End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_km_50_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_base_km_50_v1_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7034313725490197
+    - name: F1
+      type: f1
+      value: 0.8141321044546851
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_km_50_v1_mrpc
 
-This model is a fine-tuned version of [Hartunka/bert_base_km_50_v1](https://huggingface.co/Hartunka/bert_base_km_50_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_km_50_v1](https://huggingface.co/Hartunka/bert_base_km_50_v1) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1340
-- Accuracy: 0.6593
-- F1: 0.7531
-- Combined Score: 0.7062
+- Loss: 0.5894
+- Accuracy: 0.7034
+- F1: 0.8141
+- Combined Score: 0.7588
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7034313725490197,
+    "eval_combined_score": 0.7587817385018524,
+    "eval_f1": 0.8141321044546851,
+    "eval_loss": 0.5893518924713135,
+    "eval_runtime": 0.3351,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1217.397,
+    "eval_steps_per_second": 5.968,
+    "total_flos": 3377819728711680.0,
+    "train_loss": 0.37630167575109574,
+    "train_runtime": 57.9107,
+    "train_samples": 3668,
+    "train_samples_per_second": 3166.945,
+    "train_steps_per_second": 12.951
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7034313725490197,
+    "eval_combined_score": 0.7587817385018524,
+    "eval_f1": 0.8141321044546851,
+    "eval_loss": 0.5893518924713135,
+    "eval_runtime": 0.3351,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1217.397,
+    "eval_steps_per_second": 5.968
+}

logs/events.out.tfevents.1745056185.s_005_m.2788007.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bd6c2e0082792ff04ce9af2c45f322ec7ec0770593d26948497d1ee512e4aeb
+size 459

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 3377819728711680.0,
+    "train_loss": 0.37630167575109574,
+    "train_runtime": 57.9107,
+    "train_samples": 3668,
+    "train_samples_per_second": 3166.945,
+    "train_steps_per_second": 12.951
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 30,
+  "best_metric": 0.5893518924713135,
+  "best_model_checkpoint": "bert_base_km_50_v1_mrpc/checkpoint-30",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 105,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.1089715957641602,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6263,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6887254901960784,
+      "eval_combined_score": 0.7452987825395369,
+      "eval_f1": 0.8018720748829953,
+      "eval_loss": 0.5977591872215271,
+      "eval_runtime": 0.2702,
+      "eval_samples_per_second": 1509.746,
+      "eval_steps_per_second": 7.401,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.4218831062316895,
+      "learning_rate": 4.8e-05,
+      "loss": 0.572,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7034313725490197,
+      "eval_combined_score": 0.7587817385018524,
+      "eval_f1": 0.8141321044546851,
+      "eval_loss": 0.5893518924713135,
+      "eval_runtime": 0.2724,
+      "eval_samples_per_second": 1497.989,
+      "eval_steps_per_second": 7.343,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.491407871246338,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5108,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7034313725490197,
+      "eval_combined_score": 0.7552244582043344,
+      "eval_f1": 0.8070175438596491,
+      "eval_loss": 0.6016624569892883,
+      "eval_runtime": 0.2763,
+      "eval_samples_per_second": 1476.67,
+      "eval_steps_per_second": 7.239,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.704878091812134,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4158,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.737373677185623,
+      "eval_f1": 0.7909238249594813,
+      "eval_loss": 0.6796642541885376,
+      "eval_runtime": 0.2698,
+      "eval_samples_per_second": 1512.03,
+      "eval_steps_per_second": 7.412,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.1070427894592285,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2727,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6446078431372549,
+      "eval_combined_score": 0.6872946105816629,
+      "eval_f1": 0.7299813780260708,
+      "eval_loss": 0.8248001337051392,
+      "eval_runtime": 0.3065,
+      "eval_samples_per_second": 1331.354,
+      "eval_steps_per_second": 6.526,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.6518099308013916,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1534,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6176470588235294,
+      "eval_combined_score": 0.6659663865546219,
+      "eval_f1": 0.7142857142857143,
+      "eval_loss": 1.088710904121399,
+      "eval_runtime": 0.2777,
+      "eval_samples_per_second": 1469.065,
+      "eval_steps_per_second": 7.201,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.282205581665039,
+      "learning_rate": 4.3e-05,
+      "loss": 0.083,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6593137254901961,
+      "eval_combined_score": 0.7062110368125936,
+      "eval_f1": 0.7531083481349912,
+      "eval_loss": 1.1340426206588745,
+      "eval_runtime": 0.2695,
+      "eval_samples_per_second": 1514.054,
+      "eval_steps_per_second": 7.422,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "step": 105,
+      "total_flos": 3377819728711680.0,
+      "train_loss": 0.37630167575109574,
+      "train_runtime": 57.9107,
+      "train_samples_per_second": 3166.945,
+      "train_steps_per_second": 12.951
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 5
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3377819728711680.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}