Training in progress, step 100

checkpoint-100/config.json

@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "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,
+  "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_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": 107,
+  "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": "4.29.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 108,
+  "xvector_output_dim": 512
+}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a676b41704e0d5dca540325092839fe85ea446998331de5ba8c574b3bfcc71d0
+size 2490946117

checkpoint-100/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
+}

checkpoint-100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48d0e78d44dcb13959b6477b9dbef229431b5ab93be05782631cd39e19428348
+size 1262344621

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84f4b0a1d3e38a362974394f4a07af51ec686c8a9daf93b3cd2bb5425cdea3a
+size 14639

checkpoint-100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:212eedc4d8a56858e58a13e38f18435e99c318c72278bdf30c82c496f5618269
+size 557

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29275430cf69102a2c0f6c5470275a8830b6b0abdaca850328beb5c998237bd1
+size 627

checkpoint-100/trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6802721088435374,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.8199999999999998e-05,
+      "loss": 14.6495,
+      "step": 50
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.82e-05,
+      "loss": 8.9314,
+      "step": 100
+    },
+    {
+      "epoch": 0.68,
+      "eval_cer": 0.9940322843632806,
+      "eval_loss": 4.78579044342041,
+      "eval_runtime": 24.1442,
+      "eval_samples_per_second": 24.354,
+      "eval_steps_per_second": 3.065,
+      "step": 100
+    }
+  ],
+  "max_steps": 3675,
+  "num_train_epochs": 25,
+  "total_flos": 4.027747518982656e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6818a2e9b105d4d459b9ef327417424b7dc79e7c93157b85684e997060ce05b5
+size 3899

preprocessor_config.json

@@ -4,6 +4,7 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
   "return_attention_mask": true,
   "sampling_rate": 16000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b38ee507b60a42b6ab9bc9de08e6cad8b94d918b89f5b75e516b8dfb5f0b4126
+oid sha256:48d0e78d44dcb13959b6477b9dbef229431b5ab93be05782631cd39e19428348
 size 1262344621

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:732357c446b5565d7ea458be8920fde808987b3fa74a20636b4b833d7f43dd86
+oid sha256:6818a2e9b105d4d459b9ef327417424b7dc79e7c93157b85684e997060ce05b5
 size 3899