Model save

README.md

@@ -15,8 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
 # mgpt-lora-multi-belgium-balanced-1024
 
 This model is a fine-tuned version of [ai-forever/mGPT](https://huggingface.co/ai-forever/mGPT) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.4204
 
 ## Model description
 
@@ -36,16 +34,16 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 1
-- eval_batch_size: 1
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 8
-- total_train_batch_size: 8
-- total_eval_batch_size: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
 - optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 1356
+- lr_scheduler_warmup_steps: 339
 - num_epochs: 1
 
 ### Training results

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "c_proj",
-    "c_attn"
+    "c_attn",
+    "c_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa7270ff8c43a83f1579543374def1a8b497e34100d8e7b3c5f4e1b4c8ec7b15
+oid sha256:b21ba1cad039f38de5e8e2d1240cd6f19fb80b01acb6dc5bfe81e8b66b442280
 size 34621712

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8ee014ed39394825f838989fd2c8c1db60e79db6e53e4d3d5c0d00c1f079aa0
+oid sha256:3ead0c237617dec1883d24b78d9c6a79e83527bb9a22e40a2c2c0b36e160f85c
 size 5368