Training in progress, epoch 1

config.json

@@ -3,14 +3,14 @@
     "Transformer"
   ],
   "d_model": 512,
-  "dim_feedforward": 1024,
+  "dim_feedforward": 2048,
   "dropout": 0.1,
   "input_dim": 30000,
   "max_seq_len": 2000,
   "model_type": "transformer",
   "nhead": 8,
-  "num_decoder_layers": 4,
-  "num_encoder_layers": 4,
+  "num_decoder_layers": 6,
+  "num_encoder_layers": 6,
   "output_dim": 30000,
   "torch_dtype": "float32",
   "transformers_version": "4.40.2"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c94af988a66ecfa387a18ef062bd10c186e69d3ebad4e83d44ced121a8f5866
-size 211234576
+oid sha256:4db08e49d0d4dffb9d917e673961c16696f08d76ee7628311103484afa1afb4c
+size 303680184

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6f835a4d37ff18dcbf3142ab3c0bd73d6a30b60c5990175d94885226fff1661
-size 5112
+oid sha256:32d7bce52717c30632002c117f03e82b97432f2c0918d34c94382d7f381cfe6c
+size 5048