End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_50_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_tiny_lda_50_v1_book_qqp
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QQP
+      type: glue
+      args: qqp
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8727924808310661
+    - name: F1
+      type: f1
+      value: 0.8236584947711297
 ---
 
 <!-- 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_50_v1_book_qqp
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_50_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_50_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_50_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_50_v1_book) on the GLUE QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3984
-- Accuracy: 0.8820
-- F1: 0.8376
-- Combined Score: 0.8598
+- Loss: 0.3001
+- Accuracy: 0.8728
+- F1: 0.8237
+- Combined Score: 0.8482
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.8727924808310661,
+    "eval_combined_score": 0.848225487801098,
+    "eval_f1": 0.8236584947711297,
+    "eval_loss": 0.3001226484775543,
+    "eval_runtime": 13.1905,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 3065.087,
+    "eval_steps_per_second": 11.978,
+    "total_flos": 7.633075201391002e+16,
+    "train_loss": 0.21032491246691568,
+    "train_runtime": 1702.5845,
+    "train_samples": 363846,
+    "train_samples_per_second": 10685.108,
+    "train_steps_per_second": 41.76
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.8727924808310661,
+    "eval_combined_score": 0.848225487801098,
+    "eval_f1": 0.8236584947711297,
+    "eval_loss": 0.3001226484775543,
+    "eval_runtime": 13.1905,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 3065.087,
+    "eval_steps_per_second": 11.978
+}

logs/events.out.tfevents.1733838028.ki-g0008.684565.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f454f8d3ffea6d03cc837ab872b8a978a6f4792c3bcce191b4ab2d4aa10918c
+size 515

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 7.633075201391002e+16,
+    "train_loss": 0.21032491246691568,
+    "train_runtime": 1702.5845,
+    "train_samples": 363846,
+    "train_samples_per_second": 10685.108,
+    "train_steps_per_second": 41.76
+}

trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.3001226484775543,
+  "best_model_checkpoint": "bert_tiny_lda_50_v1_book_qqp/checkpoint-4266",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 11376,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.33488392829895,
+      "learning_rate": 4.9e-05,
+      "loss": 0.4008,
+      "step": 1422
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8388820183032402,
+      "eval_combined_score": 0.7992653763569924,
+      "eval_f1": 0.7596487344107445,
+      "eval_loss": 0.3669641315937042,
+      "eval_runtime": 12.8188,
+      "eval_samples_per_second": 3153.965,
+      "eval_steps_per_second": 12.326,
+      "step": 1422
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.6537423133850098,
+      "learning_rate": 4.8e-05,
+      "loss": 0.3043,
+      "step": 2844
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8635913925302993,
+      "eval_combined_score": 0.8382608772291604,
+      "eval_f1": 0.8129303619280215,
+      "eval_loss": 0.31618016958236694,
+      "eval_runtime": 12.9677,
+      "eval_samples_per_second": 3117.755,
+      "eval_steps_per_second": 12.184,
+      "step": 2844
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.41264271736145,
+      "learning_rate": 4.7e-05,
+      "loss": 0.2505,
+      "step": 4266
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8727924808310661,
+      "eval_combined_score": 0.848225487801098,
+      "eval_f1": 0.8236584947711297,
+      "eval_loss": 0.3001226484775543,
+      "eval_runtime": 12.4674,
+      "eval_samples_per_second": 3242.854,
+      "eval_steps_per_second": 12.673,
+      "step": 4266
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.307275295257568,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.2074,
+      "step": 5688
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8739549839228296,
+      "eval_combined_score": 0.8462884259021892,
+      "eval_f1": 0.8186218678815489,
+      "eval_loss": 0.3213236629962921,
+      "eval_runtime": 12.7707,
+      "eval_samples_per_second": 3165.839,
+      "eval_steps_per_second": 12.372,
+      "step": 5688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.7289059162139893,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1699,
+      "step": 7110
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8775661637397972,
+      "eval_combined_score": 0.8531251598099554,
+      "eval_f1": 0.8286841558801136,
+      "eval_loss": 0.33461794257164,
+      "eval_runtime": 12.7155,
+      "eval_samples_per_second": 3179.594,
+      "eval_steps_per_second": 12.426,
+      "step": 7110
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.772562503814697,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1392,
+      "step": 8532
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8807815978233985,
+      "eval_combined_score": 0.8601590924066056,
+      "eval_f1": 0.8395365869898128,
+      "eval_loss": 0.35863471031188965,
+      "eval_runtime": 12.772,
+      "eval_samples_per_second": 3165.527,
+      "eval_steps_per_second": 12.371,
+      "step": 8532
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.4329893589019775,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1151,
+      "step": 9954
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8820430373485035,
+      "eval_combined_score": 0.8605048885881468,
+      "eval_f1": 0.83896673982779,
+      "eval_loss": 0.3763424754142761,
+      "eval_runtime": 12.6426,
+      "eval_samples_per_second": 3197.93,
+      "eval_steps_per_second": 12.497,
+      "step": 9954
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.7860946655273438,
+      "learning_rate": 4.2e-05,
+      "loss": 0.0954,
+      "step": 11376
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8819935691318328,
+      "eval_combined_score": 0.8597938026412815,
+      "eval_f1": 0.8375940361507301,
+      "eval_loss": 0.39844101667404175,
+      "eval_runtime": 12.3325,
+      "eval_samples_per_second": 3278.323,
+      "eval_steps_per_second": 12.812,
+      "step": 11376
+    },
+    {
+      "epoch": 8.0,
+      "step": 11376,
+      "total_flos": 7.633075201391002e+16,
+      "train_loss": 0.21032491246691568,
+      "train_runtime": 1702.5845,
+      "train_samples_per_second": 10685.108,
+      "train_steps_per_second": 41.76
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 71100,
+  "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": 7.633075201391002e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}