End of training

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
+base_model: facebook/wav2vec2-xls-r-300m
 tags:
 - generated_from_trainer
-base_model: EzraWilliam/wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1
 model-index:
 - name: wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1
   results: []
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1
 
-This model is a fine-tuned version of [EzraWilliam/wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1](https://huggingface.co/EzraWilliam/wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1) on the None dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
 
 ## Model description
 
@@ -32,13 +32,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 32
+- learning_rate: 0.0003
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 1000
+- lr_scheduler_warmup_steps: 500
 - num_epochs: 30
 - mixed_precision_training: Native AMP
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "EzraWilliam/wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1",
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
   "activation_dropout": 0.0,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
@@ -9,12 +9,12 @@
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.1,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "codevector_dim": 256,
+  "codevector_dim": 768,
   "contrastive_logits_temperature": 0.1,
-  "conv_bias": false,
+  "conv_bias": true,
   "conv_dim": [
     512,
     512,
@@ -45,50 +45,41 @@
   "ctc_loss_reduction": "mean",
   "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": false,
+  "do_stable_layer_norm": true,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
-  "feat_extract_norm": "group",
-  "feat_proj_dropout": 0.1,
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
-  "freeze_feat_extract_train": true,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
-  "hidden_size": 768,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "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",
-  "no_mask_channel_overlap": false,
-  "no_mask_time_overlap": false,
   "num_adapter_layers": 3,
-  "num_attention_heads": 12,
+  "num_attention_heads": 16,
   "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_hidden_layers": 24,
   "num_negatives": 100,
-  "output_hidden_size": 768,
+  "output_hidden_size": 1024,
   "pad_token_id": 30,
-  "proj_codevector_dim": 256,
+  "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
     2,
@@ -113,6 +104,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.37.0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 32,
+  "vocab_size": 33,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:400f92add00ff328beff889a4ad7330191da12716a516b058fa9ff4f706472f5
-size 377611120
+oid sha256:807a8131841a0f1c7319655b6313cf70d5ebe9be2c5f5a6066e10807f6ee2010
+size 1261942780

runs/Jan22_13-01-32_d5d0e8fdc236/events.out.tfevents.1705928503.d5d0e8fdc236.728.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9034456d3a1b77c927c95b8675320aa2c7f20473abb0bc030b0a2c4ba10fd2c7
+size 6314

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31680f817fef871c446668b83e3fb048a9980bc5b4ff15b9952f6fe26937f1b0
+oid sha256:bdf89d1962960b3af1d6ec2106ace5a78ace764bffcff5a8cdb298813ef1f5bc
 size 4792