Training in progress, epoch 1, checkpoint

checkpoint-729/config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "facebook/mms-1b-all",
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "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": 0.05,
+  "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": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "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": 92,
+  "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": "4.34.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 95,
+  "xvector_output_dim": 512
+}

checkpoint-729/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af4fea956d9183b74cb64b0ba97b974a27b3bc2b4ea28c9465dd7755535510f
+size 18424186

checkpoint-729/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
+}

checkpoint-729/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c11ddb2b193ad3d656c349024c4911d8fc719a3953ee8a980083631a800dae06
+size 3859463050

checkpoint-729/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34df90dfc3f2029a76b587ce9924df48dd9eb2f6f72cdeeea8f63aefe9f535ae
+size 14308

checkpoint-729/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f31e50c5c870205c924d849149568b3ca13ecb1cb74a85667d361757e0ea99bc
+size 1064

checkpoint-729/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 729,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00048,
+      "loss": 7.0366,
+      "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0004933240611961058,
+      "loss": 0.4467,
+      "step": 200
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00048643949930458967,
+      "loss": 0.3946,
+      "step": 300
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0004794853963838665,
+      "loss": 0.399,
+      "step": 400
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0004726008344923505,
+      "loss": 0.3696,
+      "step": 500
+    },
+    {
+      "epoch": 0.69,
+      "eval_loss": 0.3043254017829895,
+      "eval_runtime": 65.1553,
+      "eval_samples_per_second": 11.664,
+      "eval_steps_per_second": 1.458,
+      "eval_wer": 0.265993265993266,
+      "step": 500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0004656467315716273,
+      "loss": 0.3677,
+      "step": 600
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00045869262865090403,
+      "loss": 0.3534,
+      "step": 700
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 7290,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 5.050015040194851e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-729/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3aa848da266dd9fcefac1319c4009241b1015d8306bc1c8253b19be17b56d9
+size 4536