Training in progress, epoch 1

config.json

@@ -0,0 +1,54 @@
+{
+  "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": 768,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "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": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.2",
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2013debba82b40c84fdff70840a559da95e931bf147d3e13524419b86f1f5ec
+size 598439784

runs/Aug14_14-36-15_Mac.cable.rcn.com/events.out.tfevents.1755196580.Mac.cable.rcn.com.44240.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de069622705bf505cd0fcdd7e9f0c47c704a6e97f522eb494a2d0d30fa5081a
+size 5680

runs/Aug14_14-39-02_Mac.cable.rcn.com/events.out.tfevents.1755196745.Mac.cable.rcn.com.44571.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcfea057edafa5a56b3170f325608a21a8f3ddf2f4581780a3085c68123365c9
+size 5682

runs/Aug14_14-45-54_Mac.cable.rcn.com/events.out.tfevents.1755197176.Mac.cable.rcn.com.44635.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41685a7d0051b091d633be66a3878039af99156615c541227f6773e889e8ed21
+size 5681

runs/Aug14_14-53-18_Mac.cable.rcn.com/events.out.tfevents.1755197599.Mac.cable.rcn.com.44680.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0620dbd840c7479d681db14fcb83d01046fd653261d0aa6185325c7456274eb
+size 6420

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89f298314f51f4ef3266f2ea24689cc6858ea2109de74c02ea9ce79fae5ce8f
+size 5841