End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_lda_100_v1_rte
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5270758122743683
 ---
 
 <!-- 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_100_v1_rte
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_100_v1) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6935
-- Accuracy: 0.4729
+- Loss: 0.6905
+- Accuracy: 0.5271
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.690503716468811,
+    "eval_runtime": 0.1895,
+    "eval_samples": 277,
+    "eval_samples_per_second": 1461.776,
+    "eval_steps_per_second": 10.554,
+    "total_flos": 2948159375308800.0,
+    "train_loss": 0.7451369815402561,
+    "train_runtime": 60.675,
+    "train_samples": 2490,
+    "train_samples_per_second": 2051.916,
+    "train_steps_per_second": 8.241
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.690503716468811,
+    "eval_runtime": 0.1895,
+    "eval_samples": 277,
+    "eval_samples_per_second": 1461.776,
+    "eval_steps_per_second": 10.554
+}

logs/events.out.tfevents.1732649563.ki-g0008.2137866.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c29e6675948fea61756f1467ccb3e404decf314620bd66c717da643b1557c0
+size 405

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "total_flos": 2948159375308800.0,
+    "train_loss": 0.7451369815402561,
+    "train_runtime": 60.675,
+    "train_samples": 2490,
+    "train_samples_per_second": 2051.916,
+    "train_steps_per_second": 8.241
+}

trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.690503716468811,
+  "best_model_checkpoint": "bert_base_lda_100_v1_rte/checkpoint-40",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.40931814908981323,
+      "learning_rate": 0.00098,
+      "loss": 1.1399,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7164514064788818,
+      "eval_runtime": 0.1901,
+      "eval_samples_per_second": 1456.892,
+      "eval_steps_per_second": 10.519,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5890483260154724,
+      "learning_rate": 0.00096,
+      "loss": 0.7007,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6976816058158875,
+      "eval_runtime": 0.1858,
+      "eval_samples_per_second": 1490.725,
+      "eval_steps_per_second": 10.763,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.2279863804578781,
+      "learning_rate": 0.00094,
+      "loss": 0.6974,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6907293796539307,
+      "eval_runtime": 0.1855,
+      "eval_samples_per_second": 1493.531,
+      "eval_steps_per_second": 10.784,
+      "step": 30
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.2956705391407013,
+      "learning_rate": 0.00092,
+      "loss": 0.6952,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.690503716468811,
+      "eval_runtime": 0.184,
+      "eval_samples_per_second": 1505.452,
+      "eval_steps_per_second": 10.87,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.8746032118797302,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.6971,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6917870044708252,
+      "eval_runtime": 0.2041,
+      "eval_samples_per_second": 1356.868,
+      "eval_steps_per_second": 9.797,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.19928425550460815,
+      "learning_rate": 0.00088,
+      "loss": 0.6953,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6960035562515259,
+      "eval_runtime": 0.1859,
+      "eval_samples_per_second": 1490.395,
+      "eval_steps_per_second": 10.761,
+      "step": 60
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.15525557100772858,
+      "learning_rate": 0.00086,
+      "loss": 0.6941,
+      "step": 70
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6930421590805054,
+      "eval_runtime": 0.1867,
+      "eval_samples_per_second": 1483.886,
+      "eval_steps_per_second": 10.714,
+      "step": 70
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.09055319428443909,
+      "learning_rate": 0.00084,
+      "loss": 0.6933,
+      "step": 80
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6934510469436646,
+      "eval_runtime": 0.1875,
+      "eval_samples_per_second": 1477.333,
+      "eval_steps_per_second": 10.667,
+      "step": 80
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.2684151828289032,
+      "learning_rate": 0.00082,
+      "loss": 0.6933,
+      "step": 90
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6934651136398315,
+      "eval_runtime": 0.1888,
+      "eval_samples_per_second": 1466.799,
+      "eval_steps_per_second": 10.591,
+      "step": 90
+    },
+    {
+      "epoch": 9.0,
+      "step": 90,
+      "total_flos": 2948159375308800.0,
+      "train_loss": 0.7451369815402561,
+      "train_runtime": 60.675,
+      "train_samples_per_second": 2051.916,
+      "train_steps_per_second": 8.241
+    }
+  ],
+  "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": 2948159375308800.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}