amaandhada/minichat-finetuned-working

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: GeneZC/MiniChat-3B
+model-index:
+- name: outputs
+  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. -->
+
+# outputs
+
+This model is a fine-tuned version of [GeneZC/MiniChat-3B](https://huggingface.co/GeneZC/MiniChat-3B) 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: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 0.03
+- training_steps: 100
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.38.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "GeneZC/MiniChat-3B",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3490f53ad1c2384e6fcd1011fab8528aa6d3e3d14b6aaefc311690a71e1d03eb
+size 18899832

runs/Feb02_06-25-54_6753544bef3a/events.out.tfevents.1706855154.6753544bef3a.1776.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12dafc009a72565bea9d3896e279760674b9805b55977692aaedc63c3a2c499c
+size 4866

runs/Feb02_06-27-26_6753544bef3a/events.out.tfevents.1706855246.6753544bef3a.1776.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e6c6b8875858a0b87b2b38f7e9251bea0557a73537165fc07964fd3235dcbe
+size 4866

runs/Feb02_06-32-01_6753544bef3a/events.out.tfevents.1706855522.6753544bef3a.1776.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef6cccddabcc6513e60664bc92feb7bfe8579f24b6f57c161cb55a735bc63fb9
+size 5020

runs/Feb02_06-41-49_6753544bef3a/events.out.tfevents.1706856109.6753544bef3a.1776.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d38990995c5c0937a84b6ce9d4eb9bcbececc06bc2a61f0bdb768f46c057c8f2
+size 6754

runs/Feb02_06-44-34_6753544bef3a/events.out.tfevents.1706856274.6753544bef3a.1776.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02e7c0a94c2cee979c16cda2d9680be09aeb9a7f10c2a0633e1f704110ddc881
+size 20616

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:113a76a2546f8ca5f75937248aa010808b0fbfa1c20a75f165f7100ae8a60d5c
+size 4728