Model save

README.md

@@ -0,0 +1,63 @@
+---
+base_model: meta-llama/Meta-Llama-3-8B
+datasets:
+- generator
+library_name: peft
+license: llama3
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: Llama-3-8b-sft-qlora
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/nlp-xiaobo/huggingface/runs/6m5wzyco)
+# Llama-3-8b-sft-qlora
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator 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
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- 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
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.42.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "/scratch2/nlp/plm/Meta-Llama-3-8B",
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "k_proj",
-    "down_proj",
-    "gate_proj",
+    "q_proj",
     "up_proj",
+    "gate_proj",
     "v_proj",
-    "o_proj",
-    "q_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.1104476526052114e+19,
+    "train_loss": 0.0,
+    "train_runtime": 10.0721,
+    "train_samples": 207864,
+    "train_samples_per_second": 11888.555,
+    "train_steps_per_second": 1486.082
+}

runs/Jul03_15-20-57_yofuria-System-Product-Name/events.out.tfevents.1719991599.yofuria-System-Product-Name.1685246.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e927ae70bb109f57f12084a0ebc533be4a36a8ce2e5c0f4bba59f1b703e26b4
+size 5527

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.1104476526052114e+19,
+    "train_loss": 0.0,
+    "train_runtime": 10.0721,
+    "train_samples": 207864,
+    "train_samples_per_second": 11888.555,
+    "train_steps_per_second": 1486.082
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c97f0b3cf6af4684cf10f5b3b16c4c61e6c10905899196fd0ab394c20feb7d20
-size 4795
+oid sha256:a2f5067f1985f081dd8a0167604545d06bd0d9f901c5e24a1a22153816c8b281
+size 5240