End of training

README.md

@@ -1,8 +1,11 @@
 ---
 base_model: alignment-handbook/zephyr-7b-sft-full
+datasets:
+- generation/UF6konly
 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-uf6k-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/UF6konly dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6889
-- Rewards/chosen: 0.0031
-- Rewards/rejected: -0.0066
-- Rewards/accuracies: 0.6760
-- Rewards/margins: 0.0098
-- Rewards/margins Max: 0.0449
-- Rewards/margins Min: -0.0216
+- Loss: 0.6890
+- Rewards/chosen: 0.0030
+- Rewards/rejected: -0.0067
+- Rewards/accuracies: 0.6750
+- Rewards/margins: 0.0097
+- Rewards/margins Max: 0.0448
+- Rewards/margins Min: -0.0217
 - Rewards/margins Std: 0.0219
-- Logps/rejected: -259.2438
-- Logps/chosen: -284.2815
-- Logits/rejected: -2.7640
-- Logits/chosen: -2.8026
+- Logps/rejected: -259.2527
+- Logps/chosen: -284.2960
+- Logits/rejected: -2.7684
+- Logits/chosen: -2.8066
 
 ## Model description
 

all_results.json

@@ -1,5 +1,21 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -2.8066177368164062,
+    "eval_logits/rejected": -2.768425226211548,
+    "eval_logps/chosen": -284.29595947265625,
+    "eval_logps/rejected": -259.2527160644531,
+    "eval_loss": 0.6889536380767822,
+    "eval_rewards/accuracies": 0.675000011920929,
+    "eval_rewards/chosen": 0.002974556991830468,
+    "eval_rewards/margins": 0.009712548926472664,
+    "eval_rewards/margins_max": 0.04481280967593193,
+    "eval_rewards/margins_min": -0.02172652818262577,
+    "eval_rewards/margins_std": 0.021889150142669678,
+    "eval_rewards/rejected": -0.006737993564456701,
+    "eval_runtime": 427.88,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.674,
+    "eval_steps_per_second": 0.292,
     "train_loss": 0.6900796745323483,
     "train_runtime": 3893.3874,
     "train_samples": 5263,

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": -2.8066177368164062,
+    "eval_logits/rejected": -2.768425226211548,
+    "eval_logps/chosen": -284.29595947265625,
+    "eval_logps/rejected": -259.2527160644531,
+    "eval_loss": 0.6889536380767822,
+    "eval_rewards/accuracies": 0.675000011920929,
+    "eval_rewards/chosen": 0.002974556991830468,
+    "eval_rewards/margins": 0.009712548926472664,
+    "eval_rewards/margins_max": 0.04481280967593193,
+    "eval_rewards/margins_min": -0.02172652818262577,
+    "eval_rewards/margins_std": 0.021889150142669678,
+    "eval_rewards/rejected": -0.006737993564456701,
+    "eval_runtime": 427.88,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.674,
+    "eval_steps_per_second": 0.292
+}

runs/Jul25_08-24-43_notebook-deployment-48-7d9b6c99-khd85/events.out.tfevents.1721900369.notebook-deployment-48-7d9b6c99-khd85.3153936.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc3526ef2b72303e158337c6facf9dcf0fcf313f600f51554485ea2c4e873db
+size 1017