Training in progress, step 2000

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "HybridFourierLM"
+  ],
+  "bos_token_id": 0,
+  "dropout": 0.05,
+  "dtype": "float32",
+  "eos_token_id": 0,
+  "latent_dim": 768,
+  "layer_types": [
+    "linear",
+    "linear",
+    "linear",
+    "softmax",
+    "linear",
+    "linear",
+    "linear",
+    "softmax",
+    "linear",
+    "linear",
+    "linear",
+    "softmax"
+  ],
+  "model_type": "hybrid_fourier_lm",
+  "num_layers": 12,
+  "num_modes": 64,
+  "pad_token_id": 1,
+  "tie_word_embeddings": false,
+  "time_scale": 128.0,
+  "transformers_version": "5.12.1",
+  "use_cache": false,
+  "vocab_size": 50277
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 1,
+  "transformers_version": "5.12.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5705e7af05b27ed5ad80eeb0dae22c64e16bff581aaf95045a9a3c2b27d7f21
+size 734275920

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:018db098c009b077a596bcd57ca4359ea322e874799c144a100d3d03ea3ce145
+size 5201