finetuned-distilbert-employ-feedback

README.md

@@ -0,0 +1,72 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
+tags:
+- base_model:adapter:distilbert/distilbert-base-uncased
+- lora
+- transformers
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1536
+- Accuracy: 0.9415
+- Precision: 0.9185
+- Recall: 0.9233
+- F1: 0.9209
+
+## 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: 0.001
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.176         | 1.0   | 172  | 0.1679          | 0.9431   | 0.9184    | 0.9298 | 0.9236 |
+| 0.1831        | 2.0   | 344  | 0.1629          | 0.9338   | 0.9053    | 0.9235 | 0.9131 |
+| 0.164         | 3.0   | 516  | 0.1536          | 0.9415   | 0.9185    | 0.9233 | 0.9209 |
+
+
+### Framework versions
+
+- PEFT 0.18.0
+- Transformers 4.57.3
+- Pytorch 2.9.1+cu128
+- Datasets 4.3.0
+- Tokenizers 0.22.2

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "distilbert/distilbert-base-uncased",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 4,
+  "lora_bias": false,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "pre_classifier",
+    "classifier",
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 2,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "lin1",
+    "v_lin",
+    "lin2",
+    "out_lin",
+    "k_lin",
+    "q_lin"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b91e3f61d265d509cfa2da3e977616c757d0d840e74dffebfe57b417baa89cd7
+size 3045716

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb418e858de80cd6ae52b6f15130f09dc0ba57d281d0905865883be94371424b
+size 5777