End of training
Browse files- README.md +19 -2
- all_results.json +6 -5
- eval_results.json +6 -5
- trainer_state.json +2 -2
README.md
CHANGED
|
@@ -1,9 +1,23 @@
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
model-index:
|
| 5 |
- name: mistral-2L-tiny
|
| 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-2L-tiny
|
| 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-2L-tiny
|
| 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: 0.6174228881132772
|
| 21 |
---
|
| 22 |
|
| 23 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 25 |
|
| 26 |
# mistral-2L-tiny
|
| 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: 1.4866
|
| 31 |
+
- Accuracy: 0.6174
|
| 32 |
|
| 33 |
## Model description
|
| 34 |
|
all_results.json
CHANGED
|
@@ -1,9 +1,10 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"
|
| 4 |
-
"
|
|
|
|
| 5 |
"eval_samples": 19348,
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"perplexity":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.6174228881132772,
|
| 4 |
+
"eval_loss": 1.4865760803222656,
|
| 5 |
+
"eval_runtime": 25.5787,
|
| 6 |
"eval_samples": 19348,
|
| 7 |
+
"eval_samples_per_second": 756.411,
|
| 8 |
+
"eval_steps_per_second": 94.571,
|
| 9 |
+
"perplexity": 4.421929239222526
|
| 10 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,10 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"
|
| 4 |
-
"
|
|
|
|
| 5 |
"eval_samples": 19348,
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"perplexity":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.6174228881132772,
|
| 4 |
+
"eval_loss": 1.4865760803222656,
|
| 5 |
+
"eval_runtime": 25.5787,
|
| 6 |
"eval_samples": 19348,
|
| 7 |
+
"eval_samples_per_second": 756.411,
|
| 8 |
+
"eval_steps_per_second": 94.571,
|
| 9 |
+
"perplexity": 4.421929239222526
|
| 10 |
}
|
trainer_state.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c1c0cfcc5fd730dd9a9e33e960f8de9d2d43e7ddb436de8a836ce1e9c62e701
|
| 3 |
+
size 14524352
|