End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_5_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_tiny_lda_5_v1_book_mnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7597640358014646
 ---
 
 <!-- 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_5_v1_book_mnli
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_5_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_5_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_5_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_5_v1_book) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8077
-- Accuracy: 0.7532
+- Loss: 0.6047
+- Accuracy: 0.7598
 
 ## Model description
 

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 8.0,
+    "epoch_mm": 8.0,
+    "eval_accuracy": 0.7504839531329598,
+    "eval_accuracy_mm": 0.7597640358014646,
+    "eval_loss": 0.6253408789634705,
+    "eval_loss_mm": 0.6046947240829468,
+    "eval_runtime": 4.0132,
+    "eval_runtime_mm": 3.986,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 2445.682,
+    "eval_samples_per_second_mm": 2466.655,
+    "eval_steps_per_second": 9.718,
+    "eval_steps_per_second_mm": 9.784,
+    "total_flos": 8.238688806678528e+16,
+    "train_loss": 0.47111580611207804,
+    "train_runtime": 1754.9078,
+    "train_samples": 392702,
+    "train_samples_per_second": 11188.679,
+    "train_steps_per_second": 43.706
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 8.0,
+    "epoch_mm": 8.0,
+    "eval_accuracy": 0.7504839531329598,
+    "eval_accuracy_mm": 0.7597640358014646,
+    "eval_loss": 0.6253408789634705,
+    "eval_loss_mm": 0.6046947240829468,
+    "eval_runtime": 4.0132,
+    "eval_runtime_mm": 3.986,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 2445.682,
+    "eval_samples_per_second_mm": 2466.655,
+    "eval_steps_per_second": 9.718,
+    "eval_steps_per_second_mm": 9.784
+}

logs/events.out.tfevents.1733840392.ki-g0008.683966.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81905ccaf3cff94697a4a14379210e6c18ce1ed8c6b5f445b134c054c481650
+size 734

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 8.238688806678528e+16,
+    "train_loss": 0.47111580611207804,
+    "train_runtime": 1754.9078,
+    "train_samples": 392702,
+    "train_samples_per_second": 11188.679,
+    "train_steps_per_second": 43.706
+}

trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": 0.6253408789634705,
+  "best_model_checkpoint": "bert_tiny_lda_5_v1_book_mnli/checkpoint-4602",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 12272,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.314117193222046,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7793,
+      "step": 1534
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7105450840550178,
+      "eval_loss": 0.6778525710105896,
+      "eval_runtime": 3.0986,
+      "eval_samples_per_second": 3167.56,
+      "eval_steps_per_second": 12.586,
+      "step": 1534
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9456748962402344,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6313,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7361181864493123,
+      "eval_loss": 0.6315506100654602,
+      "eval_runtime": 3.1539,
+      "eval_samples_per_second": 3112.063,
+      "eval_steps_per_second": 12.366,
+      "step": 3068
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.130629062652588,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5474,
+      "step": 4602
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7504839531329598,
+      "eval_loss": 0.6253408789634705,
+      "eval_runtime": 3.1662,
+      "eval_samples_per_second": 3099.886,
+      "eval_steps_per_second": 12.317,
+      "step": 4602
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.676422357559204,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4766,
+      "step": 6136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7538461538461538,
+      "eval_loss": 0.6401060223579407,
+      "eval_runtime": 3.0144,
+      "eval_samples_per_second": 3256.025,
+      "eval_steps_per_second": 12.938,
+      "step": 6136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.1485705375671387,
+      "learning_rate": 4.5e-05,
+      "loss": 0.414,
+      "step": 7670
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7559857361181864,
+      "eval_loss": 0.647048830986023,
+      "eval_runtime": 3.0367,
+      "eval_samples_per_second": 3232.117,
+      "eval_steps_per_second": 12.843,
+      "step": 7670
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.6102612018585205,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3555,
+      "step": 9204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7554763117677025,
+      "eval_loss": 0.7033843994140625,
+      "eval_runtime": 3.101,
+      "eval_samples_per_second": 3165.061,
+      "eval_steps_per_second": 12.576,
+      "step": 9204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.9815475940704346,
+      "learning_rate": 4.3e-05,
+      "loss": 0.304,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7553744268976057,
+      "eval_loss": 0.7439941763877869,
+      "eval_runtime": 3.0936,
+      "eval_samples_per_second": 3172.719,
+      "eval_steps_per_second": 12.607,
+      "step": 10738
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.370164394378662,
+      "learning_rate": 4.2e-05,
+      "loss": 0.2609,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7532348446255731,
+      "eval_loss": 0.807701587677002,
+      "eval_runtime": 3.1349,
+      "eval_samples_per_second": 3130.857,
+      "eval_steps_per_second": 12.44,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "step": 12272,
+      "total_flos": 8.238688806678528e+16,
+      "train_loss": 0.47111580611207804,
+      "train_runtime": 1754.9078,
+      "train_samples_per_second": 11188.679,
+      "train_steps_per_second": 43.706
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 76700,
+  "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": 8.238688806678528e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}