Training in progress, epoch 1

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: llama3.18B-Fine-tuned1
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 
@@ -27,17 +27,17 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/huzaifanaveedd111-fast-nuces/huggingface/runs/eneico7y) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/huzaifanaveedd111-fast-nuces/huggingface/runs/b4ixch8e) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.19.0
-- Transformers: 4.53.0
+- TRL: 0.19.1
+- Transformers: 4.53.1
 - Pytorch: 2.6.0+cu124
-- Datasets: 3.6.0
+- Datasets: 4.0.0
 - Tokenizers: 0.21.2
 
 ## Citations

adapter_config.json

@@ -20,6 +20,7 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "qalora_group_size": 16,
   "r": 8,
   "rank_pattern": {},
   "revision": null,
@@ -30,5 +31,6 @@
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,
+  "use_qalora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a4580fbbb6ffbbe17e853067ff56865c9041f9b70afb1fef4e5c32a88719683
+oid sha256:98f98b7a046163c7f21609c2cef5527d3f135b6b411377fdca4e2755b9bdf16f
 size 13648432

runs/Jul11_07-31-30_c35d55f5a272/events.out.tfevents.1752219098.c35d55f5a272.337.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c829fc76a175a1cda1cfd64a03e910e6866c238ad1d562e713d0e56cb42a22a
+size 6307

runs/Jul11_07-35-56_c35d55f5a272/events.out.tfevents.1752219386.c35d55f5a272.3801.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8a5c764963cb8e8650765afa2fdf3e7c62adb8c4a3248f6b9be360f4c8e5ebe
+size 6631

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dc6c7152949a5c0fe1bf012b046359c801fe5cbdc5964a72196215663ee2899
+oid sha256:954378ab4e08bb7c978ed3e9007b144251709bed68ff5ece28f2d5b53db7bbce
 size 5752