End of training

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: HuggingFaceTB/SmolLM2-135M
+base_model: HuggingFaceTB/SmolLM2-360M
 library_name: transformers
 model_name: SmolLM2-FT-MyDataset
 tags:
@@ -13,7 +13,7 @@ licence: license
 
 # Model Card for SmolLM2-FT-MyDataset
 
-This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M).
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-360M](https://huggingface.co/HuggingFaceTB/SmolLM2-360M).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -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/goutham_city/huggingface/runs/rcio3rw9) 
+[<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/goutham_city/huggingface/runs/l4yyyqt7) 
 
 
 This model was trained with SFT.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "HuggingFaceTB/SmolLM2-135M",
+  "_name_or_path": "HuggingFaceTB/SmolLM2-360M",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -9,16 +9,16 @@
   "eos_token_id": 2,
   "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 576,
-  "initializer_range": 0.041666666666666664,
-  "intermediate_size": 1536,
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
   "is_llama_config": true,
   "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 9,
-  "num_hidden_layers": 30,
-  "num_key_value_heads": 3,
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
   "pad_token_id": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c40220acb710b334bb2bade89e9fe6bdcbd7a1e99fad1e5a7637e6487b4f0263
-size 538090408
+oid sha256:1938eb01384ea35f9cb817ac4e110d3f4d8dd22ff964c74ca3b41012a53878d0
+size 1447317080

runs/Jan01_13-54-51_315e11a7424e/events.out.tfevents.1735739697.315e11a7424e.1369.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a5c04f99c296ccb3c8680944443bce8495380d1f4bb5ed2a7516cfd4f99347
+size 5502

runs/Jan01_14-02-01_315e11a7424e/events.out.tfevents.1735740126.315e11a7424e.3894.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ba47dbb03e7f67a84bb7b166ee6e017693b6b24f5a49acc5c4b2e16eeeb475
+size 32372

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5572d0816fdcf734dd43770c0367dc2ebdc3c4897db7e94bd2597bee7aac439
+oid sha256:09b5e7574e177bdf55476c5db3762481fac76e879a5e741546f98f791ace1bca
 size 5624