End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gemma-2-2b-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 generator dataset.
+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.
 
 ## Model description
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/gemma-2-9b-it",
+  "_name_or_path": "google/gemma-2-2b-it",
   "architectures": [
     "Gemma2ForCausalLM"
   ],
@@ -8,25 +8,27 @@
   "attn_logit_softcapping": 50.0,
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
-  "eos_token_id": 1,
+  "eos_token_id": [
+    1,
+    107
+  ],
   "final_logit_softcapping": 30.0,
   "head_dim": 256,
   "hidden_act": "gelu_pytorch_tanh",
   "hidden_activation": "gelu_pytorch_tanh",
-  "hidden_size": 3584,
+  "hidden_size": 2304,
   "initializer_range": 0.02,
-  "intermediate_size": 14336,
+  "intermediate_size": 9216,
   "max_position_embeddings": 8192,
   "model_type": "gemma2",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 42,
-  "num_key_value_heads": 8,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 4,
   "pad_token_id": 0,
   "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
   "rope_theta": 10000.0,
   "sliding_window": 4096,
-  "sliding_window_size": 4096,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
   "use_cache": true,