README and json

README.md

@@ -0,0 +1,110 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base
+tags:
+- audio-classification
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: wav2vec2-base_down_on
+  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. -->
+
+# wav2vec2-base_down_on
+
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the MatsRooth/down_on dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1385
+- Accuracy: 0.9962
+
+MatsRooth/down_on is the part of [superb ks](https://huggingface.co/datasets/superb)
+with the labels *down* and *on*.
+Superb ks is in turn derived from (Speech Commands dataset v1.0)[https://www.tensorflow.org/datasets/catalog/speech_commands].
+Train/validation/test splits are as in superb ks.
+
+## Intended uses 
+
+MatsRooth/down_on and this model exercise methodology for creating an audio classification dataset from
+local directory structures and audio files, and check whether fine tuning wav2vec2 classification with two labels works
+well.
+
+## Training procedure
+Training used 'sbatch' on a cluster and the program [run_audio_classification.py](https://github.com/huggingface/transformers).
+'down_on.sub' is below, start it with 'sbatch down_on.sub'.
+
+'''
+#!/bin/bash
+#SBATCH -J down_on                         # Job name
+#SBATCH -o down_on_%j.out                  # Name of stdout output log file (%j expands to jobID)
+#SBATCH -e down_on_%j.err                  # Name of stderr output log file (%j expands to jobID)
+#SBATCH -N 1                                 # Total number of nodes requested
+#SBATCH -n 1                                 # Total number of cores requested
+#SBATCH --mem=5000                          # Total amount of (real) memory requested (per node)
+#SBATCH -t 10:00:00                          # Time limit (hh:mm:ss)
+#SBATCH --partition=gpu              # Request partition for resource allocation
+#SBATCH --gres=gpu:1                         # Specify a list of generic consumable resources (per node)
+
+cd ~/ac_h
+/home/mr249/env/hugh/bin/python run_audio_classification.py \
+    --model_name_or_path facebook/wav2vec2-base \
+    --dataset_name MatsRooth/down_on \
+    --output_dir wav2vec2-base_down_on \
+    --overwrite_output_dir \
+    --remove_unused_columns False \
+    --do_train \
+    --do_eval \
+    --fp16 \
+    --learning_rate 3e-5 \
+    --max_length_seconds 1 \
+    --attention_mask False \
+    --warmup_ratio 0.1 \
+    --num_train_epochs 5 \
+    --per_device_train_batch_size 32 \
+    --gradient_accumulation_steps 4 \
+    --per_device_eval_batch_size 32 \
+    --dataloader_num_workers 1 \
+    --logging_strategy steps \
+    --logging_steps 10 \
+    --evaluation_strategy epoch \
+    --save_strategy epoch \
+    --load_best_model_at_end True \
+    --metric_for_best_model accuracy \
+    --save_total_limit 3 \
+    --seed 0
+'''
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 0
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.6089        | 1.0   | 29   | 0.1385          | 0.9962   |
+| 0.1297        | 2.0   | 58   | 0.0513          | 0.9962   |
+| 0.0835        | 3.0   | 87   | 0.0389          | 0.9885   |
+| 0.058         | 4.0   | 116  | 0.0302          | 0.9923   |
+| 0.0481        | 5.0   | 145  | 0.0245          | 0.9942   |
+
+
+### Framework versions
+
+- Transformers 4.31.0.dev0
+- Pytorch 2.0.1+cu117
+- Datasets 2.13.1
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9961612284069098,
+    "eval_loss": 0.13847295939922333,
+    "eval_runtime": 35.6829,
+    "eval_samples_per_second": 14.601,
+    "eval_steps_per_second": 0.476,
+    "train_loss": 0.17887740957325904,
+    "train_runtime": 628.2613,
+    "train_samples_per_second": 29.494,
+    "train_steps_per_second": 0.231
+}

config.json

@@ -0,0 +1,127 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base",
+  "activation_dropout": 0.0,
+  "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": [
+    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,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "finetuning_task": "audio-classification",
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "down",
+    "1": "on"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "down": "0",
+    "on": "1"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "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_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "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": "4.31.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9961612284069098,
+    "eval_loss": 0.13847295939922333,
+    "eval_runtime": 35.6829,
+    "eval_samples_per_second": 14.601,
+    "eval_steps_per_second": 0.476
+}

preprocessor_config.json

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

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.17887740957325904,
+    "train_runtime": 628.2613,
+    "train_samples_per_second": 29.494,
+    "train_steps_per_second": 0.231
+}

trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": 0.9961612284069098,
+  "best_model_checkpoint": "wav2vec2-base_down_on/checkpoint-29",
+  "epoch": 5.0,
+  "global_step": 145,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9999999999999998e-05,
+      "loss": 0.6868,
+      "step": 10
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 2.884615384615385e-05,
+      "loss": 0.6089,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9961612284069098,
+      "eval_loss": 0.13847295939922333,
+      "eval_runtime": 36.4538,
+      "eval_samples_per_second": 14.292,
+      "eval_steps_per_second": 0.466,
+      "step": 29
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.6538461538461538e-05,
+      "loss": 0.3131,
+      "step": 30
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 2.423076923076923e-05,
+      "loss": 0.151,
+      "step": 40
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.1923076923076924e-05,
+      "loss": 0.1297,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9961612284069098,
+      "eval_loss": 0.051253072917461395,
+      "eval_runtime": 36.428,
+      "eval_samples_per_second": 14.302,
+      "eval_steps_per_second": 0.467,
+      "step": 58
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1.9615384615384617e-05,
+      "loss": 0.1075,
+      "step": 60
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.7307692307692306e-05,
+      "loss": 0.084,
+      "step": 70
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.5e-05,
+      "loss": 0.0835,
+      "step": 80
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9884836852207294,
+      "eval_loss": 0.038927894085645676,
+      "eval_runtime": 36.427,
+      "eval_samples_per_second": 14.303,
+      "eval_steps_per_second": 0.467,
+      "step": 87
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 1.2692307692307693e-05,
+      "loss": 0.0741,
+      "step": 90
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 1.0384615384615384e-05,
+      "loss": 0.0684,
+      "step": 100
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 8.076923076923077e-06,
+      "loss": 0.058,
+      "step": 110
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9923224568138196,
+      "eval_loss": 0.030210411176085472,
+      "eval_runtime": 36.3815,
+      "eval_samples_per_second": 14.32,
+      "eval_steps_per_second": 0.467,
+      "step": 116
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 5.76923076923077e-06,
+      "loss": 0.0863,
+      "step": 120
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 3.4615384615384617e-06,
+      "loss": 0.0669,
+      "step": 130
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 0.0481,
+      "step": 140
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9942418426103646,
+      "eval_loss": 0.024523714557290077,
+      "eval_runtime": 36.414,
+      "eval_samples_per_second": 14.308,
+      "eval_steps_per_second": 0.467,
+      "step": 145
+    },
+    {
+      "epoch": 5.0,
+      "step": 145,
+      "total_flos": 1.682270628192e+17,
+      "train_loss": 0.17887740957325904,
+      "train_runtime": 628.2613,
+      "train_samples_per_second": 29.494,
+      "train_steps_per_second": 0.231
+    }
+  ],
+  "max_steps": 145,
+  "num_train_epochs": 5,
+  "total_flos": 1.682270628192e+17,
+  "trial_name": null,
+  "trial_params": null
+}