End of training

README.md

@@ -1,15 +1,33 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: google/bert_uncased_L-2_H-128_A-2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: bert_uncased_L-2_H-128_A-2_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: 0.00286100001416597
+    - name: Accuracy
+      type: accuracy
+      value: 0.690316379070282
 ---
 
 <!-- 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-2_H-128_A-2_cola
 
-This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on an unknown dataset.
+This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6423
-- Matthews Correlation: 0.0951
-- Accuracy: 0.6433
+- Loss: 0.6155
+- Matthews Correlation: 0.0029
+- Accuracy: 0.6903
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 14.0,
+    "eval_accuracy": 0.690316379070282,
+    "eval_loss": 0.6154815554618835,
+    "eval_matthews_correlation": 0.00286100001416597,
+    "eval_runtime": 0.3429,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 3041.787,
+    "eval_steps_per_second": 14.582,
+    "total_flos": 76047542753280.0,
+    "train_loss": 0.5838592072494891,
+    "train_runtime": 51.9503,
+    "train_samples": 8551,
+    "train_samples_per_second": 8229.977,
+    "train_steps_per_second": 32.724
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 14.0,
+    "eval_accuracy": 0.690316379070282,
+    "eval_loss": 0.6154815554618835,
+    "eval_matthews_correlation": 0.00286100001416597,
+    "eval_runtime": 0.3429,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 3041.787,
+    "eval_steps_per_second": 14.582
+}

logs/events.out.tfevents.1733343247.ki-g0008.1759256.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93b6cf1431ef3989332367b2274ed57fa66471ae428413b8c327d1fdcb700fcb
+size 475

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 14.0,
+    "total_flos": 76047542753280.0,
+    "train_loss": 0.5838592072494891,
+    "train_runtime": 51.9503,
+    "train_samples": 8551,
+    "train_samples_per_second": 8229.977,
+    "train_steps_per_second": 32.724
+}

trainer_state.json

@@ -0,0 +1,289 @@
+{
+  "best_metric": 0.6154815554618835,
+  "best_model_checkpoint": "bert_uncased_L-2_H-128_A-2_cola/checkpoint-306",
+  "epoch": 14.0,
+  "eval_steps": 500,
+  "global_step": 476,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7980750799179077,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6288,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6190507411956787,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3447,
+      "eval_samples_per_second": 3025.909,
+      "eval_steps_per_second": 14.506,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6090947389602661,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6087,
+      "step": 68
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6184253096580505,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3757,
+      "eval_samples_per_second": 2776.472,
+      "eval_steps_per_second": 13.31,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.47841307520866394,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6076,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6176126003265381,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.349,
+      "eval_samples_per_second": 2988.761,
+      "eval_steps_per_second": 14.328,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.6182640194892883,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6066,
+      "step": 136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6168822646141052,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3459,
+      "eval_samples_per_second": 3015.646,
+      "eval_steps_per_second": 14.457,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.6467083692550659,
+      "learning_rate": 4.5e-05,
+      "loss": 0.605,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.617020845413208,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3409,
+      "eval_samples_per_second": 3059.228,
+      "eval_steps_per_second": 14.666,
+      "step": 170
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.5165701508522034,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6018,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6163738369941711,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3546,
+      "eval_samples_per_second": 2941.145,
+      "eval_steps_per_second": 14.099,
+      "step": 204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.9088634848594666,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5976,
+      "step": 238
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6163157820701599,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3505,
+      "eval_samples_per_second": 2975.791,
+      "eval_steps_per_second": 14.266,
+      "step": 238
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.8111366629600525,
+      "learning_rate": 4.2e-05,
+      "loss": 0.5871,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6922339200973511,
+      "eval_loss": 0.6158953905105591,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 0.3419,
+      "eval_samples_per_second": 3050.899,
+      "eval_steps_per_second": 14.626,
+      "step": 272
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 1.0843596458435059,
+      "learning_rate": 4.1e-05,
+      "loss": 0.5824,
+      "step": 306
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.690316379070282,
+      "eval_loss": 0.6154815554618835,
+      "eval_matthews_correlation": 0.00286100001416597,
+      "eval_runtime": 0.3389,
+      "eval_samples_per_second": 3077.666,
+      "eval_steps_per_second": 14.754,
+      "step": 306
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.03415048122406,
+      "learning_rate": 4e-05,
+      "loss": 0.5711,
+      "step": 340
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6701821684837341,
+      "eval_loss": 0.6198194622993469,
+      "eval_matthews_correlation": 0.01981741616477915,
+      "eval_runtime": 0.362,
+      "eval_samples_per_second": 2881.555,
+      "eval_steps_per_second": 13.814,
+      "step": 340
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 1.5267772674560547,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.5591,
+      "step": 374
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.6720997095108032,
+      "eval_loss": 0.6221288442611694,
+      "eval_matthews_correlation": 0.06852522805215415,
+      "eval_runtime": 0.3482,
+      "eval_samples_per_second": 2995.172,
+      "eval_steps_per_second": 14.358,
+      "step": 374
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 2.8010520935058594,
+      "learning_rate": 3.8e-05,
+      "loss": 0.5496,
+      "step": 408
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.6701821684837341,
+      "eval_loss": 0.6283519864082336,
+      "eval_matthews_correlation": 0.12403836789999605,
+      "eval_runtime": 0.3537,
+      "eval_samples_per_second": 2948.641,
+      "eval_steps_per_second": 14.135,
+      "step": 408
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 3.0384879112243652,
+      "learning_rate": 3.7e-05,
+      "loss": 0.5397,
+      "step": 442
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.6548417806625366,
+      "eval_loss": 0.6349678635597229,
+      "eval_matthews_correlation": 0.10955495195400314,
+      "eval_runtime": 0.3501,
+      "eval_samples_per_second": 2978.893,
+      "eval_steps_per_second": 14.28,
+      "step": 442
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 3.0345466136932373,
+      "learning_rate": 3.6e-05,
+      "loss": 0.529,
+      "step": 476
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.6433365345001221,
+      "eval_loss": 0.6423426270484924,
+      "eval_matthews_correlation": 0.09507792970617555,
+      "eval_runtime": 0.3493,
+      "eval_samples_per_second": 2985.586,
+      "eval_steps_per_second": 14.312,
+      "step": 476
+    },
+    {
+      "epoch": 14.0,
+      "step": 476,
+      "total_flos": 76047542753280.0,
+      "train_loss": 0.5838592072494891,
+      "train_runtime": 51.9503,
+      "train_samples_per_second": 8229.977,
+      "train_steps_per_second": 32.724
+    }
+  ],
+  "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": 76047542753280.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}