Training in progress, epoch 1

config.json

@@ -0,0 +1,55 @@
+{
+  "_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": "small_llm",
+    "1": "large_llm"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "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": 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 sha256:877175f6eee04271d158c805ba3d235d23c297562fc418110eb35c95319724e6
+size 598439784

runs/Jan27_07-22-43_ubuntu-t4/events.out.tfevents.1737962564.ubuntu-t4.48513.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1390570caa0e277a5a0a7c8b5661603fcdc2dc2dff930d44811d5076b181c20c
+size 5806

runs/Jan27_07-23-26_ubuntu-t4/events.out.tfevents.1737962607.ubuntu-t4.48886.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b53b69f9c416fe3f7249ba93c2a85fec2d3d251a45544571bc74a10a5c651e45
+size 5806

runs/Jan27_07-24-21_ubuntu-t4/events.out.tfevents.1737962661.ubuntu-t4.49399.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb7c336185a44c496ac1aa8c295e758f3c8a9bca585cc431df7b269ad810149d
+size 5806

runs/Jan27_07-25-09_ubuntu-t4/events.out.tfevents.1737962709.ubuntu-t4.49758.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b1c1e9d530c83a7a053177c3acd6aca2241b0b6d254d8aeea677a01852b630e
+size 5806

runs/Jan27_07-32-02_ubuntu-t4/events.out.tfevents.1737963123.ubuntu-t4.52751.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6894bf4c9d67d9b235e308544653e447f6bd52e70eda533c86d70245036850
+size 7174

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:223f4da115fb4885b2676b67e29189b8138d58c48a2a9b949c415b5165e9716b
+size 5368