End of training

README.md

@@ -1,3 +1,55 @@
 ---
-license: apache-2.0
+base_model: meta-llama/Llama-2-7b-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: llama_causal_finetue
+  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_causal_finetue
+
+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: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.1.0+cu118
+- 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": "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,
+  "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": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fc903572c3ecc567ca259de30f7cf2aab1f71ab2e583c033bbf8f9d160b20ad
+size 319941280

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.06,
+    "total_flos": 519041285554176.0,
+    "train_loss": 1.6063518921534221,
+    "train_runtime": 71.9618,
+    "train_samples_per_second": 0.167,
+    "train_steps_per_second": 0.042
+}

runs/Nov07_05-19-02_51ef0586a7df/events.out.tfevents.1699334343.51ef0586a7df.14230.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4b452423c184d6ed27b814713787d36b7fa5bf884018a91c312d801ba667758
+size 4626

runs/Nov07_05-19-12_51ef0586a7df/events.out.tfevents.1699334354.51ef0586a7df.14230.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:385dc2179c7a3e5ff699e797ca7287252bcd8718a4e6296f54a7db6feae9d988
+size 5435

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.06,
+    "total_flos": 519041285554176.0,
+    "train_loss": 1.6063518921534221,
+    "train_runtime": 71.9618,
+    "train_samples_per_second": 0.167,
+    "train_steps_per_second": 0.042
+}

trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.06091370558375635,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001,
+      "loss": 1.5897,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002,
+      "loss": 1.7194,
+      "step": 2
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0,
+      "loss": 1.51,
+      "step": 3
+    },
+    {
+      "epoch": 0.06,
+      "step": 3,
+      "total_flos": 519041285554176.0,
+      "train_loss": 1.6063518921534221,
+      "train_runtime": 71.9618,
+      "train_samples_per_second": 0.167,
+      "train_steps_per_second": 0.042
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 3,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 519041285554176.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c0c1fb65e6a63bfc36f80ab7314a84afb2165dcc26ca7afe2b3c98d21c53a16
+size 4600