Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbd9411922642888af3b00fe2c981f1485413550aca68f65a82192a8b42bb4c7
+oid sha256:4cf7e57d5a33893268f0cdbc4d569f96a89141181281c3bdeddb01634821a3f7
 size 598442860

run-0/checkpoint-3356/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea01dbe10d001789db2d70ffa4308aecf0fa25f04c98902f85bdbb9f1036504d
+oid sha256:abe8c525a960a2871207d264ad145dc47b355e5097a9a032e3fb92dd2e2474c1
 size 1196975482

run-0/checkpoint-3356/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:399209c54274067d13fb3c584101a071f31ac1198b71c7ac31aeb2e750b5136b
+oid sha256:e73e59b6e5b9056ac0e8920fff852bc272c5c86a3b059cb9c4d16269570f8731
 size 14244

run-1/checkpoint-839/config.json

@@ -0,0 +1,58 @@
+{
+  "_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": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "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": false,
+  "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
+}

run-1/checkpoint-839/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cf7e57d5a33893268f0cdbc4d569f96a89141181281c3bdeddb01634821a3f7
+size 598442860

run-1/checkpoint-839/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f35dcab966b5282a94daf554bfb8ac889c5af645a8b92c75a900147fec04df02
+size 1196975482

run-1/checkpoint-839/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8bd53d0fd3ae53de76f4ce4413bda2fac7f45845191ef3f62010be4991b2ff9
+size 14244

run-1/checkpoint-839/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a52e8678884a6e948c39bf08155314406feafee2e504127a1b1ac12b8b9b84
+size 1064

run-1/checkpoint-839/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": 0.4791373908519745,
+  "best_model_checkpoint": "modernbert-financial-sentiment/run-1/checkpoint-839",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 839,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5959475566150179,
+      "grad_norm": 3.4977939128875732,
+      "learning_rate": 0.00023796275402835382,
+      "loss": 0.6709,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.833134684147795,
+      "eval_f1": 0.8303703737833891,
+      "eval_loss": 0.4791373908519745,
+      "eval_precision": 0.8296883223434215,
+      "eval_recall": 0.833134684147795,
+      "eval_runtime": 18.2507,
+      "eval_samples_per_second": 91.942,
+      "eval_steps_per_second": 11.506,
+      "step": 839
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1678,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 681520416768000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "adam_epsilon": 1.658518398119787e-08,
+    "dropout": 0.0017330050952681364,
+    "learning_rate": 0.0002935143307327658,
+    "lr_scheduler_type": "linear",
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "warmup_ratio": 0.13352557567852008,
+    "weight_decay": 0.09108802122030084
+  }
+}

run-1/checkpoint-839/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04cf6cefe1f017323156a5a30caf80658f8089fb6b585684f5ac1ae40be4a5c5
+size 5432

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b7d115c158685a132a9ca676c96de0196aadaa83e6cba97fbf0a9251269ccf4
+oid sha256:04cf6cefe1f017323156a5a30caf80658f8089fb6b585684f5ac1ae40be4a5c5
 size 5432