Upload 7 files

config.json

@@ -0,0 +1,56 @@
+{
+  "_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": 0,
+    "1": 1
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "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,
+  "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:f0f3c4a993a40aa745256d56db700f154c58d950be4b3b94e7d98f033a0abd9e
+size 598439784

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68304984f4258d32275272e9c2b29c0bd5336ba098a0bf188e9f6c8fd1f4e946
+size 1196969338

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:711985e623e1e9b901080083d36abd785c0b3beca6120d17049206bea4fca8b3
+size 1064

trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": 0.9577080491132333,
+  "best_model_checkpoint": "/content/drive/MyDrive/mbert/2025_02_02/t1/checkpoint-2418",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2418,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.461277961730957,
+      "learning_rate": 4.2159929973664246e-05,
+      "loss": 0.0875,
+      "step": 806
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9399813895781638,
+      "eval_f1": 0.9364009860312243,
+      "eval_loss": 0.27949896454811096,
+      "eval_precision": 0.9041574103459219,
+      "eval_recall": 0.9710293115201091,
+      "eval_runtime": 34.1792,
+      "eval_samples_per_second": 188.653,
+      "eval_steps_per_second": 5.91,
+      "step": 806
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5872113108634949,
+      "learning_rate": 1.5100460852686277e-05,
+      "loss": 0.0357,
+      "step": 1612
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9561104218362283,
+      "eval_f1": 0.9519769217715934,
+      "eval_loss": 0.19011780619621277,
+      "eval_precision": 0.9479553903345725,
+      "eval_recall": 0.9560327198364008,
+      "eval_runtime": 34.1574,
+      "eval_samples_per_second": 188.773,
+      "eval_steps_per_second": 5.914,
+      "step": 1612
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.051353733986616135,
+      "learning_rate": 0.0,
+      "loss": 0.0036,
+      "step": 2418
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9615384615384616,
+      "eval_f1": 0.9577080491132333,
+      "eval_loss": 0.20939238369464874,
+      "eval_precision": 0.9583617747440273,
+      "eval_recall": 0.9570552147239264,
+      "eval_runtime": 34.5385,
+      "eval_samples_per_second": 186.69,
+      "eval_steps_per_second": 5.849,
+      "step": 2418
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2418,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.272477999836365e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:668221a0701f82000c8c3f5106f829163fe5fc51df6629ad9158152d41c24ea8
+size 5368