End of training

README.md

@@ -29,7 +29,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/da-qc/SmolLM2-FT-DPO-Medicina_es/runs/7mmqyef0) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/da-qc/SmolLM2-FT-DPO-Medicina_es/runs/83qcp7eu) 
 
 
 This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:214c95e4ae621d6f9901aeb94163d169b808fca1754143934f031ccd7fa4bc10
+oid sha256:51849ec9a5c2330790f2ec8d17d692cc02fd68f75d88fee6eb4193bd421ac870
 size 538090408

tokenizer_config.json

@@ -147,7 +147,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
-  "model_max_length": 2048,
+  "model_max_length": 8192,
   "pad_token": "<|im_end|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71934bc2d866aef1aed23e1b7858abad8c3b29938a434db693a16ab486b2402c
-size 6200
+oid sha256:2a5c5d019da9d4aaab8d10f06f472436e915314e6c42f062a286678d83516d74
+size 6264