End of training

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: microsoft/Phi-3-mini-4k-instruct
+model-index:
+- name: phi-3-finetuned-med-text
+  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. -->
+
+# phi-3-finetuned-med-text
+
+This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on the None dataset.
+
+## 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
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- training_steps: 1000
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a00408028957d3d1c5805a6d3d6fbeaa8b75093627a5d3ad917214254924c3ff
+size 52446056

runs/Apr24_16-54-28_e0b8752f31cf/events.out.tfevents.1713977677.e0b8752f31cf.177.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd9e650e93e4303e706977671f62d0dbe6fa41d046c1a7878b9d87590901fb3f
+size 5512

runs/Apr24_17-29-52_e0b8752f31cf/events.out.tfevents.1713979801.e0b8752f31cf.14249.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eafb6b75b3b7bfd7a0ec9e966d4108c54e663e6bdc4db42aaf835c060822fa9e
+size 7020

runs/Apr24_17-58-21_e0b8752f31cf/events.out.tfevents.1713981502.e0b8752f31cf.22911.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b396805d163b0238cbdc3d58b6ec3450213fcaf2d9f8921e1f5d8d033309740
+size 7020

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf12d913283fa21c6dd5168c08a67c7288a6bf15b30d547f23eee84cb474a5e3
+size 4728