Model save

README.md

@@ -14,7 +14,7 @@ model-index:
 <!-- 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/bamalingua-bamalingua/Bamalingua-madlat/runs/mnejoedh)
+[<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/bamalingua-bamalingua/Bamalingua-madlat/runs/l1ah6hmb)
 # madlad-bm-fr
 
 This model is a fine-tuned version of [google/madlad400-3b-mt](https://huggingface.co/google/madlad400-3b-mt) on an unknown dataset.
@@ -37,14 +37,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.001
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
+- gradient_accumulation_steps: 2
 - total_train_batch_size: 16
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- training_steps: 40
+- lr_scheduler_warmup_steps: 100
+- training_steps: 1000
 
 ### Framework versions
 

adapter_config.json

@@ -13,25 +13,25 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.01,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "wo",
     "q",
-    "k",
-    "wi_0",
     "wi_1",
+    "wi_0",
+    "k",
     "v",
-    "o"
+    "o",
+    "wo"
   ],
   "target_parameters": null,
   "task_type": "SEQ_2_SEQ_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d9a94d5cf4a0cd69f841306af2cedf06818d53e1711e72e4006f6086e365a9c
-size 188910720
+oid sha256:c37f03e30916c742c86ffb33b7b40e2a23ee6e8be08bb15418eca556c6fcb989
+size 377655120

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03048a9813e893c5fe718215e2ff47b3bef689db97135fdaf79a117c60dcb34c
+oid sha256:590112cdb69410d9dc24dab5981a0de779595745d7617f6a79f70c361a2d4e91
 size 5969