Training in progress, step 60

README.md

@@ -15,8 +15,8 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/pesi/SmolLM2-135M-Instruct-TaiwanChat_CLOUD/runs/z29x47we)
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/pesi/SmolLM2-135M-Instruct-TaiwanChat_CLOUD/runs/z29x47we)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/pesi/SmolLM2-135M-Instruct-TaiwanChat_CLOUD/runs/3n6j9mm5)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/pesi/SmolLM2-135M-Instruct-TaiwanChat_CLOUD/runs/3n6j9mm5)
 # SmolLM2-135M-Instruct-TaiwanChat
 
 This model is a fine-tuned version of [unsloth/SmolLM2-135M-Instruct](https://huggingface.co/unsloth/SmolLM2-135M-Instruct) on an unknown dataset.

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/SmolLM2-135M-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:144ab0069994067311f6d6e928dc4ab81f91ab746e0f7f9655d5f05d1fe092d5
+size 19593064

tokenizer_config.json

@@ -165,7 +165,7 @@
   "extra_special_tokens": {},
   "model_max_length": 8192,
   "pad_token": "<|PAD_TOKEN|>",
-  "padding_side": "left",
+  "padding_side": "right",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "�",
   "vocab_size": 49152