End of training

README.md

@@ -1,8 +1,11 @@
 ---
 base_model: alignment-handbook/zephyr-7b-sft-full
+datasets:
+- generation/UF6k
 library_name: peft
 license: apache-2.0
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
@@ -16,22 +19,22 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-dpop-qlora-uf-oursuf6k-5e-7
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the generation/UF6k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6903
-- Positive Losses: 0.0373
+- Positive Losses: 0.0369
 - Dpo Losses: 0.6851
-- Rewards/chosen: 0.0599
-- Rewards/rejected: 0.0432
-- Rewards/accuracies: 0.6160
-- Rewards/margins: 0.0167
-- Rewards/margins Max: 0.0930
-- Rewards/margins Min: -0.0511
-- Rewards/margins Std: 0.0481
-- Logps/rejected: -254.2623
-- Logps/chosen: -278.6050
-- Logits/rejected: -2.7602
-- Logits/chosen: -2.7988
+- Rewards/chosen: 0.0601
+- Rewards/rejected: 0.0433
+- Rewards/accuracies: 0.6090
+- Rewards/margins: 0.0168
+- Rewards/margins Max: 0.0933
+- Rewards/margins Min: -0.0510
+- Rewards/margins Std: 0.0482
+- Logps/rejected: -254.2451
+- Logps/chosen: -278.5801
+- Logits/rejected: -2.7575
+- Logits/chosen: -2.7964
 
 ## Model description
 

all_results.json

@@ -1,5 +1,23 @@
 {
     "epoch": 1.0,
+    "eval_dpo_losses": 0.6851017475128174,
+    "eval_logits/chosen": -2.796370506286621,
+    "eval_logits/rejected": -2.7574775218963623,
+    "eval_logps/chosen": -278.58013916015625,
+    "eval_logps/rejected": -254.24514770507812,
+    "eval_loss": 0.6902781128883362,
+    "eval_positive_losses": 0.036926720291376114,
+    "eval_rewards/accuracies": 0.609000027179718,
+    "eval_rewards/chosen": 0.060132984071969986,
+    "eval_rewards/margins": 0.016795208677649498,
+    "eval_rewards/margins_max": 0.09327653795480728,
+    "eval_rewards/margins_min": -0.05095779150724411,
+    "eval_rewards/margins_std": 0.0482446551322937,
+    "eval_rewards/rejected": 0.04333777725696564,
+    "eval_runtime": 428.2812,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.67,
+    "eval_steps_per_second": 0.292,
     "train_loss": 0.6833745032026056,
     "train_runtime": 9125.7542,
     "train_samples": 10941,

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
+  "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": "4.39.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 1.0,
+    "eval_dpo_losses": 0.6851017475128174,
+    "eval_logits/chosen": -2.796370506286621,
+    "eval_logits/rejected": -2.7574775218963623,
+    "eval_logps/chosen": -278.58013916015625,
+    "eval_logps/rejected": -254.24514770507812,
+    "eval_loss": 0.6902781128883362,
+    "eval_positive_losses": 0.036926720291376114,
+    "eval_rewards/accuracies": 0.609000027179718,
+    "eval_rewards/chosen": 0.060132984071969986,
+    "eval_rewards/margins": 0.016795208677649498,
+    "eval_rewards/margins_max": 0.09327653795480728,
+    "eval_rewards/margins_min": -0.05095779150724411,
+    "eval_rewards/margins_std": 0.0482446551322937,
+    "eval_rewards/rejected": 0.04333777725696564,
+    "eval_runtime": 428.2812,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.67,
+    "eval_steps_per_second": 0.292
+}

runs/Jul24_06-16-31_notebook-deployment-48-7d9b6c99-khd85/events.out.tfevents.1721811448.notebook-deployment-48-7d9b6c99-khd85.3314908.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e491cf7c939a263a9efd36a9a60af9c0a1aef80a68c66354fd56bc48134d4d5
+size 1130