Training in progress, epoch 1, checkpoint

checkpoint-245/config.json

@@ -0,0 +1,130 @@
+{
+  "_name_or_path": "nguyenvulebinh/wav2vec2-base-vi",
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForViSpeechClassification"
+  ],
+  "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": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "male, northern dialect",
+    "1": "male, central dialect",
+    "2": "male, highland central dialect",
+    "3": "male, southern dialect",
+    "4": "female, northern dialect",
+    "5": "female, central dialect",
+    "6": "female, highland central dialect",
+    "7": "female, southern dialect"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "female, central dialect": "5",
+    "female, highland central dialect": "6",
+    "female, northern dialect": "4",
+    "female, southern dialect": "7",
+    "male, central dialect": "1",
+    "male, highland central dialect": "2",
+    "male, northern dialect": "0",
+    "male, southern dialect": "3"
+  },
+  "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": 0.05,
+  "model_type": "wav2vec2",
+  "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": 0,
+  "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": "4.41.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 96,
+  "xvector_output_dim": 512
+}

checkpoint-245/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54be2adffadc0c3fe71b7501550b136c3a2b143f43933fc75b5c5a637624053b
+size 383295784

checkpoint-245/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb74e1eefef71b0eebc0364ee94912847e352d975a888a1970424419c7984ea1
+size 2929542

checkpoint-245/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-245/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a11b9efeac77fb4975522b54d45beb6133ea264ad72034bdf7d3928e6cd4067b
+size 14308

checkpoint-245/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:702886d20b59a5c8c942d5a81d68abe3ebc6df4afc1956381b292733a9b392be
+size 1064

checkpoint-245/trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 245,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04081632653061224,
+      "grad_norm": 20286.314453125,
+      "learning_rate": 1.2244897959183673e-06,
+      "loss": 2.0797,
+      "step": 10
+    },
+    {
+      "epoch": 0.08163265306122448,
+      "grad_norm": 21226.833984375,
+      "learning_rate": 2.4489795918367347e-06,
+      "loss": 2.0794,
+      "step": 20
+    },
+    {
+      "epoch": 0.12244897959183673,
+      "grad_norm": 20473.34375,
+      "learning_rate": 3.673469387755102e-06,
+      "loss": 2.0791,
+      "step": 30
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 21295.623046875,
+      "learning_rate": 4.897959183673469e-06,
+      "loss": 2.0786,
+      "step": 40
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 22374.26953125,
+      "learning_rate": 6.122448979591837e-06,
+      "loss": 2.0775,
+      "step": 50
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": 27922.837890625,
+      "learning_rate": 7.346938775510204e-06,
+      "loss": 2.0762,
+      "step": 60
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 21962.65625,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 2.0751,
+      "step": 70
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 25949.669921875,
+      "learning_rate": 9.795918367346939e-06,
+      "loss": 2.073,
+      "step": 80
+    },
+    {
+      "epoch": 0.3673469387755102,
+      "grad_norm": 21337.779296875,
+      "learning_rate": 1.1020408163265306e-05,
+      "loss": 2.0711,
+      "step": 90
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 21139.53125,
+      "learning_rate": 1.2244897959183674e-05,
+      "loss": 2.068,
+      "step": 100
+    },
+    {
+      "epoch": 0.4489795918367347,
+      "grad_norm": 18687.326171875,
+      "learning_rate": 1.3469387755102042e-05,
+      "loss": 2.0621,
+      "step": 110
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 23997.892578125,
+      "learning_rate": 1.4693877551020408e-05,
+      "loss": 2.0557,
+      "step": 120
+    },
+    {
+      "epoch": 0.5306122448979592,
+      "grad_norm": 25094.125,
+      "learning_rate": 1.5918367346938776e-05,
+      "loss": 2.0436,
+      "step": 130
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 35127.62890625,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 2.0313,
+      "step": 140
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 38480.73046875,
+      "learning_rate": 1.836734693877551e-05,
+      "loss": 2.0124,
+      "step": 150
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 37025.25390625,
+      "learning_rate": 1.9591836734693877e-05,
+      "loss": 1.9832,
+      "step": 160
+    },
+    {
+      "epoch": 0.6938775510204082,
+      "grad_norm": 47326.75390625,
+      "learning_rate": 2.0816326530612247e-05,
+      "loss": 1.9503,
+      "step": 170
+    },
+    {
+      "epoch": 0.7346938775510204,
+      "grad_norm": 44386.79296875,
+      "learning_rate": 2.2040816326530613e-05,
+      "loss": 1.9033,
+      "step": 180
+    },
+    {
+      "epoch": 0.7755102040816326,
+      "grad_norm": 60427.28515625,
+      "learning_rate": 2.326530612244898e-05,
+      "loss": 1.8548,
+      "step": 190
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 60310.234375,
+      "learning_rate": 2.448979591836735e-05,
+      "loss": 1.7809,
+      "step": 200
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 73581.171875,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 1.8435,
+      "step": 210
+    },
+    {
+      "epoch": 0.8979591836734694,
+      "grad_norm": 63305.5,
+      "learning_rate": 2.6938775510204084e-05,
+      "loss": 1.7222,
+      "step": 220
+    },
+    {
+      "epoch": 0.9387755102040817,
+      "grad_norm": 78695.546875,
+      "learning_rate": 2.816326530612245e-05,
+      "loss": 1.7823,
+      "step": 230
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 118529.84375,
+      "learning_rate": 2.9387755102040816e-05,
+      "loss": 1.7203,
+      "step": 240
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2450,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.24301109962752e+18,
+  "train_batch_size": 48,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-245/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff1a5da6b40908735a2131d0c9bb8c41334e1f841f4d5b0727103f09277b756f
+size 5176