End of training

README.md

@@ -1,15 +1,33 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: google/bert_uncased_L-2_H-256_A-4
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_uncased_L-2_H-256_A-4_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7475490196078431
+    - name: F1
+      type: f1
+      value: 0.835725677830941
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,12 +35,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_uncased_L-2_H-256_A-4_mrpc
 
-This model is a fine-tuned version of [google/bert_uncased_L-2_H-256_A-4](https://huggingface.co/google/bert_uncased_L-2_H-256_A-4) on an unknown dataset.
+This model is a fine-tuned version of [google/bert_uncased_L-2_H-256_A-4](https://huggingface.co/google/bert_uncased_L-2_H-256_A-4) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5943
-- Accuracy: 0.75
-- F1: 0.8317
-- Combined Score: 0.7908
+- Loss: 0.5344
+- Accuracy: 0.7475
+- F1: 0.8357
+- Combined Score: 0.7916
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 11.0,
+    "eval_accuracy": 0.7475490196078431,
+    "eval_combined_score": 0.7916373487193921,
+    "eval_f1": 0.835725677830941,
+    "eval_loss": 0.5344022512435913,
+    "eval_runtime": 0.1438,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2837.532,
+    "eval_steps_per_second": 13.909,
+    "total_flos": 102031020478464.0,
+    "train_loss": 0.4675573955882679,
+    "train_runtime": 21.1858,
+    "train_samples": 3668,
+    "train_samples_per_second": 8656.733,
+    "train_steps_per_second": 35.401
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 11.0,
+    "eval_accuracy": 0.7475490196078431,
+    "eval_combined_score": 0.7916373487193921,
+    "eval_f1": 0.835725677830941,
+    "eval_loss": 0.5344022512435913,
+    "eval_runtime": 0.1438,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2837.532,
+    "eval_steps_per_second": 13.909
+}

logs/events.out.tfevents.1733330444.ki-g0008.1764072.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:329365b4ab234387f2c50915017467129c825ad08c2c7544c8a41f82b4c10279
+size 515

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 11.0,
+    "total_flos": 102031020478464.0,
+    "train_loss": 0.4675573955882679,
+    "train_runtime": 21.1858,
+    "train_samples": 3668,
+    "train_samples_per_second": 8656.733,
+    "train_steps_per_second": 35.401
+}

trainer_state.json

@@ -0,0 +1,249 @@
+{
+  "best_metric": 0.5344022512435913,
+  "best_model_checkpoint": "bert_uncased_L-2_H-256_A-4_mrpc/checkpoint-90",
+  "epoch": 11.0,
+  "eval_steps": 500,
+  "global_step": 165,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9149664044380188,
+      "learning_rate": 4.9e-05,
+      "loss": 0.619,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6887254901960784,
+      "eval_combined_score": 0.7516620151710319,
+      "eval_f1": 0.8145985401459854,
+      "eval_loss": 0.5955595374107361,
+      "eval_runtime": 0.1436,
+      "eval_samples_per_second": 2840.349,
+      "eval_steps_per_second": 13.923,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7355875968933105,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5893,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7009803921568627,
+      "eval_combined_score": 0.7594454199590284,
+      "eval_f1": 0.817910447761194,
+      "eval_loss": 0.583465039730072,
+      "eval_runtime": 0.1527,
+      "eval_samples_per_second": 2672.428,
+      "eval_steps_per_second": 13.1,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.3674581050872803,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5612,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_combined_score": 0.7614777618364419,
+      "eval_f1": 0.8170731707317074,
+      "eval_loss": 0.559699535369873,
+      "eval_runtime": 0.1434,
+      "eval_samples_per_second": 2844.442,
+      "eval_steps_per_second": 13.943,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.349136471748352,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5397,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7377450980392157,
+      "eval_combined_score": 0.7848851078893095,
+      "eval_f1": 0.8320251177394035,
+      "eval_loss": 0.539802074432373,
+      "eval_runtime": 0.1477,
+      "eval_samples_per_second": 2762.511,
+      "eval_steps_per_second": 13.542,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.9282344579696655,
+      "learning_rate": 4.5e-05,
+      "loss": 0.5063,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7426470588235294,
+      "eval_combined_score": 0.7881222615829215,
+      "eval_f1": 0.8335974643423137,
+      "eval_loss": 0.5358061194419861,
+      "eval_runtime": 0.1435,
+      "eval_samples_per_second": 2842.916,
+      "eval_steps_per_second": 13.936,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.279212713241577,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.476,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7475490196078431,
+      "eval_combined_score": 0.7916373487193921,
+      "eval_f1": 0.835725677830941,
+      "eval_loss": 0.5344022512435913,
+      "eval_runtime": 0.1435,
+      "eval_samples_per_second": 2842.637,
+      "eval_steps_per_second": 13.934,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.8690178394317627,
+      "learning_rate": 4.3e-05,
+      "loss": 0.4361,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7450980392156863,
+      "eval_combined_score": 0.7900093370681607,
+      "eval_f1": 0.834920634920635,
+      "eval_loss": 0.5514616370201111,
+      "eval_runtime": 0.1462,
+      "eval_samples_per_second": 2790.062,
+      "eval_steps_per_second": 13.677,
+      "step": 105
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.5032386779785156,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4014,
+      "step": 120
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.75,
+      "eval_combined_score": 0.7932692307692307,
+      "eval_f1": 0.8365384615384615,
+      "eval_loss": 0.5508028864860535,
+      "eval_runtime": 0.1417,
+      "eval_samples_per_second": 2878.654,
+      "eval_steps_per_second": 14.111,
+      "step": 120
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 2.740001916885376,
+      "learning_rate": 4.1e-05,
+      "loss": 0.3684,
+      "step": 135
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7303921568627451,
+      "eval_combined_score": 0.7778944911297851,
+      "eval_f1": 0.8253968253968254,
+      "eval_loss": 0.5901079177856445,
+      "eval_runtime": 0.142,
+      "eval_samples_per_second": 2873.896,
+      "eval_steps_per_second": 14.088,
+      "step": 135
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 3.6365294456481934,
+      "learning_rate": 4e-05,
+      "loss": 0.3396,
+      "step": 150
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7426470588235294,
+      "eval_combined_score": 0.7851166328600405,
+      "eval_f1": 0.8275862068965516,
+      "eval_loss": 0.5755388140678406,
+      "eval_runtime": 0.1465,
+      "eval_samples_per_second": 2784.301,
+      "eval_steps_per_second": 13.649,
+      "step": 150
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 2.9824297428131104,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.3061,
+      "step": 165
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.75,
+      "eval_combined_score": 0.7908415841584159,
+      "eval_f1": 0.8316831683168318,
+      "eval_loss": 0.5942506194114685,
+      "eval_runtime": 0.1433,
+      "eval_samples_per_second": 2847.49,
+      "eval_steps_per_second": 13.958,
+      "step": 165
+    },
+    {
+      "epoch": 11.0,
+      "step": 165,
+      "total_flos": 102031020478464.0,
+      "train_loss": 0.4675573955882679,
+      "train_runtime": 21.1858,
+      "train_samples_per_second": 8656.733,
+      "train_steps_per_second": 35.401
+    }
+  ],
+  "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": 102031020478464.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}