Update README.md

README.md

@@ -30,7 +30,7 @@ model-index:
 
 <p><h1> speechless-code-mistral-7b-v1.0  </h1></p>
 
-Use the following dataset to fine-tune llm_agents/Mistral-7B-v0.1 in order to improve the model's reasoning and planning abilities.
+Use the following dataset to fine-tune mistralai/Mistral-7B-v0.1 in order to improve the model's reasoning and planning abilities.
 
 Total 201,981 samples.
 - jondurbin/airoboros-2.2: Filter categories related to coding, reasoning and planning. 23,462 samples.
@@ -62,23 +62,23 @@ Total 201,981 samples.
 | grandient_accumulation_steps | 32 |
 | bf16 | True |
 
-A100-40G x 4
+A40-48G x 2
 
 | | |
 |------ | ------ |
 | epoch                    |                2.0 |
-| etrain_loss               |             0.4708 |
-| etrain_runtime            | 12:12:53.64 |
-| etrain_samples_per_second |              9.002 |
-| etrain_steps_per_second   |              0.07 |
-| eeval_loss               |     0.4851 |
-| eeval_runtime            | 0:00:10.31 |
-| eeval_samples_per_second |      19.385 |
-| eeval_steps_per_second   |      4.846 |
+| etrain_loss               |             0.5 |
+| etrain_runtime            | 1 day, 10:25:26.77 |
+| etrain_samples_per_second |              3.194 |
+| etrain_steps_per_second   |              0.025 |
+| eeval_loss               |     0.5146 |
+| eeval_runtime            | 0:00:25.04 |
+| eeval_samples_per_second |      7.985 |
+| eeval_steps_per_second   |       |
 
 | Metric | Value |
 | --- | --- |
-| humaneval-python | 46.341|
+| humaneval-python ||
 
 [Big Code Models Leaderboard](https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard)