ElifAker/gemma-2-9b-ft

README.md

@@ -0,0 +1,54 @@
+---
+base_model: google/gemma-2-9b-it
+library_name: peft
+license: gemma
+tags:
+- generated_from_trainer
+model-index:
+- name: gemma-2-9b-ft
+  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-2-9b-ft
+
+This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) 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
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.44.0
+- Pytorch 2.4.0
+- Datasets 2.21.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2-9b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "lm_head",
+    "gate_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bddddb8598f42f81eae17dcd5d184dcd911392dabb92ea14402942f935e34291
+size 3786439376

runs/Aug28_19-48-11_937cc29411e9/events.out.tfevents.1724874500.937cc29411e9.83.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:210ec8cc431988b8eb9c460bd2599da7471da56c6cf96df40bb6392f05cd4c0a
+size 6400

runs/Aug28_19-48-11_937cc29411e9/events.out.tfevents.1724874607.937cc29411e9.83.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fae4b16898250412bbd3743063f5bfb1589f93b371d9a517f8c03dc986b460c
+size 6400

runs/Aug28_19-48-11_937cc29411e9/events.out.tfevents.1724874818.937cc29411e9.83.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b81b88ed434a7c30927e8df85f47963c091783372c8ddb213b3be0e3474413
+size 6400

runs/Aug28_19-48-11_937cc29411e9/events.out.tfevents.1724875061.937cc29411e9.83.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af0c0ced7fc16ce9448ea5f7f7eb4a37146cb3025e5d543b27ac2e553225f06f
+size 6400

runs/Aug28_19-48-11_937cc29411e9/events.out.tfevents.1724875107.937cc29411e9.83.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a6195e0b17e241970c88da8d2f82359e8e1ab3bae8aa553e15e4d1b335129de
+size 6400

runs/Aug28_19-48-11_937cc29411e9/events.out.tfevents.1724875161.937cc29411e9.83.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ffe554082a74314a5b5afbcc2883bce8402739b3fa282b66fbab17f8edefbd
+size 6400

runs/Aug28_19-48-11_937cc29411e9/events.out.tfevents.1724875230.937cc29411e9.83.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:187becb4e96fe2081d8137d06254b37ec9c7992812b8f02e427297ff5074d496
+size 6400

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80a5afa107c2cf46a1f25fcd7e000fd56fff38ad18e61bba1433a52bc3cbc0e3
+size 5176