End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_rand_20_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_base_rand_20_v2_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7132352941176471
+    - name: F1
+      type: f1
+      value: 0.7965217391304348
 ---
 
 <!-- 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_rand_20_v2_mrpc
 
-This model is a fine-tuned version of [Hartunka/bert_base_rand_20_v2](https://huggingface.co/Hartunka/bert_base_rand_20_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_rand_20_v2](https://huggingface.co/Hartunka/bert_base_rand_20_v2) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3284
-- Accuracy: 0.6765
-- F1: 0.7724
-- Combined Score: 0.7244
+- Loss: 0.5865
+- Accuracy: 0.7132
+- F1: 0.7965
+- Combined Score: 0.7549
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7132352941176471,
+    "eval_combined_score": 0.7548785166240409,
+    "eval_f1": 0.7965217391304348,
+    "eval_loss": 0.5864964127540588,
+    "eval_runtime": 0.2974,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1371.83,
+    "eval_steps_per_second": 6.725,
+    "total_flos": 3377819728711680.0,
+    "train_loss": 0.36644470805213564,
+    "train_runtime": 57.9808,
+    "train_samples": 3668,
+    "train_samples_per_second": 3163.116,
+    "train_steps_per_second": 12.935
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7132352941176471,
+    "eval_combined_score": 0.7548785166240409,
+    "eval_f1": 0.7965217391304348,
+    "eval_loss": 0.5864964127540588,
+    "eval_runtime": 0.2974,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1371.83,
+    "eval_steps_per_second": 6.725
+}

logs/events.out.tfevents.1745483598.s_005_m.2892304.57

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba5bf9a0bb61d07029788ce1a383a95562fc1031a694a2528c30c5b205876d18
+size 459

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 3377819728711680.0,
+    "train_loss": 0.36644470805213564,
+    "train_runtime": 57.9808,
+    "train_samples": 3668,
+    "train_samples_per_second": 3163.116,
+    "train_steps_per_second": 12.935
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 30,
+  "best_metric": 0.5864964127540588,
+  "best_model_checkpoint": "bert_base_rand_20_v2_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": 1.2145460844039917,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6372,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7009803921568627,
+      "eval_combined_score": 0.7551776960784313,
+      "eval_f1": 0.809375,
+      "eval_loss": 0.588714063167572,
+      "eval_runtime": 0.2739,
+      "eval_samples_per_second": 1489.35,
+      "eval_steps_per_second": 7.301,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.2979806661605835,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5784,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7132352941176471,
+      "eval_combined_score": 0.7548785166240409,
+      "eval_f1": 0.7965217391304348,
+      "eval_loss": 0.5864964127540588,
+      "eval_runtime": 0.274,
+      "eval_samples_per_second": 1489.299,
+      "eval_steps_per_second": 7.3,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.0560436248779297,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5021,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7156862745098039,
+      "eval_combined_score": 0.7585280687617513,
+      "eval_f1": 0.8013698630136986,
+      "eval_loss": 0.5903182625770569,
+      "eval_runtime": 0.2837,
+      "eval_samples_per_second": 1438.195,
+      "eval_steps_per_second": 7.05,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.1111886501312256,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3739,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6936274509803921,
+      "eval_combined_score": 0.7346054669623684,
+      "eval_f1": 0.7755834829443446,
+      "eval_loss": 0.7027990221977234,
+      "eval_runtime": 0.2761,
+      "eval_samples_per_second": 1477.587,
+      "eval_steps_per_second": 7.243,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.799419403076172,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2326,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6813725490196079,
+      "eval_combined_score": 0.72377979968966,
+      "eval_f1": 0.7661870503597122,
+      "eval_loss": 0.9849025011062622,
+      "eval_runtime": 0.2726,
+      "eval_samples_per_second": 1496.876,
+      "eval_steps_per_second": 7.338,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.7601404190063477,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1394,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6642156862745098,
+      "eval_combined_score": 0.7077884238995054,
+      "eval_f1": 0.7513611615245009,
+      "eval_loss": 1.1196123361587524,
+      "eval_runtime": 0.2754,
+      "eval_samples_per_second": 1481.428,
+      "eval_steps_per_second": 7.262,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.530137062072754,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1015,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6764705882352942,
+      "eval_combined_score": 0.7244421906693712,
+      "eval_f1": 0.7724137931034483,
+      "eval_loss": 1.3284002542495728,
+      "eval_runtime": 0.2722,
+      "eval_samples_per_second": 1498.942,
+      "eval_steps_per_second": 7.348,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "step": 105,
+      "total_flos": 3377819728711680.0,
+      "train_loss": 0.36644470805213564,
+      "train_runtime": 57.9808,
+      "train_samples_per_second": 3163.116,
+      "train_steps_per_second": 12.935
+    }
+  ],
+  "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
+}