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": 30,
+  "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 sha256:77bb44d7cd5c373997aef303ddf5a30266cf3c7c3772fd6355b8504ab10cfbe6
+size 249315352

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:651030923a67daeafba93404f006f73ebcd9a1a6446146e326aef99307e383bc
+size 5112