End of training

README.md

@@ -0,0 +1,56 @@
+---
+license: other
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: google/gemma-7b
+model-index:
+- name: gemma-7b-ft-80row-alpaca-correcting-mistakes
+  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. -->
+
+# gemma-7b-ft-80row-alpaca-correcting-mistakes
+
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) 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: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 6
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 150
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-7b",
+  "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": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "task_type": "CASUAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e618935c5053056c35212faf13e63edb88e3f0028a60354b706b7ffd405f6d2b
+size 100059752

runs/Mar05_11-15-47_3f4bbc8526e7/events.out.tfevents.1709637347.3f4bbc8526e7.1808.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27358ae8dd978e9c09a6635faa5686b9c5c9b4a729a478e5266dead3c6ad65c0
+size 36606

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb8e6030d4b4c1a14064804a8b9dcb815563755af3b388a630ba0278aeafa323
+size 4920