Training in progress, step 1000

adapter_config.json

@@ -3,7 +3,7 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen3-0.6B",
+  "base_model_name_or_path": "checkpoint-1000",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -29,8 +29,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4ddc5587a7c4404aef6ba30aa8c5e6068425b48c2f7bcf4b98172a4c4c027fe
+oid sha256:e1d802bbf1c6c65a249c3be723f05726005ce0c40b1791db6fd73cb6417e7d00
 size 36715216

config.json

@@ -143,6 +143,126 @@
   },
   "downsample_rate": 5,
   "dtype": "bfloat16",
+  "encoder": {
+    "_name_or_path": "zai-org/GLM-ASR-Nano-2512",
+    "architectures": [
+      "GlmAsrForConditionalGeneration"
+    ],
+    "audio_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "dtype": null,
+      "eos_token_id": null,
+      "finetuning_task": null,
+      "head_dim": 64,
+      "hidden_act": "gelu",
+      "hidden_size": 1280,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 5120,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "max_position_embeddings": 1500,
+      "model_type": "glmasr_encoder",
+      "num_attention_heads": 20,
+      "num_hidden_layers": 32,
+      "num_key_value_heads": 20,
+      "num_mel_bins": 128,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "pad_token_id": null,
+      "partial_rotary_factor": 0.5,
+      "prefix": null,
+      "problem_type": null,
+      "return_dict": true,
+      "rope_parameters": {
+        "partial_rotary_factor": 0.5,
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      },
+      "sep_token_id": null,
+      "task_specific_params": null,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null
+    },
+    "audio_token_id": 59260,
+    "dtype": "bfloat16",
+    "hidden_size": 2048,
+    "model_type": "glmasr",
+    "num_mel_bins": 128,
+    "projector_hidden_act": "gelu",
+    "text_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_bias": false,
+      "attention_dropout": 0.0,
+      "bos_token_id": 1,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "dtype": null,
+      "eos_token_id": [
+        59246,
+        59253,
+        59255
+      ],
+      "finetuning_task": null,
+      "head_dim": 128,
+      "hidden_act": "silu",
+      "hidden_size": 2048,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 6144,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "max_position_embeddings": 8192,
+      "mlp_bias": false,
+      "model_type": "llama",
+      "num_attention_heads": 16,
+      "num_hidden_layers": 28,
+      "num_key_value_heads": 4,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "pretraining_tp": 1,
+      "problem_type": null,
+      "return_dict": true,
+      "rms_norm_eps": 1e-05,
+      "rope_parameters": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      },
+      "sep_token_id": null,
+      "task_specific_params": null,
+      "tie_word_embeddings": false,
+      "tokenizer_class": null,
+      "use_cache": true,
+      "vocab_size": 59264
+    },
+    "vocab_size": 59264
+  },
   "encoder_conv_layers": [
     [
       1,
@@ -169,11 +289,11 @@
     "v_proj"
   ],
   "mask_feature_length": 10,
-  "mask_feature_min_masks": 0,
-  "mask_feature_prob": 0.0,
-  "mask_time_length": 10,
+  "mask_feature_min_masks": 2,
+  "mask_feature_prob": 0.05,
+  "mask_time_length": 15,
   "mask_time_min_masks": 2,
-  "mask_time_prob": 0.05,
+  "mask_time_prob": 0.1,
   "max_new_tokens": 128,
   "min_new_tokens": 0,
   "model_dtype": "bfloat16",
@@ -264,7 +384,6 @@
   "transformers_version": "5.0.0.dev0",
   "use_cache": false,
   "use_lora": true,
-  "use_specaugment": false,
-  "user_prompt": "Please transcribe this English audio into text: <audio>",
+  "use_specaugment": true,
   "vocab_size": 151670
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:313aec7864cc3fe4d2665e078ed53c50de654a555f8a0bd5feb2e7510f1c5b40
+oid sha256:a2c9cdfcf8a55bad3b4c85dfa7218c8e63fb074a6b374673b0d0442d4b040bec
 size 25172384

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c16721198b4814a36169d05045565ed13372103aae1e2bf5a256f125117e24b7
+oid sha256:6cb17eae71944b178ffca38182449645e5a12a962efd2d3eb01b9a84d725d5ed
 size 5201