Training in progress, epoch 2

README.md

@@ -1,6 +1,5 @@
 ---
-base_model:
-- google/gemma-2b-it
+base_model: google/gemma-2-9b-it
 datasets:
 - generator
 library_name: peft
@@ -10,16 +9,16 @@ tags:
 - sft
 - generated_from_trainer
 model-index:
-- name: gemma-2b-it-lora-magicoder
+- name: gemma-2-9b-it-lora-magicoder
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# gemma-2b-it-lora-magicoder
+# gemma-2-9b-it-lora-magicoder
 
-This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on the alvarobartt/Magicoder-OAI dataset.
+This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) on the alvarobartt/Magicoder-OAI dataset.
 
 ## Model description
 
@@ -43,10 +42,10 @@ The following hyperparameters were used during training:
 - eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 2
+- num_devices: 4
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 16
-- total_eval_batch_size: 16
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97d5e52b5668436977b4675922d9a5540ecdfc875c8488911bbe650cec148de2
+oid sha256:9c66af4715b1ada16a73c930bee05be9361c8f37d63d20cefea0d2bc9930245a
 size 41582088