End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_100_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_tiny_lda_100_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: 0.7475490196078431
+    - name: F1
+      type: f1
+      value: 0.8303130148270182
 ---
 
 <!-- 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_tiny_lda_100_v1_book_mrpc
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1_book) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7805
-- Accuracy: 0.7574
-- F1: 0.8308
-- Combined Score: 0.7941
+- Loss: 0.5396
+- Accuracy: 0.7475
+- F1: 0.8303
+- Combined Score: 0.7889
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.7475490196078431,
+    "eval_combined_score": 0.7889310172174306,
+    "eval_f1": 0.8303130148270182,
+    "eval_loss": 0.5396482944488525,
+    "eval_runtime": 0.1366,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2987.234,
+    "eval_steps_per_second": 14.643,
+    "total_flos": 961880845148160.0,
+    "train_loss": 0.3693840710322062,
+    "train_runtime": 31.704,
+    "train_samples": 3668,
+    "train_samples_per_second": 5784.75,
+    "train_steps_per_second": 23.656
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.7475490196078431,
+    "eval_combined_score": 0.7889310172174306,
+    "eval_f1": 0.8303130148270182,
+    "eval_loss": 0.5396482944488525,
+    "eval_runtime": 0.1366,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2987.234,
+    "eval_steps_per_second": 14.643
+}

logs/events.out.tfevents.1733840586.ki-g0008.684565.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f5fa2307fabad6b46a422dfb2e5581bf8a38ba568bbc880a3a225fcfacaed3a
+size 515

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 961880845148160.0,
+    "train_loss": 0.3693840710322062,
+    "train_runtime": 31.704,
+    "train_samples": 3668,
+    "train_samples_per_second": 5784.75,
+    "train_steps_per_second": 23.656
+}

trainer_state.json

@@ -0,0 +1,231 @@
+{
+  "best_metric": 0.5396482944488525,
+  "best_model_checkpoint": "bert_tiny_lda_100_v1_book_mrpc/checkpoint-75",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6715056300163269,
+      "learning_rate": 4.9e-05,
+      "loss": 0.62,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6740196078431373,
+      "eval_combined_score": 0.7316215313383674,
+      "eval_f1": 0.7892234548335975,
+      "eval_loss": 0.5966318249702454,
+      "eval_runtime": 0.144,
+      "eval_samples_per_second": 2833.891,
+      "eval_steps_per_second": 13.892,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.4785583019256592,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5856,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7009803921568627,
+      "eval_combined_score": 0.7569319138698425,
+      "eval_f1": 0.8128834355828222,
+      "eval_loss": 0.570221483707428,
+      "eval_runtime": 0.1376,
+      "eval_samples_per_second": 2965.59,
+      "eval_steps_per_second": 14.537,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.261619806289673,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5467,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7279411764705882,
+      "eval_combined_score": 0.7737266857962697,
+      "eval_f1": 0.8195121951219512,
+      "eval_loss": 0.5471394658088684,
+      "eval_runtime": 0.1338,
+      "eval_samples_per_second": 3049.577,
+      "eval_steps_per_second": 14.949,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.409958362579346,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4866,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7426470588235294,
+      "eval_combined_score": 0.7878577106518283,
+      "eval_f1": 0.8330683624801272,
+      "eval_loss": 0.5720561742782593,
+      "eval_runtime": 0.1343,
+      "eval_samples_per_second": 3038.892,
+      "eval_steps_per_second": 14.897,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.341953754425049,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4174,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7475490196078431,
+      "eval_combined_score": 0.7889310172174306,
+      "eval_f1": 0.8303130148270182,
+      "eval_loss": 0.5396482944488525,
+      "eval_runtime": 0.1408,
+      "eval_samples_per_second": 2897.924,
+      "eval_steps_per_second": 14.206,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 6.695014476776123,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3418,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.75,
+      "eval_combined_score": 0.7855263157894737,
+      "eval_f1": 0.8210526315789475,
+      "eval_loss": 0.5986034274101257,
+      "eval_runtime": 0.1355,
+      "eval_samples_per_second": 3010.361,
+      "eval_steps_per_second": 14.757,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 15.235206604003906,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2528,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6985294117647058,
+      "eval_combined_score": 0.7289124553931161,
+      "eval_f1": 0.7592954990215265,
+      "eval_loss": 0.674554705619812,
+      "eval_runtime": 0.1624,
+      "eval_samples_per_second": 2512.728,
+      "eval_steps_per_second": 12.317,
+      "step": 105
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.43247389793396,
+      "learning_rate": 4.2e-05,
+      "loss": 0.1784,
+      "step": 120
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7303921568627451,
+      "eval_combined_score": 0.7614224935257121,
+      "eval_f1": 0.7924528301886793,
+      "eval_loss": 0.6921858191490173,
+      "eval_runtime": 0.1354,
+      "eval_samples_per_second": 3014.232,
+      "eval_steps_per_second": 14.776,
+      "step": 120
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 12.527379989624023,
+      "learning_rate": 4.1e-05,
+      "loss": 0.1522,
+      "step": 135
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7573529411764706,
+      "eval_combined_score": 0.7984495662122224,
+      "eval_f1": 0.8395461912479741,
+      "eval_loss": 0.7650738954544067,
+      "eval_runtime": 0.1325,
+      "eval_samples_per_second": 3078.1,
+      "eval_steps_per_second": 15.089,
+      "step": 135
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 6.185352802276611,
+      "learning_rate": 4e-05,
+      "loss": 0.1123,
+      "step": 150
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7573529411764706,
+      "eval_combined_score": 0.7940610859728507,
+      "eval_f1": 0.8307692307692308,
+      "eval_loss": 0.780484676361084,
+      "eval_runtime": 0.1334,
+      "eval_samples_per_second": 3059.243,
+      "eval_steps_per_second": 14.996,
+      "step": 150
+    },
+    {
+      "epoch": 10.0,
+      "step": 150,
+      "total_flos": 961880845148160.0,
+      "train_loss": 0.3693840710322062,
+      "train_runtime": 31.704,
+      "train_samples_per_second": 5784.75,
+      "train_steps_per_second": 23.656
+    }
+  ],
+  "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": 961880845148160.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}