jd0g/Mistral-7B-NLI-v0.3

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: TheBloke/Mistral-7B-v0.1-GPTQ
+model-index:
+- name: mistral-7b-nli_cot_qkv
+  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-nli_cot_qkv
+
+This model is a fine-tuned version of [TheBloke/Mistral-7B-v0.1-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7749
+
+## 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_steps: 2
+- num_epochs: 12
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step  | Validation Loss |
+|:-------------:|:-------:|:-----:|:---------------:|
+| 0.426         | 0.9998  | 1196  | 0.4255          |
+| 0.3664        | 1.9996  | 2392  | 0.4365          |
+| 0.3221        | 2.9994  | 3588  | 0.4455          |
+| 0.2804        | 4.0     | 4785  | 0.4577          |
+| 0.2403        | 4.9998  | 5981  | 0.4719          |
+| 0.2001        | 5.9996  | 7177  | 0.4948          |
+| 0.1643        | 6.9994  | 8373  | 0.5278          |
+| 0.1305        | 8.0     | 9570  | 0.5634          |
+| 0.1011        | 8.9998  | 10766 | 0.6095          |
+| 0.0768        | 9.9996  | 11962 | 0.6621          |
+| 0.0577        | 10.9994 | 13158 | 0.7225          |
+| 0.0445        | 11.9975 | 14352 | 0.7749          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.19.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "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": 64,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "up_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 sha256:957bff608676fc8192b5fdc64e10141b8e6e56908ee2b515f1c097be7115ca9e
+size 167839856

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:625aeea4c3a2749aea59aaf88750fc6751b466702553269880a1c7a2f430d90f
+size 4539