Update README.md

README.md

@@ -24,7 +24,7 @@ model-index:
     metrics:
     - name: pass@1
       type: pass@1
-      value: 0.0
+      value: 51.829
       verified: false
 ---
 
@@ -40,45 +40,11 @@ Total 201,981 samples.
 - TokenBender/python_eval_instruct_51k: “python” in output .40,309 samples
 - Spider: 8,659 samples
 
-
-| | |
-|------ | ------ |
-| lr | 2e-4 |
-| lr_scheduler_type | cosine |
-| weight_decay | 0.0 |
-| optim | paged_adamw_8bit |
-| flash_attention | True |
-| rerope | False |
-| max_new_tokens | 4096 |
-| num_train_epochs | 2 |
-| bits | 4 |
-| lora_r | 64 |
-| lora_alpha | 16 |
-| lora_dropout | 0.05 |
-| double_quant | True |
-| quant_type | nf4 |
-| dataset_format | airoboros |
-| mini_batch_size | 2 |
-| grandient_accumulation_steps | 32 |
-| bf16 | True |
-
-A100-40G x 4
-
-| | |
-|------ | ------ |
-| 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 |
+## HumanEval
 
 | Metric | Value |
 | --- | --- |
-| humaneval-python | |
+| humaneval-python | 51.829 |
 
 [Big Code Models Leaderboard](https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard)
 
@@ -94,6 +60,9 @@ CodeLlama-13B-Python: 42.89
 
 CodeLlama-13B: 35.07
 
+
+## LM-Evaluation-Harness
+
 [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
 | Metric | Value |
 | --- | --- |
@@ -104,3 +73,40 @@ CodeLlama-13B: 35.07
 | Average |  |
 
 
+## Parameters
+
+| | |
+|------ | ------ |
+| lr | 2e-4 |
+| lr_scheduler_type | cosine |
+| weight_decay | 0.0 |
+| optim | paged_adamw_8bit |
+| flash_attention | True |
+| rerope | False |
+| max_new_tokens | 4096 |
+| num_train_epochs | 2 |
+| bits | 4 |
+| lora_r | 64 |
+| lora_alpha | 16 |
+| lora_dropout | 0.05 |
+| double_quant | True |
+| quant_type | nf4 |
+| dataset_format | airoboros |
+| mini_batch_size | 2 |
+| grandient_accumulation_steps | 32 |
+| bf16 | True |
+
+A800-80G x 2
+
+| | |
+|------ | ------ |
+| epoch                    |                2.0 |
+| etrain_loss               |             0.5891 |
+| etrain_runtime            | 19:24:49.43 |
+| etrain_samples_per_second |              5.664 |
+| etrain_steps_per_second   |              0.044 |
+| eeval_loss               |     0.5872 |
+| eeval_runtime            | 0:00:15.59 |
+| eeval_samples_per_second |      12.822 |
+| eeval_steps_per_second   |      6.411 |
+