End of training

README.md

@@ -0,0 +1,55 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+tags:
+- generated_from_trainer
+datasets:
+- truthful_qa
+model-index:
+- name: llama_mc_finetune
+  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. -->
+
+# llama_mc_finetune
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the truthful_qa 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: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2
+- training_steps: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.13.1
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "base_layer"
+  ],
+  "task_type": "SEQ_CLS"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d1c82228579d983d2866efc6c53db9e6f4f7fa8c9b39ec57bf88c0994264ab
+size 320373198

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d403c5891130d9cf0429788d8aed07ac05883ec05cb5d5eb4c6cd826bc7089b
+size 320169624

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0,
+    "total_flos": 32571857534976.0,
+    "train_loss": 6.678385416666667,
+    "train_runtime": 6.9231,
+    "train_samples_per_second": 0.433,
+    "train_steps_per_second": 0.433
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0,
+    "total_flos": 32571857534976.0,
+    "train_loss": 6.678385416666667,
+    "train_runtime": 6.9231,
+    "train_samples_per_second": 0.433,
+    "train_steps_per_second": 0.433
+}

trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.004594180704441042,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 6.625,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 6.1719,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 7.2383,
+      "step": 3
+    },
+    {
+      "epoch": 0.0,
+      "step": 3,
+      "total_flos": 32571857534976.0,
+      "train_loss": 6.678385416666667,
+      "train_runtime": 6.9231,
+      "train_samples_per_second": 0.433,
+      "train_steps_per_second": 0.433
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 3,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 32571857534976.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e25ab091eda0fcef4e0a9e37f22496431e57d92ab798a86fa7a60f8d8ed78a5d
+size 4600