End of training

README.md

@@ -1,14 +1,29 @@
 ---
 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
 model-index:
 - name: bert_uncased_L-2_H-256_A-4_qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8228079809628409
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_uncased_L-2_H-256_A-4_qnli
 
-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 QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4545
-- Accuracy: 0.8098
+- Loss: 0.3967
+- Accuracy: 0.8228
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.8228079809628409,
+    "eval_loss": 0.3967478573322296,
+    "eval_runtime": 1.8739,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 2915.328,
+    "eval_steps_per_second": 11.74,
+    "total_flos": 2118971979374592.0,
+    "train_loss": 0.37647220565051565,
+    "train_runtime": 354.0501,
+    "train_samples": 104743,
+    "train_samples_per_second": 14792.116,
+    "train_steps_per_second": 57.901
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.8228079809628409,
+    "eval_loss": 0.3967478573322296,
+    "eval_runtime": 1.8739,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 2915.328,
+    "eval_steps_per_second": 11.74
+}

logs/events.out.tfevents.1733330848.ki-g0008.1764072.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b9624e9fb68f7af90ed567b54f2dabb00f04d1a4fe2d0e442af7a3267c5fbd
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 2118971979374592.0,
+    "train_loss": 0.37647220565051565,
+    "train_runtime": 354.0501,
+    "train_samples": 104743,
+    "train_samples_per_second": 14792.116,
+    "train_steps_per_second": 57.901
+}

trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": 0.3967478573322296,
+  "best_model_checkpoint": "bert_uncased_L-2_H-256_A-4_qnli/checkpoint-1230",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 3280,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.651937007904053,
+      "learning_rate": 4.9e-05,
+      "loss": 0.516,
+      "step": 410
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8056013179571664,
+      "eval_loss": 0.4329511523246765,
+      "eval_runtime": 1.8035,
+      "eval_samples_per_second": 3029.066,
+      "eval_steps_per_second": 12.198,
+      "step": 410
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.768772602081299,
+      "learning_rate": 4.8e-05,
+      "loss": 0.4487,
+      "step": 820
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8056013179571664,
+      "eval_loss": 0.426698237657547,
+      "eval_runtime": 1.8218,
+      "eval_samples_per_second": 2998.764,
+      "eval_steps_per_second": 12.076,
+      "step": 820
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.0214412212371826,
+      "learning_rate": 4.7e-05,
+      "loss": 0.4136,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8228079809628409,
+      "eval_loss": 0.3967478573322296,
+      "eval_runtime": 1.8588,
+      "eval_samples_per_second": 2939.065,
+      "eval_steps_per_second": 11.836,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.0320801734924316,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3815,
+      "step": 1640
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8116419549697969,
+      "eval_loss": 0.42323124408721924,
+      "eval_runtime": 1.7776,
+      "eval_samples_per_second": 3073.18,
+      "eval_steps_per_second": 12.376,
+      "step": 1640
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.623464584350586,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3524,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8169503935566539,
+      "eval_loss": 0.4195684790611267,
+      "eval_runtime": 1.8339,
+      "eval_samples_per_second": 2978.848,
+      "eval_steps_per_second": 11.996,
+      "step": 2050
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.532294273376465,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3243,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8184147904082006,
+      "eval_loss": 0.42495742440223694,
+      "eval_runtime": 1.8144,
+      "eval_samples_per_second": 3010.943,
+      "eval_steps_per_second": 12.125,
+      "step": 2460
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 6.312530040740967,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2993,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8145707486728904,
+      "eval_loss": 0.43530118465423584,
+      "eval_runtime": 1.7982,
+      "eval_samples_per_second": 3037.988,
+      "eval_steps_per_second": 12.234,
+      "step": 2870
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 4.634608745574951,
+      "learning_rate": 4.2e-05,
+      "loss": 0.276,
+      "step": 3280
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8098114589053633,
+      "eval_loss": 0.45451417565345764,
+      "eval_runtime": 1.895,
+      "eval_samples_per_second": 2882.823,
+      "eval_steps_per_second": 11.609,
+      "step": 3280
+    },
+    {
+      "epoch": 8.0,
+      "step": 3280,
+      "total_flos": 2118971979374592.0,
+      "train_loss": 0.37647220565051565,
+      "train_runtime": 354.0501,
+      "train_samples_per_second": 14792.116,
+      "train_steps_per_second": 57.901
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20500,
+  "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": 2118971979374592.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}