[INFO|2026-05-08 20:51:45] configuration_utils.py:670 >> loading configuration file config.json from cache at /home/sapbot/.cache/huggingface/hub/models--unsloth--SmolLM2-360M-Instruct/snapshots/7c6bf9a2faef35209646cd7f1569fae2b2394a00/config.json
[INFO|2026-05-08 20:51:45] configuration_utils.py:742 >> Model config LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "silu",
  "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": 15,
  "num_hidden_layers": 32,
  "num_key_value_heads": 5,
  "pad_token_id": 49152,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_interleaved": false,
  "rope_parameters": {
    "rope_theta": 100000,
    "rope_type": "default"
  },
  "tie_word_embeddings": true,
  "transformers.js_config": {
    "kv_cache_dtype": {
      "fp16": "float16",
      "q4f16": "float16"
    }
  },
  "transformers_version": "5.2.0",
  "use_cache": true,
  "vocab_size": 49153
}

[INFO|2026-05-08 20:51:47] configuration_utils.py:670 >> loading configuration file config.json from cache at /home/sapbot/.cache/huggingface/hub/models--unsloth--SmolLM2-360M-Instruct/snapshots/7c6bf9a2faef35209646cd7f1569fae2b2394a00/config.json
[INFO|2026-05-08 20:51:47] configuration_utils.py:742 >> Model config LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "silu",
  "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": 15,
  "num_hidden_layers": 32,
  "num_key_value_heads": 5,
  "pad_token_id": 49152,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_interleaved": false,
  "rope_parameters": {
    "rope_theta": 100000,
    "rope_type": "default"
  },
  "tie_word_embeddings": true,
  "transformers.js_config": {
    "kv_cache_dtype": {
      "fp16": "float16",
      "q4f16": "float16"
    }
  },
  "transformers_version": "5.2.0",
  "use_cache": true,
  "vocab_size": 49153
}

[INFO|2026-05-08 20:51:47] configuration_utils.py:670 >> loading configuration file config.json from cache at /home/sapbot/.cache/huggingface/hub/models--unsloth--SmolLM2-360M-Instruct/snapshots/7c6bf9a2faef35209646cd7f1569fae2b2394a00/config.json
[INFO|2026-05-08 20:51:47] configuration_utils.py:742 >> Model config LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "silu",
  "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": 15,
  "num_hidden_layers": 32,
  "num_key_value_heads": 5,
  "pad_token_id": 49152,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_interleaved": false,
  "rope_parameters": {
    "rope_theta": 100000,
    "rope_type": "default"
  },
  "tie_word_embeddings": true,
  "transformers.js_config": {
    "kv_cache_dtype": {
      "fp16": "float16",
      "q4f16": "float16"
    }
  },
  "transformers_version": "5.2.0",
  "use_cache": true,
  "vocab_size": 49153
}

[INFO|2026-05-08 20:51:49] logging.py:144 >> Add <|im_end|> to stop words.
[INFO|2026-05-08 20:51:49] logging.py:144 >> Loading dataset sapbot/gemma-3n-4b-it-423x...
[INFO|2026-05-08 20:51:51] configuration_utils.py:670 >> loading configuration file config.json from cache at /home/sapbot/.cache/huggingface/hub/models--unsloth--SmolLM2-360M-Instruct/snapshots/7c6bf9a2faef35209646cd7f1569fae2b2394a00/config.json
[INFO|2026-05-08 20:51:51] configuration_utils.py:742 >> Model config LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "silu",
  "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": 15,
  "num_hidden_layers": 32,
  "num_key_value_heads": 5,
  "pad_token_id": 49152,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_interleaved": false,
  "rope_parameters": {
    "rope_theta": 100000,
    "rope_type": "default"
  },
  "tie_word_embeddings": true,
  "transformers.js_config": {
    "kv_cache_dtype": {
      "fp16": "float16",
      "q4f16": "float16"
    }
  },
  "transformers_version": "5.2.0",
  "use_cache": true,
  "vocab_size": 49153
}

[INFO|2026-05-08 20:51:51] logging.py:144 >> KV cache is disabled during training.
[INFO|2026-05-08 20:51:52] modeling_utils.py:710 >> loading weights file model.safetensors from cache at /home/sapbot/.cache/huggingface/hub/models--unsloth--SmolLM2-360M-Instruct/snapshots/7c6bf9a2faef35209646cd7f1569fae2b2394a00/model.safetensors
[INFO|2026-05-08 20:51:52] modeling_utils.py:779 >> Will use dtype=torch.bfloat16 as defined in model's config object
[INFO|2026-05-08 20:51:52] configuration_utils.py:1014 >> Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2,
  "output_attentions": false,
  "output_hidden_states": false,
  "pad_token_id": 49152,
  "use_cache": false
}

[INFO|2026-05-08 20:51:53] configuration_utils.py:967 >> loading configuration file generation_config.json from cache at /home/sapbot/.cache/huggingface/hub/models--unsloth--SmolLM2-360M-Instruct/snapshots/7c6bf9a2faef35209646cd7f1569fae2b2394a00/generation_config.json
[INFO|2026-05-08 20:51:53] configuration_utils.py:1014 >> Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2,
  "max_length": 8192,
  "pad_token_id": 49152
}

[INFO|2026-05-08 20:51:54] dynamic_module_utils.py:406 >> Could not locate the custom_generate/generate.py inside unsloth/SmolLM2-360M-Instruct.
[INFO|2026-05-08 20:51:54] logging.py:144 >> Gradient checkpointing enabled.
[INFO|2026-05-08 20:51:54] logging.py:144 >> Using torch SDPA for faster training and inference.
[INFO|2026-05-08 20:51:54] logging.py:144 >> Upcasting trainable params to float32.
[INFO|2026-05-08 20:51:54] logging.py:144 >> Fine-tuning method: LoRA
[INFO|2026-05-08 20:51:54] logging.py:144 >> Found linear modules: o_proj,q_proj,down_proj,v_proj,k_proj,up_proj,gate_proj
[INFO|2026-05-08 20:51:56] logging.py:144 >> trainable params: 4,341,760 || all params: 366,163,840 || trainable%: 1.1857
[INFO|2026-05-08 20:51:56] trainer.py:1587 >> ***** Running training *****
[INFO|2026-05-08 20:51:56] trainer.py:1588 >>   Num examples = 423
[INFO|2026-05-08 20:51:56] trainer.py:1589 >>   Num Epochs = 3
[INFO|2026-05-08 20:51:56] trainer.py:1590 >>   Instantaneous batch size per device = 2
[INFO|2026-05-08 20:51:56] trainer.py:1593 >>   Total train batch size (w. parallel, distributed & accumulation) = 16
[INFO|2026-05-08 20:51:56] trainer.py:1594 >>   Gradient Accumulation steps = 8
[INFO|2026-05-08 20:51:56] trainer.py:1595 >>   Total optimization steps = 81
[INFO|2026-05-08 20:51:56] trainer.py:1596 >>   Number of trainable parameters = 4,341,760
[INFO|2026-05-08 20:53:35] logging.py:144 >> {'loss': 4.6997, 'learning_rate': 4.9981e-05, 'epoch': 0.19, 'throughput': 933.89}
[INFO|2026-05-08 20:55:17] logging.py:144 >> {'loss': 10.7092, 'learning_rate': 4.9981e-05, 'epoch': 0.38, 'throughput': 954.01}
[INFO|2026-05-08 20:56:59] logging.py:144 >> {'loss': 11.7926, 'learning_rate': 4.9981e-05, 'epoch': 0.57, 'throughput': 958.84}
[INFO|2026-05-08 20:58:39] logging.py:144 >> {'loss': 13.5184, 'learning_rate': 4.9925e-05, 'epoch': 0.75, 'throughput': 956.42}
[INFO|2026-05-08 21:00:25] logging.py:144 >> {'loss': 20.1784, 'learning_rate': 4.9925e-05, 'epoch': 0.94, 'throughput': 959.60}
[INFO|2026-05-08 21:02:09] logging.py:144 >> {'loss': 7.2012, 'learning_rate': 4.9831e-05, 'epoch': 1.11, 'throughput': 953.38}
[INFO|2026-05-08 21:03:58] logging.py:144 >> {'loss': 16.0000, 'learning_rate': 4.9831e-05, 'epoch': 1.30, 'throughput': 952.43}
[INFO|2026-05-08 21:05:50] logging.py:144 >> {'loss': 9.6828, 'learning_rate': 4.9831e-05, 'epoch': 1.49, 'throughput': 951.69}
[INFO|2026-05-08 21:07:46] logging.py:144 >> {'loss': 6.1018, 'learning_rate': 4.9831e-05, 'epoch': 1.68, 'throughput': 950.28}
[INFO|2026-05-08 21:09:18] logging.py:144 >> {'loss': 10.2955, 'learning_rate': 4.9700e-05, 'epoch': 1.87, 'throughput': 953.07}
[INFO|2026-05-08 21:11:03] logging.py:144 >> {'loss': 4.0894, 'learning_rate': 4.9326e-05, 'epoch': 2.04, 'throughput': 951.55}
[INFO|2026-05-08 21:12:46] logging.py:144 >> {'loss': 26.6340, 'learning_rate': 4.9326e-05, 'epoch': 2.23, 'throughput': 952.42}
[INFO|2026-05-08 21:14:35] logging.py:144 >> {'loss': 5.8759, 'learning_rate': 4.9084e-05, 'epoch': 2.42, 'throughput': 950.59}
[INFO|2026-05-08 21:16:32] logging.py:144 >> {'loss': 4.9436, 'learning_rate': 4.9084e-05, 'epoch': 2.60, 'throughput': 947.64}
[INFO|2026-05-08 21:18:21] logging.py:144 >> {'loss': 11.3494, 'learning_rate': 4.9084e-05, 'epoch': 2.79, 'throughput': 948.32}
[INFO|2026-05-08 21:19:45] logging.py:144 >> {'loss': 3.3956, 'learning_rate': 4.8492e-05, 'epoch': 2.98, 'throughput': 950.90}
[INFO|2026-05-08 21:19:53] trainer.py:3797 >> Saving model checkpoint to saves/SmolLM-360M-Instruct/lora/train_2026-05-08-20-46-08/checkpoint-81
[INFO|2026-05-08 21:19:54] configuration_utils.py:670 >> loading configuration file config.json from cache at /home/sapbot/.cache/huggingface/hub/models--unsloth--SmolLM2-360M-Instruct/snapshots/7c6bf9a2faef35209646cd7f1569fae2b2394a00/config.json
[INFO|2026-05-08 21:19:54] configuration_utils.py:742 >> Model config LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "silu",
  "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": 15,
  "num_hidden_layers": 32,
  "num_key_value_heads": 5,
  "pad_token_id": 49152,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_interleaved": false,
  "rope_parameters": {
    "rope_theta": 100000,
    "rope_type": "default"
  },
  "tie_word_embeddings": true,
  "transformers.js_config": {
    "kv_cache_dtype": {
      "fp16": "float16",
      "q4f16": "float16"
    }
  },
  "transformers_version": "5.2.0",
  "use_cache": true,
  "vocab_size": 49153
}

[INFO|2026-05-08 21:19:54] tokenization_utils_base.py:3224 >> chat template saved in saves/SmolLM-360M-Instruct/lora/train_2026-05-08-20-46-08/checkpoint-81/chat_template.jinja
[INFO|2026-05-08 21:19:54] tokenization_utils_base.py:2078 >> tokenizer config file saved in saves/SmolLM-360M-Instruct/lora/train_2026-05-08-20-46-08/checkpoint-81/tokenizer_config.json
[INFO|2026-05-08 21:19:54] trainer.py:1863 >> 

Training completed. Do not forget to share your model on huggingface.co/models =)


[INFO|2026-05-08 21:19:54] trainer.py:3797 >> Saving model checkpoint to saves/SmolLM-360M-Instruct/lora/train_2026-05-08-20-46-08
[INFO|2026-05-08 21:19:55] configuration_utils.py:670 >> loading configuration file config.json from cache at /home/sapbot/.cache/huggingface/hub/models--unsloth--SmolLM2-360M-Instruct/snapshots/7c6bf9a2faef35209646cd7f1569fae2b2394a00/config.json
[INFO|2026-05-08 21:19:55] configuration_utils.py:742 >> Model config LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 64,
  "hidden_act": "silu",
  "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": 15,
  "num_hidden_layers": 32,
  "num_key_value_heads": 5,
  "pad_token_id": 49152,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_interleaved": false,
  "rope_parameters": {
    "rope_theta": 100000,
    "rope_type": "default"
  },
  "tie_word_embeddings": true,
  "transformers.js_config": {
    "kv_cache_dtype": {
      "fp16": "float16",
      "q4f16": "float16"
    }
  },
  "transformers_version": "5.2.0",
  "use_cache": true,
  "vocab_size": 49153
}

[INFO|2026-05-08 21:19:55] tokenization_utils_base.py:3224 >> chat template saved in saves/SmolLM-360M-Instruct/lora/train_2026-05-08-20-46-08/chat_template.jinja
[INFO|2026-05-08 21:19:55] tokenization_utils_base.py:2078 >> tokenizer config file saved in saves/SmolLM-360M-Instruct/lora/train_2026-05-08-20-46-08/tokenizer_config.json
[WARNING|2026-05-08 21:19:55] logging.py:149 >> No metric eval_loss to plot.
[WARNING|2026-05-08 21:19:55] logging.py:149 >> No metric eval_accuracy to plot.
[INFO|2026-05-08 21:19:55] modelcard.py:266 >> Dropping the following result as it does not have all the necessary fields:
{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}