End of training

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "_name_or_path": "facebook/wav2vec2-base",
   "activation_dropout": 0.0,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -8,12 +8,12 @@
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.1,
   "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,
@@ -44,20 +44,19 @@
   "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_proj_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
-  "gradient_checkpointing": false,
+  "freeze_feat_extract_train": true,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
-  "hidden_size": 1024,
+  "hidden_dropout": 0.1,
+  "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,
@@ -75,18 +74,20 @@
   "mask_time_prob": 0.05,
   "mask_time_selection": "static",
   "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
   "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,
-  "pad_token_id": 30,
-  "proj_codevector_dim": 768,
+  "output_hidden_size": 768,
+  "pad_token_id": 29,
+  "proj_codevector_dim": 256,
   "tdnn_dilation": [
     1,
     2,
@@ -111,6 +112,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.17.0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 31,
+  "vocab_size": 32,
   "xvector_output_dim": 512
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf83f5a74926cfe889245f73ac8b5ace7cde339d2b177929419adaded89be70f
-size 1262053361
+oid sha256:e3f865b81f8f905500bb97f20beffbe5ea578bb79430cf76980c30725e02ac03
+size 377671575

runs/Aug24_19-13-11_600e4966b7e3/1661368456.5814097/events.out.tfevents.1661368456.600e4966b7e3.1056.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257f5964a4d633e3c58cd3fb18a0b4adc62f10d5a4cd50e4ab398dfaaa77b02f
+size 4747

runs/Aug24_19-13-11_600e4966b7e3/events.out.tfevents.1661368456.600e4966b7e3.1056.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:443b0dc2f6b7810757dac42e2ce3a1f77d43c5c5f7f0145c1b5426c7f51a275d
+size 19086

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:546ef29edf82214a99eaac149ac0a2b280d50e57f17cbbc941754bb46175fc7f
+oid sha256:e2f9d48dddaba149ac13001f0cced43881c23ba593d5feb819d0ab6371847fba
 size 2991