End of training

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:276f8671a1d25bc6297001e73aba11e736ade20e6e9924f7eb9fe29e65c30dae
+oid sha256:4ffb0518c9b30b500e5102de75e079ac19fb032c95b479947c2fc3fcf0ae9917
 size 1262079473

runs/{May11_13-22-42_b215901a7a4c → xlsrDE-vlbg-22L-attnDrp0.5}/events.out.tfevents.1652275417.b215901a7a4c.8909.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa37d02e50cb7a8830963bcfd529aab59b0cd63fcd350bad9a9b75f16dfb0ee0
-size 11926
+oid sha256:3bbe982962354b6d2278c2e7366634d1a835da0aeb8b793f44db00e35bd14102
+size 12280

xlsrDE-vlbg-22L-attnDrp0.5/config.json

@@ -0,0 +1,86 @@
+{
+  "_name_or_path": "jonatasgrosman/wav2vec2-large-xlsr-53-german",
+  "activation_dropout": 0.05,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.5,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "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": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "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,
+  "pad_token_id": 26,
+  "proj_codevector_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 38
+}

xlsrDE-vlbg-22L-attnDrp0.5/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a87e66f3cc6f15ca2a865b6eb9773a10364af58b47357890d0c0330aeb341e
+size 2490370577

xlsrDE-vlbg-22L-attnDrp0.5/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
+}

xlsrDE-vlbg-22L-attnDrp0.5/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:276f8671a1d25bc6297001e73aba11e736ade20e6e9924f7eb9fe29e65c30dae
+size 1262079473

xlsrDE-vlbg-22L-attnDrp0.5/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddec6dc8730f8a2a313a8f22759cbf95e9b86ba78767c766f5cd801c873afa96
+size 14567

xlsrDE-vlbg-22L-attnDrp0.5/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e577754545bf1ff3a2b947683d37a8442e291a87ae62ed400e596999d2b693
+size 559

xlsrDE-vlbg-22L-attnDrp0.5/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a8096b8e2cc80347e5542fcd98885e814a959f9e4087f8ad5d6add1a5bfc220
+size 623

xlsrDE-vlbg-22L-attnDrp0.5/trainer_state.json

@@ -0,0 +1,256 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 84.2051282051282,
+  "global_step": 1600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.26,
+      "learning_rate": 5.82e-05,
+      "loss": 6.4068,
+      "step": 100
+    },
+    {
+      "epoch": 5.26,
+      "eval_loss": 3.0794677734375,
+      "eval_runtime": 69.5659,
+      "eval_samples_per_second": 2.472,
+      "eval_steps_per_second": 0.316,
+      "eval_wer": 1.0,
+      "step": 100
+    },
+    {
+      "epoch": 10.51,
+      "learning_rate": 0.0001182,
+      "loss": 2.7422,
+      "step": 200
+    },
+    {
+      "epoch": 10.51,
+      "eval_loss": 2.160888910293579,
+      "eval_runtime": 7.5977,
+      "eval_samples_per_second": 22.639,
+      "eval_steps_per_second": 2.896,
+      "eval_wer": 0.9353813559322034,
+      "step": 200
+    },
+    {
+      "epoch": 15.77,
+      "learning_rate": 0.00017819999999999997,
+      "loss": 1.7003,
+      "step": 300
+    },
+    {
+      "epoch": 15.77,
+      "eval_loss": 1.4343961477279663,
+      "eval_runtime": 7.5701,
+      "eval_samples_per_second": 22.721,
+      "eval_steps_per_second": 2.906,
+      "eval_wer": 0.7319915254237288,
+      "step": 300
+    },
+    {
+      "epoch": 21.05,
+      "learning_rate": 0.0002382,
+      "loss": 0.9436,
+      "step": 400
+    },
+    {
+      "epoch": 21.05,
+      "eval_loss": 1.298806071281433,
+      "eval_runtime": 7.5752,
+      "eval_samples_per_second": 22.706,
+      "eval_steps_per_second": 2.904,
+      "eval_wer": 0.5942796610169492,
+      "step": 400
+    },
+    {
+      "epoch": 26.31,
+      "learning_rate": 0.0002982,
+      "loss": 0.6264,
+      "step": 500
+    },
+    {
+      "epoch": 26.31,
+      "eval_loss": 1.4477622509002686,
+      "eval_runtime": 7.5857,
+      "eval_samples_per_second": 22.674,
+      "eval_steps_per_second": 2.9,
+      "eval_wer": 0.551906779661017,
+      "step": 500
+    },
+    {
+      "epoch": 31.56,
+      "learning_rate": 0.0002739013452914798,
+      "loss": 0.3898,
+      "step": 600
+    },
+    {
+      "epoch": 31.56,
+      "eval_loss": 1.3976597785949707,
+      "eval_runtime": 7.5848,
+      "eval_samples_per_second": 22.677,
+      "eval_steps_per_second": 2.901,
+      "eval_wer": 0.513771186440678,
+      "step": 600
+    },
+    {
+      "epoch": 36.82,
+      "learning_rate": 0.00024699551569506723,
+      "loss": 0.2428,
+      "step": 700
+    },
+    {
+      "epoch": 36.82,
+      "eval_loss": 1.4575330018997192,
+      "eval_runtime": 7.602,
+      "eval_samples_per_second": 22.626,
+      "eval_steps_per_second": 2.894,
+      "eval_wer": 0.461864406779661,
+      "step": 700
+    },
+    {
+      "epoch": 42.1,
+      "learning_rate": 0.0002200896860986547,
+      "loss": 0.1668,
+      "step": 800
+    },
+    {
+      "epoch": 42.1,
+      "eval_loss": 1.630071997642517,
+      "eval_runtime": 7.6293,
+      "eval_samples_per_second": 22.545,
+      "eval_steps_per_second": 2.884,
+      "eval_wer": 0.4608050847457627,
+      "step": 800
+    },
+    {
+      "epoch": 47.36,
+      "learning_rate": 0.00019318385650224213,
+      "loss": 0.1095,
+      "step": 900
+    },
+    {
+      "epoch": 47.36,
+      "eval_loss": 1.733804702758789,
+      "eval_runtime": 7.5575,
+      "eval_samples_per_second": 22.759,
+      "eval_steps_per_second": 2.911,
+      "eval_wer": 0.4470338983050847,
+      "step": 900
+    },
+    {
+      "epoch": 52.62,
+      "learning_rate": 0.00016627802690582957,
+      "loss": 0.0909,
+      "step": 1000
+    },
+    {
+      "epoch": 52.62,
+      "eval_loss": 1.8613779544830322,
+      "eval_runtime": 7.5808,
+      "eval_samples_per_second": 22.689,
+      "eval_steps_per_second": 2.902,
+      "eval_wer": 0.4565677966101695,
+      "step": 1000
+    },
+    {
+      "epoch": 57.87,
+      "learning_rate": 0.00013937219730941703,
+      "loss": 0.0686,
+      "step": 1100
+    },
+    {
+      "epoch": 57.87,
+      "eval_loss": 1.890817642211914,
+      "eval_runtime": 7.5453,
+      "eval_samples_per_second": 22.796,
+      "eval_steps_per_second": 2.916,
+      "eval_wer": 0.4396186440677966,
+      "step": 1100
+    },
+    {
+      "epoch": 63.15,
+      "learning_rate": 0.00011246636771300449,
+      "loss": 0.0427,
+      "step": 1200
+    },
+    {
+      "epoch": 63.15,
+      "eval_loss": 1.997877597808838,
+      "eval_runtime": 7.52,
+      "eval_samples_per_second": 22.872,
+      "eval_steps_per_second": 2.926,
+      "eval_wer": 0.4300847457627119,
+      "step": 1200
+    },
+    {
+      "epoch": 68.41,
+      "learning_rate": 8.556053811659191e-05,
+      "loss": 0.0371,
+      "step": 1300
+    },
+    {
+      "epoch": 68.41,
+      "eval_loss": 1.9912749528884888,
+      "eval_runtime": 7.5488,
+      "eval_samples_per_second": 22.785,
+      "eval_steps_per_second": 2.914,
+      "eval_wer": 0.4247881355932203,
+      "step": 1300
+    },
+    {
+      "epoch": 73.67,
+      "learning_rate": 5.8654708520179367e-05,
+      "loss": 0.03,
+      "step": 1400
+    },
+    {
+      "epoch": 73.67,
+      "eval_loss": 2.021970272064209,
+      "eval_runtime": 7.5388,
+      "eval_samples_per_second": 22.815,
+      "eval_steps_per_second": 2.918,
+      "eval_wer": 0.4163135593220339,
+      "step": 1400
+    },
+    {
+      "epoch": 78.92,
+      "learning_rate": 3.174887892376682e-05,
+      "loss": 0.024,
+      "step": 1500
+    },
+    {
+      "epoch": 78.92,
+      "eval_loss": 2.1015753746032715,
+      "eval_runtime": 7.5452,
+      "eval_samples_per_second": 22.796,
+      "eval_steps_per_second": 2.916,
+      "eval_wer": 0.4216101694915254,
+      "step": 1500
+    },
+    {
+      "epoch": 84.21,
+      "learning_rate": 4.84304932735426e-06,
+      "loss": 0.0228,
+      "step": 1600
+    },
+    {
+      "epoch": 84.21,
+      "eval_loss": 2.079087734222412,
+      "eval_runtime": 7.5519,
+      "eval_samples_per_second": 22.776,
+      "eval_steps_per_second": 2.913,
+      "eval_wer": 0.4163135593220339,
+      "step": 1600
+    }
+  ],
+  "max_steps": 1615,
+  "num_train_epochs": 85,
+  "total_flos": 4.556905951857466e+18,
+  "trial_name": null,
+  "trial_params": null
+}

xlsrDE-vlbg-22L-attnDrp0.5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd9398cd8782fc37485b19a6d2fe9f1c5ac6c6ef41cc948b8ce181ae351d5b96
+size 2799