Model save

README.md

@@ -0,0 +1,61 @@
+---
+base_model: princeton-nlp/Llama-3-Base-8B-SFT
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: zephyr-7b-wpo-lora
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# zephyr-7b-wpo-lora
+
+This model is a fine-tuned version of [princeton-nlp/Llama-3-Base-8B-SFT](https://huggingface.co/princeton-nlp/Llama-3-Base-8B-SFT) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.44.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.14.6
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.8,
+    "total_flos": 0.0,
+    "train_loss": 0.693049430847168,
+    "train_runtime": 130.1581,
+    "train_samples": 240,
+    "train_samples_per_second": 1.844,
+    "train_steps_per_second": 0.023
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.8,
+    "total_flos": 0.0,
+    "train_loss": 0.693049430847168,
+    "train_runtime": 130.1581,
+    "train_samples": 240,
+    "train_samples_per_second": 1.844,
+    "train_steps_per_second": 0.023
+}

trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8,
+  "eval_steps": 100,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.16037533305228002,
+      "learning_rate": 5e-06,
+      "logits/chosen": -0.496604323387146,
+      "logits/rejected": -0.4112662672996521,
+      "logps/chosen": -242.63560485839844,
+      "logps/ref_response": -0.496604323387146,
+      "logps/rejected": -275.38885498046875,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.8,
+      "step": 3,
+      "total_flos": 0.0,
+      "train_loss": 0.693049430847168,
+      "train_runtime": 130.1581,
+      "train_samples_per_second": 1.844,
+      "train_steps_per_second": 0.023
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}