End of training

README.md

@@ -36,12 +36,10 @@ The following hyperparameters were used during training:
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 2
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 50
-- num_epochs: 10
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -10,16 +10,16 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 8,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
-  "target_modules": ".*(text_model|modality_projection|perceiver_resampler).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$",
+  "target_modules": ".*(text_model|modality_projection|perceiver_resampler).*(down_proj|up_proj|k_proj|v_proj).*$",
   "task_type": null,
   "use_dora": false,
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68f9431d5ec7a08cd739f176f5f8ba5fb6f79cb0fb37b27a9939f0d8a59abc40
-size 746528304
+oid sha256:7e566c0f70b30adabd6c0def369a7fcbba06fcae6074042edd85dca3d70c37c8
+size 54153232

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a59b34fbe786f0ad42a1fea86dd852176c38c56313508aa9f0ac07996fd8c27
+oid sha256:2a7cdafa13a848b10f9b5b650522cdb5d917ca05fb5ec0956f17fe8e6ceea64f
 size 5240