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: 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 |
# 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 |
+
- roneneldan/TinyStories
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
model-index:
|
9 |
- name: mistral-1L-mini
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Causal Language Modeling
|
13 |
+
type: text-generation
|
14 |
+
dataset:
|
15 |
+
name: roneneldan/TinyStories
|
16 |
+
type: roneneldan/TinyStories
|
17 |
+
metrics:
|
18 |
+
- name: Accuracy
|
19 |
+
type: accuracy
|
20 |
+
value: 0.4719044781443692
|
21 |
---
|
22 |
|
23 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
25 |
|
26 |
# mistral-1L-mini
|
27 |
|
28 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the roneneldan/TinyStories dataset.
|
29 |
+
It achieves the following results on the evaluation set:
|
30 |
+
- Loss: 2.3829
|
31 |
+
- Accuracy: 0.4719
|
32 |
|
33 |
## Model description
|
34 |
|
all_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.4719044781443692,
|
4 |
+
"eval_loss": 2.38291335105896,
|
5 |
+
"eval_runtime": 30.1857,
|
6 |
+
"eval_samples": 19348,
|
7 |
+
"eval_samples_per_second": 640.965,
|
8 |
+
"eval_steps_per_second": 80.137,
|
9 |
+
"perplexity": 10.836427237618361
|
10 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.4719044781443692,
|
4 |
+
"eval_loss": 2.38291335105896,
|
5 |
+
"eval_runtime": 30.1857,
|
6 |
+
"eval_samples": 19348,
|
7 |
+
"eval_samples_per_second": 640.965,
|
8 |
+
"eval_steps_per_second": 80.137,
|
9 |
+
"perplexity": 10.836427237618361
|
10 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01b90749ddb752f41a804b61eb5bf8c02f43f220447839990137df4f3d5296bb
|
3 |
+
size 14490121
|