End of training

README.md

@@ -29,18 +29,18 @@ 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/tdva-etsit-etsit-universidad-politecnica-de-madrid/huggingface/runs/xt8b8r98) 
+[<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/tdva-etsit-etsit-universidad-politecnica-de-madrid/huggingface/runs/xx90d4xp) 
 
 
 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).
 
 ### Framework versions
 
-- TRL: 0.13.0
-- Transformers: 4.47.1
-- Pytorch: 2.5.1+cu121
-- Datasets: 3.2.0
-- Tokenizers: 0.21.0
+- TRL: 0.16.1
+- Transformers: 4.51.1
+- Pytorch: 2.6.0+cu124
+- Datasets: 3.5.0
+- Tokenizers: 0.21.1
 
 ## Citations
 

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "Bipul8765/SmolLM2-FT-MyDataset",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -27,7 +26,7 @@
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.51.1",
   "use_cache": false,
   "vocab_size": 49152
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 2,
-  "transformers_version": "4.47.1"
+  "transformers_version": "4.51.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e51623cec056e3dea0591898efc26bb1fe93f0bf3df111787fdcbefdcdfd899a
+oid sha256:22c240c86f5f39b017382fe34df765b359abf2717448ef52dd48225c78c80d27
 size 538090408

runs/Apr15_11-15-36_794992d02057/events.out.tfevents.1744716197.794992d02057.316.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b0200023bf5579e5e52b9526272db5806049e2320a41f16a2394c617c7d653c
+size 142459

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58e730b53db66e1b42ff915b2163758b8548e5ef33922820a04f9f3bc9f40d59
-size 6264
+oid sha256:7b0d07b9d78b9da84ff7c173486953a7ac569e2f222eaa04754d3821addbdf33
+size 6200