Training in progress, step 400

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "jonatasgrosman/wav2vec2-large-xlsr-53-arabic",
-  "activation_dropout": 0.05,
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.0,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -9,10 +9,10 @@
   "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": true,
   "conv_dim": [
@@ -43,7 +43,7 @@
     2
   ],
   "ctc_loss_reduction": "mean",
-  "ctc_zero_infinity": true,
+  "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
   "do_stable_layer_norm": true,
   "eos_token_id": 2,
@@ -54,26 +54,18 @@
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
+  "hidden_dropout": 0.0,
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.1,
-  "mask_channel_length": 10,
-  "mask_channel_min_space": 1,
-  "mask_channel_other": 0.0,
-  "mask_channel_prob": 0.0,
-  "mask_channel_selection": "static",
+  "layerdrop": 0.0,
   "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,
@@ -85,8 +77,8 @@
   "num_hidden_layers": 24,
   "num_negatives": 100,
   "output_hidden_size": 1024,
-  "pad_token_id": 55,
-  "proj_codevector_dim": 256,
+  "pad_token_id": 44,
+  "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
     2,
@@ -111,6 +103,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.49.0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 58,
+  "vocab_size": 47,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5f20b9274cca7dadb1e9cf07691826097d13ca0d8808dc60f2bc11604c120fa
-size 1262045280
+oid sha256:af1118cf237d03b71e3aaed5f2c95653c9a7606dccd96b180367b93c9be77a4f
+size 1262000180

runs/Feb20_03-13-19_baaf9469ee68/events.out.tfevents.1740022227.baaf9469ee68.31.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56571ab5816c99315ef738da97cfd85a18bcea4c6a9cf36bdbee55bd650b814
+size 10206

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f00530c3459cf16b6bd514450f69227d5903a814b8357f77a0b5d0080723e59d
+oid sha256:22f81119c0a23af2d40743419a951d9d1635d636faaca58ed659174e8a423e60
 size 5304