End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_20_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_tiny_lda_20_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: 0.5342960288808665
 ---
 
 <!-- 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_book_rte
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20_v1_book) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8660
-- Accuracy: 0.5307
+- Loss: 0.6854
+- Accuracy: 0.5343
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.5342960288808665,
+    "eval_loss": 0.6853635311126709,
+    "eval_runtime": 0.0977,
+    "eval_samples": 277,
+    "eval_samples_per_second": 2836.009,
+    "eval_steps_per_second": 20.477,
+    "total_flos": 587670385489920.0,
+    "train_loss": 0.6215637260013156,
+    "train_runtime": 22.548,
+    "train_samples": 2490,
+    "train_samples_per_second": 5521.556,
+    "train_steps_per_second": 22.175
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "eval_accuracy": 0.5342960288808665,
+    "eval_loss": 0.6853635311126709,
+    "eval_runtime": 0.0977,
+    "eval_samples": 277,
+    "eval_samples_per_second": 2836.009,
+    "eval_steps_per_second": 20.477
+}

logs/events.out.tfevents.1733843032.ki-g0008.683966.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6448402cb2a93a4474b4ea977214fba509aa7bffdb232ee6b70fdde0cced3a98
+size 405

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "total_flos": 587670385489920.0,
+    "train_loss": 0.6215637260013156,
+    "train_runtime": 22.548,
+    "train_samples": 2490,
+    "train_samples_per_second": 5521.556,
+    "train_steps_per_second": 22.175
+}

trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.6853635311126709,
+  "best_model_checkpoint": "bert_tiny_lda_20_v1_book_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": 0.676283597946167,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7071,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4693140794223827,
+      "eval_loss": 0.6985418796539307,
+      "eval_runtime": 0.0972,
+      "eval_samples_per_second": 2849.964,
+      "eval_steps_per_second": 20.577,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5267872214317322,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6942,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5487364620938628,
+      "eval_loss": 0.6904473304748535,
+      "eval_runtime": 0.0969,
+      "eval_samples_per_second": 2859.525,
+      "eval_steps_per_second": 20.646,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.3493775427341461,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6872,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5379061371841155,
+      "eval_loss": 0.6892768740653992,
+      "eval_runtime": 0.0979,
+      "eval_samples_per_second": 2829.999,
+      "eval_steps_per_second": 20.433,
+      "step": 30
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.6518508791923523,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6791,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5342960288808665,
+      "eval_loss": 0.6853635311126709,
+      "eval_runtime": 0.0951,
+      "eval_samples_per_second": 2914.048,
+      "eval_steps_per_second": 21.04,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.1944053173065186,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6633,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5523465703971119,
+      "eval_loss": 0.7276800870895386,
+      "eval_runtime": 0.0942,
+      "eval_samples_per_second": 2939.35,
+      "eval_steps_per_second": 21.223,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.9696075916290283,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6418,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5415162454873647,
+      "eval_loss": 0.6989367604255676,
+      "eval_runtime": 0.0989,
+      "eval_samples_per_second": 2800.53,
+      "eval_steps_per_second": 20.22,
+      "step": 60
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.3510026931762695,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5818,
+      "step": 70
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5379061371841155,
+      "eval_loss": 0.7710613012313843,
+      "eval_runtime": 0.0973,
+      "eval_samples_per_second": 2846.18,
+      "eval_steps_per_second": 20.55,
+      "step": 70
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 4.881992340087891,
+      "learning_rate": 4.2e-05,
+      "loss": 0.5207,
+      "step": 80
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5595667870036101,
+      "eval_loss": 0.7769259810447693,
+      "eval_runtime": 0.0999,
+      "eval_samples_per_second": 2771.721,
+      "eval_steps_per_second": 20.012,
+      "step": 80
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 2.1593451499938965,
+      "learning_rate": 4.1e-05,
+      "loss": 0.419,
+      "step": 90
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5306859205776173,
+      "eval_loss": 0.8659676909446716,
+      "eval_runtime": 0.0942,
+      "eval_samples_per_second": 2939.573,
+      "eval_steps_per_second": 21.224,
+      "step": 90
+    },
+    {
+      "epoch": 9.0,
+      "step": 90,
+      "total_flos": 587670385489920.0,
+      "train_loss": 0.6215637260013156,
+      "train_runtime": 22.548,
+      "train_samples_per_second": 5521.556,
+      "train_steps_per_second": 22.175
+    }
+  ],
+  "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": 587670385489920.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}