": 0.6993006993006993,
|
| 2092 |
+
"eval_loss": 0.8130100965499878,
|
| 2093 |
+
"eval_runtime": 4.2197,
|
| 2094 |
+
"eval_samples_per_second": 67.777,
|
| 2095 |
+
"eval_steps_per_second": 0.711,
|
| 2096 |
+
"step": 718
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 221.85,
|
| 2100 |
+
"eval_accuracy": 0.7027972027972028,
|
| 2101 |
+
"eval_loss": 0.8156144022941589,
|
| 2102 |
+
"eval_runtime": 4.2344,
|
| 2103 |
+
"eval_samples_per_second": 67.542,
|
| 2104 |
+
"eval_steps_per_second": 0.708,
|
| 2105 |
+
"step": 721
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 222.77,
|
| 2109 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2110 |
+
"eval_loss": 0.8200713992118835,
|
| 2111 |
+
"eval_runtime": 4.8181,
|
| 2112 |
+
"eval_samples_per_second": 59.36,
|
| 2113 |
+
"eval_steps_per_second": 0.623,
|
| 2114 |
+
"step": 724
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 224.0,
|
| 2118 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2119 |
+
"eval_loss": 0.8227414488792419,
|
| 2120 |
+
"eval_runtime": 4.5671,
|
| 2121 |
+
"eval_samples_per_second": 62.621,
|
| 2122 |
+
"eval_steps_per_second": 0.657,
|
| 2123 |
+
"step": 728
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 224.92,
|
| 2127 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2128 |
+
"eval_loss": 0.8232228755950928,
|
| 2129 |
+
"eval_runtime": 5.221,
|
| 2130 |
+
"eval_samples_per_second": 54.779,
|
| 2131 |
+
"eval_steps_per_second": 0.575,
|
| 2132 |
+
"step": 731
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 225.85,
|
| 2136 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2137 |
+
"eval_loss": 0.8198325634002686,
|
| 2138 |
+
"eval_runtime": 4.2136,
|
| 2139 |
+
"eval_samples_per_second": 67.875,
|
| 2140 |
+
"eval_steps_per_second": 0.712,
|
| 2141 |
+
"step": 734
|
| 2142 |
+
},
|
| 2143 |
+
{
|
| 2144 |
+
"epoch": 226.77,
|
| 2145 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2146 |
+
"eval_loss": 0.8151125311851501,
|
| 2147 |
+
"eval_runtime": 4.8801,
|
| 2148 |
+
"eval_samples_per_second": 58.606,
|
| 2149 |
+
"eval_steps_per_second": 0.615,
|
| 2150 |
+
"step": 737
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 228.0,
|
| 2154 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2155 |
+
"eval_loss": 0.8136410713195801,
|
| 2156 |
+
"eval_runtime": 5.2461,
|
| 2157 |
+
"eval_samples_per_second": 54.516,
|
| 2158 |
+
"eval_steps_per_second": 0.572,
|
| 2159 |
+
"step": 741
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 228.92,
|
| 2163 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2164 |
+
"eval_loss": 0.8134062886238098,
|
| 2165 |
+
"eval_runtime": 3.6429,
|
| 2166 |
+
"eval_samples_per_second": 78.509,
|
| 2167 |
+
"eval_steps_per_second": 0.824,
|
| 2168 |
+
"step": 744
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 229.85,
|
| 2172 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2173 |
+
"eval_loss": 0.8123226761817932,
|
| 2174 |
+
"eval_runtime": 4.8374,
|
| 2175 |
+
"eval_samples_per_second": 59.122,
|
| 2176 |
+
"eval_steps_per_second": 0.62,
|
| 2177 |
+
"step": 747
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 230.77,
|
| 2181 |
+
"grad_norm": 27062.134765625,
|
| 2182 |
+
"learning_rate": 9.523809523809523e-06,
|
| 2183 |
+
"loss": 0.57,
|
| 2184 |
+
"step": 750
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 230.77,
|
| 2188 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2189 |
+
"eval_loss": 0.8095433115959167,
|
| 2190 |
+
"eval_runtime": 3.9409,
|
| 2191 |
+
"eval_samples_per_second": 72.572,
|
| 2192 |
+
"eval_steps_per_second": 0.761,
|
| 2193 |
+
"step": 750
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 232.0,
|
| 2197 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2198 |
+
"eval_loss": 0.8082302212715149,
|
| 2199 |
+
"eval_runtime": 4.0933,
|
| 2200 |
+
"eval_samples_per_second": 69.87,
|
| 2201 |
+
"eval_steps_per_second": 0.733,
|
| 2202 |
+
"step": 754
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 232.92,
|
| 2206 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2207 |
+
"eval_loss": 0.8084114193916321,
|
| 2208 |
+
"eval_runtime": 4.4952,
|
| 2209 |
+
"eval_samples_per_second": 63.624,
|
| 2210 |
+
"eval_steps_per_second": 0.667,
|
| 2211 |
+
"step": 757
|
| 2212 |
+
},
|
| 2213 |
+
{
|
| 2214 |
+
"epoch": 233.85,
|
| 2215 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2216 |
+
"eval_loss": 0.8113557696342468,
|
| 2217 |
+
"eval_runtime": 4.6955,
|
| 2218 |
+
"eval_samples_per_second": 60.909,
|
| 2219 |
+
"eval_steps_per_second": 0.639,
|
| 2220 |
+
"step": 760
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 234.77,
|
| 2224 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2225 |
+
"eval_loss": 0.8130276799201965,
|
| 2226 |
+
"eval_runtime": 4.9303,
|
| 2227 |
+
"eval_samples_per_second": 58.009,
|
| 2228 |
+
"eval_steps_per_second": 0.608,
|
| 2229 |
+
"step": 763
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 236.0,
|
| 2233 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2234 |
+
"eval_loss": 0.8153804540634155,
|
| 2235 |
+
"eval_runtime": 3.6663,
|
| 2236 |
+
"eval_samples_per_second": 78.007,
|
| 2237 |
+
"eval_steps_per_second": 0.818,
|
| 2238 |
+
"step": 767
|
| 2239 |
+
},
|
| 2240 |
+
{
|
| 2241 |
+
"epoch": 236.92,
|
| 2242 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2243 |
+
"eval_loss": 0.8160205483436584,
|
| 2244 |
+
"eval_runtime": 4.6226,
|
| 2245 |
+
"eval_samples_per_second": 61.87,
|
| 2246 |
+
"eval_steps_per_second": 0.649,
|
| 2247 |
+
"step": 770
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 237.85,
|
| 2251 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2252 |
+
"eval_loss": 0.8126419186592102,
|
| 2253 |
+
"eval_runtime": 4.6278,
|
| 2254 |
+
"eval_samples_per_second": 61.801,
|
| 2255 |
+
"eval_steps_per_second": 0.648,
|
| 2256 |
+
"step": 773
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 238.77,
|
| 2260 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2261 |
+
"eval_loss": 0.8113960027694702,
|
| 2262 |
+
"eval_runtime": 3.8362,
|
| 2263 |
+
"eval_samples_per_second": 74.552,
|
| 2264 |
+
"eval_steps_per_second": 0.782,
|
| 2265 |
+
"step": 776
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 240.0,
|
| 2269 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2270 |
+
"eval_loss": 0.8041169047355652,
|
| 2271 |
+
"eval_runtime": 5.2095,
|
| 2272 |
+
"eval_samples_per_second": 54.9,
|
| 2273 |
+
"eval_steps_per_second": 0.576,
|
| 2274 |
+
"step": 780
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 240.92,
|
| 2278 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2279 |
+
"eval_loss": 0.8005608916282654,
|
| 2280 |
+
"eval_runtime": 4.0128,
|
| 2281 |
+
"eval_samples_per_second": 71.273,
|
| 2282 |
+
"eval_steps_per_second": 0.748,
|
| 2283 |
+
"step": 783
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 241.85,
|
| 2287 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2288 |
+
"eval_loss": 0.7987480163574219,
|
| 2289 |
+
"eval_runtime": 4.8789,
|
| 2290 |
+
"eval_samples_per_second": 58.619,
|
| 2291 |
+
"eval_steps_per_second": 0.615,
|
| 2292 |
+
"step": 786
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 242.77,
|
| 2296 |
+
"eval_accuracy": 0.6993006993006993,
|
| 2297 |
+
"eval_loss": 0.7977189421653748,
|
| 2298 |
+
"eval_runtime": 4.5854,
|
| 2299 |
+
"eval_samples_per_second": 62.372,
|
| 2300 |
+
"eval_steps_per_second": 0.654,
|
| 2301 |
+
"step": 789
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 244.0,
|
| 2305 |
+
"eval_accuracy": 0.6993006993006993,
|
| 2306 |
+
"eval_loss": 0.8001275658607483,
|
| 2307 |
+
"eval_runtime": 4.7528,
|
| 2308 |
+
"eval_samples_per_second": 60.175,
|
| 2309 |
+
"eval_steps_per_second": 0.631,
|
| 2310 |
+
"step": 793
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 244.92,
|
| 2314 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2315 |
+
"eval_loss": 0.8043994903564453,
|
| 2316 |
+
"eval_runtime": 4.2699,
|
| 2317 |
+
"eval_samples_per_second": 66.98,
|
| 2318 |
+
"eval_steps_per_second": 0.703,
|
| 2319 |
+
"step": 796
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 245.85,
|
| 2323 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2324 |
+
"eval_loss": 0.8082275390625,
|
| 2325 |
+
"eval_runtime": 4.2996,
|
| 2326 |
+
"eval_samples_per_second": 66.518,
|
| 2327 |
+
"eval_steps_per_second": 0.698,
|
| 2328 |
+
"step": 799
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 246.15,
|
| 2332 |
+
"grad_norm": 99001.8359375,
|
| 2333 |
+
"learning_rate": 7.936507936507936e-06,
|
| 2334 |
+
"loss": 0.5456,
|
| 2335 |
+
"step": 800
|
| 2336 |
+
},
|
| 2337 |
+
{
|
| 2338 |
+
"epoch": 246.77,
|
| 2339 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2340 |
+
"eval_loss": 0.8120755553245544,
|
| 2341 |
+
"eval_runtime": 4.5242,
|
| 2342 |
+
"eval_samples_per_second": 63.216,
|
| 2343 |
+
"eval_steps_per_second": 0.663,
|
| 2344 |
+
"step": 802
|
| 2345 |
+
},
|
| 2346 |
+
{
|
| 2347 |
+
"epoch": 248.0,
|
| 2348 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2349 |
+
"eval_loss": 0.8106970191001892,
|
| 2350 |
+
"eval_runtime": 4.4479,
|
| 2351 |
+
"eval_samples_per_second": 64.3,
|
| 2352 |
+
"eval_steps_per_second": 0.674,
|
| 2353 |
+
"step": 806
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 248.92,
|
| 2357 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2358 |
+
"eval_loss": 0.806368887424469,
|
| 2359 |
+
"eval_runtime": 4.1522,
|
| 2360 |
+
"eval_samples_per_second": 68.88,
|
| 2361 |
+
"eval_steps_per_second": 0.723,
|
| 2362 |
+
"step": 809
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 249.85,
|
| 2366 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2367 |
+
"eval_loss": 0.8042352199554443,
|
| 2368 |
+
"eval_runtime": 4.4213,
|
| 2369 |
+
"eval_samples_per_second": 64.687,
|
| 2370 |
+
"eval_steps_per_second": 0.679,
|
| 2371 |
+
"step": 812
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"epoch": 250.77,
|
| 2375 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2376 |
+
"eval_loss": 0.8005724549293518,
|
| 2377 |
+
"eval_runtime": 4.4134,
|
| 2378 |
+
"eval_samples_per_second": 64.802,
|
| 2379 |
+
"eval_steps_per_second": 0.68,
|
| 2380 |
+
"step": 815
|
| 2381 |
+
},
|
| 2382 |
+
{
|
| 2383 |
+
"epoch": 252.0,
|
| 2384 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2385 |
+
"eval_loss": 0.7968676090240479,
|
| 2386 |
+
"eval_runtime": 3.8229,
|
| 2387 |
+
"eval_samples_per_second": 74.812,
|
| 2388 |
+
"eval_steps_per_second": 0.785,
|
| 2389 |
+
"step": 819
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 252.92,
|
| 2393 |
+
"eval_accuracy": 0.6993006993006993,
|
| 2394 |
+
"eval_loss": 0.7954707741737366,
|
| 2395 |
+
"eval_runtime": 4.2693,
|
| 2396 |
+
"eval_samples_per_second": 66.99,
|
| 2397 |
+
"eval_steps_per_second": 0.703,
|
| 2398 |
+
"step": 822
|
| 2399 |
+
},
|
| 2400 |
+
{
|
| 2401 |
+
"epoch": 253.85,
|
| 2402 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2403 |
+
"eval_loss": 0.7973347902297974,
|
| 2404 |
+
"eval_runtime": 4.1401,
|
| 2405 |
+
"eval_samples_per_second": 69.081,
|
| 2406 |
+
"eval_steps_per_second": 0.725,
|
| 2407 |
+
"step": 825
|
| 2408 |
+
},
|
| 2409 |
+
{
|
| 2410 |
+
"epoch": 254.77,
|
| 2411 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2412 |
+
"eval_loss": 0.8001494407653809,
|
| 2413 |
+
"eval_runtime": 4.4851,
|
| 2414 |
+
"eval_samples_per_second": 63.767,
|
| 2415 |
+
"eval_steps_per_second": 0.669,
|
| 2416 |
+
"step": 828
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 256.0,
|
| 2420 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2421 |
+
"eval_loss": 0.80350661277771,
|
| 2422 |
+
"eval_runtime": 4.4996,
|
| 2423 |
+
"eval_samples_per_second": 63.562,
|
| 2424 |
+
"eval_steps_per_second": 0.667,
|
| 2425 |
+
"step": 832
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 256.92,
|
| 2429 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2430 |
+
"eval_loss": 0.8035485148429871,
|
| 2431 |
+
"eval_runtime": 4.5713,
|
| 2432 |
+
"eval_samples_per_second": 62.564,
|
| 2433 |
+
"eval_steps_per_second": 0.656,
|
| 2434 |
+
"step": 835
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"epoch": 257.85,
|
| 2438 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2439 |
+
"eval_loss": 0.8012282252311707,
|
| 2440 |
+
"eval_runtime": 4.0638,
|
| 2441 |
+
"eval_samples_per_second": 70.377,
|
| 2442 |
+
"eval_steps_per_second": 0.738,
|
| 2443 |
+
"step": 838
|
| 2444 |
+
},
|
| 2445 |
+
{
|
| 2446 |
+
"epoch": 258.77,
|
| 2447 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2448 |
+
"eval_loss": 0.8000492453575134,
|
| 2449 |
+
"eval_runtime": 4.443,
|
| 2450 |
+
"eval_samples_per_second": 64.372,
|
| 2451 |
+
"eval_steps_per_second": 0.675,
|
| 2452 |
+
"step": 841
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 260.0,
|
| 2456 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2457 |
+
"eval_loss": 0.7963055968284607,
|
| 2458 |
+
"eval_runtime": 5.2655,
|
| 2459 |
+
"eval_samples_per_second": 54.316,
|
| 2460 |
+
"eval_steps_per_second": 0.57,
|
| 2461 |
+
"step": 845
|
| 2462 |
+
},
|
| 2463 |
+
{
|
| 2464 |
+
"epoch": 260.92,
|
| 2465 |
+
"eval_accuracy": 0.6958041958041958,
|
| 2466 |
+
"eval_loss": 0.7927840352058411,
|
| 2467 |
+
"eval_runtime": 5.1407,
|
| 2468 |
+
"eval_samples_per_second": 55.634,
|
| 2469 |
+
"eval_steps_per_second": 0.584,
|
| 2470 |
+
"step": 848
|
| 2471 |
+
},
|
| 2472 |
+
{
|
| 2473 |
+
"epoch": 261.54,
|
| 2474 |
+
"grad_norm": 24108.591796875,
|
| 2475 |
+
"learning_rate": 6.349206349206349e-06,
|
| 2476 |
+
"loss": 0.5369,
|
| 2477 |
+
"step": 850
|
| 2478 |
+
},
|
| 2479 |
+
{
|
| 2480 |
+
"epoch": 261.85,
|
| 2481 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2482 |
+
"eval_loss": 0.7919009327888489,
|
| 2483 |
+
"eval_runtime": 3.8577,
|
| 2484 |
+
"eval_samples_per_second": 74.138,
|
| 2485 |
+
"eval_steps_per_second": 0.778,
|
| 2486 |
+
"step": 851
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 262.77,
|
| 2490 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2491 |
+
"eval_loss": 0.791265606880188,
|
| 2492 |
+
"eval_runtime": 4.1966,
|
| 2493 |
+
"eval_samples_per_second": 68.151,
|
| 2494 |
+
"eval_steps_per_second": 0.715,
|
| 2495 |
+
"step": 854
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 264.0,
|
| 2499 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2500 |
+
"eval_loss": 0.7929325699806213,
|
| 2501 |
+
"eval_runtime": 4.063,
|
| 2502 |
+
"eval_samples_per_second": 70.391,
|
| 2503 |
+
"eval_steps_per_second": 0.738,
|
| 2504 |
+
"step": 858
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 264.92,
|
| 2508 |
+
"eval_accuracy": 0.6818181818181818,
|
| 2509 |
+
"eval_loss": 0.7954928278923035,
|
| 2510 |
+
"eval_runtime": 4.3933,
|
| 2511 |
+
"eval_samples_per_second": 65.099,
|
| 2512 |
+
"eval_steps_per_second": 0.683,
|
| 2513 |
+
"step": 861
|
| 2514 |
+
},
|
| 2515 |
+
{
|
| 2516 |
+
"epoch": 265.85,
|
| 2517 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2518 |
+
"eval_loss": 0.7962778210639954,
|
| 2519 |
+
"eval_runtime": 4.4424,
|
| 2520 |
+
"eval_samples_per_second": 64.38,
|
| 2521 |
+
"eval_steps_per_second": 0.675,
|
| 2522 |
+
"step": 864
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 266.77,
|
| 2526 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2527 |
+
"eval_loss": 0.7951834201812744,
|
| 2528 |
+
"eval_runtime": 4.2605,
|
| 2529 |
+
"eval_samples_per_second": 67.128,
|
| 2530 |
+
"eval_steps_per_second": 0.704,
|
| 2531 |
+
"step": 867
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 268.0,
|
| 2535 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2536 |
+
"eval_loss": 0.7936495542526245,
|
| 2537 |
+
"eval_runtime": 4.9467,
|
| 2538 |
+
"eval_samples_per_second": 57.816,
|
| 2539 |
+
"eval_steps_per_second": 0.606,
|
| 2540 |
+
"step": 871
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"epoch": 268.92,
|
| 2544 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2545 |
+
"eval_loss": 0.7928897738456726,
|
| 2546 |
+
"eval_runtime": 4.9925,
|
| 2547 |
+
"eval_samples_per_second": 57.286,
|
| 2548 |
+
"eval_steps_per_second": 0.601,
|
| 2549 |
+
"step": 874
|
| 2550 |
+
},
|
| 2551 |
+
{
|
| 2552 |
+
"epoch": 269.85,
|
| 2553 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2554 |
+
"eval_loss": 0.7933365702629089,
|
| 2555 |
+
"eval_runtime": 4.4133,
|
| 2556 |
+
"eval_samples_per_second": 64.804,
|
| 2557 |
+
"eval_steps_per_second": 0.68,
|
| 2558 |
+
"step": 877
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 270.77,
|
| 2562 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2563 |
+
"eval_loss": 0.7940818071365356,
|
| 2564 |
+
"eval_runtime": 4.0519,
|
| 2565 |
+
"eval_samples_per_second": 70.584,
|
| 2566 |
+
"eval_steps_per_second": 0.74,
|
| 2567 |
+
"step": 880
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 272.0,
|
| 2571 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2572 |
+
"eval_loss": 0.7939559817314148,
|
| 2573 |
+
"eval_runtime": 4.2845,
|
| 2574 |
+
"eval_samples_per_second": 66.753,
|
| 2575 |
+
"eval_steps_per_second": 0.7,
|
| 2576 |
+
"step": 884
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"epoch": 272.92,
|
| 2580 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2581 |
+
"eval_loss": 0.7929409742355347,
|
| 2582 |
+
"eval_runtime": 4.885,
|
| 2583 |
+
"eval_samples_per_second": 58.546,
|
| 2584 |
+
"eval_steps_per_second": 0.614,
|
| 2585 |
+
"step": 887
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 273.85,
|
| 2589 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2590 |
+
"eval_loss": 0.7929646968841553,
|
| 2591 |
+
"eval_runtime": 3.7177,
|
| 2592 |
+
"eval_samples_per_second": 76.929,
|
| 2593 |
+
"eval_steps_per_second": 0.807,
|
| 2594 |
+
"step": 890
|
| 2595 |
+
},
|
| 2596 |
+
{
|
| 2597 |
+
"epoch": 274.77,
|
| 2598 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2599 |
+
"eval_loss": 0.7942932844161987,
|
| 2600 |
+
"eval_runtime": 4.7663,
|
| 2601 |
+
"eval_samples_per_second": 60.004,
|
| 2602 |
+
"eval_steps_per_second": 0.629,
|
| 2603 |
+
"step": 893
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 276.0,
|
| 2607 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2608 |
+
"eval_loss": 0.7943535447120667,
|
| 2609 |
+
"eval_runtime": 4.0017,
|
| 2610 |
+
"eval_samples_per_second": 71.47,
|
| 2611 |
+
"eval_steps_per_second": 0.75,
|
| 2612 |
+
"step": 897
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 276.92,
|
| 2616 |
+
"grad_norm": 30744.533203125,
|
| 2617 |
+
"learning_rate": 4.7619047619047615e-06,
|
| 2618 |
+
"loss": 0.5388,
|
| 2619 |
+
"step": 900
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 276.92,
|
| 2623 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2624 |
+
"eval_loss": 0.7933218479156494,
|
| 2625 |
+
"eval_runtime": 4.3013,
|
| 2626 |
+
"eval_samples_per_second": 66.492,
|
| 2627 |
+
"eval_steps_per_second": 0.697,
|
| 2628 |
+
"step": 900
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 277.85,
|
| 2632 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2633 |
+
"eval_loss": 0.7914408445358276,
|
| 2634 |
+
"eval_runtime": 4.8732,
|
| 2635 |
+
"eval_samples_per_second": 58.689,
|
| 2636 |
+
"eval_steps_per_second": 0.616,
|
| 2637 |
+
"step": 903
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"epoch": 278.77,
|
| 2641 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2642 |
+
"eval_loss": 0.7903594970703125,
|
| 2643 |
+
"eval_runtime": 4.6519,
|
| 2644 |
+
"eval_samples_per_second": 61.48,
|
| 2645 |
+
"eval_steps_per_second": 0.645,
|
| 2646 |
+
"step": 906
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"epoch": 280.0,
|
| 2650 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2651 |
+
"eval_loss": 0.7888299822807312,
|
| 2652 |
+
"eval_runtime": 4.5788,
|
| 2653 |
+
"eval_samples_per_second": 62.462,
|
| 2654 |
+
"eval_steps_per_second": 0.655,
|
| 2655 |
+
"step": 910
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 280.92,
|
| 2659 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2660 |
+
"eval_loss": 0.7900360822677612,
|
| 2661 |
+
"eval_runtime": 4.5971,
|
| 2662 |
+
"eval_samples_per_second": 62.213,
|
| 2663 |
+
"eval_steps_per_second": 0.653,
|
| 2664 |
+
"step": 913
|
| 2665 |
+
},
|
| 2666 |
+
{
|
| 2667 |
+
"epoch": 281.85,
|
| 2668 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2669 |
+
"eval_loss": 0.7905992865562439,
|
| 2670 |
+
"eval_runtime": 4.4545,
|
| 2671 |
+
"eval_samples_per_second": 64.205,
|
| 2672 |
+
"eval_steps_per_second": 0.673,
|
| 2673 |
+
"step": 916
|
| 2674 |
+
},
|
| 2675 |
+
{
|
| 2676 |
+
"epoch": 282.77,
|
| 2677 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2678 |
+
"eval_loss": 0.7911333441734314,
|
| 2679 |
+
"eval_runtime": 4.4274,
|
| 2680 |
+
"eval_samples_per_second": 64.598,
|
| 2681 |
+
"eval_steps_per_second": 0.678,
|
| 2682 |
+
"step": 919
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 284.0,
|
| 2686 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2687 |
+
"eval_loss": 0.7906560897827148,
|
| 2688 |
+
"eval_runtime": 3.9207,
|
| 2689 |
+
"eval_samples_per_second": 72.947,
|
| 2690 |
+
"eval_steps_per_second": 0.765,
|
| 2691 |
+
"step": 923
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 284.92,
|
| 2695 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2696 |
+
"eval_loss": 0.7906984686851501,
|
| 2697 |
+
"eval_runtime": 4.5603,
|
| 2698 |
+
"eval_samples_per_second": 62.715,
|
| 2699 |
+
"eval_steps_per_second": 0.658,
|
| 2700 |
+
"step": 926
|
| 2701 |
+
},
|
| 2702 |
+
{
|
| 2703 |
+
"epoch": 285.85,
|
| 2704 |
+
"eval_accuracy": 0.6818181818181818,
|
| 2705 |
+
"eval_loss": 0.7905350923538208,
|
| 2706 |
+
"eval_runtime": 4.8134,
|
| 2707 |
+
"eval_samples_per_second": 59.418,
|
| 2708 |
+
"eval_steps_per_second": 0.623,
|
| 2709 |
+
"step": 929
|
| 2710 |
+
},
|
| 2711 |
+
{
|
| 2712 |
+
"epoch": 286.77,
|
| 2713 |
+
"eval_accuracy": 0.6818181818181818,
|
| 2714 |
+
"eval_loss": 0.7899833917617798,
|
| 2715 |
+
"eval_runtime": 4.0697,
|
| 2716 |
+
"eval_samples_per_second": 70.275,
|
| 2717 |
+
"eval_steps_per_second": 0.737,
|
| 2718 |
+
"step": 932
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 288.0,
|
| 2722 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2723 |
+
"eval_loss": 0.7901102304458618,
|
| 2724 |
+
"eval_runtime": 4.0126,
|
| 2725 |
+
"eval_samples_per_second": 71.276,
|
| 2726 |
+
"eval_steps_per_second": 0.748,
|
| 2727 |
+
"step": 936
|
| 2728 |
+
},
|
| 2729 |
+
{
|
| 2730 |
+
"epoch": 288.92,
|
| 2731 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2732 |
+
"eval_loss": 0.7902336120605469,
|
| 2733 |
+
"eval_runtime": 3.8328,
|
| 2734 |
+
"eval_samples_per_second": 74.619,
|
| 2735 |
+
"eval_steps_per_second": 0.783,
|
| 2736 |
+
"step": 939
|
| 2737 |
+
},
|
| 2738 |
+
{
|
| 2739 |
+
"epoch": 289.85,
|
| 2740 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2741 |
+
"eval_loss": 0.7909765839576721,
|
| 2742 |
+
"eval_runtime": 3.9497,
|
| 2743 |
+
"eval_samples_per_second": 72.411,
|
| 2744 |
+
"eval_steps_per_second": 0.76,
|
| 2745 |
+
"step": 942
|
| 2746 |
+
},
|
| 2747 |
+
{
|
| 2748 |
+
"epoch": 290.77,
|
| 2749 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2750 |
+
"eval_loss": 0.7913976907730103,
|
| 2751 |
+
"eval_runtime": 4.7881,
|
| 2752 |
+
"eval_samples_per_second": 59.731,
|
| 2753 |
+
"eval_steps_per_second": 0.627,
|
| 2754 |
+
"step": 945
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 292.0,
|
| 2758 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2759 |
+
"eval_loss": 0.7919970750808716,
|
| 2760 |
+
"eval_runtime": 4.0436,
|
| 2761 |
+
"eval_samples_per_second": 70.729,
|
| 2762 |
+
"eval_steps_per_second": 0.742,
|
| 2763 |
+
"step": 949
|
| 2764 |
+
},
|
| 2765 |
+
{
|
| 2766 |
+
"epoch": 292.31,
|
| 2767 |
+
"grad_norm": 41198.3515625,
|
| 2768 |
+
"learning_rate": 3.1746031746031746e-06,
|
| 2769 |
+
"loss": 0.5261,
|
| 2770 |
+
"step": 950
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"epoch": 292.92,
|
| 2774 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2775 |
+
"eval_loss": 0.7927921414375305,
|
| 2776 |
+
"eval_runtime": 3.9219,
|
| 2777 |
+
"eval_samples_per_second": 72.923,
|
| 2778 |
+
"eval_steps_per_second": 0.765,
|
| 2779 |
+
"step": 952
|
| 2780 |
+
},
|
| 2781 |
+
{
|
| 2782 |
+
"epoch": 293.85,
|
| 2783 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2784 |
+
"eval_loss": 0.793153703212738,
|
| 2785 |
+
"eval_runtime": 4.3649,
|
| 2786 |
+
"eval_samples_per_second": 65.522,
|
| 2787 |
+
"eval_steps_per_second": 0.687,
|
| 2788 |
+
"step": 955
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 294.77,
|
| 2792 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2793 |
+
"eval_loss": 0.7925400733947754,
|
| 2794 |
+
"eval_runtime": 4.2064,
|
| 2795 |
+
"eval_samples_per_second": 67.992,
|
| 2796 |
+
"eval_steps_per_second": 0.713,
|
| 2797 |
+
"step": 958
|
| 2798 |
+
},
|
| 2799 |
+
{
|
| 2800 |
+
"epoch": 296.0,
|
| 2801 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2802 |
+
"eval_loss": 0.7922278046607971,
|
| 2803 |
+
"eval_runtime": 4.03,
|
| 2804 |
+
"eval_samples_per_second": 70.968,
|
| 2805 |
+
"eval_steps_per_second": 0.744,
|
| 2806 |
+
"step": 962
|
| 2807 |
+
},
|
| 2808 |
+
{
|
| 2809 |
+
"epoch": 296.92,
|
| 2810 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2811 |
+
"eval_loss": 0.7919090986251831,
|
| 2812 |
+
"eval_runtime": 4.4889,
|
| 2813 |
+
"eval_samples_per_second": 63.713,
|
| 2814 |
+
"eval_steps_per_second": 0.668,
|
| 2815 |
+
"step": 965
|
| 2816 |
+
},
|
| 2817 |
+
{
|
| 2818 |
+
"epoch": 297.85,
|
| 2819 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2820 |
+
"eval_loss": 0.7922202348709106,
|
| 2821 |
+
"eval_runtime": 4.3742,
|
| 2822 |
+
"eval_samples_per_second": 65.383,
|
| 2823 |
+
"eval_steps_per_second": 0.686,
|
| 2824 |
+
"step": 968
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 298.77,
|
| 2828 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2829 |
+
"eval_loss": 0.7921380400657654,
|
| 2830 |
+
"eval_runtime": 4.27,
|
| 2831 |
+
"eval_samples_per_second": 66.979,
|
| 2832 |
+
"eval_steps_per_second": 0.703,
|
| 2833 |
+
"step": 971
|
| 2834 |
+
},
|
| 2835 |
+
{
|
| 2836 |
+
"epoch": 300.0,
|
| 2837 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2838 |
+
"eval_loss": 0.7912278175354004,
|
| 2839 |
+
"eval_runtime": 4.209,
|
| 2840 |
+
"eval_samples_per_second": 67.95,
|
| 2841 |
+
"eval_steps_per_second": 0.713,
|
| 2842 |
+
"step": 975
|
| 2843 |
+
},
|
| 2844 |
+
{
|
| 2845 |
+
"epoch": 300.92,
|
| 2846 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2847 |
+
"eval_loss": 0.7907286882400513,
|
| 2848 |
+
"eval_runtime": 4.5975,
|
| 2849 |
+
"eval_samples_per_second": 62.208,
|
| 2850 |
+
"eval_steps_per_second": 0.653,
|
| 2851 |
+
"step": 978
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 301.85,
|
| 2855 |
+
"eval_accuracy": 0.6853146853146853,
|
| 2856 |
+
"eval_loss": 0.7895866632461548,
|
| 2857 |
+
"eval_runtime": 4.0629,
|
| 2858 |
+
"eval_samples_per_second": 70.394,
|
| 2859 |
+
"eval_steps_per_second": 0.738,
|
| 2860 |
+
"step": 981
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"epoch": 302.77,
|
| 2864 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2865 |
+
"eval_loss": 0.7885376811027527,
|
| 2866 |
+
"eval_runtime": 4.0112,
|
| 2867 |
+
"eval_samples_per_second": 71.301,
|
| 2868 |
+
"eval_steps_per_second": 0.748,
|
| 2869 |
+
"step": 984
|
| 2870 |
+
},
|
| 2871 |
+
{
|
| 2872 |
+
"epoch": 304.0,
|
| 2873 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2874 |
+
"eval_loss": 0.7877256870269775,
|
| 2875 |
+
"eval_runtime": 4.4199,
|
| 2876 |
+
"eval_samples_per_second": 64.708,
|
| 2877 |
+
"eval_steps_per_second": 0.679,
|
| 2878 |
+
"step": 988
|
| 2879 |
+
},
|
| 2880 |
+
{
|
| 2881 |
+
"epoch": 304.92,
|
| 2882 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2883 |
+
"eval_loss": 0.7874112725257874,
|
| 2884 |
+
"eval_runtime": 4.0366,
|
| 2885 |
+
"eval_samples_per_second": 70.852,
|
| 2886 |
+
"eval_steps_per_second": 0.743,
|
| 2887 |
+
"step": 991
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 305.85,
|
| 2891 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2892 |
+
"eval_loss": 0.7876228094100952,
|
| 2893 |
+
"eval_runtime": 4.3519,
|
| 2894 |
+
"eval_samples_per_second": 65.718,
|
| 2895 |
+
"eval_steps_per_second": 0.689,
|
| 2896 |
+
"step": 994
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 306.77,
|
| 2900 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2901 |
+
"eval_loss": 0.7879106402397156,
|
| 2902 |
+
"eval_runtime": 5.3443,
|
| 2903 |
+
"eval_samples_per_second": 53.515,
|
| 2904 |
+
"eval_steps_per_second": 0.561,
|
| 2905 |
+
"step": 997
|
| 2906 |
+
},
|
| 2907 |
+
{
|
| 2908 |
+
"epoch": 307.69,
|
| 2909 |
+
"grad_norm": 31167.6875,
|
| 2910 |
+
"learning_rate": 1.5873015873015873e-06,
|
| 2911 |
+
"loss": 0.5188,
|
| 2912 |
+
"step": 1000
|
| 2913 |
+
},
|
| 2914 |
+
{
|
| 2915 |
+
"epoch": 308.0,
|
| 2916 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2917 |
+
"eval_loss": 0.7883804440498352,
|
| 2918 |
+
"eval_runtime": 4.1413,
|
| 2919 |
+
"eval_samples_per_second": 69.06,
|
| 2920 |
+
"eval_steps_per_second": 0.724,
|
| 2921 |
+
"step": 1001
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 308.92,
|
| 2925 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2926 |
+
"eval_loss": 0.7886692881584167,
|
| 2927 |
+
"eval_runtime": 4.049,
|
| 2928 |
+
"eval_samples_per_second": 70.634,
|
| 2929 |
+
"eval_steps_per_second": 0.741,
|
| 2930 |
+
"step": 1004
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 309.85,
|
| 2934 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2935 |
+
"eval_loss": 0.7890444397926331,
|
| 2936 |
+
"eval_runtime": 4.612,
|
| 2937 |
+
"eval_samples_per_second": 62.012,
|
| 2938 |
+
"eval_steps_per_second": 0.65,
|
| 2939 |
+
"step": 1007
|
| 2940 |
+
},
|
| 2941 |
+
{
|
| 2942 |
+
"epoch": 310.77,
|
| 2943 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2944 |
+
"eval_loss": 0.7894096970558167,
|
| 2945 |
+
"eval_runtime": 3.8027,
|
| 2946 |
+
"eval_samples_per_second": 75.209,
|
| 2947 |
+
"eval_steps_per_second": 0.789,
|
| 2948 |
+
"step": 1010
|
| 2949 |
+
},
|
| 2950 |
+
{
|
| 2951 |
+
"epoch": 312.0,
|
| 2952 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2953 |
+
"eval_loss": 0.7899323105812073,
|
| 2954 |
+
"eval_runtime": 4.3345,
|
| 2955 |
+
"eval_samples_per_second": 65.983,
|
| 2956 |
+
"eval_steps_per_second": 0.692,
|
| 2957 |
+
"step": 1014
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 312.92,
|
| 2961 |
+
"eval_accuracy": 0.6888111888111889,
|
| 2962 |
+
"eval_loss": 0.7903538346290588,
|
| 2963 |
+
"eval_runtime": 4.5846,
|
| 2964 |
+
"eval_samples_per_second": 62.383,
|
| 2965 |
+
"eval_steps_per_second": 0.654,
|
| 2966 |
+
"step": 1017
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 313.85,
|
| 2970 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2971 |
+
"eval_loss": 0.7907257080078125,
|
| 2972 |
+
"eval_runtime": 4.136,
|
| 2973 |
+
"eval_samples_per_second": 69.148,
|
| 2974 |
+
"eval_steps_per_second": 0.725,
|
| 2975 |
+
"step": 1020
|
| 2976 |
+
},
|
| 2977 |
+
{
|
| 2978 |
+
"epoch": 314.77,
|
| 2979 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2980 |
+
"eval_loss": 0.790963888168335,
|
| 2981 |
+
"eval_runtime": 4.2526,
|
| 2982 |
+
"eval_samples_per_second": 67.252,
|
| 2983 |
+
"eval_steps_per_second": 0.705,
|
| 2984 |
+
"step": 1023
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 316.0,
|
| 2988 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2989 |
+
"eval_loss": 0.7912085056304932,
|
| 2990 |
+
"eval_runtime": 4.1188,
|
| 2991 |
+
"eval_samples_per_second": 69.437,
|
| 2992 |
+
"eval_steps_per_second": 0.728,
|
| 2993 |
+
"step": 1027
|
| 2994 |
+
},
|
| 2995 |
+
{
|
| 2996 |
+
"epoch": 316.92,
|
| 2997 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2998 |
+
"eval_loss": 0.7911705374717712,
|
| 2999 |
+
"eval_runtime": 4.1524,
|
| 3000 |
+
"eval_samples_per_second": 68.876,
|
| 3001 |
+
"eval_steps_per_second": 0.722,
|
| 3002 |
+
"step": 1030
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 317.85,
|
| 3006 |
+
"eval_accuracy": 0.6923076923076923,
|
| 3007 |
+
"eval_loss": 0.7911967039108276,
|
| 3008 |
+
"eval_runtime": 3.9058,
|
| 3009 |
+
"eval_samples_per_second": 73.225,
|
| 3010 |
+
"eval_steps_per_second": 0.768,
|
| 3011 |
+
"step": 1033
|
| 3012 |
+
},
|
| 3013 |
+
{
|
| 3014 |
+
"epoch": 318.77,
|
| 3015 |
+
"eval_accuracy": 0.6923076923076923,
|
| 3016 |
+
"eval_loss": 0.7912610173225403,
|
| 3017 |
+
"eval_runtime": 4.6095,
|
| 3018 |
+
"eval_samples_per_second": 62.046,
|
| 3019 |
+
"eval_steps_per_second": 0.651,
|
| 3020 |
+
"step": 1036
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 320.0,
|
| 3024 |
+
"eval_accuracy": 0.6923076923076923,
|
| 3025 |
+
"eval_loss": 0.7912730574607849,
|
| 3026 |
+
"eval_runtime": 5.5705,
|
| 3027 |
+
"eval_samples_per_second": 51.342,
|
| 3028 |
+
"eval_steps_per_second": 0.539,
|
| 3029 |
+
"step": 1040
|
| 3030 |
+
},
|
| 3031 |
+
{
|
| 3032 |
+
"epoch": 320.92,
|
| 3033 |
+
"eval_accuracy": 0.6923076923076923,
|
| 3034 |
+
"eval_loss": 0.7911974787712097,
|
| 3035 |
+
"eval_runtime": 4.9154,
|
| 3036 |
+
"eval_samples_per_second": 58.185,
|
| 3037 |
+
"eval_steps_per_second": 0.61,
|
| 3038 |
+
"step": 1043
|
| 3039 |
+
},
|
| 3040 |
+
{
|
| 3041 |
+
"epoch": 321.85,
|
| 3042 |
+
"eval_accuracy": 0.6923076923076923,
|
| 3043 |
+
"eval_loss": 0.7911575436592102,
|
| 3044 |
+
"eval_runtime": 4.8387,
|
| 3045 |
+
"eval_samples_per_second": 59.107,
|
| 3046 |
+
"eval_steps_per_second": 0.62,
|
| 3047 |
+
"step": 1046
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 322.77,
|
| 3051 |
+
"eval_accuracy": 0.6923076923076923,
|
| 3052 |
+
"eval_loss": 0.7911355495452881,
|
| 3053 |
+
"eval_runtime": 4.1368,
|
| 3054 |
+
"eval_samples_per_second": 69.135,
|
| 3055 |
+
"eval_steps_per_second": 0.725,
|
| 3056 |
+
"step": 1049
|
| 3057 |
+
},
|
| 3058 |
+
{
|
| 3059 |
+
"epoch": 323.08,
|
| 3060 |
+
"grad_norm": 53824.44140625,
|
| 3061 |
+
"learning_rate": 0.0,
|
| 3062 |
+
"loss": 0.5194,
|
| 3063 |
+
"step": 1050
|
| 3064 |
+
},
|
| 3065 |
+
{
|
| 3066 |
+
"epoch": 323.08,
|
| 3067 |
+
"eval_accuracy": 0.6923076923076923,
|
| 3068 |
+
"eval_loss": 0.7911302447319031,
|
| 3069 |
+
"eval_runtime": 4.2304,
|
| 3070 |
+
"eval_samples_per_second": 67.606,
|
| 3071 |
+
"eval_steps_per_second": 0.709,
|
| 3072 |
+
"step": 1050
|
| 3073 |
+
},
|
| 3074 |
+
{
|
| 3075 |
+
"epoch": 323.08,
|
| 3076 |
+
"step": 1050,
|
| 3077 |
+
"total_flos": 4.380490432252032e+18,
|
| 3078 |
+
"train_loss": 0.8143934268043155,
|
| 3079 |
+
"train_runtime": 4784.9132,
|
| 3080 |
+
"train_samples_per_second": 113.231,
|
| 3081 |
+
"train_steps_per_second": 0.219
|
| 3082 |
+
}
|
| 3083 |
+
],
|
| 3084 |
+
"logging_steps": 50,
|
| 3085 |
+
"max_steps": 1050,
|
| 3086 |
+
"num_input_tokens_seen": 0,
|
| 3087 |
+
"num_train_epochs": 350,
|
| 3088 |
+
"save_steps": 500,
|
| 3089 |
+
"total_flos": 4.380490432252032e+18,
|
| 3090 |
+
"train_batch_size": 128,
|
| 3091 |
+
"trial_name": null,
|
| 3092 |
+
"trial_params": null
|
| 3093 |
+
}
|