End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_20_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_base_lda_20_v1_book_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7720588235294118
+    - name: F1
+      type: f1
+      value: 0.8312159709618874
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_lda_20_v1_book_mrpc
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_20_v1_book](https://huggingface.co/gokulsrinivasagan/bert_base_lda_20_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_20_v1_book](https://huggingface.co/gokulsrinivasagan/bert_base_lda_20_v1_book) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9451
-- Accuracy: 0.7892
-- F1: 0.8604
-- Combined Score: 0.8248
+- Loss: 0.5004
+- Accuracy: 0.7721
+- F1: 0.8312
+- Combined Score: 0.8016
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.7720588235294118,
+    "eval_combined_score": 0.8016373972456496,
+    "eval_f1": 0.8312159709618874,
+    "eval_loss": 0.500350832939148,
+    "eval_runtime": 0.2783,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1466.246,
+    "eval_steps_per_second": 7.187,
+    "total_flos": 3860365404241920.0,
+    "train_loss": 0.29748196005821226,
+    "train_runtime": 73.0701,
+    "train_samples": 3668,
+    "train_samples_per_second": 2509.917,
+    "train_steps_per_second": 10.264
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.7720588235294118,
+    "eval_combined_score": 0.8016373972456496,
+    "eval_f1": 0.8312159709618874,
+    "eval_loss": 0.500350832939148,
+    "eval_runtime": 0.2783,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1466.246,
+    "eval_steps_per_second": 7.187
+}

logs/events.out.tfevents.1733838842.ki-g0008.520107.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab19ecfb3963f7084928d8d9b26ebf0c04d9079a9ba30a5d568304b1661bec77
+size 507

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 3860365404241920.0,
+    "train_loss": 0.29748196005821226,
+    "train_runtime": 73.0701,
+    "train_samples": 3668,
+    "train_samples_per_second": 2509.917,
+    "train_steps_per_second": 10.264
+}

trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.500350832939148,
+  "best_model_checkpoint": "bert_base_lda_20_v1_book_mrpc/checkpoint-45",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8366120457649231,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6176,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7034313725490197,
+      "eval_combined_score": 0.7607382426654872,
+      "eval_f1": 0.8180451127819548,
+      "eval_loss": 0.5701425075531006,
+      "eval_runtime": 0.2709,
+      "eval_samples_per_second": 1505.899,
+      "eval_steps_per_second": 7.382,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.57491135597229,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5574,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7377450980392157,
+      "eval_combined_score": 0.7824428236561184,
+      "eval_f1": 0.827140549273021,
+      "eval_loss": 0.5201883316040039,
+      "eval_runtime": 0.275,
+      "eval_samples_per_second": 1483.741,
+      "eval_steps_per_second": 7.273,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 11.440605163574219,
+      "learning_rate": 4.7e-05,
+      "loss": 0.4414,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7720588235294118,
+      "eval_combined_score": 0.8016373972456496,
+      "eval_f1": 0.8312159709618874,
+      "eval_loss": 0.500350832939148,
+      "eval_runtime": 0.271,
+      "eval_samples_per_second": 1505.604,
+      "eval_steps_per_second": 7.38,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 11.457358360290527,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3089,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7598039215686274,
+      "eval_combined_score": 0.802124183006536,
+      "eval_f1": 0.8444444444444446,
+      "eval_loss": 0.6027812361717224,
+      "eval_runtime": 0.2712,
+      "eval_samples_per_second": 1504.514,
+      "eval_steps_per_second": 7.375,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 14.267647743225098,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1931,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8161764705882353,
+      "eval_combined_score": 0.8444210026964944,
+      "eval_f1": 0.8726655348047537,
+      "eval_loss": 0.614952027797699,
+      "eval_runtime": 0.2719,
+      "eval_samples_per_second": 1500.302,
+      "eval_steps_per_second": 7.354,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.210010051727295,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1366,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7794117647058824,
+      "eval_combined_score": 0.8171252371916509,
+      "eval_f1": 0.8548387096774194,
+      "eval_loss": 0.7471214532852173,
+      "eval_runtime": 0.2727,
+      "eval_samples_per_second": 1496.147,
+      "eval_steps_per_second": 7.334,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 5.463342189788818,
+      "learning_rate": 4.3e-05,
+      "loss": 0.0839,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7990196078431373,
+      "eval_combined_score": 0.8322966891674703,
+      "eval_f1": 0.8655737704918033,
+      "eval_loss": 0.7483032941818237,
+      "eval_runtime": 0.2727,
+      "eval_samples_per_second": 1496.383,
+      "eval_steps_per_second": 7.335,
+      "step": 105
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 8.97471809387207,
+      "learning_rate": 4.2e-05,
+      "loss": 0.0409,
+      "step": 120
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7892156862745098,
+      "eval_combined_score": 0.8248026483320601,
+      "eval_f1": 0.8603896103896104,
+      "eval_loss": 0.9451467394828796,
+      "eval_runtime": 0.2778,
+      "eval_samples_per_second": 1468.73,
+      "eval_steps_per_second": 7.2,
+      "step": 120
+    },
+    {
+      "epoch": 8.0,
+      "step": 120,
+      "total_flos": 3860365404241920.0,
+      "train_loss": 0.29748196005821226,
+      "train_runtime": 73.0701,
+      "train_samples_per_second": 2509.917,
+      "train_steps_per_second": 10.264
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 750,
+  "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": 3860365404241920.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}