suvoo/suvoLLM-568-mistral-ft-2epochs

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
+model-index:
+- name: 568_com
+  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. -->
+
+# 568_com
+
+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 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: 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: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

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 sha256:2ef23c80a62de0cde3890a9e3b41b1fbd11fddd0997d0d63d341fe98d60e5d3f
+size 8397056

runs/Apr18_04-32-30_61e1652f69bf/events.out.tfevents.1713414755.61e1652f69bf.2492.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e988846ed2c774abc9ac52a6cf54919f12a0d1ba1d086c31d0f575e74b5c13e
+size 5199

runs/Apr18_04-34-14_61e1652f69bf/events.out.tfevents.1713414859.61e1652f69bf.2492.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3c60bc9701ad53b5bc2d9099f2283d041c22b671f72032c6d8b01e8c1a6ab3c
+size 5200

runs/Apr18_04-36-10_61e1652f69bf/events.out.tfevents.1713414974.61e1652f69bf.2492.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950de001b7d9d9d364383701f53b1bb275bdb5dadfb4d0f70f1e81022fbf3dc1
+size 5198

runs/Apr18_04-38-38_61e1652f69bf/events.out.tfevents.1713415124.61e1652f69bf.2492.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ef7c09899de3a168574a7af1f1f7765dff64c83b89cd5fe3111a650436adde1
+size 5405

runs/Apr18_04-59-50_61e1652f69bf/events.out.tfevents.1713416396.61e1652f69bf.2492.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f47bba2ad51099de8e81c5001aa39f3408917cb75cf81bd39ed549361ecb207
+size 5955

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f79eb9f7976864602fc09bf530ee1dd54ff59335735c17c48a890af97af29d4e
+size 4856