yongqianghf/yongqianghf-ft

README.md

@@ -0,0 +1,72 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
+tags:
+- generated_from_trainer
+model-index:
+- name: shawgpt-ft
+  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. -->
+
+# shawgpt-ft
+
+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.
+It achieves the following results on the evaluation set:
+- Loss: 1.9800
+
+## 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: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 4.5922        | 0.9231 | 3    | 3.9586          |
+| 4.041         | 1.8462 | 6    | 3.4341          |
+| 3.4744        | 2.7692 | 9    | 2.9952          |
+| 2.2714        | 4.0    | 13   | 2.5796          |
+| 2.7159        | 4.9231 | 16   | 2.4308          |
+| 2.501         | 5.8462 | 19   | 2.2380          |
+| 2.3221        | 6.7692 | 22   | 2.1414          |
+| 1.6694        | 8.0    | 26   | 2.0941          |
+| 2.1571        | 8.9231 | 29   | 1.9993          |
+| 1.4553        | 9.2308 | 30   | 1.9800          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.3
+- Pytorch 2.0.1+cu117
+- Datasets 2.19.1
+- Tokenizers 0.20.3

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:c055992fc1867adc41c028eb17ac038740d3ff415920e1e2faef29d47c86a9b5
+size 8397056

runs/Dec19_01-16-09_8947bdbfb423/events.out.tfevents.1734571010.8947bdbfb423.11776.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3352460fa7c1dfec274eac216d283b06b46e1fa7ddd3cdf8913d30a56302b776
+size 10453

runs/Dec19_01-16-09_8947bdbfb423/events.out.tfevents.1734571565.8947bdbfb423.11776.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03232002a47aee6e04de13d1b6cc9dfc22418156b3ddd3e960ea156a8cad65bd
+size 10453

runs/Dec19_01-32-30_8947bdbfb423/events.out.tfevents.1734571952.8947bdbfb423.12002.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1624e7af5df67bb97faa2e4b6b4e371556141338bbf3bb62bf8ce09e2ab119ff
+size 10453

runs/Dec19_01-42-47_8947bdbfb423/events.out.tfevents.1734572568.8947bdbfb423.12209.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45587ccbfc934f7ad52fac380e8d7ef016e492a30ff2ffdf4e937a324ef654d8
+size 10801

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebd052e56e23640072a6b1e2c1395ca25cac6963a092b9a5f9e6329335e51651
+size 4795