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:
+- generation/UF
 model-index:
 - name: zephyr-7b-dpop-ours-qlora-5e-6-epoch3
   results: []
@@ -16,22 +19,22 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpop-ours-qlora-5e-6-epoch3
 
-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: 5.2224
-- Positive Losses: 49.9806
-- Dpo Losses: 0.6312
-- Rewards/chosen: -0.4578
-- Rewards/rejected: -0.7482
-- Rewards/accuracies: 0.6627
-- Rewards/margins: 0.2904
-- Rewards/margins Max: 1.0718
-- Rewards/margins Min: -0.5332
-- Rewards/margins Std: 0.7245
-- Logps/rejected: -333.9995
-- Logps/chosen: -330.9984
-- Logits/rejected: -2.5367
-- Logits/chosen: -2.5873
+- Loss: 5.2043
+- Positive Losses: 49.6926
+- Dpo Losses: 0.6309
+- Rewards/chosen: -0.4548
+- Rewards/rejected: -0.7461
+- Rewards/accuracies: 0.6706
+- Rewards/margins: 0.2913
+- Rewards/margins Max: 1.0735
+- Rewards/margins Min: -0.5345
+- Rewards/margins Std: 0.7255
+- Logps/rejected: -333.7965
+- Logps/chosen: -330.7057
+- Logits/rejected: -2.5363
+- Logits/chosen: -2.5869
 
 ## Model description
 

all_results.json

@@ -1,5 +1,23 @@
 {
     "epoch": 3.0,
+    "eval_dpo_losses": 0.6309279203414917,
+    "eval_logits/chosen": -2.586883544921875,
+    "eval_logits/rejected": -2.536296844482422,
+    "eval_logps/chosen": -330.7057189941406,
+    "eval_logps/rejected": -333.7965087890625,
+    "eval_loss": 5.204337120056152,
+    "eval_positive_losses": 49.692630767822266,
+    "eval_rewards/accuracies": 0.670634925365448,
+    "eval_rewards/chosen": -0.4548453986644745,
+    "eval_rewards/margins": 0.2912927269935608,
+    "eval_rewards/margins_max": 1.0734634399414062,
+    "eval_rewards/margins_min": -0.5345237851142883,
+    "eval_rewards/margins_std": 0.7254678010940552,
+    "eval_rewards/rejected": -0.7461380958557129,
+    "eval_runtime": 284.396,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 7.032,
+    "eval_steps_per_second": 0.222,
     "train_loss": 0.48024289137880566,
     "train_runtime": 8933.1726,
     "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": 3.0,
+    "eval_dpo_losses": 0.6309279203414917,
+    "eval_logits/chosen": -2.586883544921875,
+    "eval_logits/rejected": -2.536296844482422,
+    "eval_logps/chosen": -330.7057189941406,
+    "eval_logps/rejected": -333.7965087890625,
+    "eval_loss": 5.204337120056152,
+    "eval_positive_losses": 49.692630767822266,
+    "eval_rewards/accuracies": 0.670634925365448,
+    "eval_rewards/chosen": -0.4548453986644745,
+    "eval_rewards/margins": 0.2912927269935608,
+    "eval_rewards/margins_max": 1.0734634399414062,
+    "eval_rewards/margins_min": -0.5345237851142883,
+    "eval_rewards/margins_std": 0.7254678010940552,
+    "eval_rewards/rejected": -0.7461380958557129,
+    "eval_runtime": 284.396,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 7.032,
+    "eval_steps_per_second": 0.222
+}

runs/Jul26_16-02-56_node23/events.out.tfevents.1721986917.node23.101786.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dd019560d4b7b8aa7f331deebc833e8fde42ae2b85ff952f61052dd627102ef
+size 1130