End of training

README.md

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

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9975470155355682,
+    "eval_logits/chosen": 3.4378178119659424,
+    "eval_logits/rejected": 3.4508590698242188,
+    "eval_logps/chosen": -546.7545166015625,
+    "eval_logps/rejected": -452.174072265625,
+    "eval_loss": 0.6908814907073975,
+    "eval_rewards/accuracies": 0.625,
+    "eval_rewards/chosen": 0.005891335662454367,
+    "eval_rewards/margins": 0.004598129540681839,
+    "eval_rewards/rejected": 0.0012932071695104241,
+    "eval_runtime": 6.9308,
+    "eval_samples": 80,
+    "eval_samples_per_second": 11.543,
+    "eval_steps_per_second": 2.886,
     "total_flos": 0.0,
     "train_loss": 0.6921662518235504,
     "train_runtime": 665.2967,

config.json

@@ -0,0 +1,40 @@
+{
+  "_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,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "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 +1,16 @@
+{
+    "epoch": 0.9975470155355682,
+    "eval_logits/chosen": 3.4378178119659424,
+    "eval_logits/rejected": 3.4508590698242188,
+    "eval_logps/chosen": -546.7545166015625,
+    "eval_logps/rejected": -452.174072265625,
+    "eval_loss": 0.6908814907073975,
+    "eval_rewards/accuracies": 0.625,
+    "eval_rewards/chosen": 0.005891335662454367,
+    "eval_rewards/margins": 0.004598129540681839,
+    "eval_rewards/rejected": 0.0012932071695104241,
+    "eval_runtime": 6.9308,
+    "eval_samples": 80,
+    "eval_samples_per_second": 11.543,
+    "eval_steps_per_second": 2.886
+}