Training in progress, step 50

README.md

@@ -27,7 +27,7 @@ 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/erdenkalilaeyev-bah-e-ehir-cyprus-university/huggingface/runs/pddfjaby) 
+[<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/erdenkalilaeyev-bah-e-ehir-cyprus-university/huggingface/runs/bsu7eh33) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -13,7 +13,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 8,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
@@ -23,20 +23,12 @@
     "embed_tokens"
   ],
   "peft_type": "LORA",
-  "r": 32,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "k_proj",
     "v_proj",
-    "fc2",
-    "q_proj",
-    "gate_proj",
-    "fc1",
-    "up_proj",
-    "down_proj",
-    "out_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dcd26aadf24f808813c023ca32bea2b31a427e55ce3bd78d4b712085b07376b
-size 2993118096
+oid sha256:e198a48c4a129ecd196a3dfa192389e899b093f1f6ccb804438dbb16a01c2622
+size 2697942384

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a305404e6f9dc8297963c448c1d49430687151ccbc8db599f96037eb3943bafb
+oid sha256:da0b388d2d5c9938e523ade0f9a37b4b8fb1b621c8bfd42edbb506309e93e711
 size 33384822

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2302e944cf78fcb479b1349e190717a509833854ebcf407a67a33cdd9e6f4bd6
+oid sha256:1790ce2ff92522986951769c96444b9a6b6a20279d5251b0f21d5949f55416b0
 size 5752