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: 0.4788
 - Rewards/chosen: -2.6215
-- Rewards/rejected: -3.9183
-- Rewards/accuracies: 0.7475
-- Rewards/margins: 1.2968
-- Logps/rejected: -636.4029
-- Logps/chosen: -526.7561
-- Logits/rejected: -1.0296
-- Logits/chosen: -1.1658
+- Rewards/rejected: -3.9187
+- Rewards/accuracies: 0.7465
+- Rewards/margins: 1.2972
+- Logps/rejected: -636.4379
+- Logps/chosen: -526.7527
+- Logits/rejected: -1.0290
+- Logits/chosen: -1.1652
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -1.1651915311813354,
+    "eval_logits/rejected": -1.0289729833602905,
+    "eval_logps/chosen": -526.7527465820312,
+    "eval_logps/rejected": -636.4378662109375,
+    "eval_loss": 0.47883233428001404,
+    "eval_rewards/accuracies": 0.7465000152587891,
+    "eval_rewards/chosen": -2.6215085983276367,
+    "eval_rewards/margins": 1.2971659898757935,
+    "eval_rewards/rejected": -3.9186742305755615,
+    "eval_runtime": 1597.3624,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 1.252,
+    "eval_steps_per_second": 0.157,
     "total_flos": 0.0,
     "train_loss": 0.517807064771465,
     "train_runtime": 164396.369,

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": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -1.1651915311813354,
+    "eval_logits/rejected": -1.0289729833602905,
+    "eval_logps/chosen": -526.7527465820312,
+    "eval_logps/rejected": -636.4378662109375,
+    "eval_loss": 0.47883233428001404,
+    "eval_rewards/accuracies": 0.7465000152587891,
+    "eval_rewards/chosen": -2.6215085983276367,
+    "eval_rewards/margins": 1.2971659898757935,
+    "eval_rewards/rejected": -3.9186742305755615,
+    "eval_runtime": 1597.3624,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 1.252,
+    "eval_steps_per_second": 0.157
+}

runs/Oct21_18-48-09_CZC40873G5/events.out.tfevents.1729699092.CZC40873G5.1073085.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d874bd82f7865d074882620849e1e0e405fbcf92b920f4475879b525df4830b
+size 828