End of training

checkpoint-11000/config.json

@@ -1,117 +0,0 @@
-{
-  "_name_or_path": "facebook/wav2vec2-base",
-  "activation_dropout": 0.0,
-  "adapter_kernel_size": 3,
-  "adapter_stride": 2,
-  "add_adapter": false,
-  "apply_spec_augment": true,
-  "architectures": [
-    "Wav2Vec2ForCTC"
-  ],
-  "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": "mean",
-  "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,
-  "freeze_feat_extract_train": true,
-  "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "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": 29,
-  "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": "4.17.0",
-  "use_weighted_layer_sum": false,
-  "vocab_size": 32,
-  "xvector_output_dim": 512
-}

checkpoint-11000/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dd8499aff7c74a76a48088e9546e9b85bd3d4fa0194062019bbb60b1d5e91082
-size 721687499

checkpoint-11000/preprocessor_config.json

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

checkpoint-11000/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6cf498c1fa08223b228f427a79968055619ec91d8255ce93830627bb36991315
-size 377674359

checkpoint-11000/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:52741bf6eec20c8efdb03b06e4414e0f1bd3c8b76df069357832db9f29d25205
-size 14709

checkpoint-11000/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5d03287726e511ee9901ed5dcad64705231663930b31be0cca8f2fd96155f5fa
-size 1383

checkpoint-11000/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2824b5a2cfd8db81b18261ebf13ddf0123bff1114317ccc746bebf6dec98b4f6
-size 1465

checkpoint-11000/trainer_state.json

@@ -1,181 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.7649513212795549,
-  "global_step": 11000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.07,
-      "learning_rate": 6.926286509040334e-06,
-      "loss": 4.774,
-      "step": 1000
-    },
-    {
-      "epoch": 0.07,
-      "eval_loss": 3.751659393310547,
-      "eval_runtime": 1332.6627,
-      "eval_samples_per_second": 14.954,
-      "eval_steps_per_second": 1.869,
-      "eval_wer": 0.9998903721229055,
-      "step": 1000
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 1.388038942976356e-05,
-      "loss": 2.6101,
-      "step": 2000
-    },
-    {
-      "epoch": 0.14,
-      "eval_loss": 1.871416449546814,
-      "eval_runtime": 1316.0433,
-      "eval_samples_per_second": 15.142,
-      "eval_steps_per_second": 1.893,
-      "eval_wer": 0.8383243761408947,
-      "step": 2000
-    },
-    {
-      "epoch": 0.21,
-      "learning_rate": 2.0827538247566067e-05,
-      "loss": 1.0668,
-      "step": 3000
-    },
-    {
-      "epoch": 0.21,
-      "eval_loss": 1.1693328619003296,
-      "eval_runtime": 1341.5462,
-      "eval_samples_per_second": 14.855,
-      "eval_steps_per_second": 1.857,
-      "eval_wer": 0.5603386736556563,
-      "step": 3000
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 2.778164116828929e-05,
-      "loss": 0.723,
-      "step": 4000
-    },
-    {
-      "epoch": 0.28,
-      "eval_loss": 0.9989805221557617,
-      "eval_runtime": 1327.4867,
-      "eval_samples_per_second": 15.012,
-      "eval_steps_per_second": 1.876,
-      "eval_wer": 0.49050316646100817,
-      "step": 4000
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 2.9473806212331944e-05,
-      "loss": 0.6017,
-      "step": 5000
-    },
-    {
-      "epoch": 0.35,
-      "eval_loss": 0.8713716268539429,
-      "eval_runtime": 1328.1471,
-      "eval_samples_per_second": 15.004,
-      "eval_steps_per_second": 1.876,
-      "eval_wer": 0.41481404052662174,
-      "step": 5000
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 2.870112811002936e-05,
-      "loss": 0.5528,
-      "step": 6000
-    },
-    {
-      "epoch": 0.42,
-      "eval_loss": 0.8598363399505615,
-      "eval_runtime": 1323.0407,
-      "eval_samples_per_second": 15.062,
-      "eval_steps_per_second": 1.883,
-      "eval_wer": 0.3851915683415087,
-      "step": 6000
-    },
-    {
-      "epoch": 0.49,
-      "learning_rate": 2.7929222685829086e-05,
-      "loss": 0.506,
-      "step": 7000
-    },
-    {
-      "epoch": 0.49,
-      "eval_loss": 0.8419894576072693,
-      "eval_runtime": 1332.8363,
-      "eval_samples_per_second": 14.952,
-      "eval_steps_per_second": 1.869,
-      "eval_wer": 0.3734664844634353,
-      "step": 7000
-    },
-    {
-      "epoch": 0.56,
-      "learning_rate": 2.7157317261628804e-05,
-      "loss": 0.4817,
-      "step": 8000
-    },
-    {
-      "epoch": 0.56,
-      "eval_loss": 0.8419905304908752,
-      "eval_runtime": 1321.7221,
-      "eval_samples_per_second": 15.077,
-      "eval_steps_per_second": 1.885,
-      "eval_wer": 0.36988700680202735,
-      "step": 8000
-    },
-    {
-      "epoch": 0.63,
-      "learning_rate": 2.6384639159326225e-05,
-      "loss": 0.4621,
-      "step": 9000
-    },
-    {
-      "epoch": 0.63,
-      "eval_loss": 0.8424670696258545,
-      "eval_runtime": 1317.3235,
-      "eval_samples_per_second": 15.128,
-      "eval_steps_per_second": 1.891,
-      "eval_wer": 0.355694020946573,
-      "step": 9000
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 2.561273373512595e-05,
-      "loss": 0.4482,
-      "step": 10000
-    },
-    {
-      "epoch": 0.7,
-      "eval_loss": 0.7687897086143494,
-      "eval_runtime": 1333.2181,
-      "eval_samples_per_second": 14.947,
-      "eval_steps_per_second": 1.868,
-      "eval_wer": 0.343775176169449,
-      "step": 10000
-    },
-    {
-      "epoch": 0.76,
-      "learning_rate": 2.4840055632823366e-05,
-      "loss": 0.4311,
-      "step": 11000
-    },
-    {
-      "epoch": 0.76,
-      "eval_loss": 0.7420344948768616,
-      "eval_runtime": 1329.3248,
-      "eval_samples_per_second": 14.991,
-      "eval_steps_per_second": 1.874,
-      "eval_wer": 0.3233537972037243,
-      "step": 11000
-    }
-  ],
-  "max_steps": 43140,
-  "num_train_epochs": 3,
-  "total_flos": 6.544117165842432e+18,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-11000/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4b79046a7afb70c92afa454068301926cad11aa0178291c44093bd55bab1d8d7
-size 3921

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1f928ac291c2221863022c023a522c5d0cf5707956cfd9ca96199dce6e04d77
+oid sha256:cd8180bb9c3c96e8907373ff0e6f57f01678b9bd95cafa100ee1865b0c7f46ab
 size 377674359