Training in progress, step 2000

config.json

@@ -1,268 +1,107 @@
 {
+  "_name_or_path": "fav-kky/wav2vec2-base-cs-80k-ClTRUS",
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
   "architectures": [
-    "SpeechEncoderDecoderModel"
+    "Wav2Vec2ForCTC"
   ],
-  "decoder": {
-    "_attn_implementation_autoset": false,
-    "_name_or_path": "fav-kky/gpt2-small-cs",
-    "activation_function": "gelu",
-    "add_cross_attention": true,
-    "architectures": [
-      "GPT2LMHeadModel"
-    ],
-    "attn_pdrop": 0.1,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": 0,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "early_stopping": false,
-    "embd_pdrop": 0.1,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 0,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "gradient_checkpointing": false,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "initializer_range": 0.02,
-    "is_decoder": true,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_epsilon": 1e-05,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "gpt2",
-    "n_ctx": 1024,
-    "n_embd": 512,
-    "n_head": 8,
-    "n_inner": null,
-    "n_layer": 4,
-    "n_positions": 1024,
-    "no_repeat_ngram_size": 0,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "reorder_and_upcast_attn": false,
-    "repetition_penalty": 1.0,
-    "resid_pdrop": 0.1,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "scale_attn_by_inverse_layer_idx": false,
-    "scale_attn_weights": true,
-    "sep_token_id": null,
-    "summary_activation": null,
-    "summary_first_dropout": 0.1,
-    "summary_proj_to_labels": true,
-    "summary_type": "cls_index",
-    "summary_use_proj": true,
-    "suppress_tokens": null,
-    "task_specific_params": {
-      "text-generation": {
-        "do_sample": true,
-        "max_length": 1024
-      }
-    },
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": "float32",
-    "torchscript": false,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": true,
-    "vocab_size": 50000
-  },
-  "decoder_start_token_id": 0,
-  "encoder": {
-    "_attn_implementation_autoset": false,
-    "_name_or_path": "fav-kky/wav2vec2-base-cs-80k-ClTRUS",
-    "activation_dropout": 0.1,
-    "adapter_attn_dim": null,
-    "adapter_kernel_size": 3,
-    "adapter_stride": 2,
-    "add_adapter": false,
-    "add_cross_attention": false,
-    "apply_spec_augment": true,
-    "architectures": [
-      "Wav2Vec2ForPreTraining"
-    ],
-    "attention_dropout": 0.1,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": 1,
-    "chunk_size_feed_forward": 0,
-    "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
-    ],
-    "cross_attention_hidden_size": null,
-    "ctc_loss_reduction": "sum",
-    "ctc_zero_infinity": false,
-    "decoder_start_token_id": null,
-    "diversity_loss_weight": 0.1,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "do_stable_layer_norm": false,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 2,
-    "exponential_decay_length_penalty": null,
-    "feat_extract_activation": "gelu",
-    "feat_extract_norm": "group",
-    "feat_proj_dropout": 0.0,
-    "feat_quantizer_dropout": 0.0,
-    "final_dropout": 0.1,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "gelu",
-    "hidden_dropout": 0.1,
-    "hidden_size": 768,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "initializer_range": 0.02,
-    "intermediate_size": 3072,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-05,
-    "layerdrop": 0.1,
-    "length_penalty": 1.0,
-    "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,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "wav2vec2",
-    "no_repeat_ngram_size": 0,
-    "num_adapter_layers": 3,
-    "num_attention_heads": 12,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "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,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_size": 768,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": 0,
-    "prefix": null,
-    "problem_type": null,
-    "proj_codevector_dim": 256,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "tdnn_dilation": [
-      1,
-      2,
-      3,
-      1,
-      1
-    ],
-    "tdnn_dim": [
-      512,
-      512,
-      512,
-      512,
-      1500
-    ],
-    "tdnn_kernel": [
-      5,
-      3,
-      3,
-      1,
-      1
-    ],
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": "float32",
-    "torchscript": false,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_weighted_layer_sum": false,
-    "vocab_size": 32,
-    "xvector_output_dim": 512
-  },
-  "eos_token_id": 0,
-  "is_encoder_decoder": true,
-  "model_type": "speech-encoder-decoder",
+  "attention_dropout": 0.2,
+  "bos_token_id": 3,
+  "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": "mean",
+  "ctc_zero_infinity": true,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 4,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.2,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 6,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
   "pad_token_id": 0,
-  "tie_word_embeddings": false,
+  "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": "4.49.0"
+  "transformers_version": "4.49.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 1000,
+  "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:410c8714a1ba2abb625e37c5a51bafb93c584dfafce29c604ed27fb0c765b174
-size 550862672
+oid sha256:db4f7385f16543aa01cda93b2d438e0f8583752e641185b8a5ba17fe67c3d7b6
+size 210468024

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b388a5a8ccab94e6fbf978de93ac3a32ab3e55dc3adb48d3ab73083d93ee01b1
-size 5304
+oid sha256:8eeb8e583efac0c346e0af9c032e855e0c1651a223a6f0de2ca5c4fd6211fcf5
+size 5624