Training in progress, epoch 1

config.json

@@ -0,0 +1,67 @@
+{
+  "_name_or_path": "answerdotai/ModernBERT-base",
+  "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": "4_solutions_harmful_unnecessary",
+    "1": "0_not_relevant",
+    "2": "2_not_human",
+    "3": "3_not_bad",
+    "4": "1_not_happening",
+    "5": "6_proponents_biased",
+    "6": "5_science_is_unreliable",
+    "7": "7_fossil_fuels_needed"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "0_not_relevant": "1",
+    "1_not_happening": "4",
+    "2_not_human": "2",
+    "3_not_bad": "3",
+    "4_solutions_harmful_unnecessary": "0",
+    "5_science_is_unreliable": "6",
+    "6_proponents_biased": "5",
+    "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",
+  "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:de45088bfe841421adaa528402313719b6ac8b7b0091e8275cfeaf5994bcb9f4
+size 598458240

runs/Jan06_15-06-12_7edaa2ca5086/events.out.tfevents.1736175982.7edaa2ca5086.2838.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:239bd89c0372ae55312d814945a522dffa8ec361a7fec8211bc8737ff85debf5
+size 4184

runs/Jan06_15-08-11_7edaa2ca5086/events.out.tfevents.1736176096.7edaa2ca5086.9215.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20c19f352a3c609613ab22c997d77b48fff2506704976a247c2ee49789329105
+size 6216

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f61e2141ff076e99410ae03eef983bc33dab26318e28d34f2e1a5a118d79e73
+size 5368