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-512_A-8
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: bert_uncased_L-4_H-512_A-8_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: 0.25880032134413367
+    - name: Accuracy
+      type: accuracy
+      value: 0.7248322367668152
 ---
 
 <!-- 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-512_A-8_cola
 
-This model is a fine-tuned version of [google/bert_uncased_L-4_H-512_A-8](https://huggingface.co/google/bert_uncased_L-4_H-512_A-8) on an unknown dataset.
+This model is a fine-tuned version of [google/bert_uncased_L-4_H-512_A-8](https://huggingface.co/google/bert_uncased_L-4_H-512_A-8) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7861
-- Matthews Correlation: 0.3320
-- Accuracy: 0.7383
+- Loss: 0.5796
+- Matthews Correlation: 0.2588
+- Accuracy: 0.7248
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.7248322367668152,
+    "eval_loss": 0.5796323418617249,
+    "eval_matthews_correlation": 0.25880032134413367,
+    "eval_runtime": 0.4304,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 2423.557,
+    "eval_steps_per_second": 11.618,
+    "total_flos": 1352756961386496.0,
+    "train_loss": 0.39837659457150626,
+    "train_runtime": 51.07,
+    "train_samples": 8551,
+    "train_samples_per_second": 8371.844,
+    "train_steps_per_second": 33.288
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.7248322367668152,
+    "eval_loss": 0.5796323418617249,
+    "eval_matthews_correlation": 0.25880032134413367,
+    "eval_runtime": 0.4304,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 2423.557,
+    "eval_steps_per_second": 11.618
+}

logs/events.out.tfevents.1733334957.ki-g0008.1761130.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aae2badc8df8098dea708c7be625a4aa9b1d8aae2675acbd0790068107cbe1b
+size 475

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 1352756961386496.0,
+    "train_loss": 0.39837659457150626,
+    "train_runtime": 51.07,
+    "train_samples": 8551,
+    "train_samples_per_second": 8371.844,
+    "train_steps_per_second": 33.288
+}

trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": 0.5796323418617249,
+  "best_model_checkpoint": "bert_uncased_L-4_H-512_A-8_cola/checkpoint-102",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 272,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.0610241889953613,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6069,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6017993688583374,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4175,
+      "eval_samples_per_second": 2498.326,
+      "eval_steps_per_second": 11.977,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.6431570053100586,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5619,
+      "step": 68
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7075743079185486,
+      "eval_loss": 0.5890989303588867,
+      "eval_matthews_correlation": 0.17662106561217966,
+      "eval_runtime": 0.405,
+      "eval_samples_per_second": 2575.131,
+      "eval_steps_per_second": 12.345,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.699745178222656,
+      "learning_rate": 4.7e-05,
+      "loss": 0.4858,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7248322367668152,
+      "eval_loss": 0.5796323418617249,
+      "eval_matthews_correlation": 0.25880032134413367,
+      "eval_runtime": 0.418,
+      "eval_samples_per_second": 2494.999,
+      "eval_steps_per_second": 11.961,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.655884265899658,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4109,
+      "step": 136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7305848598480225,
+      "eval_loss": 0.6467021703720093,
+      "eval_matthews_correlation": 0.28378357752187156,
+      "eval_runtime": 0.4224,
+      "eval_samples_per_second": 2469.299,
+      "eval_steps_per_second": 11.837,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.219986438751221,
+      "learning_rate": 4.5e-05,
+      "loss": 0.349,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7353787422180176,
+      "eval_loss": 0.6379130482673645,
+      "eval_matthews_correlation": 0.31330896181005025,
+      "eval_runtime": 0.4161,
+      "eval_samples_per_second": 2506.686,
+      "eval_steps_per_second": 12.017,
+      "step": 170
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.237408638000488,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.294,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7440076470375061,
+      "eval_loss": 0.6804817914962769,
+      "eval_matthews_correlation": 0.34360532578167496,
+      "eval_runtime": 0.4228,
+      "eval_samples_per_second": 2466.837,
+      "eval_steps_per_second": 11.826,
+      "step": 204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 6.214964866638184,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2564,
+      "step": 238
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7363374829292297,
+      "eval_loss": 0.7497751712799072,
+      "eval_matthews_correlation": 0.3178110608461884,
+      "eval_runtime": 0.4185,
+      "eval_samples_per_second": 2492.131,
+      "eval_steps_per_second": 11.947,
+      "step": 238
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 5.947281837463379,
+      "learning_rate": 4.2e-05,
+      "loss": 0.2222,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7382550239562988,
+      "eval_loss": 0.7860784530639648,
+      "eval_matthews_correlation": 0.3319729838669631,
+      "eval_runtime": 0.4208,
+      "eval_samples_per_second": 2478.611,
+      "eval_steps_per_second": 11.882,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "step": 272,
+      "total_flos": 1352756961386496.0,
+      "train_loss": 0.39837659457150626,
+      "train_runtime": 51.07,
+      "train_samples_per_second": 8371.844,
+      "train_steps_per_second": 33.288
+    }
+  ],
+  "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": 1352756961386496.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}