End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_lda_100_v1_qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5053999633900788
 ---
 
 <!-- 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_100_v1_qnli
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_100_v1) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6934
-- Accuracy: 0.4946
+- Loss: 0.6914
+- Accuracy: 0.5054
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.5053999633900788,
+    "eval_loss": 0.69140625,
+    "eval_runtime": 3.5427,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 1542.042,
+    "eval_steps_per_second": 6.21,
+    "total_flos": 1.1023616508628992e+17,
+    "train_loss": 0.6958369836574647,
+    "train_runtime": 1397.9533,
+    "train_samples": 104743,
+    "train_samples_per_second": 3746.298,
+    "train_steps_per_second": 14.664
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.5053999633900788,
+    "eval_loss": 0.69140625,
+    "eval_runtime": 3.5427,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 1542.042,
+    "eval_steps_per_second": 6.21
+}

logs/events.out.tfevents.1732641795.ki-g0008.2137866.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d158a02440572af55248c2c9d8da01853f5f99935044f5e5c390b5723040b94d
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 1.1023616508628992e+17,
+    "train_loss": 0.6958369836574647,
+    "train_runtime": 1397.9533,
+    "train_samples": 104743,
+    "train_samples_per_second": 3746.298,
+    "train_steps_per_second": 14.664
+}

trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": 0.69140625,
+  "best_model_checkpoint": "bert_base_lda_100_v1_qnli/checkpoint-1230",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 3280,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.23485292494297028,
+      "learning_rate": 0.00098,
+      "loss": 0.7139,
+      "step": 410
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6933804750442505,
+      "eval_runtime": 3.5205,
+      "eval_samples_per_second": 1551.757,
+      "eval_steps_per_second": 6.249,
+      "step": 410
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.09086626023054123,
+      "learning_rate": 0.00096,
+      "loss": 0.6933,
+      "step": 820
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6933804750442505,
+      "eval_runtime": 3.45,
+      "eval_samples_per_second": 1583.494,
+      "eval_steps_per_second": 6.377,
+      "step": 820
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.12760137021541595,
+      "learning_rate": 0.00094,
+      "loss": 0.6933,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.69140625,
+      "eval_runtime": 3.4972,
+      "eval_samples_per_second": 1562.095,
+      "eval_steps_per_second": 6.291,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.01812651753425598,
+      "learning_rate": 0.00092,
+      "loss": 0.6931,
+      "step": 1640
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6933382749557495,
+      "eval_runtime": 3.4925,
+      "eval_samples_per_second": 1564.198,
+      "eval_steps_per_second": 6.299,
+      "step": 1640
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.051437895745038986,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.6932,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6934648156166077,
+      "eval_runtime": 3.4809,
+      "eval_samples_per_second": 1569.414,
+      "eval_steps_per_second": 6.32,
+      "step": 2050
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.05455218255519867,
+      "learning_rate": 0.00088,
+      "loss": 0.6932,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6933382749557495,
+      "eval_runtime": 3.5969,
+      "eval_samples_per_second": 1518.792,
+      "eval_steps_per_second": 6.116,
+      "step": 2460
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.06181074306368828,
+      "learning_rate": 0.00086,
+      "loss": 0.6933,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5053999633900788,
+      "eval_loss": 0.6932539343833923,
+      "eval_runtime": 3.6153,
+      "eval_samples_per_second": 1511.066,
+      "eval_steps_per_second": 6.085,
+      "step": 2870
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.13051092624664307,
+      "learning_rate": 0.00084,
+      "loss": 0.6934,
+      "step": 3280
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.4946000366099213,
+      "eval_loss": 0.6934226751327515,
+      "eval_runtime": 3.4839,
+      "eval_samples_per_second": 1568.091,
+      "eval_steps_per_second": 6.315,
+      "step": 3280
+    },
+    {
+      "epoch": 8.0,
+      "step": 3280,
+      "total_flos": 1.1023616508628992e+17,
+      "train_loss": 0.6958369836574647,
+      "train_runtime": 1397.9533,
+      "train_samples_per_second": 3746.298,
+      "train_steps_per_second": 14.664
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20500,
+  "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": 1.1023616508628992e+17,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}