End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_km_10_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_base_km_10_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: 0.7181372549019608
+    - name: F1
+      type: f1
+      value: 0.8177496038034865
 ---
 
 <!-- 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_10_v1_mrpc
 
-This model is a fine-tuned version of [Hartunka/bert_base_km_10_v1](https://huggingface.co/Hartunka/bert_base_km_10_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_km_10_v1](https://huggingface.co/Hartunka/bert_base_km_10_v1) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3684
-- Accuracy: 0.6495
-- F1: 0.7478
-- Combined Score: 0.6987
+- Loss: 0.5816
+- Accuracy: 0.7181
+- F1: 0.8177
+- Combined Score: 0.7679
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7181372549019608,
+    "eval_combined_score": 0.7679434293527236,
+    "eval_f1": 0.8177496038034865,
+    "eval_loss": 0.5815861225128174,
+    "eval_runtime": 0.286,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1426.58,
+    "eval_steps_per_second": 6.993,
+    "total_flos": 3377819728711680.0,
+    "train_loss": 0.3347021750041417,
+    "train_runtime": 58.4476,
+    "train_samples": 3668,
+    "train_samples_per_second": 3137.856,
+    "train_steps_per_second": 12.832
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7181372549019608,
+    "eval_combined_score": 0.7679434293527236,
+    "eval_f1": 0.8177496038034865,
+    "eval_loss": 0.5815861225128174,
+    "eval_runtime": 0.286,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1426.58,
+    "eval_steps_per_second": 6.993
+}

logs/events.out.tfevents.1744977632.s_005_m.2772371.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6551fb7be30e91b13c58b282a7f39f8cdd1d0d4018420f6c9a622d9c07c58efe
+size 459

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 3377819728711680.0,
+    "train_loss": 0.3347021750041417,
+    "train_runtime": 58.4476,
+    "train_samples": 3668,
+    "train_samples_per_second": 3137.856,
+    "train_steps_per_second": 12.832
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 30,
+  "best_metric": 0.5815861225128174,
+  "best_model_checkpoint": "bert_base_km_10_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": 1.2988574504852295,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6351,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7156862745098039,
+      "eval_combined_score": 0.7639920045688178,
+      "eval_f1": 0.8122977346278317,
+      "eval_loss": 0.6032212376594543,
+      "eval_runtime": 0.2716,
+      "eval_samples_per_second": 1502.213,
+      "eval_steps_per_second": 7.364,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.8030914068222046,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5595,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7181372549019608,
+      "eval_combined_score": 0.7679434293527236,
+      "eval_f1": 0.8177496038034865,
+      "eval_loss": 0.5815861225128174,
+      "eval_runtime": 0.2716,
+      "eval_samples_per_second": 1502.163,
+      "eval_steps_per_second": 7.364,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.2205817699432373,
+      "learning_rate": 4.7e-05,
+      "loss": 0.4644,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6911764705882353,
+      "eval_combined_score": 0.7362132352941176,
+      "eval_f1": 0.78125,
+      "eval_loss": 0.6316073536872864,
+      "eval_runtime": 0.282,
+      "eval_samples_per_second": 1446.589,
+      "eval_steps_per_second": 7.091,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.9814860820770264,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3359,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6617647058823529,
+      "eval_combined_score": 0.7115051903114187,
+      "eval_f1": 0.7612456747404844,
+      "eval_loss": 0.7270227074623108,
+      "eval_runtime": 0.286,
+      "eval_samples_per_second": 1426.563,
+      "eval_steps_per_second": 6.993,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.06840705871582,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1929,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6519607843137255,
+      "eval_combined_score": 0.6930215906587354,
+      "eval_f1": 0.7340823970037453,
+      "eval_loss": 0.9278217554092407,
+      "eval_runtime": 0.2799,
+      "eval_samples_per_second": 1457.546,
+      "eval_steps_per_second": 7.145,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.972137928009033,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.0954,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6519607843137255,
+      "eval_combined_score": 0.702287012365922,
+      "eval_f1": 0.7526132404181185,
+      "eval_loss": 1.1869008541107178,
+      "eval_runtime": 0.2886,
+      "eval_samples_per_second": 1413.731,
+      "eval_steps_per_second": 6.93,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.5582962036132812,
+      "learning_rate": 4.3e-05,
+      "loss": 0.0598,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6495098039215687,
+      "eval_combined_score": 0.6986526091918248,
+      "eval_f1": 0.7477954144620811,
+      "eval_loss": 1.3683987855911255,
+      "eval_runtime": 0.2782,
+      "eval_samples_per_second": 1466.718,
+      "eval_steps_per_second": 7.19,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "step": 105,
+      "total_flos": 3377819728711680.0,
+      "train_loss": 0.3347021750041417,
+      "train_runtime": 58.4476,
+      "train_samples_per_second": 3137.856,
+      "train_steps_per_second": 12.832
+    }
+  ],
+  "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
+}