Model save

README.md

@@ -0,0 +1,55 @@
+---
+license: mit
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: microsoft/phi-2
+model-index:
+- name: phi-2-finetuned-big
+  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-finetuned-big
+
+This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1
+- training_steps: 600
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- 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,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "fc2",
+    "v_proj",
+    "fc1",
+    "Wqkv",
+    "lm_head"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b61841a04498984a4aa30fae23cb25532463112c4c7e583881f8fc912a5bfcf
+size 604714936

runs/Jan13_22-36-44_ba93f2c7300c/events.out.tfevents.1705185408.ba93f2c7300c.2477.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0718492c734727dfbe5e59e69275c70c438aabc52dcf6bb3b221fdc8f6e6a4e
+size 5872

runs/Jan13_22-37-26_ba93f2c7300c/events.out.tfevents.1705185446.ba93f2c7300c.2477.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e14364bbdb1c5b22a8a94a399c8d5815e462fbbe77e9e8fbe9cd1c599a5868c8
+size 5452

runs/Jan13_22-39-47_ba93f2c7300c/events.out.tfevents.1705185589.ba93f2c7300c.2477.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbddcb2532e105e20b564b5a1ad0113abeab30d39a15a4c107c1e23aa91b2114
+size 5359

runs/Jan13_22-41-05_ba93f2c7300c/events.out.tfevents.1705185671.ba93f2c7300c.2477.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23bee38d8360b9e71343fd2ab55ef3f54d98c27522ab057a32fd0892d6902c32
+size 7388

runs/Jan13_22-45-34_ba93f2c7300c/events.out.tfevents.1705185936.ba93f2c7300c.2477.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae4a2c08c6d8189725a81865226b6decc13007d877a0ed62d4116b8d935b93cf
+size 4184

runs/Jan13_22-46-21_ba93f2c7300c/events.out.tfevents.1705185981.ba93f2c7300c.7320.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ea42aadcdaba36ff0750bdf1901036a032bd318cff8b1f6297d18fb516e441e
+size 7284

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a1a1e2c9438a2fd6af58c2824b1e327eccd23df60ba1fa9a3b754f2ab596bc3
+size 4728