Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/scratch/elec/puhe/p/palp3/sami_ASR/downloaded-large-sami/wav2vec2-large-sami-22k-finetuned",
+  "_name_or_path": "/scratch/elec/puhe/p/palp3/sami_ASR/downloaded-base-sami/wav2vec2-base-sami-22k-finetuned",
   "activation_dropout": 0.0,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
@@ -12,9 +12,9 @@
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "codevector_dim": 768,
+  "codevector_dim": 256,
   "contrastive_logits_temperature": 0.1,
-  "conv_bias": true,
+  "conv_bias": false,
   "conv_dim": [
     512,
     512,
@@ -45,48 +45,39 @@
   "ctc_loss_reduction": "mean",
   "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": true,
+  "do_stable_layer_norm": false,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
-  "feat_extract_dropout": 0.0,
-  "feat_extract_norm": "layer",
+  "feat_extract_norm": "group",
   "feat_proj_dropout": 0.0,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
   "hidden_act": "gelu",
   "hidden_dropout": 0.0,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.0,
-  "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_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": 24,
+  "num_hidden_layers": 12,
   "num_negatives": 100,
-  "output_hidden_size": 1024,
+  "output_hidden_size": 768,
   "pad_token_id": 0,
-  "proj_codevector_dim": 768,
+  "proj_codevector_dim": 256,
   "tdnn_dilation": [
     1,
     2,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c41bdc2c4bec0ba6c501af7dcfedc3acb48f8fb63a17f4c2b5b3387aac1cbf7
-size 1261996080
+oid sha256:d64f602d3bc48b7d2214d78d6e932836d2cd0bc942dd69dbcdf1958c5eb1fa47
+size 377654192

preprocessor_config.json

@@ -1,10 +1,10 @@
 {
-  "do_normalize": true,
+  "do_normalize": false,
   "feature_extractor_type": "Wav2Vec2FeatureExtractor",
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0,
   "processor_class": "Wav2Vec2Processor",
-  "return_attention_mask": true,
+  "return_attention_mask": false,
   "sampling_rate": 16000
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:090ebc22eda3c0d13719dceb2f9d1b53e7de52abe90a402ed8a53898c536e2ed
+oid sha256:3774c36946cb93e738d91f3499c3b3dadf5dc03a52a4dce57046d7f63d1147e6
 size 5496