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/UF6k
 model-index:
 - name: zephyr-7b-dpo-oursuf6k-qlora-5e-6
   results: []
@@ -16,20 +19,20 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-oursuf6k-qlora-5e-6
 
-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/UF6k dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5973
-- Rewards/chosen: -2.1734
-- Rewards/rejected: -2.9762
-- Rewards/accuracies: 0.6786
-- Rewards/margins: 0.8029
-- Rewards/margins Max: 2.4273
-- Rewards/margins Min: -0.7515
-- Rewards/margins Std: 1.4233
-- Logps/rejected: -556.8073
-- Logps/chosen: -502.5607
-- Logits/rejected: -1.7934
-- Logits/chosen: -1.8380
+- Loss: 0.5972
+- Rewards/chosen: -2.1562
+- Rewards/rejected: -2.9617
+- Rewards/accuracies: 0.6865
+- Rewards/margins: 0.8055
+- Rewards/margins Max: 2.4253
+- Rewards/margins Min: -0.7592
+- Rewards/margins Std: 1.4237
+- Logps/rejected: -555.3531
+- Logps/chosen: -500.8411
+- Logits/rejected: -1.8009
+- Logits/chosen: -1.8449
 
 ## Model description
 

all_results.json

@@ -1,5 +1,21 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -1.844919204711914,
+    "eval_logits/rejected": -1.8009027242660522,
+    "eval_logps/chosen": -500.84112548828125,
+    "eval_logps/rejected": -555.3530883789062,
+    "eval_loss": 0.5972276329994202,
+    "eval_rewards/accuracies": 0.6865079402923584,
+    "eval_rewards/chosen": -2.1561989784240723,
+    "eval_rewards/margins": 0.8055059313774109,
+    "eval_rewards/margins_max": 2.425264835357666,
+    "eval_rewards/margins_min": -0.7591551542282104,
+    "eval_rewards/margins_std": 1.4236739873886108,
+    "eval_rewards/rejected": -2.961704730987549,
+    "eval_runtime": 282.7661,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 7.073,
+    "eval_steps_per_second": 0.223,
     "train_loss": 0.42957196057888497,
     "train_runtime": 6346.2002,
     "train_samples": 10941,

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": -1.844919204711914,
+    "eval_logits/rejected": -1.8009027242660522,
+    "eval_logps/chosen": -500.84112548828125,
+    "eval_logps/rejected": -555.3530883789062,
+    "eval_loss": 0.5972276329994202,
+    "eval_rewards/accuracies": 0.6865079402923584,
+    "eval_rewards/chosen": -2.1561989784240723,
+    "eval_rewards/margins": 0.8055059313774109,
+    "eval_rewards/margins_max": 2.425264835357666,
+    "eval_rewards/margins_min": -0.7591551542282104,
+    "eval_rewards/margins_std": 1.4236739873886108,
+    "eval_rewards/rejected": -2.961704730987549,
+    "eval_runtime": 282.7661,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 7.073,
+    "eval_steps_per_second": 0.223
+}

runs/Jul24_19-27-40_node03/events.out.tfevents.1721823719.node03.3774365.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a471cae7d2e87e18447c211ce05ae0d9d9aaae763beeaada5aa441243f73bf7
+size 1017