End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_tiny_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_tiny_lda_100_v1_rte
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6937
-- Accuracy: 0.4729
+- Loss: 0.6911
+- Accuracy: 0.5271
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.6910818815231323,
+    "eval_runtime": 0.0902,
+    "eval_samples": 277,
+    "eval_samples_per_second": 3069.608,
+    "eval_steps_per_second": 22.163,
+    "total_flos": 652967094988800.0,
+    "train_loss": 0.7079746341705322,
+    "train_runtime": 20.9087,
+    "train_samples": 2490,
+    "train_samples_per_second": 5954.454,
+    "train_steps_per_second": 23.913
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.5270758122743683,
+    "eval_loss": 0.6910818815231323,
+    "eval_runtime": 0.0902,
+    "eval_samples": 277,
+    "eval_samples_per_second": 3069.608,
+    "eval_steps_per_second": 22.163
+}

logs/events.out.tfevents.1732662292.ki-g0008.2137866.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58b6f0630277f8c09a6bfe10593c4e165adc277b8d05dc8d3fc222a90a03a705
+size 405

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 652967094988800.0,
+    "train_loss": 0.7079746341705322,
+    "train_runtime": 20.9087,
+    "train_samples": 2490,
+    "train_samples_per_second": 5954.454,
+    "train_steps_per_second": 23.913
+}

trainer_state.json

@@ -0,0 +1,211 @@
+{
+  "best_metric": 0.6910818815231323,
+  "best_model_checkpoint": "bert_tiny_lda_100_v1_rte/checkpoint-50",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8250333070755005,
+      "learning_rate": 0.00098,
+      "loss": 0.8226,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.7099644541740417,
+      "eval_runtime": 0.0907,
+      "eval_samples_per_second": 3054.549,
+      "eval_steps_per_second": 22.055,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.27419352531433105,
+      "learning_rate": 0.00096,
+      "loss": 0.7009,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7083004713058472,
+      "eval_runtime": 0.0923,
+      "eval_samples_per_second": 3001.194,
+      "eval_steps_per_second": 21.669,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.2973408102989197,
+      "learning_rate": 0.00094,
+      "loss": 0.696,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6955804228782654,
+      "eval_runtime": 0.0912,
+      "eval_samples_per_second": 3038.309,
+      "eval_steps_per_second": 21.937,
+      "step": 30
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.25628429651260376,
+      "learning_rate": 0.00092,
+      "loss": 0.695,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6930421590805054,
+      "eval_runtime": 0.0958,
+      "eval_samples_per_second": 2892.623,
+      "eval_steps_per_second": 20.885,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.6449291706085205,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.6933,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6910818815231323,
+      "eval_runtime": 0.0889,
+      "eval_samples_per_second": 3114.696,
+      "eval_steps_per_second": 22.489,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.27499687671661377,
+      "learning_rate": 0.00088,
+      "loss": 0.6964,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.698697030544281,
+      "eval_runtime": 0.0888,
+      "eval_samples_per_second": 3117.998,
+      "eval_steps_per_second": 22.513,
+      "step": 60
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.1044619083404541,
+      "learning_rate": 0.00086,
+      "loss": 0.694,
+      "step": 70
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6921958923339844,
+      "eval_runtime": 0.0893,
+      "eval_samples_per_second": 3100.888,
+      "eval_steps_per_second": 22.389,
+      "step": 70
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.16408830881118774,
+      "learning_rate": 0.00084,
+      "loss": 0.6941,
+      "step": 80
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6951573491096497,
+      "eval_runtime": 0.0897,
+      "eval_samples_per_second": 3088.335,
+      "eval_steps_per_second": 22.298,
+      "step": 80
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.14835208654403687,
+      "learning_rate": 0.00082,
+      "loss": 0.6942,
+      "step": 90
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6926190257072449,
+      "eval_runtime": 0.092,
+      "eval_samples_per_second": 3011.868,
+      "eval_steps_per_second": 21.746,
+      "step": 90
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.11492882668972015,
+      "learning_rate": 0.0008,
+      "loss": 0.6932,
+      "step": 100
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6936765909194946,
+      "eval_runtime": 0.0892,
+      "eval_samples_per_second": 3106.792,
+      "eval_steps_per_second": 22.432,
+      "step": 100
+    },
+    {
+      "epoch": 10.0,
+      "step": 100,
+      "total_flos": 652967094988800.0,
+      "train_loss": 0.7079746341705322,
+      "train_runtime": 20.9087,
+      "train_samples_per_second": 5954.454,
+      "train_steps_per_second": 23.913
+    }
+  ],
+  "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": 652967094988800.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}