End of training

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 2.0,
+    "eval_cer": 0.9555030929683531,
+    "eval_loss": 3.2690865993499756,
+    "eval_runtime": 316.6745,
+    "eval_samples": 4470,
+    "eval_samples_per_second": 14.115,
+    "eval_steps_per_second": 1.765,
+    "eval_wer": 0.9960036558484615,
+    "train_loss": 6.151403113256527,
+    "train_runtime": 1933.761,
+    "train_samples": 10156,
+    "train_samples_per_second": 10.504,
+    "train_steps_per_second": 0.163
+}

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-1b",
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "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": 0.0,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 64,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.25,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.75,
+  "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": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 114,
+  "proj_codevector_dim": 1024,
+  "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": "4.16.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 117,
+  "xvector_output_dim": 512
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 2.0,
+    "eval_cer": 0.9555030929683531,
+    "eval_loss": 3.2690865993499756,
+    "eval_runtime": 316.6745,
+    "eval_samples": 4470,
+    "eval_samples_per_second": 14.115,
+    "eval_steps_per_second": 1.765,
+    "eval_wer": 0.9960036558484615
+}

preprocessor_config.json

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

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9e2417124e4aebce1112b5dee41210ec0bffa22510a19599ea81b67d502bf50
+size 3850912241

runs/Feb05_11-12-46_job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5/1644059994.7984114/events.out.tfevents.1644059994.job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5.40363.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:805b6725c2c625980469f5486c5b1f0d6a1ddbd9e0a578d19bcfd7b6a113273a
+size 4820

runs/Feb05_11-12-46_job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5/events.out.tfevents.1644059994.job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5.40363.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6a40397531a9561ab71c4bdfab1af810e4c76c7eb0bc810c59212dde40af10f
+size 5109

runs/Feb05_11-12-46_job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5/events.out.tfevents.1644062249.job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5.40363.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb094037ad651437489be941c5852e9459616a578b359837ed178abd2701e3ad
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 6.151403113256527,
+    "train_runtime": 1933.761,
+    "train_samples": 10156,
+    "train_samples_per_second": 10.504,
+    "train_steps_per_second": 0.163
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9952755905511812,
+  "global_step": 316,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.0,
+      "step": 316,
+      "total_flos": 9.23014088962431e+18,
+      "train_loss": 6.151403113256527,
+      "train_runtime": 1933.761,
+      "train_samples_per_second": 10.504,
+      "train_steps_per_second": 0.163
+    }
+  ],
+  "max_steps": 316,
+  "num_train_epochs": 2,
+  "total_flos": 9.23014088962431e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8749b659e6cb0292a3a6fab3c1d1ee227af0eead5e759d6d5b52e3e0151400bd
+size 3055