End of training

README.md

@@ -1,8 +1,11 @@
 ---
 base_model: alignment-handbook/zephyr-7b-sft-full
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 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-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 HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.6789
-- Positive Losses: 0.2612
+- Positive Losses: 0.2624
 - Dpo Losses: 0.6395
-- Rewards/chosen: 0.2320
+- Rewards/chosen: 0.2321
 - Rewards/rejected: 0.1098
-- Rewards/accuracies: 0.7220
-- Rewards/margins: 0.1222
-- Rewards/margins Max: 0.4482
-- Rewards/margins Min: -0.1549
+- Rewards/accuracies: 0.7180
+- Rewards/margins: 0.1223
+- Rewards/margins Max: 0.4485
+- Rewards/margins Min: -0.1548
 - Rewards/margins Std: 0.2025
-- Logps/rejected: -247.6030
-- Logps/chosen: -261.3938
-- Logits/rejected: -2.6204
-- Logits/chosen: -2.6544
+- Logps/rejected: -247.6011
+- Logps/chosen: -261.3811
+- Logits/rejected: -2.6202
+- Logits/chosen: -2.6543
 
 ## Model description
 

all_results.json

@@ -1,5 +1,23 @@
 {
     "epoch": 1.0,
+    "eval_dpo_losses": 0.6394718289375305,
+    "eval_logits/chosen": -2.6543400287628174,
+    "eval_logits/rejected": -2.6202285289764404,
+    "eval_logps/chosen": -261.381103515625,
+    "eval_logps/rejected": -247.60108947753906,
+    "eval_loss": 0.6789140701293945,
+    "eval_positive_losses": 0.2623763382434845,
+    "eval_rewards/accuracies": 0.7179999947547913,
+    "eval_rewards/chosen": 0.2321232557296753,
+    "eval_rewards/margins": 0.1223447397351265,
+    "eval_rewards/margins_max": 0.4485361576080322,
+    "eval_rewards/margins_min": -0.15482433140277863,
+    "eval_rewards/margins_std": 0.20253273844718933,
+    "eval_rewards/rejected": 0.1097785010933876,
+    "eval_runtime": 428.1146,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.672,
+    "eval_steps_per_second": 0.292,
     "train_loss": 0.6795008113577053,
     "train_runtime": 46141.1523,
     "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": 0.6394718289375305,
+    "eval_logits/chosen": -2.6543400287628174,
+    "eval_logits/rejected": -2.6202285289764404,
+    "eval_logps/chosen": -261.381103515625,
+    "eval_logps/rejected": -247.60108947753906,
+    "eval_loss": 0.6789140701293945,
+    "eval_positive_losses": 0.2623763382434845,
+    "eval_rewards/accuracies": 0.7179999947547913,
+    "eval_rewards/chosen": 0.2321232557296753,
+    "eval_rewards/margins": 0.1223447397351265,
+    "eval_rewards/margins_max": 0.4485361576080322,
+    "eval_rewards/margins_min": -0.15482433140277863,
+    "eval_rewards/margins_std": 0.20253273844718933,
+    "eval_rewards/rejected": 0.1097785010933876,
+    "eval_runtime": 428.1146,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.672,
+    "eval_steps_per_second": 0.292
+}

runs/Jul14_16-51-33_notebook-deployment-48-7d9b6c99-p5kv4/events.out.tfevents.1721023257.notebook-deployment-48-7d9b6c99-p5kv4.34769.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28a8dd141528899548be3a7082103424d018334e8b4afe26537b0cf588fb8fd1
+size 1130