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_mnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7538649308380797
 ---
 
 <!-- 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_mnli
 
-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 MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7886
-- Accuracy: 0.7494
+- Loss: 0.6090
+- Accuracy: 0.7539
 
 ## Model description
 

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 8.0,
+    "epoch_mm": 8.0,
+    "eval_accuracy": 0.7480387162506368,
+    "eval_accuracy_mm": 0.7538649308380797,
+    "eval_loss": 0.6271984577178955,
+    "eval_loss_mm": 0.6090428233146667,
+    "eval_runtime": 3.0117,
+    "eval_runtime_mm": 3.0667,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 3258.93,
+    "eval_samples_per_second_mm": 3206.058,
+    "eval_steps_per_second": 12.949,
+    "eval_steps_per_second_mm": 12.717,
+    "total_flos": 8.238688806678528e+16,
+    "train_loss": 0.48412183739215797,
+    "train_runtime": 1741.3957,
+    "train_samples": 392702,
+    "train_samples_per_second": 11275.496,
+    "train_steps_per_second": 44.045
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 8.0,
+    "epoch_mm": 8.0,
+    "eval_accuracy": 0.7480387162506368,
+    "eval_accuracy_mm": 0.7538649308380797,
+    "eval_loss": 0.6271984577178955,
+    "eval_loss_mm": 0.6090428233146667,
+    "eval_runtime": 3.0117,
+    "eval_runtime_mm": 3.0667,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 3258.93,
+    "eval_samples_per_second_mm": 3206.058,
+    "eval_steps_per_second": 12.949,
+    "eval_steps_per_second_mm": 12.717
+}

logs/events.out.tfevents.1733845318.ki-g0008.683966.35

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:728a934f19abe2bc17ae8f21ccc4154d009e386bcdd911ce12f3ddbd70897ed9
+size 734

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 8.238688806678528e+16,
+    "train_loss": 0.48412183739215797,
+    "train_runtime": 1741.3957,
+    "train_samples": 392702,
+    "train_samples_per_second": 11275.496,
+    "train_steps_per_second": 44.045
+}

trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": 0.6271984577178955,
+  "best_model_checkpoint": "bert_tiny_lda_20_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": 2.495577335357666,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7934,
+      "step": 1534
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7075904228222109,
+      "eval_loss": 0.6956771612167358,
+      "eval_runtime": 3.1529,
+      "eval_samples_per_second": 3113.034,
+      "eval_steps_per_second": 12.37,
+      "step": 1534
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9987071752548218,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6416,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7346917982679572,
+      "eval_loss": 0.642723798751831,
+      "eval_runtime": 3.0621,
+      "eval_samples_per_second": 3205.288,
+      "eval_steps_per_second": 12.736,
+      "step": 3068
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.235865831375122,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5572,
+      "step": 4602
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7480387162506368,
+      "eval_loss": 0.6271984577178955,
+      "eval_runtime": 3.1008,
+      "eval_samples_per_second": 3165.298,
+      "eval_steps_per_second": 12.577,
+      "step": 4602
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.5112252235412598,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4879,
+      "step": 6136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7506877228731533,
+      "eval_loss": 0.6482094526290894,
+      "eval_runtime": 3.1438,
+      "eval_samples_per_second": 3122.017,
+      "eval_steps_per_second": 12.405,
+      "step": 6136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.551162004470825,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4275,
+      "step": 7670
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7511971472236373,
+      "eval_loss": 0.650538444519043,
+      "eval_runtime": 3.1497,
+      "eval_samples_per_second": 3116.155,
+      "eval_steps_per_second": 12.382,
+      "step": 7670
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.8887412548065186,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3699,
+      "step": 9204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7559857361181864,
+      "eval_loss": 0.6815374493598938,
+      "eval_runtime": 3.0601,
+      "eval_samples_per_second": 3207.359,
+      "eval_steps_per_second": 12.744,
+      "step": 9204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.065505027770996,
+      "learning_rate": 4.3e-05,
+      "loss": 0.32,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7517065715741212,
+      "eval_loss": 0.7475242018699646,
+      "eval_runtime": 3.0148,
+      "eval_samples_per_second": 3255.562,
+      "eval_steps_per_second": 12.936,
+      "step": 10738
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.0034844875335693,
+      "learning_rate": 4.2e-05,
+      "loss": 0.2754,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7493632195618951,
+      "eval_loss": 0.7886086106300354,
+      "eval_runtime": 3.068,
+      "eval_samples_per_second": 3199.101,
+      "eval_steps_per_second": 12.712,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "step": 12272,
+      "total_flos": 8.238688806678528e+16,
+      "train_loss": 0.48412183739215797,
+      "train_runtime": 1741.3957,
+      "train_samples_per_second": 11275.496,
+      "train_steps_per_second": 44.045
+    }
+  ],
+  "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
+}