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_wnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE WNLI
+      type: glue
+      args: wnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.4507042253521127
 ---
 
 <!-- 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_wnli
 
-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 WNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7329
-- Accuracy: 0.2958
+- Loss: 0.7073
+- Accuracy: 0.4507
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.4507042253521127,
+    "eval_loss": 0.7072514295578003,
+    "eval_runtime": 0.0346,
+    "eval_samples": 71,
+    "eval_samples_per_second": 2054.273,
+    "eval_steps_per_second": 28.933,
+    "total_flos": 116563804707840.0,
+    "train_loss": 0.6961876210712251,
+    "train_runtime": 9.8803,
+    "train_samples": 635,
+    "train_samples_per_second": 3213.471,
+    "train_steps_per_second": 15.182
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.4507042253521127,
+    "eval_loss": 0.7072514295578003,
+    "eval_runtime": 0.0346,
+    "eval_samples": 71,
+    "eval_samples_per_second": 2054.273,
+    "eval_steps_per_second": 28.933
+}

logs/events.out.tfevents.1733843493.ki-g0008.683966.33

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd68d49c0495d0a763989ac76b8c76cc12a2db5b447e6688101ac806323068cf
+size 405

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 116563804707840.0,
+    "train_loss": 0.6961876210712251,
+    "train_runtime": 9.8803,
+    "train_samples": 635,
+    "train_samples_per_second": 3213.471,
+    "train_steps_per_second": 15.182
+}

trainer_state.json

@@ -0,0 +1,163 @@
+{
+  "best_metric": 0.7072514295578003,
+  "best_model_checkpoint": "bert_tiny_lda_20_v1_book_wnli/checkpoint-6",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 21,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.473922610282898,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7059,
+      "step": 3
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.323943661971831,
+      "eval_loss": 0.7168244123458862,
+      "eval_runtime": 0.0302,
+      "eval_samples_per_second": 2354.246,
+      "eval_steps_per_second": 33.158,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9136478900909424,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6968,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4507042253521127,
+      "eval_loss": 0.7072514295578003,
+      "eval_runtime": 0.0299,
+      "eval_samples_per_second": 2376.471,
+      "eval_steps_per_second": 33.471,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7124316692352295,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6986,
+      "step": 9
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.39436619718309857,
+      "eval_loss": 0.724141538143158,
+      "eval_runtime": 0.0319,
+      "eval_samples_per_second": 2223.4,
+      "eval_steps_per_second": 31.315,
+      "step": 9
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.6699673533439636,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6968,
+      "step": 12
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4647887323943662,
+      "eval_loss": 0.7089017033576965,
+      "eval_runtime": 0.0333,
+      "eval_samples_per_second": 2132.03,
+      "eval_steps_per_second": 30.029,
+      "step": 12
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.0129752159118652,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6932,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4788732394366197,
+      "eval_loss": 0.7105523347854614,
+      "eval_runtime": 0.0305,
+      "eval_samples_per_second": 2330.479,
+      "eval_steps_per_second": 32.824,
+      "step": 15
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.6613156795501709,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6931,
+      "step": 18
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.323943661971831,
+      "eval_loss": 0.7261773347854614,
+      "eval_runtime": 0.0349,
+      "eval_samples_per_second": 2031.639,
+      "eval_steps_per_second": 28.615,
+      "step": 18
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.5985599160194397,
+      "learning_rate": 4.3e-05,
+      "loss": 0.689,
+      "step": 21
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.29577464788732394,
+      "eval_loss": 0.7329445481300354,
+      "eval_runtime": 0.0305,
+      "eval_samples_per_second": 2330.297,
+      "eval_steps_per_second": 32.821,
+      "step": 21
+    },
+    {
+      "epoch": 7.0,
+      "step": 21,
+      "total_flos": 116563804707840.0,
+      "train_loss": 0.6961876210712251,
+      "train_runtime": 9.8803,
+      "train_samples_per_second": 3213.471,
+      "train_steps_per_second": 15.182
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "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": 116563804707840.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}