vjvk/shoptalk_assist_mistral_7b_qlora_finetuned_essential_fields

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: result
+  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. -->
+
+# result
+
+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: 0.4904
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.8013        | 0.9912 | 28   | 0.7742          |
+| 0.7042        | 1.9823 | 56   | 0.5279          |
+| 0.5777        | 2.9735 | 84   | 0.4869          |
+| 0.5117        | 4.0    | 113  | 0.4764          |
+| 0.503         | 4.9912 | 141  | 0.4750          |
+| 0.4824        | 5.9823 | 169  | 0.4781          |
+| 0.4634        | 6.9735 | 197  | 0.4782          |
+| 0.4288        | 8.0    | 226  | 0.4851          |
+| 0.4327        | 8.9912 | 254  | 0.4886          |
+| 0.4123        | 9.9115 | 280  | 0.4904          |
+
+
+### 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": null,
+  "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 sha256:6cc86ef1beb6ab5858c49d9e8950fd64178c060e8e19a7824d5e5656181f5acb
+size 8398144

runs/Jul08_02-19-03_f3f5bd0ebacd/events.out.tfevents.1720405151.f3f5bd0ebacd.2343.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dcef6cf70f836bb773e8080bef644f1eef1b867f4f5de884686de44f2bf090c
+size 10862

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1382aaa147a6f5a13b7df583782b9dc4a3b1c42849296c2690fa7feb657c689c
+size 5240