Training in progress, step 500

adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-0.6B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:814316293a633a52e1fc4d99f87d7c51269cdaef1bb231290e7da5f104fb2ddc
+size 36715216

config.json

@@ -156,7 +156,7 @@
     ]
   ],
   "encoder_dim": 1280,
-  "freeze_projector": false,
+  "freeze_projector": true,
   "inference_warmup_tokens": 10,
   "label_smoothing": 0.0,
   "length_penalty": 1.0,
@@ -264,7 +264,7 @@
   "transformers_version": "5.0.0.dev0",
   "use_cache": false,
   "use_lora": true,
-  "use_specaugment": true,
+  "use_specaugment": false,
   "user_prompt": "Please transcribe this English audio into text: <audio>",
   "vocab_size": 151670
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd81933460f9e0e2c85d61b9ba4306da250cdd4810b930971ead7cd572dcd15e
+oid sha256:ae8deda98b54ef1819a1ad53bac391559c73d6d1f9f5e00728a514a8e594b685
 size 5201