Training in progress, step 500

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "afg1/RNAMamba-14M",
+  "architectures": [
+    "RNAMambaContrastive"
+  ],
+  "bos_token_id": 0,
+  "conv_kernel": 4,
+  "eos_token_id": 0,
+  "expand": 2,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.1,
+  "intermediate_size": 1024,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "mamba",
+  "num_hidden_layers": 8,
+  "pad_token_id": 0,
+  "rescale_prenorm_residual": false,
+  "residual_in_fp32": true,
+  "state_size": 16,
+  "time_step_floor": 0.0001,
+  "time_step_init_scheme": "random",
+  "time_step_max": 0.1,
+  "time_step_min": 0.001,
+  "time_step_rank": 48,
+  "time_step_scale": 1.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_bias": false,
+  "use_cache": true,
+  "use_conv_bias": true,
+  "vocab_size": 9
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6ecada65dbc9ee28b1b8f23fe81eb6ca1188f8955385b757ce18ad621081bb
+size 55325072

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb0d27dc352d02290b54677a7a8d2fe1070a8b9c6745349f28bf587a09f366a
+size 4920