Training in progress, step 10000

config.json

@@ -0,0 +1,17 @@
+{
+  "architectures": [
+    "TransformerNet"
+  ],
+  "d_model": 512,
+  "dim_feedforward": 1024,
+  "dropout": 0.1,
+  "input_dim": 30000,
+  "max_seq_len": 850,
+  "model_type": "transformer",
+  "nhead": 8,
+  "num_decoder_layers": 6,
+  "num_encoder_layers": 6,
+  "output_dim": 30000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba7ac8d85531978b8002c3db85d720977baffc5cb74d98e5b2dadd6594f0f011
+size 252674096

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75e9a3d5f09f3f42477bf8bbf11a49a2dfd4c7727964f632ae3e665f3f9e3a6
+size 5112