Model save

README.md

@@ -0,0 +1,63 @@
+---
+license: mit
+library_name: peft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+base_model: microsoft/Phi-3-mini-4k-instruct
+model-index:
+- name: phi_3-offline-dpo-noise-0.0-42
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/causal/huggingface/runs/pnu5z3m9)
+# phi_3-offline-dpo-noise-0.0-42
+
+This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) 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: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 16
+- 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 4.42.3
+- Pytorch 2.3.0+cu121
+- Datasets 2.14.6
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9230769230769231,
+    "total_flos": 0.0,
+    "train_loss": 0.6940749088923136,
+    "train_runtime": 53.4359,
+    "train_samples": 200,
+    "train_samples_per_second": 3.743,
+    "train_steps_per_second": 0.056
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9230769230769231,
+    "total_flos": 0.0,
+    "train_loss": 0.6940749088923136,
+    "train_runtime": 53.4359,
+    "train_samples": 200,
+    "train_samples_per_second": 3.743,
+    "train_steps_per_second": 0.056
+}

trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9230769230769231,
+  "eval_steps": 100,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.22362739856280167,
+      "learning_rate": 5e-06,
+      "logits/chosen": 11.287857055664062,
+      "logits/rejected": 11.603424072265625,
+      "logps/chosen": -380.2095642089844,
+      "logps/rejected": -391.62744140625,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "step": 3,
+      "total_flos": 0.0,
+      "train_loss": 0.6940749088923136,
+      "train_runtime": 53.4359,
+      "train_samples_per_second": 3.743,
+      "train_steps_per_second": 0.056
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "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
+}