End of training

README.md

@@ -1,8 +1,11 @@
 ---
 base_model: alignment-handbook/zephyr-7b-sft-full
+datasets:
+- generation/UF
 library_name: peft
 license: apache-2.0
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
@@ -16,20 +19,20 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-dpo-qlora-uf-ours-5e-7-epoch1
 
-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/UF dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6854
-- Rewards/chosen: 0.0408
-- Rewards/rejected: 0.0192
-- Rewards/accuracies: 0.5900
-- Rewards/margins: 0.0216
-- Rewards/margins Max: 0.1281
-- Rewards/margins Min: -0.0713
-- Rewards/margins Std: 0.0665
-- Logps/rejected: -256.6587
-- Logps/chosen: -280.5105
-- Logits/rejected: -2.7434
-- Logits/chosen: -2.7814
+- Loss: 0.6853
+- Rewards/chosen: 0.0412
+- Rewards/rejected: 0.0193
+- Rewards/accuracies: 0.5880
+- Rewards/margins: 0.0219
+- Rewards/margins Max: 0.1290
+- Rewards/margins Min: -0.0714
+- Rewards/margins Std: 0.0669
+- Logps/rejected: -256.6506
+- Logps/chosen: -280.4748
+- Logits/rejected: -2.7413
+- Logits/chosen: -2.7795
 
 ## Model description
 

all_results.json

@@ -1,5 +1,21 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -2.7795233726501465,
+    "eval_logits/rejected": -2.7412893772125244,
+    "eval_logps/chosen": -280.4747619628906,
+    "eval_logps/rejected": -256.65057373046875,
+    "eval_loss": 0.6853376626968384,
+    "eval_rewards/accuracies": 0.5879999995231628,
+    "eval_rewards/chosen": 0.041186705231666565,
+    "eval_rewards/margins": 0.02190316654741764,
+    "eval_rewards/margins_max": 0.12900841236114502,
+    "eval_rewards/margins_min": -0.07138193398714066,
+    "eval_rewards/margins_std": 0.06693326681852341,
+    "eval_rewards/rejected": 0.019283540546894073,
+    "eval_runtime": 428.8609,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.664,
+    "eval_steps_per_second": 0.291,
     "train_loss": 0.6630057381912017,
     "train_runtime": 4226.0112,
     "train_samples": 5678,

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 +1,19 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.7795233726501465,
+    "eval_logits/rejected": -2.7412893772125244,
+    "eval_logps/chosen": -280.4747619628906,
+    "eval_logps/rejected": -256.65057373046875,
+    "eval_loss": 0.6853376626968384,
+    "eval_rewards/accuracies": 0.5879999995231628,
+    "eval_rewards/chosen": 0.041186705231666565,
+    "eval_rewards/margins": 0.02190316654741764,
+    "eval_rewards/margins_max": 0.12900841236114502,
+    "eval_rewards/margins_min": -0.07138193398714066,
+    "eval_rewards/margins_std": 0.06693326681852341,
+    "eval_rewards/rejected": 0.019283540546894073,
+    "eval_runtime": 428.8609,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.664,
+    "eval_steps_per_second": 0.291
+}

runs/Jul29_11-02-19_notebook-deployment-48-7d9b6c99-khd85/events.out.tfevents.1722255746.notebook-deployment-48-7d9b6c99-khd85.3446412.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:341b5b1b2c78200929a38e786633c2cc32547c5d3ef6be0aaa10724a83173f36
+size 1017