🔄 Incremental label | Acc: 0.995, F1: 0.993

README.md

@@ -21,19 +21,19 @@ Fine-tuned FinBERT model for financial sentiment analysis in TradePulse.
 
 ## Performance
 
-*Last training: 2025-07-30 10:33*  
-*Dataset: `base_reference.csv` (637 samples)*
+*Last training: 2025-07-30 15:51*  
+*Dataset: `base_reference.csv` (1797 samples)*
 
 | Metric | Value |
 |--------|-------|
-| Loss | 1.2841 |
-| Accuracy | 0.8313 |
-| F1 Score | 0.8290 |
+| Loss | 0.0141 |
+| Accuracy | 0.9978 |
+| F1 Score | 0.9978 |
 
-| F1 Macro | 0.8290 |
+| F1 Macro | 0.9978 |
 
-| Precision | 0.8333 |
-| Recall | 0.8313 |
+| Precision | 0.9978 |
+| Recall | 0.9978 |
 
 ## Training Details
 
@@ -65,4 +65,4 @@ predictions = outputs.logits.softmax(dim=-1)
 ## Model Card Authors
 
 - TradePulse ML Team
-- Auto-generated on 2025-07-30 10:33:35
+- Auto-generated on 2025-07-30 15:51:35

checkpoint-240/trainer_state.json

@@ -1,240 +0,0 @@
-{
-  "best_metric": 0.829041087388282,
-  "best_model_checkpoint": "hf-sentiment-production/checkpoint-240",
-  "epoch": 2.0,
-  "eval_steps": 500,
-  "global_step": 240,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.08333333333333333,
-      "grad_norm": 0.06056511402130127,
-      "learning_rate": 8.403361344537816e-07,
-      "loss": 0.1772,
-      "step": 10
-    },
-    {
-      "epoch": 0.16666666666666666,
-      "grad_norm": 0.029755454510450363,
-      "learning_rate": 1.6806722689075632e-06,
-      "loss": 0.1311,
-      "step": 20
-    },
-    {
-      "epoch": 0.25,
-      "grad_norm": 0.014640219509601593,
-      "learning_rate": 2.521008403361345e-06,
-      "loss": 0.0002,
-      "step": 30
-    },
-    {
-      "epoch": 0.3333333333333333,
-      "grad_norm": 0.11976221948862076,
-      "learning_rate": 3.3613445378151265e-06,
-      "loss": 0.0001,
-      "step": 40
-    },
-    {
-      "epoch": 0.4166666666666667,
-      "grad_norm": 0.3207981586456299,
-      "learning_rate": 4.201680672268908e-06,
-      "loss": 0.0008,
-      "step": 50
-    },
-    {
-      "epoch": 0.5,
-      "grad_norm": 0.010227964259684086,
-      "learning_rate": 5.04201680672269e-06,
-      "loss": 0.0001,
-      "step": 60
-    },
-    {
-      "epoch": 0.5833333333333334,
-      "grad_norm": 0.003333959961310029,
-      "learning_rate": 5.882352941176471e-06,
-      "loss": 0.0001,
-      "step": 70
-    },
-    {
-      "epoch": 0.6666666666666666,
-      "grad_norm": 0.0037250840105116367,
-      "learning_rate": 6.722689075630253e-06,
-      "loss": 0.0178,
-      "step": 80
-    },
-    {
-      "epoch": 0.75,
-      "grad_norm": 0.0019598035141825676,
-      "learning_rate": 7.563025210084034e-06,
-      "loss": 0.0004,
-      "step": 90
-    },
-    {
-      "epoch": 0.8333333333333334,
-      "grad_norm": 0.005815756041556597,
-      "learning_rate": 8.403361344537815e-06,
-      "loss": 0.0002,
-      "step": 100
-    },
-    {
-      "epoch": 0.9166666666666666,
-      "grad_norm": 0.2174970656633377,
-      "learning_rate": 9.243697478991598e-06,
-      "loss": 0.0001,
-      "step": 110
-    },
-    {
-      "epoch": 1.0,
-      "grad_norm": 1.864820660557598e-05,
-      "learning_rate": 9.917355371900828e-06,
-      "loss": 0.0001,
-      "step": 120
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.8125,
-      "eval_f1": 0.8079910714285715,
-      "eval_f1_macro": 0.7952380952380952,
-      "eval_loss": 1.5992441177368164,
-      "eval_precision": 0.8254665124476757,
-      "eval_precision_macro": 0.8422633472864801,
-      "eval_recall": 0.8125,
-      "eval_recall_macro": 0.7739716990467395,
-      "eval_runtime": 88.2636,
-      "eval_samples_per_second": 1.813,
-      "eval_steps_per_second": 0.453,
-      "step": 120
-    },
-    {
-      "epoch": 1.0833333333333333,
-      "grad_norm": 0.0010791183449327946,
-      "learning_rate": 9.090909090909091e-06,
-      "loss": 0.0001,
-      "step": 130
-    },
-    {
-      "epoch": 1.1666666666666667,
-      "grad_norm": 0.0033589524682611227,
-      "learning_rate": 8.264462809917356e-06,
-      "loss": 0.0002,
-      "step": 140
-    },
-    {
-      "epoch": 1.25,
-      "grad_norm": 0.07826946675777435,
-      "learning_rate": 7.43801652892562e-06,
-      "loss": 0.0001,
-      "step": 150
-    },
-    {
-      "epoch": 1.3333333333333333,
-      "grad_norm": 0.008779647760093212,
-      "learning_rate": 6.611570247933885e-06,
-      "loss": 0.0003,
-      "step": 160
-    },
-    {
-      "epoch": 1.4166666666666667,
-      "grad_norm": 0.007557153236120939,
-      "learning_rate": 5.785123966942149e-06,
-      "loss": 0.0001,
-      "step": 170
-    },
-    {
-      "epoch": 1.5,
-      "grad_norm": 0.10376619547605515,
-      "learning_rate": 4.958677685950414e-06,
-      "loss": 0.0005,
-      "step": 180
-    },
-    {
-      "epoch": 1.5833333333333335,
-      "grad_norm": 0.016951242461800575,
-      "learning_rate": 4.132231404958678e-06,
-      "loss": 0.0044,
-      "step": 190
-    },
-    {
-      "epoch": 1.6666666666666665,
-      "grad_norm": 0.026832090690732002,
-      "learning_rate": 3.3057851239669424e-06,
-      "loss": 0.0001,
-      "step": 200
-    },
-    {
-      "epoch": 1.75,
-      "grad_norm": 0.0011464687995612621,
-      "learning_rate": 2.479338842975207e-06,
-      "loss": 0.0006,
-      "step": 210
-    },
-    {
-      "epoch": 1.8333333333333335,
-      "grad_norm": 0.15988384187221527,
-      "learning_rate": 1.6528925619834712e-06,
-      "loss": 0.0002,
-      "step": 220
-    },
-    {
-      "epoch": 1.9166666666666665,
-      "grad_norm": 0.2989813983440399,
-      "learning_rate": 8.264462809917356e-07,
-      "loss": 0.1214,
-      "step": 230
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 5.207050435274141e-06,
-      "learning_rate": 0.0,
-      "loss": 0.3908,
-      "step": 240
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.83125,
-      "eval_f1": 0.829041087388282,
-      "eval_f1_macro": 0.8202912942734194,
-      "eval_loss": 1.2841339111328125,
-      "eval_precision": 0.8333425925925926,
-      "eval_precision_macro": 0.8355555555555556,
-      "eval_recall": 0.83125,
-      "eval_recall_macro": 0.8112252751481567,
-      "eval_runtime": 88.1774,
-      "eval_samples_per_second": 1.815,
-      "eval_steps_per_second": 0.454,
-      "step": 240
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 240,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "EarlyStoppingCallback": {
-      "args": {
-        "early_stopping_patience": 1,
-        "early_stopping_threshold": 0.0
-      },
-      "attributes": {
-        "early_stopping_patience_counter": 0
-      }
-    },
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 251010200512512.0,
-  "train_batch_size": 4,
-  "trial_name": null,
-  "trial_params": null
-}

{checkpoint-240 → checkpoint-674}/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa2bc7c9841dfe824d6c70bfd3916308d9a44b7693233a545b97104d85ddd8ae
+oid sha256:65c86576e3490028c001970eeed1a443b627250e862d0a08874ada27469ca34a
 size 439039996

checkpoint-674/trainer_state.json

@@ -0,0 +1,541 @@
+{
+  "best_metric": 0.9977731894655975,
+  "best_model_checkpoint": "hf-sentiment-production/checkpoint-674",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 674,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02967359050445104,
+      "grad_norm": 0.33146166801452637,
+      "learning_rate": 2.9761904761904765e-07,
+      "loss": 1.2128,
+      "step": 10
+    },
+    {
+      "epoch": 0.05934718100890208,
+      "grad_norm": 12.761545181274414,
+      "learning_rate": 5.952380952380953e-07,
+      "loss": 1.3721,
+      "step": 20
+    },
+    {
+      "epoch": 0.08902077151335312,
+      "grad_norm": 9.993690490722656,
+      "learning_rate": 8.928571428571429e-07,
+      "loss": 0.7583,
+      "step": 30
+    },
+    {
+      "epoch": 0.11869436201780416,
+      "grad_norm": 48.96151351928711,
+      "learning_rate": 1.1904761904761906e-06,
+      "loss": 0.2415,
+      "step": 40
+    },
+    {
+      "epoch": 0.14836795252225518,
+      "grad_norm": 158.08262634277344,
+      "learning_rate": 1.4880952380952381e-06,
+      "loss": 0.7109,
+      "step": 50
+    },
+    {
+      "epoch": 0.17804154302670624,
+      "grad_norm": 11.123541831970215,
+      "learning_rate": 1.7857142857142859e-06,
+      "loss": 0.2779,
+      "step": 60
+    },
+    {
+      "epoch": 0.20771513353115728,
+      "grad_norm": 5.884549617767334,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 0.2621,
+      "step": 70
+    },
+    {
+      "epoch": 0.23738872403560832,
+      "grad_norm": 87.84249877929688,
+      "learning_rate": 2.380952380952381e-06,
+      "loss": 0.7296,
+      "step": 80
+    },
+    {
+      "epoch": 0.26706231454005935,
+      "grad_norm": 0.09888105094432831,
+      "learning_rate": 2.6785714285714285e-06,
+      "loss": 0.6088,
+      "step": 90
+    },
+    {
+      "epoch": 0.29673590504451036,
+      "grad_norm": 5.604600429534912,
+      "learning_rate": 2.9761904761904763e-06,
+      "loss": 0.5594,
+      "step": 100
+    },
+    {
+      "epoch": 0.3264094955489614,
+      "grad_norm": 0.04671299830079079,
+      "learning_rate": 3.273809523809524e-06,
+      "loss": 0.2191,
+      "step": 110
+    },
+    {
+      "epoch": 0.3560830860534125,
+      "grad_norm": 2.0412070751190186,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 0.0897,
+      "step": 120
+    },
+    {
+      "epoch": 0.3857566765578635,
+      "grad_norm": 1.162245273590088,
+      "learning_rate": 3.869047619047619e-06,
+      "loss": 0.0154,
+      "step": 130
+    },
+    {
+      "epoch": 0.41543026706231456,
+      "grad_norm": 4.64531946182251,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.1424,
+      "step": 140
+    },
+    {
+      "epoch": 0.44510385756676557,
+      "grad_norm": 0.0003644149692263454,
+      "learning_rate": 4.464285714285715e-06,
+      "loss": 0.0236,
+      "step": 150
+    },
+    {
+      "epoch": 0.47477744807121663,
+      "grad_norm": 0.0010449385736137629,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 0.0082,
+      "step": 160
+    },
+    {
+      "epoch": 0.5044510385756676,
+      "grad_norm": 0.0023269294761121273,
+      "learning_rate": 5.05952380952381e-06,
+      "loss": 0.0005,
+      "step": 170
+    },
+    {
+      "epoch": 0.5341246290801187,
+      "grad_norm": 19.690420150756836,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 0.0044,
+      "step": 180
+    },
+    {
+      "epoch": 0.5637982195845698,
+      "grad_norm": 5.873505592346191,
+      "learning_rate": 5.654761904761905e-06,
+      "loss": 0.002,
+      "step": 190
+    },
+    {
+      "epoch": 0.5934718100890207,
+      "grad_norm": 0.2877367436885834,
+      "learning_rate": 5.9523809523809525e-06,
+      "loss": 0.1023,
+      "step": 200
+    },
+    {
+      "epoch": 0.6231454005934718,
+      "grad_norm": 0.008003341034054756,
+      "learning_rate": 6.25e-06,
+      "loss": 0.0003,
+      "step": 210
+    },
+    {
+      "epoch": 0.6528189910979229,
+      "grad_norm": 79.11434936523438,
+      "learning_rate": 6.547619047619048e-06,
+      "loss": 0.0245,
+      "step": 220
+    },
+    {
+      "epoch": 0.6824925816023739,
+      "grad_norm": 0.00577218271791935,
+      "learning_rate": 6.845238095238096e-06,
+      "loss": 0.0001,
+      "step": 230
+    },
+    {
+      "epoch": 0.712166172106825,
+      "grad_norm": 0.003522080834954977,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.7418397626112759,
+      "grad_norm": 0.0008736816816963255,
+      "learning_rate": 7.440476190476191e-06,
+      "loss": 0.0001,
+      "step": 250
+    },
+    {
+      "epoch": 0.771513353115727,
+      "grad_norm": 5.390814476413652e-05,
+      "learning_rate": 7.738095238095238e-06,
+      "loss": 0.0001,
+      "step": 260
+    },
+    {
+      "epoch": 0.8011869436201781,
+      "grad_norm": 0.00016854175191838294,
+      "learning_rate": 8.035714285714286e-06,
+      "loss": 0.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.8308605341246291,
+      "grad_norm": 9.450274956179783e-05,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.0001,
+      "step": 280
+    },
+    {
+      "epoch": 0.8605341246290801,
+      "grad_norm": 7.811003888491541e-05,
+      "learning_rate": 8.630952380952381e-06,
+      "loss": 0.0001,
+      "step": 290
+    },
+    {
+      "epoch": 0.8902077151335311,
+      "grad_norm": 0.0032586443703621626,
+      "learning_rate": 8.92857142857143e-06,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.9198813056379822,
+      "grad_norm": 0.0009132844279520214,
+      "learning_rate": 9.226190476190477e-06,
+      "loss": 0.0044,
+      "step": 310
+    },
+    {
+      "epoch": 0.9495548961424333,
+      "grad_norm": 0.0014514722861349583,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 0.0001,
+      "step": 320
+    },
+    {
+      "epoch": 0.9792284866468842,
+      "grad_norm": 0.00012150395195931196,
+      "learning_rate": 9.821428571428573e-06,
+      "loss": 0.0006,
+      "step": 330
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9933333333333333,
+      "eval_f1": 0.9932911444421615,
+      "eval_f1_macro": 0.991480035613999,
+      "eval_loss": 0.05405780300498009,
+      "eval_precision": 0.9934188034188034,
+      "eval_precision_macro": 0.9957264957264957,
+      "eval_recall": 0.9933333333333333,
+      "eval_recall_macro": 0.9874999999999999,
+      "eval_runtime": 259.5646,
+      "eval_samples_per_second": 1.734,
+      "eval_steps_per_second": 0.435,
+      "step": 337
+    },
+    {
+      "epoch": 1.0089020771513353,
+      "grad_norm": 0.00010033950820798054,
+      "learning_rate": 9.88165680473373e-06,
+      "loss": 0.1403,
+      "step": 340
+    },
+    {
+      "epoch": 1.0385756676557865,
+      "grad_norm": 0.013481284491717815,
+      "learning_rate": 9.585798816568049e-06,
+      "loss": 0.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.0682492581602374,
+      "grad_norm": 0.0009898018324747682,
+      "learning_rate": 9.289940828402368e-06,
+      "loss": 0.0,
+      "step": 360
+    },
+    {
+      "epoch": 1.0979228486646884,
+      "grad_norm": 0.00012659125786740333,
+      "learning_rate": 8.994082840236687e-06,
+      "loss": 0.0,
+      "step": 370
+    },
+    {
+      "epoch": 1.1275964391691395,
+      "grad_norm": 0.00047182640992105007,
+      "learning_rate": 8.698224852071006e-06,
+      "loss": 0.0,
+      "step": 380
+    },
+    {
+      "epoch": 1.1572700296735905,
+      "grad_norm": 0.0001335637061856687,
+      "learning_rate": 8.402366863905327e-06,
+      "loss": 0.0,
+      "step": 390
+    },
+    {
+      "epoch": 1.1869436201780414,
+      "grad_norm": 0.0002707823005039245,
+      "learning_rate": 8.106508875739646e-06,
+      "loss": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.2166172106824926,
+      "grad_norm": 0.00016450774273835123,
+      "learning_rate": 7.810650887573965e-06,
+      "loss": 0.0,
+      "step": 410
+    },
+    {
+      "epoch": 1.2462908011869436,
+      "grad_norm": 0.0005354972090572119,
+      "learning_rate": 7.5147928994082845e-06,
+      "loss": 0.0,
+      "step": 420
+    },
+    {
+      "epoch": 1.2759643916913945,
+      "grad_norm": 0.00011406593694118783,
+      "learning_rate": 7.218934911242604e-06,
+      "loss": 0.0,
+      "step": 430
+    },
+    {
+      "epoch": 1.3056379821958457,
+      "grad_norm": 0.16808006167411804,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 0.0001,
+      "step": 440
+    },
+    {
+      "epoch": 1.3353115727002967,
+      "grad_norm": 8.87056376086548e-05,
+      "learning_rate": 6.627218934911244e-06,
+      "loss": 0.0,
+      "step": 450
+    },
+    {
+      "epoch": 1.3649851632047478,
+      "grad_norm": 0.0005222823820076883,
+      "learning_rate": 6.331360946745563e-06,
+      "loss": 0.0,
+      "step": 460
+    },
+    {
+      "epoch": 1.3946587537091988,
+      "grad_norm": 1.3695029338123277e-05,
+      "learning_rate": 6.035502958579882e-06,
+      "loss": 0.0,
+      "step": 470
+    },
+    {
+      "epoch": 1.4243323442136497,
+      "grad_norm": 5.737605533795431e-05,
+      "learning_rate": 5.739644970414202e-06,
+      "loss": 0.0,
+      "step": 480
+    },
+    {
+      "epoch": 1.454005934718101,
+      "grad_norm": 0.005723549518734217,
+      "learning_rate": 5.443786982248521e-06,
+      "loss": 0.0,
+      "step": 490
+    },
+    {
+      "epoch": 1.4836795252225519,
+      "grad_norm": 1.2021506336168386e-05,
+      "learning_rate": 5.14792899408284e-06,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.513353115727003,
+      "grad_norm": 4.697950862464495e-05,
+      "learning_rate": 4.85207100591716e-06,
+      "loss": 0.0,
+      "step": 510
+    },
+    {
+      "epoch": 1.543026706231454,
+      "grad_norm": 0.000708841485902667,
+      "learning_rate": 4.55621301775148e-06,
+      "loss": 0.0,
+      "step": 520
+    },
+    {
+      "epoch": 1.572700296735905,
+      "grad_norm": 1.7618485799175687e-05,
+      "learning_rate": 4.2603550295858e-06,
+      "loss": 0.0,
+      "step": 530
+    },
+    {
+      "epoch": 1.6023738872403561,
+      "grad_norm": 0.00013081534416414797,
+      "learning_rate": 3.964497041420119e-06,
+      "loss": 0.0,
+      "step": 540
+    },
+    {
+      "epoch": 1.632047477744807,
+      "grad_norm": 0.00028243096312507987,
+      "learning_rate": 3.668639053254438e-06,
+      "loss": 0.0,
+      "step": 550
+    },
+    {
+      "epoch": 1.6617210682492582,
+      "grad_norm": 0.0002703359059523791,
+      "learning_rate": 3.3727810650887576e-06,
+      "loss": 0.0,
+      "step": 560
+    },
+    {
+      "epoch": 1.6913946587537092,
+      "grad_norm": 2.5464911232120357e-05,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 0.0,
+      "step": 570
+    },
+    {
+      "epoch": 1.7210682492581602,
+      "grad_norm": 2.6416844775667414e-05,
+      "learning_rate": 2.7810650887573965e-06,
+      "loss": 0.0,
+      "step": 580
+    },
+    {
+      "epoch": 1.7507418397626113,
+      "grad_norm": 0.012607904151082039,
+      "learning_rate": 2.485207100591716e-06,
+      "loss": 0.051,
+      "step": 590
+    },
+    {
+      "epoch": 1.7804154302670623,
+      "grad_norm": 0.0064520263113081455,
+      "learning_rate": 2.1893491124260358e-06,
+      "loss": 0.0001,
+      "step": 600
+    },
+    {
+      "epoch": 1.8100890207715135,
+      "grad_norm": 0.00013779209984932095,
+      "learning_rate": 1.8934911242603552e-06,
+      "loss": 0.0,
+      "step": 610
+    },
+    {
+      "epoch": 1.8397626112759644,
+      "grad_norm": 0.00019228862947784364,
+      "learning_rate": 1.5976331360946749e-06,
+      "loss": 0.0,
+      "step": 620
+    },
+    {
+      "epoch": 1.8694362017804154,
+      "grad_norm": 3.4337310353294015e-05,
+      "learning_rate": 1.301775147928994e-06,
+      "loss": 0.0,
+      "step": 630
+    },
+    {
+      "epoch": 1.8991097922848663,
+      "grad_norm": 0.000257375038927421,
+      "learning_rate": 1.0059171597633138e-06,
+      "loss": 0.0,
+      "step": 640
+    },
+    {
+      "epoch": 1.9287833827893175,
+      "grad_norm": 0.0015161657938733697,
+      "learning_rate": 7.100591715976332e-07,
+      "loss": 0.001,
+      "step": 650
+    },
+    {
+      "epoch": 1.9584569732937687,
+      "grad_norm": 0.0051199602894485,
+      "learning_rate": 4.1420118343195276e-07,
+      "loss": 0.0,
+      "step": 660
+    },
+    {
+      "epoch": 1.9881305637982196,
+      "grad_norm": 0.0002789547143038362,
+      "learning_rate": 1.183431952662722e-07,
+      "loss": 0.0,
+      "step": 670
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9977777777777778,
+      "eval_f1": 0.9977731894655975,
+      "eval_f1_macro": 0.9971836215366922,
+      "eval_loss": 0.01406792365014553,
+      "eval_precision": 0.997787356321839,
+      "eval_precision_macro": 0.9985632183908045,
+      "eval_recall": 0.9977777777777778,
+      "eval_recall_macro": 0.9958333333333332,
+      "eval_runtime": 251.8116,
+      "eval_samples_per_second": 1.787,
+      "eval_steps_per_second": 0.449,
+      "step": 674
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 674,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 708827547359232.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa2bc7c9841dfe824d6c70bfd3916308d9a44b7693233a545b97104d85ddd8ae
+oid sha256:65c86576e3490028c001970eeed1a443b627250e862d0a08874ada27469ca34a
 size 439039996

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76b8cf3932f11a5314ed3d8475b3e07f076b574cf6ed23ea9ee7b8a1833b39a3
+oid sha256:ee8d368ce496fb886ffa4923127a0a81a3a9f151c0978b2be2437bacdbc4f72a
 size 5521