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": 1,
+  "num_experts": 8,
+  "num_hidden_layers": 12,
+  "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:dff1bb2468ad0b0034e3841324ec59d29efddaa1b339e8201a1940345ecf82a6
+size 900372486

runs/Oct12_12-42-11_nid006633/events.out.tfevents.1760265757.nid006633.58746.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6ab3681018a3e5f4f1a36ad5bc60e1e92c904368beb5954f3d59b8c8460203
+size 15846

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf058f9c69fe5d0d1948263dc652aae1ab6b9e94617746e58f9fff63039f515
+size 5432