Training in progress, step 500

config.json

@@ -1,6 +1,6 @@
 {
   "_name_or_path": "facebook/mms-1b-all",
-  "activation_dropout": 0.05,
+  "activation_dropout": 0.055,
   "adapter_attn_dim": 16,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -9,7 +9,7 @@
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.094,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "codevector_dim": 1024,
@@ -50,22 +50,22 @@
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
   "feat_extract_norm": "layer",
-  "feat_proj_dropout": 0.0,
+  "feat_proj_dropout": 0.04,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.05,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
+  "hidden_dropout": 0.047,
   "hidden_size": 1280,
   "initializer_range": 0.02,
   "intermediate_size": 5120,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
+  "layerdrop": 0.041,
   "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_prob": 0.05,
+  "mask_time_prob": 0.082,
   "model_type": "wav2vec2",
   "num_adapter_layers": 3,
   "num_attention_heads": 16,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c27fe8d4fdf56af9a29efecf6958f7e203ef2a77659700ddcbf470b294a17199
+oid sha256:78bf7e886ac5bde4f377cbc8c8dd7c2f9568f12834edc14b0b14b333740397ba
 size 1929521404

runs/May29_17-14-10_maxim-ubuntu3080/events.out.tfevents.1716992148.maxim-ubuntu3080.295161.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4073e7f2796690f96fb14f12646844fb2993f3bec4b6d234d87984f20ae32704
+size 6812

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18706134b4881a89d17c04f3d1005ba72900c793a83648ef5cd9c88dba08d049
+oid sha256:4b93558dcd67db4933de255e66d06c0fac02381b35a986a5dc748cf2d3846918
 size 6648