Training in progress, step 1000

config.json

@@ -0,0 +1,36 @@
+{
+  "adapter_reduction": 16,
+  "architectures": [
+    "DistillationWrapper"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "embedding_size": 128,
+  "expert_intermediate_size": 2624,
+  "group_depth": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_norm_eps": 1e-06,
+  "load_balancing_loss_coef": 0.1,
+  "lora_alpha": 32,
+  "lora_rank": 16,
+  "max_position_embeddings": 8192,
+  "model_type": "ModernALBERT",
+  "num_attention_heads": 12,
+  "num_expert_modules": 2,
+  "num_experts": 4,
+  "num_hidden_layers": 15,
+  "pad_token_id": 0,
+  "router_jitter_noise": 0.01,
+  "top_k": 1,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_adapter": true,
+  "use_cache": true,
+  "use_moa": true,
+  "vocab_size": 50368
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb67712b65eb533a8deeefbca69a7a1fbb89c032022b7f93cbc85cd8f711463c
+size 381944306

runs/Oct18_13-48-50_nid007013/events.out.tfevents.1760788147.nid007013.245776.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74d1c4705d65d4d6558d95e6d13ab116c45c6ca5499e937ed5198b077fb37c91
+size 15820

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f1c2b5c6584fb21be0c50e23c85bf35c3dafa694c9050bc06eb22d89190f615
+size 5432