End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
base_model: liswei/OpenELM-1_1B-zh-base
|
| 3 |
tags:
|
| 4 |
- llama-factory
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
| 7 |
- name: OpenELM-1_1B-zh-cp
|
|
@@ -13,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# OpenELM-1_1B-zh-cp
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [liswei/OpenELM-1_1B-zh-base](https://huggingface.co/liswei/OpenELM-1_1B-zh-base) on
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 2 |
base_model: liswei/OpenELM-1_1B-zh-base
|
| 3 |
tags:
|
| 4 |
- llama-factory
|
| 5 |
+
- full
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
- name: OpenELM-1_1B-zh-cp
|
|
|
|
| 14 |
|
| 15 |
# OpenELM-1_1B-zh-cp
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [liswei/OpenELM-1_1B-zh-base](https://huggingface.co/liswei/OpenELM-1_1B-zh-base) on the zhtw-news-and-articles-2B dataset.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 5.404563590201999e+18,
|
| 4 |
+
"train_loss": 3.236852196415412,
|
| 5 |
+
"train_runtime": 292848.6684,
|
| 6 |
+
"train_samples_per_second": 0.74,
|
| 7 |
+
"train_steps_per_second": 0.046
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 5.404563590201999e+18,
|
| 4 |
+
"train_loss": 3.236852196415412,
|
| 5 |
+
"train_runtime": 292848.6684,
|
| 6 |
+
"train_samples_per_second": 0.74,
|
| 7 |
+
"train_steps_per_second": 0.046
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_loss.png
ADDED
|