Training in progress, step 100

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "answerdotai/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": "quality",
+    "1": "accuracy",
+    "2": "creativity",
+    "3": "style"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 2624,
+  "label2id": {
+    "accuracy": 1,
+    "creativity": 2,
+    "quality": 0,
+    "style": 3
+  },
+  "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": "multi_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:a455c39787083d5e3c1a080542778a49c9efbf2e0084093c78b4abc734e8b15f
+size 1583359840

runs/May27_09-21-27_b1f8e2e2f08b/events.out.tfevents.1748337687.b1f8e2e2f08b.8609.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5709920462ef199b8a2614791b772098b827667bc016089a6836f9260f7f6682
+size 5945

runs/May27_09-22-34_b1f8e2e2f08b/events.out.tfevents.1748337755.b1f8e2e2f08b.8609.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e62ffab4d45857fc6e9d48089e42a9b5d0c29982216dc2cc70b9576c360711cc
+size 5946

runs/May27_09-26-18_b1f8e2e2f08b/events.out.tfevents.1748337979.b1f8e2e2f08b.9268.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25bdb2f1127fb2fd326d4785e2ad9fe8e963e349783a83e80e77271a609d59e8
+size 6774

runs/May27_09-27-27_b1f8e2e2f08b/events.out.tfevents.1748338048.b1f8e2e2f08b.9839.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:150fe82350a98b0843fc0d9087f140851ba99bfd301898ea0b583de7c3e34803
+size 5946

runs/May27_09-28-22_b1f8e2e2f08b/events.out.tfevents.1748338103.b1f8e2e2f08b.10369.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f5008c74772e68135adbce7a99eb83ebedff645ad8af7ad5fe1249dfaafb09
+size 7040

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3f01074225a271877d8138820ed90152d26f1818b76ee61d1e1c5e39db50221
+size 5368