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/carenhan89-university-of-melbourne/huggingface/runs/x42q5k0f) 
+[<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/drcarenhan/huggingface/runs/fb80wq3e) 
 
 
 This model was trained with SFT.
 
 ### 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: 4.51.3
+- Pytorch: 2.6.0+cu124
+- Datasets: 3.5.0
+- Tokenizers: 0.21.1
 
 ## Citations
 

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "HuggingFaceTB/SmolLM2-135M",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -27,7 +26,7 @@
   "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.51.3",
   "use_cache": true,
   "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": "4.51.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c40220acb710b334bb2bade89e9fe6bdcbd7a1e99fad1e5a7637e6487b4f0263
+oid sha256:c0a9d4de9424b2d01a2644b503b36348f3d0b86d2042eac9fedcab393cd2e29e
 size 538090408

runs/Apr24_22-41-39_973b74cf76e2/events.out.tfevents.1745534507.973b74cf76e2.1541.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945491adeffcfc84c0d180089aa1c6e879fcb3d4314798cd43e5449bda56f0af
+size 44264

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1024,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc88af7c877643d1e7bf0d7705d5701937f2d3651a5204b2f891ad81720ee531
+oid sha256:048724bdd18a05e1f1642a2b2ebf6c88ef96a87e3d4a9e4c794728c36b3e9383
 size 5624