Training in progress, epoch 1

README.md

@@ -0,0 +1,52 @@
+---
+license: other
+base_model: microsoft/phi-2
+tags:
+- generated_from_trainer
+model-index:
+- name: phi-2_0-finetuned
+  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-2_0-finetuned
+
+This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown 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
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "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,
+  "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": [
+    "out_proj",
+    "fc1",
+    "Wqkv",
+    "fc2"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ba17178121819c51484cd36d9e13a59b7c7764d2520d1fe201ee359c00471c3
+size 83919184

runs/Dec14_23-09-14_ed47a091b7a7/events.out.tfevents.1702595357.ed47a091b7a7.360.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13cb692720cae3382b2030aa2d3122193f983660308615dfe726c86686bed0ef
+size 6664

runs/Dec14_23-37-30_ed47a091b7a7/events.out.tfevents.1702597060.ed47a091b7a7.360.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2cfbabc6bb5f00fc71942b36ec9fb4862643d5a51e2ca32791df613f150cefa
+size 4360

runs/Dec14_23-54-27_ed47a091b7a7/events.out.tfevents.1702598069.ed47a091b7a7.18901.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c103620db6c62a0b76b388fdd3a271f5f237a04e89e29e64d3e0d4088957a9c
+size 5903

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95f21066116443e5663e0958a46cfa3f084aa685716407ff3b9bb50b5559b79b
+size 4600