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-512_A-8
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_uncased_L-2_H-512_A-8_qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8405637927878455
 ---
 
 <!-- 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-512_A-8_qnli
 
-This model is a fine-tuned version of [google/bert_uncased_L-2_H-512_A-8](https://huggingface.co/google/bert_uncased_L-2_H-512_A-8) on an unknown dataset.
+This model is a fine-tuned version of [google/bert_uncased_L-2_H-512_A-8](https://huggingface.co/google/bert_uncased_L-2_H-512_A-8) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5216
-- Accuracy: 0.8298
+- Loss: 0.3808
+- Accuracy: 0.8406
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.8405637927878455,
+    "eval_loss": 0.3807711601257324,
+    "eval_runtime": 1.8876,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 2894.148,
+    "eval_steps_per_second": 11.655,
+    "total_flos": 8455451629756416.0,
+    "train_loss": 0.2916111713502465,
+    "train_runtime": 409.9013,
+    "train_samples": 104743,
+    "train_samples_per_second": 12776.613,
+    "train_steps_per_second": 50.012
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.8405637927878455,
+    "eval_loss": 0.3807711601257324,
+    "eval_runtime": 1.8876,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 2894.148,
+    "eval_steps_per_second": 11.655
+}

logs/events.out.tfevents.1733341731.ki-g0008.1764072.41

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b02a694752b50ab6ea4ac98ea1c62ff0aee184f934a1ffc6a365150e5561174d
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 8455451629756416.0,
+    "train_loss": 0.2916111713502465,
+    "train_runtime": 409.9013,
+    "train_samples": 104743,
+    "train_samples_per_second": 12776.613,
+    "train_steps_per_second": 50.012
+}

trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": 0.3807711601257324,
+  "best_model_checkpoint": "bert_uncased_L-2_H-512_A-8_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": 3.704665422439575,
+      "learning_rate": 4.9e-05,
+      "loss": 0.4759,
+      "step": 410
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8218927329306241,
+      "eval_loss": 0.4064705967903137,
+      "eval_runtime": 1.9649,
+      "eval_samples_per_second": 2780.268,
+      "eval_steps_per_second": 11.196,
+      "step": 410
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.4869890213012695,
+      "learning_rate": 4.8e-05,
+      "loss": 0.4,
+      "step": 820
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8308621636463481,
+      "eval_loss": 0.3839970529079437,
+      "eval_runtime": 1.9038,
+      "eval_samples_per_second": 2869.529,
+      "eval_steps_per_second": 11.556,
+      "step": 820
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.3017778396606445,
+      "learning_rate": 4.7e-05,
+      "loss": 0.3491,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8405637927878455,
+      "eval_loss": 0.3807711601257324,
+      "eval_runtime": 1.9034,
+      "eval_samples_per_second": 2870.082,
+      "eval_steps_per_second": 11.558,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.749648571014404,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3005,
+      "step": 1640
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8339740069558851,
+      "eval_loss": 0.40541014075279236,
+      "eval_runtime": 1.9447,
+      "eval_samples_per_second": 2809.232,
+      "eval_steps_per_second": 11.313,
+      "step": 1640
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.2832560539245605,
+      "learning_rate": 4.5e-05,
+      "loss": 0.256,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.833424858136555,
+      "eval_loss": 0.4340633451938629,
+      "eval_runtime": 1.9075,
+      "eval_samples_per_second": 2863.93,
+      "eval_steps_per_second": 11.533,
+      "step": 2050
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 7.070403575897217,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.215,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8321435108914516,
+      "eval_loss": 0.44678622484207153,
+      "eval_runtime": 1.9666,
+      "eval_samples_per_second": 2777.914,
+      "eval_steps_per_second": 11.187,
+      "step": 2460
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 5.293684959411621,
+      "learning_rate": 4.3e-05,
+      "loss": 0.182,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8288486179754714,
+      "eval_loss": 0.5105521082878113,
+      "eval_runtime": 1.8846,
+      "eval_samples_per_second": 2898.763,
+      "eval_steps_per_second": 11.674,
+      "step": 2870
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 13.799646377563477,
+      "learning_rate": 4.2e-05,
+      "loss": 0.1543,
+      "step": 3280
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.829763866007688,
+      "eval_loss": 0.521552562713623,
+      "eval_runtime": 1.9238,
+      "eval_samples_per_second": 2839.692,
+      "eval_steps_per_second": 11.436,
+      "step": 3280
+    },
+    {
+      "epoch": 8.0,
+      "step": 3280,
+      "total_flos": 8455451629756416.0,
+      "train_loss": 0.2916111713502465,
+      "train_runtime": 409.9013,
+      "train_samples_per_second": 12776.613,
+      "train_steps_per_second": 50.012
+    }
+  ],
+  "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": 8455451629756416.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}