Model save

README.md

@@ -1,9 +1,9 @@
 ---
 library_name: peft
 license: apache-2.0
-base_model: google/madlad400-3b-mt
+base_model: jbochi/madlad400-3b-mt
 tags:
-- base_model:adapter:google/madlad400-3b-mt
+- base_model:adapter:jbochi/madlad400-3b-mt
 - lora
 - transformers
 model-index:
@@ -14,10 +14,10 @@ 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/l1ah6hmb)
+[<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/97dtmqsk)
 # 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.
+This model is a fine-tuned version of [jbochi/madlad400-3b-mt](https://huggingface.co/jbochi/madlad400-3b-mt) on an unknown dataset.
 
 ## Model description
 
@@ -44,8 +44,8 @@ The following hyperparameters were used during training:
 - 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
-- lr_scheduler_warmup_steps: 100
-- training_steps: 1000
+- lr_scheduler_warmup_steps: 10
+- training_steps: 120
 
 ### Framework versions
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/madlad400-3b-mt",
+  "base_model_name_or_path": "jbochi/madlad400-3b-mt",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q",
     "wi_1",
-    "wi_0",
     "k",
+    "wo",
     "v",
     "o",
-    "wo"
+    "wi_0",
+    "q"
   ],
   "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:c37f03e30916c742c86ffb33b7b40e2a23ee6e8be08bb15418eca556c6fcb989
+oid sha256:ef0b981bf4cb7b49cd9e57a9f8393fc806aab652c933d344f7d649b19183731d
 size 377655120

tokenizer_config.json

@@ -1,5 +1,5 @@
 {
-  "add_prefix_space": null,
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:590112cdb69410d9dc24dab5981a0de779595745d7617f6a79f70c361a2d4e91
+oid sha256:96d92d485f95500cc7b523016e3add629a32cc75691dab30405ffccd0ac4cdf5
 size 5969