End of training

README.md

@@ -2,10 +2,13 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
 base_model: alignment-handbook/zephyr-7b-sft-full
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: zephyr-dpop-qlora-uf-5e-7-real
   results: []
@@ -16,22 +19,22 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-dpop-qlora-uf-5e-7-real
 
-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 HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6811
-- Positive Losses: 0.1287
-- Dpo Losses: 0.6627
-- Rewards/chosen: 0.1640
+- Positive Losses: 0.1281
+- Dpo Losses: 0.6626
+- Rewards/chosen: 0.1641
 - Rewards/rejected: 0.0983
-- Rewards/accuracies: 0.7202
+- Rewards/accuracies: 0.7262
 - Rewards/margins: 0.0657
-- Rewards/margins Max: 0.2509
-- Rewards/margins Min: -0.1025
-- Rewards/margins Std: 0.1169
-- Logps/rejected: -252.3186
-- Logps/chosen: -268.0970
-- Logits/rejected: -2.7445
-- Logits/chosen: -2.7830
+- Rewards/margins Max: 0.2505
+- Rewards/margins Min: -0.1023
+- Rewards/margins Std: 0.1168
+- Logps/rejected: -252.3152
+- Logps/chosen: -268.0898
+- Logits/rejected: -2.7475
+- Logits/chosen: -2.7856
 
 ## Model description
 

all_results.json

@@ -1,5 +1,23 @@
 {
     "epoch": 1.0,
+    "eval_dpo_losses": 0.6626402139663696,
+    "eval_logits/chosen": -2.78564453125,
+    "eval_logits/rejected": -2.747466802597046,
+    "eval_logps/chosen": -268.0898132324219,
+    "eval_logps/rejected": -252.3152313232422,
+    "eval_loss": 0.6810576319694519,
+    "eval_positive_losses": 0.1281057745218277,
+    "eval_rewards/accuracies": 0.726190447807312,
+    "eval_rewards/chosen": 0.16405092179775238,
+    "eval_rewards/margins": 0.06570956110954285,
+    "eval_rewards/margins_max": 0.2505451738834381,
+    "eval_rewards/margins_min": -0.10226902365684509,
+    "eval_rewards/margins_std": 0.11677397042512894,
+    "eval_rewards/rejected": 0.09834136068820953,
+    "eval_runtime": 388.0843,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 5.154,
+    "eval_steps_per_second": 0.162,
     "train_loss": 0.6809778677109991,
     "train_runtime": 43303.5615,
     "train_samples": 61134,

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": 0.6626402139663696,
+    "eval_logits/chosen": -2.78564453125,
+    "eval_logits/rejected": -2.747466802597046,
+    "eval_logps/chosen": -268.0898132324219,
+    "eval_logps/rejected": -252.3152313232422,
+    "eval_loss": 0.6810576319694519,
+    "eval_positive_losses": 0.1281057745218277,
+    "eval_rewards/accuracies": 0.726190447807312,
+    "eval_rewards/chosen": 0.16405092179775238,
+    "eval_rewards/margins": 0.06570956110954285,
+    "eval_rewards/margins_max": 0.2505451738834381,
+    "eval_rewards/margins_min": -0.10226902365684509,
+    "eval_rewards/margins_std": 0.11677397042512894,
+    "eval_rewards/rejected": 0.09834136068820953,
+    "eval_runtime": 388.0843,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 5.154,
+    "eval_steps_per_second": 0.162
+}

runs/Jul15_18-05-12_node26/events.out.tfevents.1721078403.node26.36570.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4970c5ba5100d823c5bce8dbae203e58220b1868940b34e2577efd5cb4b88f9f
+size 1130