End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_5_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: bert_base_lda_5_v1_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: 0.0
+    - name: Accuracy
+      type: accuracy
+      value: 0.6912751793861389
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,9 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_lda_5_v1_cola
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_5_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_5_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_5_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_5_v1) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6257
+- Loss: 0.6183
 - Matthews Correlation: 0.0
 - Accuracy: 0.6913
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6183110475540161,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 0.6645,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 1569.501,
+    "eval_steps_per_second": 7.524,
+    "total_flos": 1.012438185472512e+16,
+    "train_loss": 0.6631240346073325,
+    "train_runtime": 151.6801,
+    "train_samples": 8551,
+    "train_samples_per_second": 2818.761,
+    "train_steps_per_second": 11.208
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6183110475540161,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 0.6645,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 1569.501,
+    "eval_steps_per_second": 7.524
+}

logs/events.out.tfevents.1732640007.ki-g0008.2136607.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b093adda679fcf913bd8e316363ef59c37ef30bf696a253407a6f1b53e0488d
+size 475

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "total_flos": 1.012438185472512e+16,
+    "train_loss": 0.6631240346073325,
+    "train_runtime": 151.6801,
+    "train_samples": 8551,
+    "train_samples_per_second": 2818.761,
+    "train_steps_per_second": 11.208
+}

trainer_state.json

@@ -0,0 +1,204 @@
+{
+  "best_metric": 0.6183110475540161,
+  "best_model_checkpoint": "bert_base_lda_5_v1_cola/checkpoint-136",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 306,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.0946457386016846,
+      "learning_rate": 0.00098,
+      "loss": 1.0659,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.620131254196167,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.673,
+      "eval_samples_per_second": 1549.697,
+      "eval_steps_per_second": 7.429,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8950899243354797,
+      "learning_rate": 0.00096,
+      "loss": 0.6315,
+      "step": 68
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.619966447353363,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6704,
+      "eval_samples_per_second": 1555.756,
+      "eval_steps_per_second": 7.458,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.0940829515457153,
+      "learning_rate": 0.00094,
+      "loss": 0.61,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6210225820541382,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6796,
+      "eval_samples_per_second": 1534.67,
+      "eval_steps_per_second": 7.357,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.41540974378585815,
+      "learning_rate": 0.00092,
+      "loss": 0.6103,
+      "step": 136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6183110475540161,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6842,
+      "eval_samples_per_second": 1524.426,
+      "eval_steps_per_second": 7.308,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.882623016834259,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.6103,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.622185468673706,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6821,
+      "eval_samples_per_second": 1529.048,
+      "eval_steps_per_second": 7.33,
+      "step": 170
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.45722779631614685,
+      "learning_rate": 0.00088,
+      "loss": 0.6105,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6192323565483093,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6777,
+      "eval_samples_per_second": 1539.028,
+      "eval_steps_per_second": 7.378,
+      "step": 204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.1227401494979858,
+      "learning_rate": 0.00086,
+      "loss": 0.6098,
+      "step": 238
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6202510595321655,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6848,
+      "eval_samples_per_second": 1523.07,
+      "eval_steps_per_second": 7.301,
+      "step": 238
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.3862515985965729,
+      "learning_rate": 0.00084,
+      "loss": 0.6104,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6233483552932739,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6616,
+      "eval_samples_per_second": 1576.417,
+      "eval_steps_per_second": 7.557,
+      "step": 272
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.5181242227554321,
+      "learning_rate": 0.00082,
+      "loss": 0.6095,
+      "step": 306
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6256685256958008,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6813,
+      "eval_samples_per_second": 1530.94,
+      "eval_steps_per_second": 7.339,
+      "step": 306
+    },
+    {
+      "epoch": 9.0,
+      "step": 306,
+      "total_flos": 1.012438185472512e+16,
+      "train_loss": 0.6631240346073325,
+      "train_runtime": 151.6801,
+      "train_samples_per_second": 2818.761,
+      "train_steps_per_second": 11.208
+    }
+  ],
+  "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": 1.012438185472512e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}