Training in progress, step 4800

last-checkpoint/config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "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": 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": false,
+  "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,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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_prob": 0.075,
+  "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,
+  "proj_codevector_dim": 768,
+  "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": "4.23.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 81,
+  "xvector_output_dim": 512
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a40fe4eb4646a99819376de89cad6d2f936e4fc21a42be155239db9665e214e9
+size 2490723217

last-checkpoint/preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5971caf93277533e76dd4eda4616a1d896c56fc4c8b77c374aa639938e7baca8
+size 1262230833

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c588b9e31769b33d78ed6785c4986e8911b719007af182ab911b44e91eaf1276
+size 14567

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcf4d1a322767767fb41959a40e4c19029c6c19c14602f1e1a4cff6ab33492ec
+size 559

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc866df3ca7994652c92151602986956af84e29e8e900cc98047054e01623ceb
+size 623

last-checkpoint/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.2551967577461105,
+  "global_step": 4800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0002976391096979332,
+      "loss": 6.4525,
+      "step": 800
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 1.4264159202575684,
+      "eval_runtime": 579.6055,
+      "eval_samples_per_second": 37.262,
+      "eval_steps_per_second": 4.658,
+      "eval_wer": 0.9522086267891338,
+      "step": 800
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00029127980922098566,
+      "loss": 1.105,
+      "step": 1600
+    },
+    {
+      "epoch": 0.42,
+      "eval_loss": 0.5966897010803223,
+      "eval_runtime": 638.739,
+      "eval_samples_per_second": 33.812,
+      "eval_steps_per_second": 4.227,
+      "eval_wer": 0.6514394209860115,
+      "step": 1600
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028492050874403814,
+      "loss": 0.7933,
+      "step": 2400
+    },
+    {
+      "epoch": 0.63,
+      "eval_loss": 0.44666677713394165,
+      "eval_runtime": 578.27,
+      "eval_samples_per_second": 37.348,
+      "eval_steps_per_second": 4.669,
+      "eval_wer": 0.5045276037778715,
+      "step": 2400
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00027856120826709056,
+      "loss": 0.6926,
+      "step": 3200
+    },
+    {
+      "epoch": 0.84,
+      "eval_loss": 0.3889370858669281,
+      "eval_runtime": 574.1787,
+      "eval_samples_per_second": 37.614,
+      "eval_steps_per_second": 4.702,
+      "eval_wer": 0.4508941611762033,
+      "step": 3200
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0002722019077901431,
+      "loss": 0.6258,
+      "step": 4000
+    },
+    {
+      "epoch": 1.05,
+      "eval_loss": 0.33456486463546753,
+      "eval_runtime": 575.0581,
+      "eval_samples_per_second": 37.556,
+      "eval_steps_per_second": 4.695,
+      "eval_wer": 0.39778001363149523,
+      "step": 4000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0002658426073131955,
+      "loss": 0.5666,
+      "step": 4800
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 0.31256240606307983,
+      "eval_runtime": 592.8115,
+      "eval_samples_per_second": 36.431,
+      "eval_steps_per_second": 4.555,
+      "eval_wer": 0.3761481289149979,
+      "step": 4800
+    }
+  ],
+  "max_steps": 38240,
+  "num_train_epochs": 10,
+  "total_flos": 1.5254772631049953e+19,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78f0314bc753f30b5d93d4be104533ba3cd7d837c7358b019a8ab73183149b42
+size 3439

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a271053de3a37133ae2bddd8c864ad394c671314aa068e85534203254810174
+oid sha256:5971caf93277533e76dd4eda4616a1d896c56fc4c8b77c374aa639938e7baca8
 size 1262230833

runs/Oct22_17-03-58_9e5f78d3a62d/1666459123.7949953/events.out.tfevents.1666459123.9e5f78d3a62d.75.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8407d2683164ddf9539aa9816869eb0349642136c24b61b19b651abb9b7c1fc
+size 5570

runs/Oct22_17-03-58_9e5f78d3a62d/events.out.tfevents.1666459123.9e5f78d3a62d.75.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c067b75a6796def291003c3de3afc71c029ddb9ddcbb2d8743fc2d7e165d9a2
+size 5699

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4033fcd8e67dce330e711cf22738b88ae3860329ea7760913077a6254b5968c9
+oid sha256:78f0314bc753f30b5d93d4be104533ba3cd7d837c7358b019a8ab73183149b42
 size 3439