End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_20_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_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_base_lda_20_v1_book_rte
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_20_v1_book](https://huggingface.co/gokulsrinivasagan/bert_base_lda_20_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_20_v1_book](https://huggingface.co/gokulsrinivasagan/bert_base_lda_20_v1_book) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2664
-- Accuracy: 0.5668
+- Loss: 0.6921
+- Accuracy: 0.5343
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.5342960288808665,
+    "eval_loss": 0.6920831203460693,
+    "eval_runtime": 0.193,
+    "eval_samples": 277,
+    "eval_samples_per_second": 1435.176,
+    "eval_steps_per_second": 10.362,
+    "total_flos": 2620586111385600.0,
+    "train_loss": 0.5152381032705307,
+    "train_runtime": 53.7127,
+    "train_samples": 2490,
+    "train_samples_per_second": 2317.886,
+    "train_steps_per_second": 9.309
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.5342960288808665,
+    "eval_loss": 0.6920831203460693,
+    "eval_runtime": 0.193,
+    "eval_samples": 277,
+    "eval_samples_per_second": 1435.176,
+    "eval_steps_per_second": 10.362
+}

logs/events.out.tfevents.1733845449.ki-g0008.520107.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e1fbf3deb554c3688d19707c4477a6d7521f2b9b12edbe30a5af6f63a1d5f2
+size 405

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 2620586111385600.0,
+    "train_loss": 0.5152381032705307,
+    "train_runtime": 53.7127,
+    "train_samples": 2490,
+    "train_samples_per_second": 2317.886,
+    "train_steps_per_second": 9.309
+}

trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": 0.6920831203460693,
+  "best_model_checkpoint": "bert_base_lda_20_v1_book_rte/checkpoint-30",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5645230412483215,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7001,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5018050541516246,
+      "eval_loss": 0.6986829042434692,
+      "eval_runtime": 0.1899,
+      "eval_samples_per_second": 1458.522,
+      "eval_steps_per_second": 10.531,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6046182513237,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6865,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5126353790613718,
+      "eval_loss": 0.693359375,
+      "eval_runtime": 0.1886,
+      "eval_samples_per_second": 1468.356,
+      "eval_steps_per_second": 10.602,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.138460397720337,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6669,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5342960288808665,
+      "eval_loss": 0.6920831203460693,
+      "eval_runtime": 0.2054,
+      "eval_samples_per_second": 1348.569,
+      "eval_steps_per_second": 9.737,
+      "step": 30
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.583211421966553,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6301,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.555956678700361,
+      "eval_loss": 0.7333966493606567,
+      "eval_runtime": 0.1961,
+      "eval_samples_per_second": 1412.44,
+      "eval_steps_per_second": 10.198,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.975888967514038,
+      "learning_rate": 4.5e-05,
+      "loss": 0.5188,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5415162454873647,
+      "eval_loss": 0.9070555567741394,
+      "eval_runtime": 0.2112,
+      "eval_samples_per_second": 1311.381,
+      "eval_steps_per_second": 9.468,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.132864475250244,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.4111,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5776173285198556,
+      "eval_loss": 1.0800586938858032,
+      "eval_runtime": 0.2186,
+      "eval_samples_per_second": 1267.431,
+      "eval_steps_per_second": 9.151,
+      "step": 60
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 5.962082386016846,
+      "learning_rate": 4.3e-05,
+      "loss": 0.284,
+      "step": 70
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5848375451263538,
+      "eval_loss": 1.0944857597351074,
+      "eval_runtime": 0.1992,
+      "eval_samples_per_second": 1390.588,
+      "eval_steps_per_second": 10.04,
+      "step": 70
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 6.078020095825195,
+      "learning_rate": 4.2e-05,
+      "loss": 0.2243,
+      "step": 80
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5667870036101083,
+      "eval_loss": 1.2663503885269165,
+      "eval_runtime": 0.1933,
+      "eval_samples_per_second": 1432.711,
+      "eval_steps_per_second": 10.344,
+      "step": 80
+    },
+    {
+      "epoch": 8.0,
+      "step": 80,
+      "total_flos": 2620586111385600.0,
+      "train_loss": 0.5152381032705307,
+      "train_runtime": 53.7127,
+      "train_samples_per_second": 2317.886,
+      "train_steps_per_second": 9.309
+    }
+  ],
+  "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": 2620586111385600.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}