End of training

README.md

@@ -1,9 +1,12 @@
 ---
 base_model: HuggingFaceTB/SmolLM2-135M-Instruct
+datasets:
+- HuggingFaceH4/ultrachat_200k
 library_name: transformers
 model_name: smollm2-135m-sft-qlora-test
 tags:
 - generated_from_trainer
+- alignment-handbook
 - trl
 - sft
 licence: license
@@ -11,7 +14,7 @@ licence: license
 
 # Model Card for smollm2-135m-sft-qlora-test
 
-This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct).
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct) on the [['HuggingFaceH4/ultrachat_200k']](https://huggingface.co/datasets/['HuggingFaceH4/ultrachat_200k']) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,4 +1,9 @@
 {
+    "eval_loss": 1.6983668804168701,
+    "eval_runtime": 14.6688,
+    "eval_samples": 232,
+    "eval_samples_per_second": 15.816,
+    "eval_steps_per_second": 1.977,
     "total_flos": 2381129238708224.0,
     "train_loss": 0.0,
     "train_runtime": 0.6875,

config.json

@@ -0,0 +1,55 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "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,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 49152
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "eval_loss": 1.6983668804168701,
+    "eval_runtime": 14.6688,
+    "eval_samples": 232,
+    "eval_samples_per_second": 15.816,
+    "eval_steps_per_second": 1.977
+}