Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Phi-3-mini-4k-instruct
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: Phi-3-mini-4k-instruct-8bit-LMSYS-finetuned-v03
+  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-mini-4k-instruct-8bit-LMSYS-finetuned-v03
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4867
+
+## 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: 5e-07
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 0
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.2
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.43.3
+- Pytorch 2.2.2+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.4867475926876068,
+    "eval_runtime": 138.0836,
+    "eval_samples": 558,
+    "eval_samples_per_second": 4.041,
+    "eval_steps_per_second": 4.041,
+    "total_flos": 1.3318012341259592e+18,
+    "train_loss": 0.5598785406739636,
+    "train_runtime": 54928.4731,
+    "train_samples_per_second": 0.984,
+    "train_steps_per_second": 0.984
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.4867475926876068,
+    "eval_runtime": 138.0836,
+    "eval_samples": 558,
+    "eval_samples_per_second": 4.041,
+    "eval_steps_per_second": 4.041
+}

tokenizer_config.json

@@ -123,7 +123,7 @@
   "legacy": false,
   "model_max_length": 4096,
   "pad_token": "<unk>",
-  "padding_side": "right",
+  "padding_side": "left",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.3318012341259592e+18,
+    "train_loss": 0.5598785406739636,
+    "train_runtime": 54928.4731,
+    "train_samples_per_second": 0.984,
+    "train_steps_per_second": 0.984
+}