Training in progress, step 1000

config.json

@@ -0,0 +1,17 @@
+{
+  "architectures": [
+    "TransformerModel"
+  ],
+  "d_model": 512,
+  "dim_feedforward": 2048,
+  "dropout": 0.1,
+  "input_dim": 30000,
+  "max_seq_len": 1024,
+  "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 sha256:1c54966ff2695bf818ff9c3030be8c5bd7a44664bae8c7ff2610eb9cd2cf9c04
+size 301681360

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66be1e45b42a318679645b1ba500707c12112c58715cc7047750012a94b0b613
+size 5112