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: []
@@ -16,15 +22,15 @@ 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: 0.5159
-- Rewards/chosen: -4.0804
-- Rewards/rejected: -5.8780
-- Rewards/accuracies: 0.7475
-- Rewards/margins: 1.7976
-- Logps/rejected: -832.3694
-- Logps/chosen: -672.6617
+- Loss: 0.5156
+- Rewards/chosen: -4.0806
+- Rewards/rejected: -5.8791
+- Rewards/accuracies: 0.7495
+- Rewards/margins: 1.7985
+- Logps/rejected: -832.4777
+- Logps/chosen: -672.6758
 - Logits/rejected: -1.1337
 - Logits/chosen: -1.4991
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -1.4990795850753784,
+    "eval_logits/rejected": -1.133651852607727,
+    "eval_logps/chosen": -672.6758422851562,
+    "eval_logps/rejected": -832.4777221679688,
+    "eval_loss": 0.5156374573707581,
+    "eval_rewards/accuracies": 0.7494999766349792,
+    "eval_rewards/chosen": -4.080562114715576,
+    "eval_rewards/margins": 1.7984988689422607,
+    "eval_rewards/rejected": -5.879061698913574,
+    "eval_runtime": 1082.4235,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 1.848,
+    "eval_steps_per_second": 1.848,
     "train_loss": 0.5464587531257954,
     "train_runtime": 239691.3187,
     "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": -1.4990795850753784,
+    "eval_logits/rejected": -1.133651852607727,
+    "eval_logps/chosen": -672.6758422851562,
+    "eval_logps/rejected": -832.4777221679688,
+    "eval_loss": 0.5156374573707581,
+    "eval_rewards/accuracies": 0.7494999766349792,
+    "eval_rewards/chosen": -4.080562114715576,
+    "eval_rewards/margins": 1.7984988689422607,
+    "eval_rewards/rejected": -5.879061698913574,
+    "eval_runtime": 1082.4235,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 1.848,
+    "eval_steps_per_second": 1.848
+}

runs/Mar14_09-04-38_mashina/events.out.tfevents.1710644357.mashina.40189.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1069a76c84c14df062515d8b862fec0780821db80985fdb2bdc6d11d0e475c87
+size 828