End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_50_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_lda_50_v1_book_rte
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5018050541516246
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_lda_50_v1_book_rte
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_50_v1_book](https://huggingface.co/gokulsrinivasagan/bert_base_lda_50_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_50_v1_book](https://huggingface.co/gokulsrinivasagan/bert_base_lda_50_v1_book) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8455
-- Accuracy: 0.5451
+- Loss: 0.6885
+- Accuracy: 0.5018
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 12.0,
+    "eval_accuracy": 0.5018050541516246,
+    "eval_loss": 0.6885294318199158,
+    "eval_runtime": 0.2076,
+    "eval_samples": 277,
+    "eval_samples_per_second": 1334.252,
+    "eval_steps_per_second": 9.634,
+    "total_flos": 3930879167078400.0,
+    "train_loss": 0.665597399075826,
+    "train_runtime": 82.9578,
+    "train_samples": 2490,
+    "train_samples_per_second": 1500.764,
+    "train_steps_per_second": 6.027
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 12.0,
+    "eval_accuracy": 0.5018050541516246,
+    "eval_loss": 0.6885294318199158,
+    "eval_runtime": 0.2076,
+    "eval_samples": 277,
+    "eval_samples_per_second": 1334.252,
+    "eval_steps_per_second": 9.634
+}

logs/events.out.tfevents.1738023379.ki-g0008.3474952.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22eb789b6201276788c3541f5e0a22381770c81511da06750994edfc7f6569f
+size 405

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 12.0,
+    "total_flos": 3930879167078400.0,
+    "train_loss": 0.665597399075826,
+    "train_runtime": 82.9578,
+    "train_samples": 2490,
+    "train_samples_per_second": 1500.764,
+    "train_steps_per_second": 6.027
+}

trainer_state.json

@@ -0,0 +1,243 @@
+{
+  "best_metric": 0.6885294318199158,
+  "best_model_checkpoint": "bert_base_lda_50_v1_book_rte/checkpoint-70",
+  "epoch": 12.0,
+  "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": 1.1835660934448242,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7099,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5342960288808665,
+      "eval_loss": 0.7058890461921692,
+      "eval_runtime": 0.2015,
+      "eval_samples_per_second": 1374.69,
+      "eval_steps_per_second": 9.926,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.46133843064308167,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6998,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4657039711191336,
+      "eval_loss": 0.695397138595581,
+      "eval_runtime": 0.2173,
+      "eval_samples_per_second": 1274.527,
+      "eval_steps_per_second": 9.202,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.24930205941200256,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6965,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6917728781700134,
+      "eval_runtime": 0.2022,
+      "eval_samples_per_second": 1369.641,
+      "eval_steps_per_second": 9.889,
+      "step": 30
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.26202183961868286,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6924,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6914203763008118,
+      "eval_runtime": 0.1937,
+      "eval_samples_per_second": 1429.777,
+      "eval_steps_per_second": 10.323,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.5008444786071777,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6932,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6945933103561401,
+      "eval_runtime": 0.197,
+      "eval_samples_per_second": 1405.948,
+      "eval_steps_per_second": 10.151,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.41217923164367676,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6962,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.47653429602888087,
+      "eval_loss": 0.6997545957565308,
+      "eval_runtime": 0.2079,
+      "eval_samples_per_second": 1332.137,
+      "eval_steps_per_second": 9.618,
+      "step": 60
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.4133719801902771,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6918,
+      "step": 70
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5018050541516246,
+      "eval_loss": 0.6885294318199158,
+      "eval_runtime": 0.1997,
+      "eval_samples_per_second": 1387.181,
+      "eval_steps_per_second": 10.016,
+      "step": 70
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.377682685852051,
+      "learning_rate": 4.2e-05,
+      "loss": 0.6802,
+      "step": 80
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5523465703971119,
+      "eval_loss": 0.7131938338279724,
+      "eval_runtime": 0.1899,
+      "eval_samples_per_second": 1458.301,
+      "eval_steps_per_second": 10.529,
+      "step": 80
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 1.3383139371871948,
+      "learning_rate": 4.1e-05,
+      "loss": 0.6651,
+      "step": 90
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5523465703971119,
+      "eval_loss": 0.6923511028289795,
+      "eval_runtime": 0.2007,
+      "eval_samples_per_second": 1379.971,
+      "eval_steps_per_second": 9.964,
+      "step": 90
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 4.568511486053467,
+      "learning_rate": 4e-05,
+      "loss": 0.6437,
+      "step": 100
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.5054151624548736,
+      "eval_loss": 0.807532548904419,
+      "eval_runtime": 0.1992,
+      "eval_samples_per_second": 1390.759,
+      "eval_steps_per_second": 10.042,
+      "step": 100
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 1.6954079866409302,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.6004,
+      "step": 110
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.5451263537906137,
+      "eval_loss": 0.7967392802238464,
+      "eval_runtime": 0.1982,
+      "eval_samples_per_second": 1397.445,
+      "eval_steps_per_second": 10.09,
+      "step": 110
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 5.426494121551514,
+      "learning_rate": 3.8e-05,
+      "loss": 0.518,
+      "step": 120
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.5451263537906137,
+      "eval_loss": 0.8455197811126709,
+      "eval_runtime": 0.1962,
+      "eval_samples_per_second": 1411.762,
+      "eval_steps_per_second": 10.193,
+      "step": 120
+    },
+    {
+      "epoch": 12.0,
+      "step": 120,
+      "total_flos": 3930879167078400.0,
+      "train_loss": 0.665597399075826,
+      "train_runtime": 82.9578,
+      "train_samples_per_second": 1500.764,
+      "train_steps_per_second": 6.027
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 500,
+  "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": 3930879167078400.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}