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:
 - matthews_correlation
 - accuracy
 model-index:
 - name: bert_uncased_L-4_H-256_A-4_cola
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.2650812590803394
+    - name: Accuracy
+      type: accuracy
+      value: 0.7027804255485535
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,11 +35,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_uncased_L-4_H-256_A-4_cola
 
-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 COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6849
-- Matthews Correlation: 0.2891
-- Accuracy: 0.7229
+- Loss: 0.5943
+- Matthews Correlation: 0.2651
+- Accuracy: 0.7028
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 13.0,
+    "eval_accuracy": 0.7027804255485535,
+    "eval_loss": 0.594317615032196,
+    "eval_matthews_correlation": 0.2650812590803394,
+    "eval_runtime": 0.3708,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 2812.994,
+    "eval_steps_per_second": 13.485,
+    "total_flos": 550803537183744.0,
+    "train_loss": 0.48016954007731305,
+    "train_runtime": 58.7871,
+    "train_samples": 8551,
+    "train_samples_per_second": 7272.855,
+    "train_steps_per_second": 28.918
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 13.0,
+    "eval_accuracy": 0.7027804255485535,
+    "eval_loss": 0.594317615032196,
+    "eval_matthews_correlation": 0.2650812590803394,
+    "eval_runtime": 0.3708,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 2812.994,
+    "eval_steps_per_second": 13.485
+}

logs/events.out.tfevents.1733330262.ki-g0008.1761130.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae2254d02e778810464279625577af6498a47fbaf507773f908cd8915494fb39
+size 475

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 13.0,
+    "total_flos": 550803537183744.0,
+    "train_loss": 0.48016954007731305,
+    "train_runtime": 58.7871,
+    "train_samples": 8551,
+    "train_samples_per_second": 7272.855,
+    "train_steps_per_second": 28.918
+}

trainer_state.json

@@ -0,0 +1,272 @@
+{
+  "best_metric": 0.594317615032196,
+  "best_model_checkpoint": "bert_uncased_L-4_H-256_A-4_cola/checkpoint-272",
+  "epoch": 13.0,
+  "eval_steps": 500,
+  "global_step": 442,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7306916117668152,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6358,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6181724667549133,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3646,
+      "eval_samples_per_second": 2860.687,
+      "eval_steps_per_second": 13.714,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.307898998260498,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6077,
+      "step": 68
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6183644533157349,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3634,
+      "eval_samples_per_second": 2869.845,
+      "eval_steps_per_second": 13.758,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.0871206521987915,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5982,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6034744381904602,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3533,
+      "eval_samples_per_second": 2951.77,
+      "eval_steps_per_second": 14.15,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.731250047683716,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.575,
+      "step": 136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7008628845214844,
+      "eval_loss": 0.5996922254562378,
+      "eval_matthews_correlation": 0.14575368331233524,
+      "eval_runtime": 0.3613,
+      "eval_samples_per_second": 2886.693,
+      "eval_steps_per_second": 13.838,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.3647537231445312,
+      "learning_rate": 4.5e-05,
+      "loss": 0.5391,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7027804255485535,
+      "eval_loss": 0.5991552472114563,
+      "eval_matthews_correlation": 0.20180765302151601,
+      "eval_runtime": 0.3609,
+      "eval_samples_per_second": 2889.849,
+      "eval_steps_per_second": 13.854,
+      "step": 170
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.75225830078125,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.4999,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7085330486297607,
+      "eval_loss": 0.6159256100654602,
+      "eval_matthews_correlation": 0.20881396361085017,
+      "eval_runtime": 0.3562,
+      "eval_samples_per_second": 2928.16,
+      "eval_steps_per_second": 14.037,
+      "step": 204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.2108917236328125,
+      "learning_rate": 4.3e-05,
+      "loss": 0.4722,
+      "step": 238
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7248322367668152,
+      "eval_loss": 0.5974001884460449,
+      "eval_matthews_correlation": 0.2782178633384921,
+      "eval_runtime": 0.3589,
+      "eval_samples_per_second": 2906.354,
+      "eval_steps_per_second": 13.933,
+      "step": 238
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 6.835243225097656,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4437,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7027804255485535,
+      "eval_loss": 0.594317615032196,
+      "eval_matthews_correlation": 0.2650812590803394,
+      "eval_runtime": 0.364,
+      "eval_samples_per_second": 2865.076,
+      "eval_steps_per_second": 13.735,
+      "step": 272
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 4.6481523513793945,
+      "learning_rate": 4.1e-05,
+      "loss": 0.4204,
+      "step": 306
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7209970951080322,
+      "eval_loss": 0.6238888502120972,
+      "eval_matthews_correlation": 0.26177616056277936,
+      "eval_runtime": 0.3545,
+      "eval_samples_per_second": 2942.021,
+      "eval_steps_per_second": 14.104,
+      "step": 306
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 3.829261302947998,
+      "learning_rate": 4e-05,
+      "loss": 0.3956,
+      "step": 340
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7190795540809631,
+      "eval_loss": 0.635987401008606,
+      "eval_matthews_correlation": 0.2655383665053918,
+      "eval_runtime": 0.3562,
+      "eval_samples_per_second": 2928.301,
+      "eval_steps_per_second": 14.038,
+      "step": 340
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 4.431561470031738,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.3671,
+      "step": 374
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.7200383543968201,
+      "eval_loss": 0.6876468658447266,
+      "eval_matthews_correlation": 0.25924407660585813,
+      "eval_runtime": 0.3568,
+      "eval_samples_per_second": 2923.405,
+      "eval_steps_per_second": 14.014,
+      "step": 374
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 5.241647720336914,
+      "learning_rate": 3.8e-05,
+      "loss": 0.3546,
+      "step": 408
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.7238734364509583,
+      "eval_loss": 0.7041077613830566,
+      "eval_matthews_correlation": 0.26652745805658656,
+      "eval_runtime": 0.3705,
+      "eval_samples_per_second": 2814.793,
+      "eval_steps_per_second": 13.494,
+      "step": 408
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 7.836996078491211,
+      "learning_rate": 3.7e-05,
+      "loss": 0.333,
+      "step": 442
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.7229146957397461,
+      "eval_loss": 0.6848821640014648,
+      "eval_matthews_correlation": 0.2891167063650506,
+      "eval_runtime": 0.3563,
+      "eval_samples_per_second": 2927.4,
+      "eval_steps_per_second": 14.034,
+      "step": 442
+    },
+    {
+      "epoch": 13.0,
+      "step": 442,
+      "total_flos": 550803537183744.0,
+      "train_loss": 0.48016954007731305,
+      "train_runtime": 58.7871,
+      "train_samples_per_second": 7272.855,
+      "train_steps_per_second": 28.918
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1700,
+  "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": 550803537183744.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}