End of training

README.md

@@ -1,15 +1,33 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: google/bert_uncased_L-4_H-256_A-4
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_uncased_L-4_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: 0.7720588235294118
+    - name: F1
+      type: f1
+      value: 0.8393782383419689
 ---
 
 <!-- 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-4_H-256_A-4_mrpc
 
-This model is a fine-tuned version of [google/bert_uncased_L-4_H-256_A-4](https://huggingface.co/google/bert_uncased_L-4_H-256_A-4) on an unknown dataset.
+This model is a fine-tuned version of [google/bert_uncased_L-4_H-256_A-4](https://huggingface.co/google/bert_uncased_L-4_H-256_A-4) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5756
-- Accuracy: 0.7794
-- F1: 0.8469
-- Combined Score: 0.8132
+- Loss: 0.5071
+- Accuracy: 0.7721
+- F1: 0.8394
+- Combined Score: 0.8057
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 12.0,
+    "eval_accuracy": 0.7720588235294118,
+    "eval_combined_score": 0.8057185309356903,
+    "eval_f1": 0.8393782383419689,
+    "eval_loss": 0.5070627331733704,
+    "eval_runtime": 0.1551,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2630.167,
+    "eval_steps_per_second": 12.893,
+    "total_flos": 218095665758208.0,
+    "train_loss": 0.4133431394894918,
+    "train_runtime": 25.962,
+    "train_samples": 3668,
+    "train_samples_per_second": 7064.168,
+    "train_steps_per_second": 28.888
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 12.0,
+    "eval_accuracy": 0.7720588235294118,
+    "eval_combined_score": 0.8057185309356903,
+    "eval_f1": 0.8393782383419689,
+    "eval_loss": 0.5070627331733704,
+    "eval_runtime": 0.1551,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2630.167,
+    "eval_steps_per_second": 12.893
+}

logs/events.out.tfevents.1733330332.ki-g0008.1761130.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a83434d7b4163d5d1b34f524675b3e6e51a54461675f6ebf26d3bd81aef164c6
+size 515

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 12.0,
+    "total_flos": 218095665758208.0,
+    "train_loss": 0.4133431394894918,
+    "train_runtime": 25.962,
+    "train_samples": 3668,
+    "train_samples_per_second": 7064.168,
+    "train_steps_per_second": 28.888
+}

trainer_state.json

@@ -0,0 +1,267 @@
+{
+  "best_metric": 0.5070627331733704,
+  "best_model_checkpoint": "bert_uncased_L-4_H-256_A-4_mrpc/checkpoint-105",
+  "epoch": 12.0,
+  "eval_steps": 500,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9642578363418579,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6375,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6936274509803921,
+      "eval_combined_score": 0.7553056727815577,
+      "eval_f1": 0.8169838945827232,
+      "eval_loss": 0.6024385690689087,
+      "eval_runtime": 0.156,
+      "eval_samples_per_second": 2615.794,
+      "eval_steps_per_second": 12.823,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.6478321552276611,
+      "learning_rate": 4.8e-05,
+      "loss": 0.594,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6985294117647058,
+      "eval_combined_score": 0.7576104584904007,
+      "eval_f1": 0.8166915052160953,
+      "eval_loss": 0.5776079297065735,
+      "eval_runtime": 0.1598,
+      "eval_samples_per_second": 2553.282,
+      "eval_steps_per_second": 12.516,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.1746251583099365,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5504,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7279411764705882,
+      "eval_combined_score": 0.7776564358247187,
+      "eval_f1": 0.827371695178849,
+      "eval_loss": 0.5475428104400635,
+      "eval_runtime": 0.1486,
+      "eval_samples_per_second": 2745.65,
+      "eval_steps_per_second": 13.459,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.050297737121582,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5155,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7598039215686274,
+      "eval_combined_score": 0.7971316905140435,
+      "eval_f1": 0.8344594594594595,
+      "eval_loss": 0.5082876086235046,
+      "eval_runtime": 0.1558,
+      "eval_samples_per_second": 2618.432,
+      "eval_steps_per_second": 12.835,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.48883056640625,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4668,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7598039215686274,
+      "eval_combined_score": 0.7971316905140435,
+      "eval_f1": 0.8344594594594595,
+      "eval_loss": 0.5116193890571594,
+      "eval_runtime": 0.1902,
+      "eval_samples_per_second": 2144.58,
+      "eval_steps_per_second": 10.513,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.939922332763672,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.4292,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7696078431372549,
+      "eval_combined_score": 0.8064705882352942,
+      "eval_f1": 0.8433333333333334,
+      "eval_loss": 0.5237414836883545,
+      "eval_runtime": 0.1477,
+      "eval_samples_per_second": 2761.45,
+      "eval_steps_per_second": 13.537,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.8994574546813965,
+      "learning_rate": 4.3e-05,
+      "loss": 0.3859,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7720588235294118,
+      "eval_combined_score": 0.8057185309356903,
+      "eval_f1": 0.8393782383419689,
+      "eval_loss": 0.5070627331733704,
+      "eval_runtime": 0.1535,
+      "eval_samples_per_second": 2658.103,
+      "eval_steps_per_second": 13.03,
+      "step": 105
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 4.1840901374816895,
+      "learning_rate": 4.2e-05,
+      "loss": 0.3455,
+      "step": 120
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7720588235294118,
+      "eval_combined_score": 0.8073492087190206,
+      "eval_f1": 0.8426395939086294,
+      "eval_loss": 0.5299550890922546,
+      "eval_runtime": 0.1493,
+      "eval_samples_per_second": 2733.148,
+      "eval_steps_per_second": 13.398,
+      "step": 120
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 4.495199203491211,
+      "learning_rate": 4.1e-05,
+      "loss": 0.3049,
+      "step": 135
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7720588235294118,
+      "eval_combined_score": 0.8065422322775264,
+      "eval_f1": 0.841025641025641,
+      "eval_loss": 0.5408151745796204,
+      "eval_runtime": 0.1508,
+      "eval_samples_per_second": 2706.105,
+      "eval_steps_per_second": 13.265,
+      "step": 135
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 3.322133779525757,
+      "learning_rate": 4e-05,
+      "loss": 0.2735,
+      "step": 150
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7745098039215687,
+      "eval_combined_score": 0.8084877786731131,
+      "eval_f1": 0.8424657534246576,
+      "eval_loss": 0.5336543321609497,
+      "eval_runtime": 0.1546,
+      "eval_samples_per_second": 2638.334,
+      "eval_steps_per_second": 12.933,
+      "step": 150
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 8.718647956848145,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.2454,
+      "step": 165
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.7647058823529411,
+      "eval_combined_score": 0.8023529411764705,
+      "eval_f1": 0.84,
+      "eval_loss": 0.5962408185005188,
+      "eval_runtime": 0.1487,
+      "eval_samples_per_second": 2744.506,
+      "eval_steps_per_second": 13.453,
+      "step": 165
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 5.987424373626709,
+      "learning_rate": 3.8e-05,
+      "loss": 0.2117,
+      "step": 180
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.7794117647058824,
+      "eval_combined_score": 0.8131752701080432,
+      "eval_f1": 0.846938775510204,
+      "eval_loss": 0.5755988955497742,
+      "eval_runtime": 0.1478,
+      "eval_samples_per_second": 2761.343,
+      "eval_steps_per_second": 13.536,
+      "step": 180
+    },
+    {
+      "epoch": 12.0,
+      "step": 180,
+      "total_flos": 218095665758208.0,
+      "train_loss": 0.4133431394894918,
+      "train_runtime": 25.962,
+      "train_samples_per_second": 7064.168,
+      "train_steps_per_second": 28.888
+    }
+  ],
+  "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": 218095665758208.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}