End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: mehdikhfifi/lala
+base_model: facebook/wav2vec2-base
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # lala
 
-This model is a fine-tuned version of [mehdikhfifi/lala](https://huggingface.co/mehdikhfifi/lala) on the None dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
 
 ## Model description
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "mehdikhfifi/lala",
+  "_name_or_path": "facebook/wav2vec2-base",
   "activation_dropout": 0.0,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
@@ -12,9 +12,9 @@
   "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,
@@ -45,19 +45,19 @@
   "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_extract_norm": "group",
   "feat_proj_dropout": 0.0,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.1,
   "mask_channel_length": 10,
@@ -75,18 +75,20 @@
   "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,
+  "output_hidden_size": 768,
   "pad_token_id": 35,
-  "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 sha256:6dc0180cc317bf3f50ee17e9a41358432626b67b38b58a9119a972d22d4bc8b4
-size 1261963280
+oid sha256:7cd11786c1efb3f228f5ef1790d067a184737f3c05a9fc24204d78bff56a8cba
+size 377629584

runs/Jan02_23-14-39_a9a4bbae442b/events.out.tfevents.1704237290.a9a4bbae442b.2732.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb6e52550fe64b6c44e9a24a0353f8f350808622e723e34d78773d3b221aed52
+size 7835

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b103fe990fd03adafc1e8d2a2a8099bfc3856a7c547bb423daa27236bec391a4
+oid sha256:871a8861f0501786990a507d27c9a6f395a1dae697bdbefbcdf57efb2a091d8e
 size 4728