Training in progress, epoch 1

config.json

@@ -0,0 +1,132 @@
+{
+  "_name_or_path": "ntu-spml/distilhubert",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": false,
+  "architectures": [
+    "HubertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": false,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "\u062e\u0627\u0621",
+    "1": "\u062b\u0627\u0621",
+    "10": "\u0643\u0627\u0641",
+    "11": "\u0627\u0644\u0641",
+    "12": "\u0642\u0627\u0641",
+    "13": "\u0641\u0627\u0621",
+    "14": "\u0647\u0627\u0621",
+    "15": "\u062f\u0627\u0644",
+    "16": "\u0628\u0627\u0621",
+    "17": "\u0637\u0627\u0621",
+    "18": "\u063a\u064a\u0646",
+    "19": "\u0633\u064a\u0646",
+    "2": "\u0646\u0648\u0646",
+    "20": "\u062a\u0627\u0621",
+    "21": "\u0638\u0627\u0621",
+    "22": "\u064a\u0627\u0621",
+    "23": "\u0630\u0627\u0644",
+    "24": "\u0644\u0627\u0645",
+    "25": "\u062c\u064a\u0645",
+    "26": "\u0639\u064a\u0646",
+    "27": "\u0648\u0627\u0648",
+    "3": "\u0645\u064a\u0645",
+    "4": "\u0636\u0627\u062f",
+    "5": "\u0631\u0627\u0621",
+    "6": "\u0634\u064a\u0646",
+    "7": "\u0632\u0627\u064a",
+    "8": "\u0635\u0627\u062f",
+    "9": "\u062d\u0627\u0621"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "\u0627\u0644\u0641": "11",
+    "\u0628\u0627\u0621": "16",
+    "\u062a\u0627\u0621": "20",
+    "\u062b\u0627\u0621": "1",
+    "\u062c\u064a\u0645": "25",
+    "\u062d\u0627\u0621": "9",
+    "\u062e\u0627\u0621": "0",
+    "\u062f\u0627\u0644": "15",
+    "\u0630\u0627\u0644": "23",
+    "\u0631\u0627\u0621": "5",
+    "\u0632\u0627\u064a": "7",
+    "\u0633\u064a\u0646": "19",
+    "\u0634\u064a\u0646": "6",
+    "\u0635\u0627\u062f": "8",
+    "\u0636\u0627\u062f": "4",
+    "\u0637\u0627\u0621": "17",
+    "\u0638\u0627\u0621": "21",
+    "\u0639\u064a\u0646": "26",
+    "\u063a\u064a\u0646": "18",
+    "\u0641\u0627\u0621": "13",
+    "\u0642\u0627\u0641": "12",
+    "\u0643\u0627\u0641": "10",
+    "\u0644\u0627\u0645": "24",
+    "\u0645\u064a\u0645": "3",
+    "\u0646\u0648\u0646": "2",
+    "\u0647\u0627\u0621": "14",
+    "\u0648\u0627\u0648": "27",
+    "\u064a\u0627\u0621": "22"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7c512eb7e8381cce3c1be9b727010f9632e4941c768c5ec383bf704b124ddef
+size 94790240

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

runs/Jul15_10-34-22_a30b4e5ca9ec/events.out.tfevents.1721039716.a30b4e5ca9ec.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a01bdb29b777fc7bab97fdddd3594ef6d3bdf200724e9a2b80c6dd4fb04246de
+size 54564

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd8ff9d63785cfa9c21d5d3c102863736b3f94b93b5bddd53ff40dc74e745c2e
+size 5176