End of training

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "patrickvonplaten/wav2vec2-base",
-  "activation_dropout": 0.0,
+  "_name_or_path": "facebook/wav2vec2-base-960h",
+  "activation_dropout": 0.1,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
   "add_adapter": false,
@@ -12,7 +12,6 @@
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "codevector_dim": 256,
-  "contrastive_logit_temperature": 0.1,
   "contrastive_logits_temperature": 0.1,
   "conv_bias": false,
   "conv_dim": [
@@ -48,40 +47,27 @@
   "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": 0.0,
-  "freeze_feat_extract_train": true,
-  "gumbel_softmax_temperature": [
-    2.0,
-    0.5,
-    0.999995
-  ],
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.05,
-  "mask_channel_length": 10,
-  "mask_channel_min_space": 1,
-  "mask_channel_other": 0.0,
-  "mask_channel_prob": 0.0,
-  "mask_channel_selection": "static",
+  "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_min_space": 1,
-  "mask_time_other": 0.0,
   "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": 12,
   "num_codevector_groups": 2,
@@ -90,11 +76,9 @@
   "num_conv_pos_embeddings": 128,
   "num_feat_extract_layers": 7,
   "num_hidden_layers": 12,
-  "num_latent_groups": 2,
-  "num_latent_vars": 320,
   "num_negatives": 100,
   "output_hidden_size": 768,
-  "pad_token_id": 0,
+  "pad_token_id": 25,
   "proj_codevector_dim": 256,
   "tdnn_dilation": [
     1,
@@ -121,7 +105,5 @@
   "transformers_version": "4.17.0",
   "use_weighted_layer_sum": false,
   "vocab_size": 32,
-  "vq_final_dim": 256,
-  "vq_latent_dim": 256,
   "xvector_output_dim": 512
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7479d7af81b47b5bd077c283dbb5b8a4c4d92a26dbc7ea79f9cd3bf174bbd7cf
+oid sha256:86c36dee21a2153ba0b94898777a03ef8abdeff7a26e4a28bf8a5f0bb94c1604
 size 377671575

runs/Jun22_02-55-37_d84e2f912cf2/1655866617.0669518/events.out.tfevents.1655866617.d84e2f912cf2.613.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4210a7d37fe433dfa44f201a4cf06db8709e357d0b07dbc38da96961a6e8edc9
+size 4825

runs/Jun22_02-55-37_d84e2f912cf2/events.out.tfevents.1655866617.d84e2f912cf2.613.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d525dde076edc60fa32ca4ae8901ff1da1322f381997911dd4d6f7202138a8b7
+size 5132

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16cbbce8643941d0eefb0a2a414264ead87c850c14880bcac0130577694e8559
+oid sha256:f92578c9d163f5ccd5123bee2c0c315c74f938807b36077b0cd99d77edacafa1
 size 3055