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-256_A-4
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_uncased_L-4_H-256_A-4_rte
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.631768953068592
 ---
 
 <!-- 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-256_A-4_rte
 
-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 RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7181
-- Accuracy: 0.6426
+- Loss: 0.6545
+- Accuracy: 0.6318
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 11.0,
+    "eval_accuracy": 0.631768953068592,
+    "eval_loss": 0.6545313000679016,
+    "eval_runtime": 0.109,
+    "eval_samples": 277,
+    "eval_samples_per_second": 2541.141,
+    "eval_steps_per_second": 18.348,
+    "total_flos": 135715200952320.0,
+    "train_loss": 0.5592600172216242,
+    "train_runtime": 17.1765,
+    "train_samples": 2490,
+    "train_samples_per_second": 7248.287,
+    "train_steps_per_second": 29.11
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 11.0,
+    "eval_accuracy": 0.631768953068592,
+    "eval_loss": 0.6545313000679016,
+    "eval_runtime": 0.109,
+    "eval_samples": 277,
+    "eval_samples_per_second": 2541.141,
+    "eval_steps_per_second": 18.348
+}

logs/events.out.tfevents.1733332677.ki-g0008.1761130.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a7a4fa597dd452aaa12bc30e07b025238f45279b35612c5b528ac5c82a269e2
+size 405

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 11.0,
+    "total_flos": 135715200952320.0,
+    "train_loss": 0.5592600172216242,
+    "train_runtime": 17.1765,
+    "train_samples": 2490,
+    "train_samples_per_second": 7248.287,
+    "train_steps_per_second": 29.11
+}

trainer_state.json

@@ -0,0 +1,227 @@
+{
+  "best_metric": 0.6545313000679016,
+  "best_model_checkpoint": "bert_uncased_L-4_H-256_A-4_rte/checkpoint-60",
+  "epoch": 11.0,
+  "eval_steps": 500,
+  "global_step": 110,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6118650436401367,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6982,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5451263537906137,
+      "eval_loss": 0.6899396181106567,
+      "eval_runtime": 0.1077,
+      "eval_samples_per_second": 2571.103,
+      "eval_steps_per_second": 18.564,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.40018174052238464,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6864,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5523465703971119,
+      "eval_loss": 0.684510350227356,
+      "eval_runtime": 0.1293,
+      "eval_samples_per_second": 2143.061,
+      "eval_steps_per_second": 15.473,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6659122705459595,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6733,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5884476534296029,
+      "eval_loss": 0.6736800074577332,
+      "eval_runtime": 0.1076,
+      "eval_samples_per_second": 2573.928,
+      "eval_steps_per_second": 18.584,
+      "step": 30
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.1046839952468872,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6495,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5884476534296029,
+      "eval_loss": 0.6554038524627686,
+      "eval_runtime": 0.112,
+      "eval_samples_per_second": 2474.068,
+      "eval_steps_per_second": 17.863,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.7684160470962524,
+      "learning_rate": 4.5e-05,
+      "loss": 0.61,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6101083032490975,
+      "eval_loss": 0.6572829484939575,
+      "eval_runtime": 0.107,
+      "eval_samples_per_second": 2587.716,
+      "eval_steps_per_second": 18.684,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.965494155883789,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.5697,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.631768953068592,
+      "eval_loss": 0.6545313000679016,
+      "eval_runtime": 0.1066,
+      "eval_samples_per_second": 2598.184,
+      "eval_steps_per_second": 18.759,
+      "step": 60
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.221747636795044,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5279,
+      "step": 70
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6353790613718412,
+      "eval_loss": 0.6647728681564331,
+      "eval_runtime": 0.1061,
+      "eval_samples_per_second": 2610.76,
+      "eval_steps_per_second": 18.85,
+      "step": 70
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.2942957878112793,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4859,
+      "step": 80
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6173285198555957,
+      "eval_loss": 0.677759051322937,
+      "eval_runtime": 0.1049,
+      "eval_samples_per_second": 2640.121,
+      "eval_steps_per_second": 19.062,
+      "step": 80
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 3.2669131755828857,
+      "learning_rate": 4.1e-05,
+      "loss": 0.4524,
+      "step": 90
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6137184115523465,
+      "eval_loss": 0.6933205723762512,
+      "eval_runtime": 0.1118,
+      "eval_samples_per_second": 2477.93,
+      "eval_steps_per_second": 17.891,
+      "step": 90
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.6377601623535156,
+      "learning_rate": 4e-05,
+      "loss": 0.4126,
+      "step": 100
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6245487364620939,
+      "eval_loss": 0.6991878747940063,
+      "eval_runtime": 0.1073,
+      "eval_samples_per_second": 2581.775,
+      "eval_steps_per_second": 18.641,
+      "step": 100
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 3.629044771194458,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.386,
+      "step": 110
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.6425992779783394,
+      "eval_loss": 0.7180766463279724,
+      "eval_runtime": 0.1125,
+      "eval_samples_per_second": 2461.274,
+      "eval_steps_per_second": 17.771,
+      "step": 110
+    },
+    {
+      "epoch": 11.0,
+      "step": 110,
+      "total_flos": 135715200952320.0,
+      "train_loss": 0.5592600172216242,
+      "train_runtime": 17.1765,
+      "train_samples_per_second": 7248.287,
+      "train_steps_per_second": 29.11
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 500,
+  "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": 135715200952320.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}