End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_20_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_tiny_lda_20_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_tiny_lda_20_v1_rte
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20_v1) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7016
-- Accuracy: 0.4729
+- Loss: 0.6920
+- Accuracy: 0.5271
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.6919703483581543,
+    "eval_runtime": 0.0907,
+    "eval_samples": 277,
+    "eval_samples_per_second": 3054.758,
+    "eval_steps_per_second": 22.056,
+    "total_flos": 391780256993280.0,
+    "train_loss": 0.7266074577967326,
+    "train_runtime": 12.795,
+    "train_samples": 2490,
+    "train_samples_per_second": 9730.346,
+    "train_steps_per_second": 39.078
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.6919703483581543,
+    "eval_runtime": 0.0907,
+    "eval_samples": 277,
+    "eval_samples_per_second": 3054.758,
+    "eval_steps_per_second": 22.056
+}

logs/events.out.tfevents.1732658236.ki-g0008.2136969.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb7dddc0e028a7941639fb2bf9c73aaff37af6a1cc0cc2055e687046f8effe86
+size 405

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 391780256993280.0,
+    "train_loss": 0.7266074577967326,
+    "train_runtime": 12.795,
+    "train_samples": 2490,
+    "train_samples_per_second": 9730.346,
+    "train_steps_per_second": 39.078
+}

trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": 0.6919703483581543,
+  "best_model_checkpoint": "bert_tiny_lda_20_v1_rte/checkpoint-10",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6528123617172241,
+      "learning_rate": 0.00098,
+      "loss": 0.7827,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6919703483581543,
+      "eval_runtime": 0.0925,
+      "eval_samples_per_second": 2994.349,
+      "eval_steps_per_second": 21.62,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 61.58826446533203,
+      "learning_rate": 0.00096,
+      "loss": 0.7523,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.9407504796981812,
+      "eval_runtime": 0.0956,
+      "eval_samples_per_second": 2897.052,
+      "eval_steps_per_second": 20.917,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.22817732393741608,
+      "learning_rate": 0.00094,
+      "loss": 0.7355,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6925626397132874,
+      "eval_runtime": 0.0957,
+      "eval_samples_per_second": 2895.327,
+      "eval_steps_per_second": 20.905,
+      "step": 30
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.17734946310520172,
+      "learning_rate": 0.00092,
+      "loss": 0.6946,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6931407451629639,
+      "eval_runtime": 0.0931,
+      "eval_samples_per_second": 2975.598,
+      "eval_steps_per_second": 21.484,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.5333439111709595,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.6954,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6965110898017883,
+      "eval_runtime": 0.0932,
+      "eval_samples_per_second": 2970.774,
+      "eval_steps_per_second": 21.45,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.4501447379589081,
+      "learning_rate": 0.00088,
+      "loss": 0.699,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7016019821166992,
+      "eval_runtime": 0.0946,
+      "eval_samples_per_second": 2926.696,
+      "eval_steps_per_second": 21.131,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "step": 60,
+      "total_flos": 391780256993280.0,
+      "train_loss": 0.7266074577967326,
+      "train_runtime": 12.795,
+      "train_samples_per_second": 9730.346,
+      "train_steps_per_second": 39.078
+    }
+  ],
+  "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": 391780256993280.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}