Training in progress, epoch 0

config.json

@@ -0,0 +1,110 @@
+{
+  "_name_or_path": "philschmid/tiny-random-wav2vec2",
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    32,
+    32,
+    32
+  ],
+  "conv_kernel": [
+    8,
+    8,
+    8
+  ],
+  "conv_stride": [
+    4,
+    4,
+    4
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 16,
+  "id2label": {
+    "0": "onboard",
+    "1": "restock",
+    "2": "return",
+    "3": "unknown"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 20,
+  "label2id": {
+    "onboard": "0",
+    "restock": "1",
+    "return": "2",
+    "unknown": "3"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 2,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 2,
+  "num_conv_pos_embeddings": 16,
+  "num_feat_extract_layers": 3,
+  "num_hidden_layers": 4,
+  "num_negatives": 10,
+  "output_hidden_size": 16,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40b500343271885c17609f06d8d18af3590834de8fc0248d3ea5b9d812001ea3
+size 138624

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": false,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

runs/Feb21_10-11-18_voice-ai-transformer/events.out.tfevents.1708510337.voice-ai-transformer.12536.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8853505d5f75e232f1dbe083c2cec677a084e7c99de9068bd64b51aea9628e8d
+size 20438

runs/Feb21_10-11-18_voice-ai-transformer/events.out.tfevents.1708523120.voice-ai-transformer.12536.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf0676706531fe48753d2b6921932ceb7939b65cba989761ded9d74eadbe1e4
+size 10563

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a3031a74b4466b0953d4c47c499383efb59e12d1766841a46e84728fc9608e8
+size 4219