Devparker-2002/Mistral-FineTuned-7B-Model-v1

README.md

@@ -0,0 +1,54 @@
+---
+base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
+library_name: peft
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: output
+  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. -->
+
+# output
+
+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.
+
+## 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: 8
+- 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_ratio: 0.4
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.12.0
+- 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 sha256:33901e1a2793c5844d43d1135fd88ee73b7dc9dbbe54e6bbbc939f76f89c417f
+size 8397056

runs/Jul08_09-27-04_94fbed62739a/events.out.tfevents.1720430831.94fbed62739a.3210.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b871bf5b4438886bd3eb6cd119ae002684ea5fc2b67f7e04370f812648c5b897
+size 5464

runs/Jul08_09-28-12_94fbed62739a/events.out.tfevents.1720430896.94fbed62739a.3210.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b00c548f1d77a7cf1850a3118a6188309b17cab95d04e5bd7288aff379ae057
+size 5463

runs/Jul08_09-29-01_94fbed62739a/events.out.tfevents.1720430946.94fbed62739a.3210.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a27e3da1fc6ab30fd5cda1e122d7e3e2e1f59dc13f0b29a5d3cf67da2f8112
+size 5463

runs/Jul08_09-31-16_94fbed62739a/events.out.tfevents.1720431079.94fbed62739a.3210.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97155f27d745cb7804f68a0e779a0c843a4ce5b6d6451798132b84a5de812311
+size 5463

runs/Jul08_09-33-14_94fbed62739a/events.out.tfevents.1720431198.94fbed62739a.3210.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0b93a4c917204777bd24430f8af4647214a632875c28f17736cf7b07d4ed103
+size 5673

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00271a1f5541a05ebe40bdee04efc87a50d5784c38f638157accde8d98a46cb0
+size 5112