End of training

README.md

@@ -2,10 +2,16 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
+- trl
+- dpo
+- generated_from_trainer
 - trl
 - dpo
 - generated_from_trainer
 base_model: mistralai/Mistral-7B-v0.1
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: zephyr-7b-dpo-qlora
   results: []
@@ -16,17 +22,17 @@ 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 the None 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: 0.4921
+- Loss: 0.4920
 - Rewards/chosen: -2.5098
-- Rewards/rejected: -3.5900
-- Rewards/accuracies: 0.7550
-- Rewards/margins: 1.0803
-- Logps/rejected: -600.2638
-- Logps/chosen: -516.2831
+- Rewards/rejected: -3.5905
+- Rewards/accuracies: 0.7560
+- Rewards/margins: 1.0807
+- Logps/rejected: -600.3103
+- Logps/chosen: -516.2818
 - Logits/rejected: 2.5098
-- Logits/chosen: 2.2971
+- Logits/chosen: 2.2972
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": 2.2971765995025635,
+    "eval_logits/rejected": 2.509765625,
+    "eval_logps/chosen": -516.2817993164062,
+    "eval_logps/rejected": -600.310302734375,
+    "eval_loss": 0.4919675290584564,
+    "eval_rewards/accuracies": 0.7559999823570251,
+    "eval_rewards/chosen": -2.5097556114196777,
+    "eval_rewards/margins": 1.0807288885116577,
+    "eval_rewards/rejected": -3.590484380722046,
+    "eval_runtime": 449.3054,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.451,
+    "eval_steps_per_second": 0.278,
     "train_loss": 0.528951391499704,
     "train_runtime": 37787.7404,
     "train_samples": 61135,

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "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_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": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": 2.2971765995025635,
+    "eval_logits/rejected": 2.509765625,
+    "eval_logps/chosen": -516.2817993164062,
+    "eval_logps/rejected": -600.310302734375,
+    "eval_loss": 0.4919675290584564,
+    "eval_rewards/accuracies": 0.7559999823570251,
+    "eval_rewards/chosen": -2.5097556114196777,
+    "eval_rewards/margins": 1.0807288885116577,
+    "eval_rewards/rejected": -3.590484380722046,
+    "eval_runtime": 449.3054,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.451,
+    "eval_steps_per_second": 0.278
+}

runs/Mar07_10-37-47_ale-dpo-1-0-0/events.out.tfevents.1709846645.ale-dpo-1-0-0.1134.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1c391730d9bd5ec37b05c71a93210760587fdd6ca385a28eef9ba593ec7bbc7
+size 828