Training in progress, step 50

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "answerdotai/ModernBERT-base",
+  "architectures": [
+    "ModernBertForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_probs_dropout_prob": 0.15,
+  "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_dropout_prob": 0.15,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0_not_relevant",
+    "1": "1_not_happening",
+    "2": "2_not_human",
+    "3": "3_not_bad",
+    "4": "4_solutions_harmful_unnecessary",
+    "5": "5_science_unreliable",
+    "6": "6_proponents_biased",
+    "7": "7_fossil_fuels_needed"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "0_not_relevant": 0,
+    "1_not_happening": 1,
+    "2_not_human": 2,
+    "3_not_bad": 3,
+    "4_solutions_harmful_unnecessary": 4,
+    "5_science_unreliable": 5,
+    "6_proponents_biased": 6,
+    "7_fossil_fuels_needed": 7
+  },
+  "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",
+  "reference_compile": true,
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0.dev0",
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:384557bf0277d61358ee2486e396dc538de0bda4fca6c83774c78fed0920fc3e
+size 598458240

runs/Jan20_16-21-16_2c149c3d8dda/events.out.tfevents.1737390088.2c149c3d8dda.901.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01321ef3dcfe0a7e84fd81126003dd2f62898af57dd57487b0e3be91e4f86e15
+size 6791

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59aa0e1f8cfe5daf5c246afe92cb24c1a7a5f7595cd7cb761231ed2fe9a777a7
+size 5368