bruhjeet26/NERFT

README.md

@@ -0,0 +1,78 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: openaccess-ai-collective/tiny-mistral
+model-index:
+- name: mistral-LLM-NER
+  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-LLM-NER
+
+This model is a fine-tuned version of [openaccess-ai-collective/tiny-mistral](https://huggingface.co/openaccess-ai-collective/tiny-mistral) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1446
+
+## 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: 0.00025
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1
+- training_steps: 500
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 7.9928        | 0.23  | 25   | 5.6978          |
+| 3.9614        | 0.45  | 50   | 2.6379          |
+| 2.3449        | 0.68  | 75   | 2.0141          |
+| 1.9745        | 0.9   | 100  | 1.7486          |
+| 1.7972        | 1.13  | 125  | 1.6622          |
+| 1.5265        | 1.35  | 150  | 1.6077          |
+| 1.3779        | 1.58  | 175  | 1.4895          |
+| 1.2514        | 1.8   | 200  | 1.4698          |
+| 1.3015        | 2.03  | 225  | 1.4646          |
+| 1.1816        | 2.25  | 250  | 1.4042          |
+| 1.0834        | 2.48  | 275  | 1.3628          |
+| 1.2907        | 2.7   | 300  | 1.3486          |
+| 1.4177        | 2.93  | 325  | 1.2939          |
+| 1.1508        | 3.15  | 350  | 1.2380          |
+| 0.9248        | 3.38  | 375  | 1.2098          |
+| 1.0663        | 3.6   | 400  | 1.1924          |
+| 1.0292        | 3.83  | 425  | 1.1797          |
+| 0.9591        | 4.05  | 450  | 1.1630          |
+| 0.837         | 4.28  | 475  | 1.1533          |
+| 0.9954        | 4.5   | 500  | 1.1446          |
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openaccess-ai-collective/tiny-mistral",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "lm_head"
+  ],
+  "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 sha256:87f70524d1ab0f018a066cc5e8f15270a43e48f42b2535cc58f7d02570d8f945
+size 118733696

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2cdd1106b9df54c56f3e0a62c9aec808144f7993ee32341b1e473198c379adf
+size 4856