Model save

README.md

@@ -0,0 +1,69 @@
+---
+license: mit
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+base_model: microsoft/phi-2
+model-index:
+- name: phi-2-sft-ultrachat-lora
+  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-sft-ultrachat-lora
+
+This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2118
+
+## 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
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.2101        | 1.0   | 7993 | 1.2118          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu118
+- Datasets 2.14.6
+- Tokenizers 0.15.2

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35d69b156bb3fdce3c9a59e7d36805244f50e6fd8da08ddd0796632e253f5974
+oid sha256:2aa003956b29e05f1b63aa859edcae1b240d153b0900f7613998eb44d72ec4f0
 size 41977616

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.2118308544158936,
+    "eval_runtime": 1435.6881,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 19.717,
+    "eval_steps_per_second": 0.616,
+    "train_loss": 1.2476971375693162,
+    "train_runtime": 45278.0566,
+    "train_samples": 207865,
+    "train_samples_per_second": 5.649,
+    "train_steps_per_second": 0.177
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.2118308544158936,
+    "eval_runtime": 1435.6881,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 19.717,
+    "eval_steps_per_second": 0.616
+}

runs/Feb28_19-01-03_gpu4-119-4/events.out.tfevents.1709107312.gpu4-119-4.114762.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5c79d47b3fb6a2ca520590bfda3a02b05e083fdcd6a06bbd9e4c1636c8b3177
-size 252857
+oid sha256:c266f6249a0157015d5fee7eb184a18b1bdafd3710e4cb927a7e0e3c95464e01
+size 256308

runs/Feb28_19-01-03_gpu4-119-4/events.out.tfevents.1709154026.gpu4-119-4.114762.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a96fd914b21059dcba50ca0f06f3bc092f22e8d59fbab0a73ab2b8def68a528
+size 359

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.2476971375693162,
+    "train_runtime": 45278.0566,
+    "train_samples": 207865,
+    "train_samples_per_second": 5.649,
+    "train_steps_per_second": 0.177
+}