End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_50_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_tiny_lda_50_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: 0.7529495524816925
 ---
 
 <!-- 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_50_v1_book_mnli
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_50_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_50_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_50_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_50_v1_book) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8192
-- Accuracy: 0.7524
+- Loss: 0.6057
+- Accuracy: 0.7529
 
 ## Model description
 

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 8.0,
+    "epoch_mm": 8.0,
+    "eval_accuracy": 0.746001018848701,
+    "eval_accuracy_mm": 0.7529495524816925,
+    "eval_loss": 0.6320216059684753,
+    "eval_loss_mm": 0.6057317852973938,
+    "eval_runtime": 4.1042,
+    "eval_runtime_mm": 3.8559,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 2391.48,
+    "eval_samples_per_second_mm": 2549.89,
+    "eval_steps_per_second": 9.503,
+    "eval_steps_per_second_mm": 10.114,
+    "total_flos": 8.238688806678528e+16,
+    "train_loss": 0.49373503862801243,
+    "train_runtime": 1747.808,
+    "train_samples": 392702,
+    "train_samples_per_second": 11234.129,
+    "train_steps_per_second": 43.884
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 8.0,
+    "epoch_mm": 8.0,
+    "eval_accuracy": 0.746001018848701,
+    "eval_accuracy_mm": 0.7529495524816925,
+    "eval_loss": 0.6320216059684753,
+    "eval_loss_mm": 0.6057317852973938,
+    "eval_runtime": 4.1042,
+    "eval_runtime_mm": 3.8559,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 2391.48,
+    "eval_samples_per_second_mm": 2549.89,
+    "eval_steps_per_second": 9.503,
+    "eval_steps_per_second_mm": 10.114
+}

logs/events.out.tfevents.1733840393.ki-g0008.684565.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be3ec2e316f0d59566efd9075ffcf7f5248c1b7aca85931f3fc693c8431c0c43
+size 734

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 8.238688806678528e+16,
+    "train_loss": 0.49373503862801243,
+    "train_runtime": 1747.808,
+    "train_samples": 392702,
+    "train_samples_per_second": 11234.129,
+    "train_steps_per_second": 43.884
+}

trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": 0.6320216059684753,
+  "best_model_checkpoint": "bert_tiny_lda_50_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": 2.0899927616119385,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7973,
+      "step": 1534
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6962812022414672,
+      "eval_loss": 0.7053520679473877,
+      "eval_runtime": 3.0516,
+      "eval_samples_per_second": 3216.379,
+      "eval_steps_per_second": 12.78,
+      "step": 1534
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7895665168762207,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6499,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7318390219052471,
+      "eval_loss": 0.6405845880508423,
+      "eval_runtime": 3.0059,
+      "eval_samples_per_second": 3265.223,
+      "eval_steps_per_second": 12.974,
+      "step": 3068
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.9897078275680542,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5649,
+      "step": 4602
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.746001018848701,
+      "eval_loss": 0.6320216059684753,
+      "eval_runtime": 3.1253,
+      "eval_samples_per_second": 3140.461,
+      "eval_steps_per_second": 12.479,
+      "step": 4602
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.48475980758667,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4962,
+      "step": 6136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7493632195618951,
+      "eval_loss": 0.6454228162765503,
+      "eval_runtime": 3.0695,
+      "eval_samples_per_second": 3197.568,
+      "eval_steps_per_second": 12.706,
+      "step": 6136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.6358773708343506,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4374,
+      "step": 7670
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7514009169638308,
+      "eval_loss": 0.6634415984153748,
+      "eval_runtime": 3.0131,
+      "eval_samples_per_second": 3257.417,
+      "eval_steps_per_second": 12.943,
+      "step": 7670
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.395132541656494,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3831,
+      "step": 9204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7517065715741212,
+      "eval_loss": 0.7041948437690735,
+      "eval_runtime": 3.1426,
+      "eval_samples_per_second": 3123.205,
+      "eval_steps_per_second": 12.41,
+      "step": 9204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.9493460655212402,
+      "learning_rate": 4.3e-05,
+      "loss": 0.3325,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7551706571574122,
+      "eval_loss": 0.7309978008270264,
+      "eval_runtime": 3.07,
+      "eval_samples_per_second": 3197.11,
+      "eval_steps_per_second": 12.704,
+      "step": 10738
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.8644189834594727,
+      "learning_rate": 4.2e-05,
+      "loss": 0.2885,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7524197656647987,
+      "eval_loss": 0.8191949725151062,
+      "eval_runtime": 3.0717,
+      "eval_samples_per_second": 3195.302,
+      "eval_steps_per_second": 12.697,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "step": 12272,
+      "total_flos": 8.238688806678528e+16,
+      "train_loss": 0.49373503862801243,
+      "train_runtime": 1747.808,
+      "train_samples_per_second": 11234.129,
+      "train_steps_per_second": 43.884
+    }
+  ],
+  "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
+}