End of training
Browse files- README.md +14 -2
- all_results.json +4 -3
- eval_results.json +6 -6
README.md
CHANGED
|
@@ -4,11 +4,23 @@ license: llama3.2
|
|
| 4 |
base_model: meta-llama/Llama-3.2-1B
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: test
|
| 11 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -16,7 +28,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# test
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 2.6568
|
| 22 |
- Accuracy: 0.5231
|
|
|
|
| 4 |
base_model: meta-llama/Llama-3.2-1B
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- LabHC/bias_in_bios
|
| 9 |
metrics:
|
| 10 |
- accuracy
|
| 11 |
model-index:
|
| 12 |
- name: test
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
name: Causal Language Modeling
|
| 16 |
+
type: text-generation
|
| 17 |
+
dataset:
|
| 18 |
+
name: LabHC/bias_in_bios
|
| 19 |
+
type: LabHC/bias_in_bios
|
| 20 |
+
metrics:
|
| 21 |
+
- name: Accuracy
|
| 22 |
+
type: accuracy
|
| 23 |
+
value: 0.5230967495584936
|
| 24 |
---
|
| 25 |
|
| 26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 28 |
|
| 29 |
# test
|
| 30 |
|
| 31 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on the LabHC/bias_in_bios dataset.
|
| 32 |
It achieves the following results on the evaluation set:
|
| 33 |
- Loss: 2.6568
|
| 34 |
- Accuracy: 0.5231
|
all_results.json
CHANGED
|
@@ -2,9 +2,10 @@
|
|
| 2 |
"epoch": 1.0,
|
| 3 |
"eval_accuracy": 0.5230967495584936,
|
| 4 |
"eval_loss": 2.656780958175659,
|
| 5 |
-
"eval_runtime": 59.
|
| 6 |
-
"
|
| 7 |
-
"
|
|
|
|
| 8 |
"perplexity": 14.250342737440896,
|
| 9 |
"total_flos": 1695049253388288.0,
|
| 10 |
"train_loss": 2.676516035912742,
|
|
|
|
| 2 |
"epoch": 1.0,
|
| 3 |
"eval_accuracy": 0.5230967495584936,
|
| 4 |
"eval_loss": 2.656780958175659,
|
| 5 |
+
"eval_runtime": 59.8291,
|
| 6 |
+
"eval_samples": 5125,
|
| 7 |
+
"eval_samples_per_second": 85.661,
|
| 8 |
+
"eval_steps_per_second": 10.714,
|
| 9 |
"perplexity": 14.250342737440896,
|
| 10 |
"total_flos": 1695049253388288.0,
|
| 11 |
"train_loss": 2.676516035912742,
|
eval_results.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 2.
|
| 5 |
-
"eval_runtime": 59.
|
| 6 |
"eval_samples": 5125,
|
| 7 |
-
"eval_samples_per_second": 85.
|
| 8 |
-
"eval_steps_per_second": 10.
|
| 9 |
-
"perplexity": 14.
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.5230967495584936,
|
| 4 |
+
"eval_loss": 2.656780958175659,
|
| 5 |
+
"eval_runtime": 59.8291,
|
| 6 |
"eval_samples": 5125,
|
| 7 |
+
"eval_samples_per_second": 85.661,
|
| 8 |
+
"eval_steps_per_second": 10.714,
|
| 9 |
+
"perplexity": 14.250342737440896
|
| 10 |
}
|