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-6-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: 0.8935
-- Rewards/chosen: -4.8886
-- Rewards/rejected: -5.8224
-- Rewards/accuracies: 0.6470
-- Rewards/margins: 0.9339
-- Rewards/margins Max: 4.5089
-- Rewards/margins Min: -2.8033
-- Rewards/margins Std: 2.4986
-- Logps/rejected: -840.8231
-- Logps/chosen: -773.4503
-- Logits/rejected: -1.3417
-- Logits/chosen: -1.4023
+- Loss: 0.9016
+- Rewards/chosen: -5.0415
+- Rewards/rejected: -5.9633
+- Rewards/accuracies: 0.6560
+- Rewards/margins: 0.9219
+- Rewards/margins Max: 4.5250
+- Rewards/margins Min: -2.8411
+- Rewards/margins Std: 2.5079
+- Logps/rejected: -854.9131
+- Logps/chosen: -788.7391
+- Logits/rejected: -1.3435
+- Logits/chosen: -1.4046
 
 ## Model description
 

all_results.json

@@ -1,5 +1,21 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -1.404586672782898,
+    "eval_logits/rejected": -1.3435096740722656,
+    "eval_logps/chosen": -788.7391357421875,
+    "eval_logps/rejected": -854.9130859375,
+    "eval_loss": 0.9015858173370361,
+    "eval_rewards/accuracies": 0.656000018119812,
+    "eval_rewards/chosen": -5.041457653045654,
+    "eval_rewards/margins": 0.9218845367431641,
+    "eval_rewards/margins_max": 4.525033473968506,
+    "eval_rewards/margins_min": -2.841050386428833,
+    "eval_rewards/margins_std": 2.5078797340393066,
+    "eval_rewards/rejected": -5.96334171295166,
+    "eval_runtime": 428.0105,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.673,
+    "eval_steps_per_second": 0.292,
     "train_loss": 0.3073710792501208,
     "train_runtime": 4217.5244,
     "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": -1.404586672782898,
+    "eval_logits/rejected": -1.3435096740722656,
+    "eval_logps/chosen": -788.7391357421875,
+    "eval_logps/rejected": -854.9130859375,
+    "eval_loss": 0.9015858173370361,
+    "eval_rewards/accuracies": 0.656000018119812,
+    "eval_rewards/chosen": -5.041457653045654,
+    "eval_rewards/margins": 0.9218845367431641,
+    "eval_rewards/margins_max": 4.525033473968506,
+    "eval_rewards/margins_min": -2.841050386428833,
+    "eval_rewards/margins_std": 2.5078797340393066,
+    "eval_rewards/rejected": -5.96334171295166,
+    "eval_runtime": 428.0105,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.673,
+    "eval_steps_per_second": 0.292
+}

runs/Jul29_11-02-20_notebook-deployment-48-7d9b6c99-khd85/events.out.tfevents.1722255734.notebook-deployment-48-7d9b6c99-khd85.3446415.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2faecd81cca4149ca790018938c8e92dd7c9b1b3e94cba290612a56878989ff
+size 1017