End of training

README.md

@@ -2,9 +2,12 @@
 library_name: peft
 base_model: HuggingFaceTB/smollm2-1.7B-8k-mix7-ep2-v2
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: smollm2-1.7B-8k-mix7-ep2-v2-qlora-r16-a16-lr3e4-mix1-dpo
   results: []
@@ -15,17 +18,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # smollm2-1.7B-8k-mix7-ep2-v2-qlora-r16-a16-lr3e4-mix1-dpo
 
-This model is a fine-tuned version of [HuggingFaceTB/smollm2-1.7B-8k-mix7-ep2-v2](https://huggingface.co/HuggingFaceTB/smollm2-1.7B-8k-mix7-ep2-v2) on an unknown dataset.
+This model is a fine-tuned version of [gabrielmbmb/smollm2-1.7B-8k-mix7-ep2-v2-qlora-r16-a16-lr3e4-mix1](https://huggingface.co/gabrielmbmb/smollm2-1.7B-8k-mix7-ep2-v2-qlora-r16-a16-lr3e4-mix1) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5157
-- Rewards/chosen: -4.3456
-- Rewards/rejected: -5.3593
-- Rewards/accuracies: 0.7695
-- Rewards/margins: 1.0137
-- Logps/rejected: -842.1772
-- Logps/chosen: -747.2964
-- Logits/rejected: -1.2109
-- Logits/chosen: -1.1871
+- Loss: 0.5156
+- Rewards/chosen: -4.3948
+- Rewards/rejected: -5.4305
+- Rewards/accuracies: 0.7656
+- Rewards/margins: 1.0357
+- Logps/rejected: -849.2994
+- Logps/chosen: -752.2209
+- Logits/rejected: -1.2614
+- Logits/chosen: -1.2341
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9984301412872841,
+    "eval_logits/chosen": -1.234063982963562,
+    "eval_logits/rejected": -1.2614085674285889,
+    "eval_logps/chosen": -752.220947265625,
+    "eval_logps/rejected": -849.2994384765625,
+    "eval_loss": 0.51555335521698,
+    "eval_rewards/accuracies": 0.765625,
+    "eval_rewards/chosen": -4.394815921783447,
+    "eval_rewards/margins": 1.0356953144073486,
+    "eval_rewards/rejected": -5.430510997772217,
+    "eval_runtime": 33.965,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 58.884,
+    "eval_steps_per_second": 0.942,
     "total_flos": 0.0,
     "train_loss": 0.5423707397229016,
     "train_runtime": 2137.6738,

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "HuggingFaceTB/smollm2-1.7B-8k-mix7-ep2-v2",
+  "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": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "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_scaling": null,
+  "rope_theta": 130000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": true,
+  "vocab_size": 49152
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9984301412872841,
+    "eval_logits/chosen": -1.234063982963562,
+    "eval_logits/rejected": -1.2614085674285889,
+    "eval_logps/chosen": -752.220947265625,
+    "eval_logps/rejected": -849.2994384765625,
+    "eval_loss": 0.51555335521698,
+    "eval_rewards/accuracies": 0.765625,
+    "eval_rewards/chosen": -4.394815921783447,
+    "eval_rewards/margins": 1.0356953144073486,
+    "eval_rewards/rejected": -5.430510997772217,
+    "eval_runtime": 33.965,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 58.884,
+    "eval_steps_per_second": 0.942
+}

runs/Nov05_11-27-51_ip-26-0-167-175/events.out.tfevents.1730808720.ip-26-0-167-175.3215185.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e71f7643d17defc27a00307a59b700fbd2ee36f8f8770427aed90de57fc87c9
+size 828