Training in progress, step 500

config.json

@@ -12,7 +12,7 @@
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "codevector_dim": 768,
+  "codevector_dim": 1024,
   "contrastive_logits_temperature": 0.1,
   "conv_bias": true,
   "conv_dim": [
@@ -56,9 +56,9 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout": 0.0,
-  "hidden_size": 1024,
+  "hidden_size": 1280,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 5120,
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.0,
   "mask_feature_length": 10,
@@ -75,11 +75,11 @@
   "num_conv_pos_embedding_groups": 16,
   "num_conv_pos_embeddings": 128,
   "num_feat_extract_layers": 7,
-  "num_hidden_layers": 24,
+  "num_hidden_layers": 48,
   "num_negatives": 100,
-  "output_hidden_size": 1024,
+  "output_hidden_size": 1280,
   "pad_token_id": 134,
-  "proj_codevector_dim": 768,
+  "proj_codevector_dim": 1024,
   "tdnn_dilation": [
     1,
     2,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbe828923ff212ff36b9c741977539a4c4a187298e75b64b554890268d5d20fe
-size 1262369180
+oid sha256:ce8f234555a22f342432d31d274dda3dd43933776f21f146fb75d81c3d462d97
+size 3850792988

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd9d8b07ea2187f9fd4b8c6f9ac3c330cfb81858a0b4462788e78e08e7f87575
+oid sha256:5daf68aa70760b5b599eab40e2b6569b0d9a78c06ddedb170982dc3b31e51cf4
 size 4984