Training in progress, step 500

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "allenai/longformer-base-4096",
+  "architectures": [
+    "LongformerForSequenceClassification"
+  ],
+  "attention_mode": "longformer",
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ODE",
+    "1": "PDE",
+    "2": "assir_high_fidelity",
+    "3": "assir_low_fidelity"
+  },
+  "ignore_attention_mask": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ODE": 0,
+    "PDE": 1,
+    "assir_high_fidelity": 2,
+    "assir_low_fidelity": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "onnx_export": false,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

logs/events.out.tfevents.1737656773.yadi.2769897.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e4737668fe4ad7bbf18e066efa8d68e610e2a802f63fb241b881ad70d0f574
+size 9296

logs/events.out.tfevents.1737657261.yadi.2783404.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b65a03d5732157079bc280ddf3d2b4ac9b93daa5085bc9ee67e25e33718fbe0c
+size 19633

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:019edac10b3250ae38fd9697e84d67f04a79d7300b9a5a0684b8e028de5ad43d
+size 594684336

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08f5dbb3645cefe2754beb4faacafdcfce4d8aef13f1c09a70c6b9c5531b7c9
+size 5304