Adapter

README.md

@@ -0,0 +1,57 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: meta-llama/Llama-2-7b-hf
+model-index:
+- name: Adapter
+  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. -->
+
+# Adapter
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown 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
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2
+- training_steps: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.2.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "base_layer"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2436678237584e664f8fa19926c6bc740291eb07999bece5d55bc63099d04c60
+size 959884168

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0,
+    "total_flos": 333801262080000.0,
+    "train_loss": 1.2641676783561706,
+    "train_runtime": 52.6099,
+    "train_samples_per_second": 0.76,
+    "train_steps_per_second": 0.19
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0,
+    "total_flos": 333801262080000.0,
+    "train_loss": 1.2641676783561706,
+    "train_runtime": 52.6099,
+    "train_samples_per_second": 0.76,
+    "train_steps_per_second": 0.19
+}

trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0007727975270479134,
+  "eval_steps": 500,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001,
+      "loss": 2.0357,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 1.8357,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.000175,
+      "loss": 1.4764,
+      "step": 3
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.9966,
+      "step": 4
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.000125,
+      "loss": 1.339,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001,
+      "loss": 1.0031,
+      "step": 6
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.9943,
+      "step": 7
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5e-05,
+      "loss": 1.1203,
+      "step": 8
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.5e-05,
+      "loss": 0.9072,
+      "step": 9
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.9334,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "step": 10,
+      "total_flos": 333801262080000.0,
+      "train_loss": 1.2641676783561706,
+      "train_runtime": 52.6099,
+      "train_samples_per_second": 0.76,
+      "train_steps_per_second": 0.19
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 10,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 333801262080000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f1c62c602a1ddff417feb535d1e72776f88b3b26d149c83aa329759e46e44d9
+size 4664