End of training

README.md

@@ -1,8 +1,11 @@
 ---
 base_model: mistralai/Mistral-7B-v0.1
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 library_name: peft
 license: apache-2.0
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
@@ -16,17 +19,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-qlora
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-qlora](https://huggingface.co/alignment-handbook/zephyr-7b-sft-qlora) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.4945
-- Rewards/chosen: -2.5678
-- Rewards/rejected: -3.6349
+- Rewards/chosen: -2.5530
+- Rewards/rejected: -3.6159
 - Rewards/accuracies: 0.7778
-- Rewards/margins: 1.0671
-- Logps/rejected: -608.1346
-- Logps/chosen: -521.7063
-- Logits/rejected: -0.9901
-- Logits/chosen: -1.1024
+- Rewards/margins: 1.0629
+- Logps/rejected: -606.2373
+- Logps/chosen: -520.2218
+- Logits/rejected: -0.9908
+- Logits/chosen: -1.1030
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9997382884061764,
+    "eval_logits/chosen": -1.103013515472412,
+    "eval_logits/rejected": -0.990799069404602,
+    "eval_logps/chosen": -520.2218017578125,
+    "eval_logps/rejected": -606.2373046875,
+    "eval_loss": 0.4944952428340912,
+    "eval_rewards/accuracies": 0.7777777910232544,
+    "eval_rewards/chosen": -2.5530030727386475,
+    "eval_rewards/margins": 1.0629230737686157,
+    "eval_rewards/rejected": -3.6159262657165527,
+    "eval_runtime": 318.8167,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 6.273,
+    "eval_steps_per_second": 0.198,
     "total_flos": 0.0,
     "train_loss": 0.5319095570379527,
     "train_runtime": 23762.0752,

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "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_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9997382884061764,
+    "eval_logits/chosen": -1.103013515472412,
+    "eval_logits/rejected": -0.990799069404602,
+    "eval_logps/chosen": -520.2218017578125,
+    "eval_logps/rejected": -606.2373046875,
+    "eval_loss": 0.4944952428340912,
+    "eval_rewards/accuracies": 0.7777777910232544,
+    "eval_rewards/chosen": -2.5530030727386475,
+    "eval_rewards/margins": 1.0629230737686157,
+    "eval_rewards/rejected": -3.6159262657165527,
+    "eval_runtime": 318.8167,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 6.273,
+    "eval_steps_per_second": 0.198
+}

runs/Sep12_19-06-53_qa-a100-005.crc.nd.edu/events.out.tfevents.1726207078.qa-a100-005.crc.nd.edu.304505.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e330eebb07ae54ca9b6005da35a0840ad55c18f162a4d1592cdd80f63086ce62
+size 828