Training in progress, epoch 1

config.json

@@ -0,0 +1,55 @@
+{
+  "_name_or_path": "./ModernBERT-large",
+  "architectures": [
+    "ModernBertForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "small_llm",
+    "1": "large_llm"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 2624,
+  "label2id": {
+    "large_llm": "1",
+    "small_llm": "0"
+  },
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "reference_compile": true,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0.dev0",
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70fb2e6e2ddbb873b39795de1dc0fafb335e7e77e643d0130c0132f49c0ef763
+size 1583351632

runs/Feb16_22-20-40_nile/events.out.tfevents.1739715647.nile.1418169.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:684e5c5ca79dbbfa569787bec6adfe6f010d73af6c512008d0380d5e505faffd
+size 5811

runs/Feb16_22-29-56_nile/events.out.tfevents.1739716201.nile.1418169.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0af222f6d16db52baa1c0083873122855d54e94e5f57440427ffe8856a7394e
+size 5811

runs/Feb16_22-30-36_nile/events.out.tfevents.1739716241.nile.1418169.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12a1d024745beadd4495f942a3195190cb78b0b48e59d5d5a86f480779ab007e
+size 5809

runs/Feb16_22-31-27_nile/events.out.tfevents.1739716290.nile.1418169.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:815d0c43844d45091ce87d3e9c03020c31eefad599651a0ba2692e4fd5992c54
+size 5809

runs/Feb16_22-33-34_nile/events.out.tfevents.1739716417.nile.1418169.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eec2cdf68d8539d6fb0e722247e2f5ac1ef26789e444d1d52acf4843acea771
+size 22158

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d5541d1bd3fd658bb103971900ca14ff966ca1044f38917cd8935f3c4546ab
+size 5368