mzamfirdaus/test-peft-train

README.md

@@ -0,0 +1,101 @@
+---
+license: mit
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: microsoft/phi-2
+model-index:
+- name: final-checkpoint
+ 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. -->
+
+# final-checkpoint
+
+This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3170
+
+## 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: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1
+- training_steps: 1000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.6634 | 0.05 | 25 | 1.3938 |
+| 1.1888 | 0.1 | 50 | 1.3917 |
+| 1.4465 | 0.15 | 75 | 1.3522 |
+| 1.205 | 0.2 | 100 | 1.3718 |
+| 1.4403 | 0.25 | 125 | 1.3429 |
+| 1.1372 | 0.3 | 150 | 1.3639 |
+| 1.4064 | 0.35 | 175 | 1.3408 |
+| 1.1466 | 0.4 | 200 | 1.3473 |
+| 1.4435 | 0.45 | 225 | 1.3355 |
+| 1.2273 | 0.5 | 250 | 1.3414 |
+| 1.4578 | 0.55 | 275 | 1.3364 |
+| 1.1637 | 0.6 | 300 | 1.3362 |
+| 1.429 | 0.65 | 325 | 1.3305 |
+| 1.2027 | 0.7 | 350 | 1.3306 |
+| 1.3971 | 0.75 | 375 | 1.3287 |
+| 1.184 | 0.8 | 400 | 1.3312 |
+| 1.4383 | 0.85 | 425 | 1.3262 |
+| 1.1996 | 0.9 | 450 | 1.3271 |
+| 1.448 | 0.95 | 475 | 1.3250 |
+| 1.1902 | 1.0 | 500 | 1.3277 |
+| 1.4134 | 1.05 | 525 | 1.3237 |
+| 1.1459 | 1.1 | 550 | 1.3263 |
+| 1.3473 | 1.15 | 575 | 1.3225 |
+| 1.1879 | 1.2 | 600 | 1.3232 |
+| 1.3742 | 1.25 | 625 | 1.3217 |
+| 1.1129 | 1.3 | 650 | 1.3225 |
+| 1.3756 | 1.35 | 675 | 1.3201 |
+| 1.1268 | 1.4 | 700 | 1.3216 |
+| 1.4186 | 1.45 | 725 | 1.3200 |
+| 1.1602 | 1.5 | 750 | 1.3196 |
+| 1.4368 | 1.55 | 775 | 1.3189 |
+| 1.1397 | 1.6 | 800 | 1.3193 |
+| 1.3991 | 1.65 | 825 | 1.3186 |
+| 1.1293 | 1.7 | 850 | 1.3190 |
+| 1.4509 | 1.75 | 875 | 1.3177 |
+| 1.1433 | 1.8 | 900 | 1.3175 |
+| 1.3638 | 1.85 | 925 | 1.3170 |
+| 1.144 | 1.9 | 950 | 1.3172 |
+| 1.3376 | 1.95 | 975 | 1.3170 |
+| 1.1152 | 2.0 | 1000 | 1.3170 |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.39.3
+- Pytorch 2.1.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,31 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "microsoft/phi-2",
+ "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": 32,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "k_proj",
+ "v_proj",
+ "q_proj",
+ "dense"
+ ],
+ "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:f37e419bdc4e96d362c82b7d19d42545fea372c315898289c7c2d3cf5bf80c54
+size 83920464

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f8d585734f31bfcae63cd51e26b61a1d05f1a94d1e01eb362c87e48a0839bb
+size 4920