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": 4096,
+  "group_depth": 4,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2624,
+  "layer_norm_eps": 1e-06,
+  "load_balancing_loss_coef": 0.2,
+  "lora_alpha": 32,
+  "lora_rank": 16,
+  "max_position_embeddings": 8192,
+  "model_type": "ModernALBERT",
+  "num_attention_heads": 16,
+  "num_expert_modules": 2,
+  "num_experts": 8,
+  "num_hidden_layers": 16,
+  "pad_token_id": 0,
+  "router_jitter_noise": 0.01,
+  "top_k": 2,
+  "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 sha256:10c94ee44d5fd3f96485a0ad445a02898afeae7635aac0440a7cc6a84661bd17
+size 944335770

runs/Oct11_18-31-15_nid006866/events.out.tfevents.1760200290.nid006866.192383.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0094eeb35601c85574c9c7e86835fe51f152a7ed9d6dee743e7d6f8d1989ac1
+size 15846

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d472134b354500e4549af5c6fc87591e76df71f0736984c1cd624ddc7a991f9b
+size 5432