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
@@ -16,22 +19,22 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-dpop-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: 0.7024
-- Positive Losses: 0.1592
-- Dpo Losses: 0.6845
-- Rewards/chosen: 0.0528
-- Rewards/rejected: 0.0346
+- Positive Losses: 0.1617
+- Dpo Losses: 0.6844
+- Rewards/chosen: 0.0533
+- Rewards/rejected: 0.0348
 - Rewards/accuracies: 0.5940
-- Rewards/margins: 0.0182
-- Rewards/margins Max: 0.1072
-- Rewards/margins Min: -0.0591
-- Rewards/margins Std: 0.0555
-- Logps/rejected: -255.1217
-- Logps/chosen: -279.3168
-- Logits/rejected: -2.7478
-- Logits/chosen: -2.7859
+- Rewards/margins: 0.0185
+- Rewards/margins Max: 0.1082
+- Rewards/margins Min: -0.0600
+- Rewards/margins Std: 0.0561
+- Logps/rejected: -255.0996
+- Logps/chosen: -279.2664
+- Logits/rejected: -2.7455
+- Logits/chosen: -2.7839
 
 ## Model description
 

all_results.json

@@ -1,5 +1,23 @@
 {
     "epoch": 1.0,
+    "eval_dpo_losses": 0.6843776702880859,
+    "eval_logits/chosen": -2.7839062213897705,
+    "eval_logits/rejected": -2.7455294132232666,
+    "eval_logps/chosen": -279.266357421875,
+    "eval_logps/rejected": -255.0995635986328,
+    "eval_loss": 0.7023824453353882,
+    "eval_positive_losses": 0.16172000765800476,
+    "eval_rewards/accuracies": 0.593999981880188,
+    "eval_rewards/chosen": 0.05327073112130165,
+    "eval_rewards/margins": 0.018477285280823708,
+    "eval_rewards/margins_max": 0.10823574662208557,
+    "eval_rewards/margins_min": -0.059972915798425674,
+    "eval_rewards/margins_std": 0.05609079822897911,
+    "eval_rewards/rejected": 0.034793443977832794,
+    "eval_runtime": 427.9806,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.673,
+    "eval_steps_per_second": 0.292,
     "train_loss": 0.6688590748209349,
     "train_runtime": 4310.2257,
     "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 +1,21 @@
+{
+    "epoch": 1.0,
+    "eval_dpo_losses": 0.6843776702880859,
+    "eval_logits/chosen": -2.7839062213897705,
+    "eval_logits/rejected": -2.7455294132232666,
+    "eval_logps/chosen": -279.266357421875,
+    "eval_logps/rejected": -255.0995635986328,
+    "eval_loss": 0.7023824453353882,
+    "eval_positive_losses": 0.16172000765800476,
+    "eval_rewards/accuracies": 0.593999981880188,
+    "eval_rewards/chosen": 0.05327073112130165,
+    "eval_rewards/margins": 0.018477285280823708,
+    "eval_rewards/margins_max": 0.10823574662208557,
+    "eval_rewards/margins_min": -0.059972915798425674,
+    "eval_rewards/margins_std": 0.05609079822897911,
+    "eval_rewards/rejected": 0.034793443977832794,
+    "eval_runtime": 427.9806,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 4.673,
+    "eval_steps_per_second": 0.292
+}

runs/Jul29_11-02-19_notebook-deployment-48-7d9b6c99-khd85/events.out.tfevents.1722255822.notebook-deployment-48-7d9b6c99-khd85.3446418.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5933541825561d1896b992fe53b9f88b396ee9eabca6180cf4f1b5c52f17c89d
+size 1130