End of training

README.md

@@ -2,10 +2,16 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
+- trl
+- dpo
+- generated_from_trainer
 - trl
 - dpo
 - generated_from_trainer
 base_model: mistralai/Mistral-7B-v0.1
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: zephyr-7b
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-qlora](https://huggingface.co/alignment-handbook/zephyr-7b-sft-qlora) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6182
-- Rewards/chosen: -0.4457
-- Rewards/rejected: -0.8122
-- Rewards/accuracies: 0.3672
-- Rewards/margins: 0.3666
-- Logps/rejected: -158.4149
-- Logps/chosen: -108.4784
-- Logits/rejected: 0.9580
-- Logits/chosen: 0.9035
+- Loss: 0.6171
+- Rewards/chosen: -0.4648
+- Rewards/rejected: -0.8388
+- Rewards/accuracies: 0.3711
+- Rewards/margins: 0.3740
+- Logps/rejected: -161.0705
+- Logps/chosen: -110.3948
+- Logits/rejected: 1.0411
+- Logits/chosen: 0.9868
 - Use Label: 0.0
 - Pred Label: 0.0
 

all_results.json

@@ -1,5 +1,20 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": 0.9867910742759705,
+    "eval_logits/rejected": 1.0411394834518433,
+    "eval_logps/chosen": -110.39482879638672,
+    "eval_logps/rejected": -161.07052612304688,
+    "eval_loss": 0.617142915725708,
+    "eval_pred_label": 0.0,
+    "eval_rewards/accuracies": 0.37109375,
+    "eval_rewards/chosen": -0.4648258090019226,
+    "eval_rewards/margins": 0.3739502727985382,
+    "eval_rewards/rejected": -0.8387760519981384,
+    "eval_runtime": 125.4187,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 15.947,
+    "eval_steps_per_second": 0.255,
+    "eval_use_label": 0.0,
     "train_loss": 0.6389844682481554,
     "train_runtime": 9615.2592,
     "train_samples": 61135,

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": 0.9867910742759705,
+    "eval_logits/rejected": 1.0411394834518433,
+    "eval_logps/chosen": -110.39482879638672,
+    "eval_logps/rejected": -161.07052612304688,
+    "eval_loss": 0.617142915725708,
+    "eval_pred_label": 0.0,
+    "eval_rewards/accuracies": 0.37109375,
+    "eval_rewards/chosen": -0.4648258090019226,
+    "eval_rewards/margins": 0.3739502727985382,
+    "eval_rewards/rejected": -0.8387760519981384,
+    "eval_runtime": 125.4187,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 15.947,
+    "eval_steps_per_second": 0.255,
+    "eval_use_label": 0.0
+}

runs/Mar19_21-02-18_uclaml04.cs.ucla.edu/events.out.tfevents.1710917327.uclaml04.cs.ucla.edu.3973422.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e1ce971f095d751d88b2a0b0e9410d4518ff9f751ad5d42499104b2270e5f2
+size 935