vjvk/shoptalk_assist_mistral_7b_qlora_finetuned_small_chunks

README.md

@@ -0,0 +1,72 @@
+---
+base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
+library_name: peft
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: Mistral-7B-Instruct-v0.2-GPTQ_finetune_s1000
+  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. -->
+
+# Mistral-7B-Instruct-v0.2-GPTQ_finetune_s1000
+
+This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6456
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.2303        | 0.9829 | 43   | 0.8563          |
+| 0.6964        | 1.9886 | 87   | 0.7045          |
+| 0.6032        | 2.9943 | 131  | 0.6661          |
+| 0.558         | 4.0    | 175  | 0.6472          |
+| 0.5376        | 4.9829 | 218  | 0.6400          |
+| 0.4962        | 5.9886 | 262  | 0.6360          |
+| 0.4754        | 6.9943 | 306  | 0.6359          |
+| 0.4593        | 8.0    | 350  | 0.6393          |
+| 0.456         | 8.9829 | 393  | 0.6430          |
+| 0.4305        | 9.8286 | 430  | 0.6456          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ",
+  "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": [
+    "q_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:d37d1db1466a6a062c7de9c6172e2fa1f57fced0e87fd6982c667b3ba5e4ee62
+size 8397056

runs/Jul03_03-32-45_8f517729a969/events.out.tfevents.1719977568.8f517729a969.395.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7861019e9530428524bf23051a29297528094499c933c87719290cd9f44fd802
+size 10853

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a95de755d5d4509b83a28d28cb7bdde5f0e02c6bdde425580847444a89132834
+size 5240