End of training

README.md

@@ -0,0 +1,55 @@
+---
+library_name: transformers
+language:
+- en
+tags:
+- generated_from_trainer
+datasets:
+- maliced/l2-arctic
+model-index:
+- name: MDD Transformer Tiny
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# MDD Transformer Tiny
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the L2 Arctic dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 4000
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.52.1
+- Pytorch 2.7.0+cpu
+- Datasets 3.6.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,65 @@
+{
+  "architectures": [
+    "MDDTransformer"
+  ],
+  "batch_first": true,
+  "d_model": 32,
+  "dim_feedforward": 256,
+  "hidden_dropout_prob": 0.1,
+  "input_channels": 2,
+  "max_source_positions": 3000,
+  "model_type": "mdd_transformer",
+  "num_attention_heads_decoder": 2,
+  "num_attention_heads_encoder": 4,
+  "num_classes": 43,
+  "num_cross_attention_heads": 2,
+  "num_decoder_layers": 2,
+  "num_encoder_layers": 2,
+  "num_mel_bins": 80,
+  "projector_activation": "softmax",
+  "tokens": [
+    "SIL",
+    "AA",
+    "AE",
+    "AH",
+    "AO",
+    "AW",
+    "AX",
+    "AY",
+    "B",
+    "CH",
+    "D",
+    "DH",
+    "EH",
+    "ER",
+    "EY",
+    "F",
+    "G",
+    "HH",
+    "IH",
+    "IY",
+    "JH",
+    "K",
+    "L",
+    "M",
+    "N",
+    "NG",
+    "OW",
+    "OY",
+    "P",
+    "R",
+    "S",
+    "SH",
+    "T",
+    "TH",
+    "UH",
+    "UW",
+    "V",
+    "W",
+    "Y",
+    "Z",
+    "ZH"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f291c1714d1e5a15c46164bc2a10b97d0fc5a41cb5deadef791e846dc889424f
+size 1009420

runs/May27_16-11-16_malice-laptop/events.out.tfevents.1748355078.malice-laptop.11100.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c720f110efed1c99126b1563bb71d8d34b34bcfc14deb60a76a0b13b6370e09
+size 5332

runs/May27_16-12-13_malice-laptop/events.out.tfevents.1748355134.malice-laptop.6824.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e78fee00a4f11ff51899dbd65a0789a5341028b1e8170efb5c355a59e550ffe7
+size 5332

runs/May27_16-37-57_malice-laptop/events.out.tfevents.1748356678.malice-laptop.25796.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95f88132bd68add91882bc13b8a5ce5860403435d3022fae70b0ac152b8906e8
+size 6789

runs/May28_09-27-16_malice-laptop/events.out.tfevents.1748417237.malice-laptop.8860.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a272f3ac2d0301112f89bafbc4acbd8d208457e2ad9ee63b4a0528fdda1ffb7
+size 13752

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b17ce7621ffe3a4122167d221279f8d655576ed09c879cb4a647add2b919921
+size 5841