Upload 7 files
Browse files- loss_epoch.png +0 -0
- loss_iteration.png +0 -0
- model_state.safetensors +3 -0
- sample_length_distribution.png +0 -0
- training_report.txt +14 -0
- vocab.txt +0 -0
- vocab_frequency.png +0 -0
loss_epoch.png
ADDED
|
loss_iteration.png
ADDED
|
model_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a1ce34b7f7657be506fa879c2972bda8518bef014d34b18a1f6c50dbff0d3e3
|
| 3 |
+
size 150614776
|
sample_length_distribution.png
ADDED
|
training_report.txt
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Transformer Decoder-Only Model Training Report
|
| 2 |
+
===========================================
|
| 3 |
+
|
| 4 |
+
Training Start Time: Wed Mar 26 20:17:27 2025
|
| 5 |
+
Total Training Time: 191.49 seconds
|
| 6 |
+
Total Epochs: 1
|
| 7 |
+
Total Iterations: 547
|
| 8 |
+
Batch Size: 64
|
| 9 |
+
Learning Rate: 0.0001
|
| 10 |
+
Max Sequence Length: 128
|
| 11 |
+
Dataset Limit: 35000 rows
|
| 12 |
+
|
| 13 |
+
Epoch-wise Average Loss Values:
|
| 14 |
+
Epoch 1: 8.3391
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vocab_frequency.png
ADDED
|