initial commit

adapter_config.json

@@ -0,0 +1,18 @@
+{
+  "base_model_name_or_path": "decapoda-research/llama-7b-hf",
+  "bias": "none",
+  "enable_lora": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "merge_weights": false,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e727cf45b015a892bb23deb0e0e016963f52d0106d8996430fc2bd1d9638b4c
+size 16822989

traininglogs.txt

@@ -0,0 +1,18 @@
+{'loss': 2.4072, 'learning_rate': 5.9999999999999995e-05, 'epoch': 0.17}
+{'loss': 1.9372, 'learning_rate': 0.00011399999999999999, 'epoch': 0.34}
+{'loss': 1.4099, 'learning_rate': 0.00017399999999999997, 'epoch': 0.51}
+{'loss': 1.2822, 'learning_rate': 0.000234, 'epoch': 0.68}
+{'loss': 1.2445, 'learning_rate': 0.000294, 'epoch': 0.85}
+{'loss': 1.2077, 'learning_rate': 0.00027848605577689237, 'epoch': 1.02}
+{'loss': 1.1843, 'learning_rate': 0.0002545816733067729, 'epoch': 1.19}
+{'loss': 1.18, 'learning_rate': 0.00023067729083665336, 'epoch': 1.37}
+{'loss': 1.1533, 'learning_rate': 0.00020677290836653385, 'epoch': 1.54}
+{'loss': 1.1383, 'learning_rate': 0.00018286852589641432, 'epoch': 1.71}
+{'loss': 1.1389, 'learning_rate': 0.0001589641434262948, 'epoch': 1.88}
+{'loss': 1.1331, 'learning_rate': 0.00013505976095617528, 'epoch': 2.05}
+{'loss': 1.1001, 'learning_rate': 0.00011115537848605577, 'epoch': 2.22}
+{'loss': 1.1082, 'learning_rate': 8.725099601593625e-05, 'epoch': 2.39}
+{'loss': 1.0986, 'learning_rate': 6.334661354581673e-05, 'epoch': 2.56}
+{'loss': 1.0954, 'learning_rate': 3.9442231075697205e-05, 'epoch': 2.73}
+{'loss': 1.1076, 'learning_rate': 1.5537848605577688e-05, 'epoch': 2.9}
+{'train_runtime': 9669.9054, 'train_samples_per_second': 4.654, 'train_steps_per_second': 0.036, 'train_loss': 1.283483600344753, 'epoch': 3.0}