End of training

README.md

@@ -1,14 +1,29 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: google/bert_uncased_L-4_H-128_A-2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_uncased_L-4_H-128_A-2_qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8121911037891268
 ---
 
 <!-- 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-4_H-128_A-2_qnli
 
-This model is a fine-tuned version of [google/bert_uncased_L-4_H-128_A-2](https://huggingface.co/google/bert_uncased_L-4_H-128_A-2) on an unknown dataset.
+This model is a fine-tuned version of [google/bert_uncased_L-4_H-128_A-2](https://huggingface.co/google/bert_uncased_L-4_H-128_A-2) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4378
-- Accuracy: 0.8089
+- Loss: 0.4085
+- Accuracy: 0.8122
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.8121911037891268,
+    "eval_loss": 0.4085180163383484,
+    "eval_runtime": 1.8033,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 3029.397,
+    "eval_steps_per_second": 12.2,
+    "total_flos": 1042683134386176.0,
+    "train_loss": 0.4172675435136004,
+    "train_runtime": 366.5213,
+    "train_samples": 104743,
+    "train_samples_per_second": 14288.8,
+    "train_steps_per_second": 55.931
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.8121911037891268,
+    "eval_loss": 0.4085180163383484,
+    "eval_runtime": 1.8033,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 3029.397,
+    "eval_steps_per_second": 12.2
+}

logs/events.out.tfevents.1733335757.ki-g0008.1764072.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74152b1ad941de8e8d16f182b5ba29ba4d3a081ebf7d9ea46f38c3796a8ef7cc
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 1042683134386176.0,
+    "train_loss": 0.4172675435136004,
+    "train_runtime": 366.5213,
+    "train_samples": 104743,
+    "train_samples_per_second": 14288.8,
+    "train_steps_per_second": 55.931
+}

trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": 0.4085180163383484,
+  "best_model_checkpoint": "bert_uncased_L-4_H-128_A-2_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": 3.4298832416534424,
+      "learning_rate": 4.9e-05,
+      "loss": 0.5299,
+      "step": 410
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7730184880102507,
+      "eval_loss": 0.4914644956588745,
+      "eval_runtime": 1.8337,
+      "eval_samples_per_second": 2979.213,
+      "eval_steps_per_second": 11.998,
+      "step": 410
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.848660945892334,
+      "learning_rate": 4.8e-05,
+      "loss": 0.4658,
+      "step": 820
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8039538714991763,
+      "eval_loss": 0.4280793368816376,
+      "eval_runtime": 1.8382,
+      "eval_samples_per_second": 2971.913,
+      "eval_steps_per_second": 11.968,
+      "step": 820
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.989725351333618,
+      "learning_rate": 4.7e-05,
+      "loss": 0.4407,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8121911037891268,
+      "eval_loss": 0.4085180163383484,
+      "eval_runtime": 1.8098,
+      "eval_samples_per_second": 3018.513,
+      "eval_steps_per_second": 12.156,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.224192142486572,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4184,
+      "step": 1640
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8114589053633535,
+      "eval_loss": 0.4172177016735077,
+      "eval_runtime": 1.8502,
+      "eval_samples_per_second": 2952.647,
+      "eval_steps_per_second": 11.891,
+      "step": 1640
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.754832744598389,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3983,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8103606077246934,
+      "eval_loss": 0.4166114330291748,
+      "eval_runtime": 1.8312,
+      "eval_samples_per_second": 2983.233,
+      "eval_steps_per_second": 12.014,
+      "step": 2050
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.021646499633789,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3799,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8063335163829398,
+      "eval_loss": 0.43288013339042664,
+      "eval_runtime": 1.8894,
+      "eval_samples_per_second": 2891.457,
+      "eval_steps_per_second": 11.644,
+      "step": 2460
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 5.725554943084717,
+      "learning_rate": 4.3e-05,
+      "loss": 0.3614,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8151198974922204,
+      "eval_loss": 0.41815581917762756,
+      "eval_runtime": 1.8448,
+      "eval_samples_per_second": 2961.37,
+      "eval_steps_per_second": 11.926,
+      "step": 2870
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 7.54054594039917,
+      "learning_rate": 4.2e-05,
+      "loss": 0.3438,
+      "step": 3280
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8088962108731467,
+      "eval_loss": 0.43782010674476624,
+      "eval_runtime": 1.8321,
+      "eval_samples_per_second": 2981.877,
+      "eval_steps_per_second": 12.008,
+      "step": 3280
+    },
+    {
+      "epoch": 8.0,
+      "step": 3280,
+      "total_flos": 1042683134386176.0,
+      "train_loss": 0.4172675435136004,
+      "train_runtime": 366.5213,
+      "train_samples_per_second": 14288.8,
+      "train_steps_per_second": 55.931
+    }
+  ],
+  "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": 1042683134386176.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}