End of training
Browse files- README.md +69 -0
- config.json +126 -0
- emissions.csv +2 -0
- model.safetensors +3 -0
- preprocessor_config.json +9 -0
- runs/Jan26_12-43-29_ee552674aaf0/events.out.tfevents.1737895415.ee552674aaf0.1460.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/wav2vec2-base
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: FrugalAI
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# FrugalAI
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.3655
|
| 22 |
+
- Accuracy: 0.9352
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 1e-05
|
| 42 |
+
- train_batch_size: 2
|
| 43 |
+
- eval_batch_size: 2
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 4
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 50 |
+
- num_epochs: 7
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 55 |
+
|:-------------:|:------:|:-----:|:---------------:|:--------:|
|
| 56 |
+
| 1.6006 | 0.9998 | 3527 | 0.3393 | 0.9120 |
|
| 57 |
+
| 1.4189 | 1.9998 | 7054 | 0.3683 | 0.9249 |
|
| 58 |
+
| 1.2676 | 2.9998 | 10581 | 0.4339 | 0.9177 |
|
| 59 |
+
| 1.2291 | 3.9998 | 14108 | 0.3656 | 0.9318 |
|
| 60 |
+
| 1.0559 | 4.9998 | 17635 | 0.3414 | 0.9331 |
|
| 61 |
+
| 0.9488 | 5.9998 | 21162 | 0.3655 | 0.9352 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 4.47.1
|
| 67 |
+
- Pytorch 2.5.1+cu121
|
| 68 |
+
- Datasets 3.2.0
|
| 69 |
+
- Tokenizers 0.21.0
|
config.json
ADDED
|
@@ -0,0 +1,126 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_attn_dim": null,
|
| 5 |
+
"adapter_kernel_size": 3,
|
| 6 |
+
"adapter_stride": 2,
|
| 7 |
+
"add_adapter": false,
|
| 8 |
+
"apply_spec_augment": true,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"Wav2Vec2ForSequenceClassification"
|
| 11 |
+
],
|
| 12 |
+
"attention_dropout": 0.1,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"classifier_proj_size": 256,
|
| 15 |
+
"codevector_dim": 256,
|
| 16 |
+
"contrastive_logits_temperature": 0.1,
|
| 17 |
+
"conv_bias": false,
|
| 18 |
+
"conv_dim": [
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512,
|
| 25 |
+
512
|
| 26 |
+
],
|
| 27 |
+
"conv_kernel": [
|
| 28 |
+
10,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
3,
|
| 33 |
+
2,
|
| 34 |
+
2
|
| 35 |
+
],
|
| 36 |
+
"conv_stride": [
|
| 37 |
+
5,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2,
|
| 43 |
+
2
|
| 44 |
+
],
|
| 45 |
+
"ctc_loss_reduction": "sum",
|
| 46 |
+
"ctc_zero_infinity": false,
|
| 47 |
+
"diversity_loss_weight": 0.1,
|
| 48 |
+
"do_stable_layer_norm": false,
|
| 49 |
+
"eos_token_id": 2,
|
| 50 |
+
"feat_extract_activation": "gelu",
|
| 51 |
+
"feat_extract_norm": "group",
|
| 52 |
+
"feat_proj_dropout": 0.1,
|
| 53 |
+
"feat_quantizer_dropout": 0.0,
|
| 54 |
+
"final_dropout": 0.0,
|
| 55 |
+
"freeze_feat_extract_train": true,
|
| 56 |
+
"hidden_act": "gelu",
|
| 57 |
+
"hidden_dropout": 0.1,
|
| 58 |
+
"hidden_size": 768,
|
| 59 |
+
"id2label": {
|
| 60 |
+
"0": "chainsaw",
|
| 61 |
+
"1": "environment"
|
| 62 |
+
},
|
| 63 |
+
"initializer_range": 0.02,
|
| 64 |
+
"intermediate_size": 3072,
|
| 65 |
+
"label2id": {
|
| 66 |
+
"chainsaw": "0",
|
| 67 |
+
"environment": "1"
|
| 68 |
+
},
|
| 69 |
+
"layer_norm_eps": 1e-05,
|
| 70 |
+
"layerdrop": 0.0,
|
| 71 |
+
"mask_channel_length": 10,
|
| 72 |
+
"mask_channel_min_space": 1,
|
| 73 |
+
"mask_channel_other": 0.0,
|
| 74 |
+
"mask_channel_prob": 0.0,
|
| 75 |
+
"mask_channel_selection": "static",
|
| 76 |
+
"mask_feature_length": 10,
|
| 77 |
+
"mask_feature_min_masks": 0,
|
| 78 |
+
"mask_feature_prob": 0.0,
|
| 79 |
+
"mask_time_length": 10,
|
| 80 |
+
"mask_time_min_masks": 2,
|
| 81 |
+
"mask_time_min_space": 1,
|
| 82 |
+
"mask_time_other": 0.0,
|
| 83 |
+
"mask_time_prob": 0.05,
|
| 84 |
+
"mask_time_selection": "static",
|
| 85 |
+
"model_type": "wav2vec2",
|
| 86 |
+
"no_mask_channel_overlap": false,
|
| 87 |
+
"no_mask_time_overlap": false,
|
| 88 |
+
"num_adapter_layers": 3,
|
| 89 |
+
"num_attention_heads": 12,
|
| 90 |
+
"num_codevector_groups": 2,
|
| 91 |
+
"num_codevectors_per_group": 320,
|
| 92 |
+
"num_conv_pos_embedding_groups": 16,
|
| 93 |
+
"num_conv_pos_embeddings": 128,
|
| 94 |
+
"num_feat_extract_layers": 7,
|
| 95 |
+
"num_hidden_layers": 12,
|
| 96 |
+
"num_negatives": 100,
|
| 97 |
+
"output_hidden_size": 768,
|
| 98 |
+
"pad_token_id": 0,
|
| 99 |
+
"proj_codevector_dim": 256,
|
| 100 |
+
"tdnn_dilation": [
|
| 101 |
+
1,
|
| 102 |
+
2,
|
| 103 |
+
3,
|
| 104 |
+
1,
|
| 105 |
+
1
|
| 106 |
+
],
|
| 107 |
+
"tdnn_dim": [
|
| 108 |
+
512,
|
| 109 |
+
512,
|
| 110 |
+
512,
|
| 111 |
+
512,
|
| 112 |
+
1500
|
| 113 |
+
],
|
| 114 |
+
"tdnn_kernel": [
|
| 115 |
+
5,
|
| 116 |
+
3,
|
| 117 |
+
3,
|
| 118 |
+
1,
|
| 119 |
+
1
|
| 120 |
+
],
|
| 121 |
+
"torch_dtype": "float32",
|
| 122 |
+
"transformers_version": "4.47.1",
|
| 123 |
+
"use_weighted_layer_sum": false,
|
| 124 |
+
"vocab_size": 32,
|
| 125 |
+
"xvector_output_dim": 512
|
| 126 |
+
}
|
emissions.csv
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
| 2 |
+
2025-01-26T15:09:12,codecarbon,5faaf6b4-ff04-4ca1-9315-dcb8e608ec78,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,8705.248333129,0.1261530079238971,1.4491603581692755e-05,42.5,32.293039304405184,4.7530388832092285,0.10264580731599099,0.15384368363040402,0.011474747192826767,0.2679642381392215,Singapore,SGP,,,,Linux-6.1.85+-x86_64-with-glibc2.35,3.11.11,2.8.3,2,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x Tesla T4,103.8507,1.2872,12.67477035522461,machine,N,1.0
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:328bf7323f0a3dfb4bd35251cede3afa47414d65cabc9fc2a8584b6825eee3a9
|
| 3 |
+
size 378302360
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"return_attention_mask": false,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
runs/Jan26_12-43-29_ee552674aaf0/events.out.tfevents.1737895415.ee552674aaf0.1460.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba27a2d3f66bc01d8c7950fc190843370519e824140f5fd040518e58f1b50c61
|
| 3 |
+
size 18093
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaf872945fb330f3d94967768ec179f63bcbaa020774c85da9d8cadf7bf460dc
|
| 3 |
+
size 5368
|