End of training

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: xls-r-amharic
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/hallo23/huggingface/runs/5pgjd6az)
+# xls-r-amharic
+
+This model is a fine-tuned version of [ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition](https://huggingface.co/ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1237
+- Accuracy: 0.9778
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|
+| 0.2847        | 2.0202  | 500  | 0.2479          | 0.9212   |
+| 0.1138        | 4.0404  | 1000 | 0.2063          | 0.9434   |
+| 0.0614        | 6.0606  | 1500 | 0.1415          | 0.9657   |
+| 0.0349        | 8.0808  | 2000 | 0.1383          | 0.9737   |
+| 0.0143        | 10.1010 | 2500 | 0.0901          | 0.9818   |
+| 0.0178        | 12.1212 | 3000 | 0.1188          | 0.9778   |
+| 0.0222        | 14.1414 | 3500 | 0.1237          | 0.9778   |
+
+
+### Framework versions
+
+- Transformers 4.41.0.dev0
+- Pytorch 2.1.2
+- Datasets 2.19.1.dev0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 14.969696969696969,
+    "total_flos": 3.163398064220592e+18,
+    "train_loss": 0.13106194541521884,
+    "train_runtime": 5199.6798,
+    "train_samples": 1979,
+    "train_samples_per_second": 5.709,
+    "train_steps_per_second": 0.713
+}

config.json

@@ -0,0 +1,133 @@
+{
+  "_name_or_path": "ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition",
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSpeechClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "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": "mean",
+  "ctc_zero_infinity": true,
+  "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": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "finetuning_task": "wav2vec2_clf",
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "01Neutral",
+    "1": "02Fearful",
+    "2": "03Happy",
+    "3": "04Sad",
+    "4": "05Angry"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "01Neutral": 0,
+    "02Fearful": 1,
+    "03Happy": 2,
+    "04Sad": 3,
+    "05Angry": 4
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "pooling_mode": "mean",
+  "problem_type": "single_label_classification",
+  "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": "4.41.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 33,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d911bd0218782e553ea1cabe9b0bdaf44506550ac800220bf7f18648d7e41c59
+size 1266026604

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": true,
+  "sampling_rate": 16000
+}

runs/May03_06-24-46_a6df16a6f07f/events.out.tfevents.1714717488.a6df16a6f07f.35.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b56c0d802cdf41d8000f253885489b412dd8a5ebdf1625cea719488fcf351c3c
+size 17270

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 14.969696969696969,
+    "total_flos": 3.163398064220592e+18,
+    "train_loss": 0.13106194541521884,
+    "train_runtime": 5199.6798,
+    "train_samples": 1979,
+    "train_samples_per_second": 5.709,
+    "train_steps_per_second": 0.713
+}

trainer_state.json

@@ -0,0 +1,373 @@
+{
+  "best_metric": 0.09009132534265518,
+  "best_model_checkpoint": "/kaggle/working/xls-r-amharic/checkpoint-2500",
+  "epoch": 14.969696969696969,
+  "eval_steps": 500,
+  "global_step": 3705,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 3.749224901199341,
+      "learning_rate": 9.730094466936572e-06,
+      "loss": 1.1928,
+      "step": 100
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 5.272401809692383,
+      "learning_rate": 9.46288798920378e-06,
+      "loss": 0.7006,
+      "step": 200
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 2.211305618286133,
+      "learning_rate": 9.192982456140351e-06,
+      "loss": 0.3993,
+      "step": 300
+    },
+    {
+      "epoch": 1.6161616161616161,
+      "grad_norm": 0.4073326289653778,
+      "learning_rate": 8.923076923076925e-06,
+      "loss": 0.2935,
+      "step": 400
+    },
+    {
+      "epoch": 2.0202020202020203,
+      "grad_norm": 10.367269515991211,
+      "learning_rate": 8.65587044534413e-06,
+      "loss": 0.2847,
+      "step": 500
+    },
+    {
+      "epoch": 2.0202020202020203,
+      "eval_accuracy": 0.9212121367454529,
+      "eval_loss": 0.247890442609787,
+      "eval_runtime": 43.8986,
+      "eval_samples_per_second": 11.276,
+      "eval_steps_per_second": 2.825,
+      "step": 500
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "grad_norm": 14.821730613708496,
+      "learning_rate": 8.385964912280704e-06,
+      "loss": 0.1788,
+      "step": 600
+    },
+    {
+      "epoch": 2.8282828282828283,
+      "grad_norm": 1.658502221107483,
+      "learning_rate": 8.116059379217275e-06,
+      "loss": 0.1541,
+      "step": 700
+    },
+    {
+      "epoch": 3.2323232323232323,
+      "grad_norm": 7.924429416656494,
+      "learning_rate": 7.846153846153847e-06,
+      "loss": 0.1683,
+      "step": 800
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 0.14956633746623993,
+      "learning_rate": 7.576248313090419e-06,
+      "loss": 0.1315,
+      "step": 900
+    },
+    {
+      "epoch": 4.040404040404041,
+      "grad_norm": 0.08813250064849854,
+      "learning_rate": 7.306342780026991e-06,
+      "loss": 0.1138,
+      "step": 1000
+    },
+    {
+      "epoch": 4.040404040404041,
+      "eval_accuracy": 0.9434343576431274,
+      "eval_loss": 0.20633606612682343,
+      "eval_runtime": 43.6554,
+      "eval_samples_per_second": 11.339,
+      "eval_steps_per_second": 2.84,
+      "step": 1000
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 2.7388453483581543,
+      "learning_rate": 7.036437246963563e-06,
+      "loss": 0.1113,
+      "step": 1100
+    },
+    {
+      "epoch": 4.848484848484849,
+      "grad_norm": 1.112307071685791,
+      "learning_rate": 6.766531713900135e-06,
+      "loss": 0.1174,
+      "step": 1200
+    },
+    {
+      "epoch": 5.252525252525253,
+      "grad_norm": 0.9322103261947632,
+      "learning_rate": 6.496626180836708e-06,
+      "loss": 0.1025,
+      "step": 1300
+    },
+    {
+      "epoch": 5.656565656565657,
+      "grad_norm": 0.03639671951532364,
+      "learning_rate": 6.22672064777328e-06,
+      "loss": 0.0754,
+      "step": 1400
+    },
+    {
+      "epoch": 6.0606060606060606,
+      "grad_norm": 0.024523159489035606,
+      "learning_rate": 5.956815114709852e-06,
+      "loss": 0.0614,
+      "step": 1500
+    },
+    {
+      "epoch": 6.0606060606060606,
+      "eval_accuracy": 0.965656578540802,
+      "eval_loss": 0.1415119469165802,
+      "eval_runtime": 43.7636,
+      "eval_samples_per_second": 11.311,
+      "eval_steps_per_second": 2.833,
+      "step": 1500
+    },
+    {
+      "epoch": 6.4646464646464645,
+      "grad_norm": 0.04833903908729553,
+      "learning_rate": 5.686909581646424e-06,
+      "loss": 0.0296,
+      "step": 1600
+    },
+    {
+      "epoch": 6.8686868686868685,
+      "grad_norm": 0.018174033612012863,
+      "learning_rate": 5.417004048582997e-06,
+      "loss": 0.086,
+      "step": 1700
+    },
+    {
+      "epoch": 7.2727272727272725,
+      "grad_norm": 0.2865201532840729,
+      "learning_rate": 5.147098515519568e-06,
+      "loss": 0.0671,
+      "step": 1800
+    },
+    {
+      "epoch": 7.6767676767676765,
+      "grad_norm": 0.0348142571747303,
+      "learning_rate": 4.877192982456141e-06,
+      "loss": 0.0512,
+      "step": 1900
+    },
+    {
+      "epoch": 8.080808080808081,
+      "grad_norm": 0.2693362832069397,
+      "learning_rate": 4.607287449392713e-06,
+      "loss": 0.0349,
+      "step": 2000
+    },
+    {
+      "epoch": 8.080808080808081,
+      "eval_accuracy": 0.973737359046936,
+      "eval_loss": 0.13826610147953033,
+      "eval_runtime": 43.9764,
+      "eval_samples_per_second": 11.256,
+      "eval_steps_per_second": 2.82,
+      "step": 2000
+    },
+    {
+      "epoch": 8.484848484848484,
+      "grad_norm": 0.033031389117240906,
+      "learning_rate": 4.337381916329285e-06,
+      "loss": 0.0251,
+      "step": 2100
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 0.13385087251663208,
+      "learning_rate": 4.067476383265857e-06,
+      "loss": 0.0367,
+      "step": 2200
+    },
+    {
+      "epoch": 9.292929292929292,
+      "grad_norm": 41.249717712402344,
+      "learning_rate": 3.7975708502024296e-06,
+      "loss": 0.0501,
+      "step": 2300
+    },
+    {
+      "epoch": 9.696969696969697,
+      "grad_norm": 0.02456289902329445,
+      "learning_rate": 3.527665317139002e-06,
+      "loss": 0.0555,
+      "step": 2400
+    },
+    {
+      "epoch": 10.1010101010101,
+      "grad_norm": 0.010708549991250038,
+      "learning_rate": 3.2577597840755737e-06,
+      "loss": 0.0143,
+      "step": 2500
+    },
+    {
+      "epoch": 10.1010101010101,
+      "eval_accuracy": 0.9818181991577148,
+      "eval_loss": 0.09009132534265518,
+      "eval_runtime": 44.1262,
+      "eval_samples_per_second": 11.218,
+      "eval_steps_per_second": 2.81,
+      "step": 2500
+    },
+    {
+      "epoch": 10.505050505050505,
+      "grad_norm": 0.012150867842137814,
+      "learning_rate": 2.9905533063427807e-06,
+      "loss": 0.0486,
+      "step": 2600
+    },
+    {
+      "epoch": 10.909090909090908,
+      "grad_norm": 0.008297057822346687,
+      "learning_rate": 2.7206477732793525e-06,
+      "loss": 0.0349,
+      "step": 2700
+    },
+    {
+      "epoch": 11.313131313131313,
+      "grad_norm": 0.013805734924972057,
+      "learning_rate": 2.4507422402159244e-06,
+      "loss": 0.0214,
+      "step": 2800
+    },
+    {
+      "epoch": 11.717171717171716,
+      "grad_norm": 0.011365755461156368,
+      "learning_rate": 2.180836707152497e-06,
+      "loss": 0.0229,
+      "step": 2900
+    },
+    {
+      "epoch": 12.121212121212121,
+      "grad_norm": 0.02992076426744461,
+      "learning_rate": 1.910931174089069e-06,
+      "loss": 0.0178,
+      "step": 3000
+    },
+    {
+      "epoch": 12.121212121212121,
+      "eval_accuracy": 0.9777777791023254,
+      "eval_loss": 0.1187622994184494,
+      "eval_runtime": 43.9086,
+      "eval_samples_per_second": 11.273,
+      "eval_steps_per_second": 2.824,
+      "step": 3000
+    },
+    {
+      "epoch": 12.525252525252526,
+      "grad_norm": 0.09338176250457764,
+      "learning_rate": 1.6410256410256412e-06,
+      "loss": 0.0252,
+      "step": 3100
+    },
+    {
+      "epoch": 12.929292929292929,
+      "grad_norm": 0.27980300784111023,
+      "learning_rate": 1.3738191632928477e-06,
+      "loss": 0.0387,
+      "step": 3200
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 0.007048506755381823,
+      "learning_rate": 1.1039136302294197e-06,
+      "loss": 0.0093,
+      "step": 3300
+    },
+    {
+      "epoch": 13.737373737373737,
+      "grad_norm": 0.00685643358156085,
+      "learning_rate": 8.34008097165992e-07,
+      "loss": 0.0222,
+      "step": 3400
+    },
+    {
+      "epoch": 14.141414141414142,
+      "grad_norm": 0.14381413161754608,
+      "learning_rate": 5.641025641025642e-07,
+      "loss": 0.0222,
+      "step": 3500
+    },
+    {
+      "epoch": 14.141414141414142,
+      "eval_accuracy": 0.9777777791023254,
+      "eval_loss": 0.12370182573795319,
+      "eval_runtime": 44.0309,
+      "eval_samples_per_second": 11.242,
+      "eval_steps_per_second": 2.816,
+      "step": 3500
+    },
+    {
+      "epoch": 14.545454545454545,
+      "grad_norm": 0.015089770779013634,
+      "learning_rate": 2.941970310391363e-07,
+      "loss": 0.0304,
+      "step": 3600
+    },
+    {
+      "epoch": 14.94949494949495,
+      "grad_norm": 1.67782723903656,
+      "learning_rate": 2.4291497975708507e-08,
+      "loss": 0.0173,
+      "step": 3700
+    },
+    {
+      "epoch": 14.969696969696969,
+      "step": 3705,
+      "total_flos": 3.163398064220592e+18,
+      "train_loss": 0.13106194541521884,
+      "train_runtime": 5199.6798,
+      "train_samples_per_second": 5.709,
+      "train_steps_per_second": 0.713
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3705,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.163398064220592e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b13ee671522b5df37fb1d01d3fa7843a6541ac54f9e525ca78713c402dc00ab7
+size 5112