End of training
Browse files- .gitattributes +1 -0
- README.md +19 -2
- all_results.json +10 -0
- eval_results.json +10 -0
- trainer_state.json +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -1,9 +1,23 @@
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
model-index:
|
| 5 |
- name: lua-mistral-1L-mini
|
| 6 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -11,7 +25,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 11 |
|
| 12 |
# lua-mistral-1L-mini
|
| 13 |
|
| 14 |
-
This model is a fine-tuned version of [](https://huggingface.co/) on
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
## Model description
|
| 17 |
|
|
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- nilq/small-lua-stack
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: lua-mistral-1L-mini
|
| 10 |
+
results:
|
| 11 |
+
- task:
|
| 12 |
+
name: Causal Language Modeling
|
| 13 |
+
type: text-generation
|
| 14 |
+
dataset:
|
| 15 |
+
name: nilq/small-lua-stack
|
| 16 |
+
type: nilq/small-lua-stack
|
| 17 |
+
metrics:
|
| 18 |
+
- name: Accuracy
|
| 19 |
+
type: accuracy
|
| 20 |
+
value: 0.4208221928842605
|
| 21 |
---
|
| 22 |
|
| 23 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 25 |
|
| 26 |
# lua-mistral-1L-mini
|
| 27 |
|
| 28 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the nilq/small-lua-stack dataset.
|
| 29 |
+
It achieves the following results on the evaluation set:
|
| 30 |
+
- Loss: 3.0245
|
| 31 |
+
- Accuracy: 0.4208
|
| 32 |
|
| 33 |
## Model description
|
| 34 |
|
all_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.4208221928842605,
|
| 4 |
+
"eval_loss": 3.024461269378662,
|
| 5 |
+
"eval_runtime": 1245.0525,
|
| 6 |
+
"eval_samples": 570721,
|
| 7 |
+
"eval_samples_per_second": 458.391,
|
| 8 |
+
"eval_steps_per_second": 57.3,
|
| 9 |
+
"perplexity": 20.582913078211558
|
| 10 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.4208221928842605,
|
| 4 |
+
"eval_loss": 3.024461269378662,
|
| 5 |
+
"eval_runtime": 1245.0525,
|
| 6 |
+
"eval_samples": 570721,
|
| 7 |
+
"eval_samples_per_second": 458.391,
|
| 8 |
+
"eval_steps_per_second": 57.3,
|
| 9 |
+
"perplexity": 20.582913078211558
|
| 10 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b92bd8df649264d37ee75c8a29c83c6e8a6cdcf3d031681e970f0c3f68ae8846
|
| 3 |
+
size 37132265
|