End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_olda_book_10_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_tiny_olda_book_10_v1_qqp
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QQP
+      type: glue
+      args: qqp
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8799901063566659
+    - name: F1
+      type: f1
+      value: 0.841251145138071
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_tiny_olda_book_10_v1_qqp
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_olda_book_10_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_olda_book_10_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_olda_book_10_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_olda_book_10_v1) on the GLUE QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3817
-- Accuracy: 0.8864
-- F1: 0.8520
-- Combined Score: 0.8692
+- Loss: 0.2816
+- Accuracy: 0.8800
+- F1: 0.8413
+- Combined Score: 0.8606
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.8799901063566659,
+    "eval_combined_score": 0.8606206257473684,
+    "eval_f1": 0.841251145138071,
+    "eval_loss": 0.2816171944141388,
+    "eval_runtime": 8.7095,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 4642.071,
+    "eval_steps_per_second": 18.141,
+    "total_flos": 7.633075201391002e+16,
+    "train_loss": 0.19880325113503072,
+    "train_runtime": 1177.802,
+    "train_samples": 363846,
+    "train_samples_per_second": 15445.975,
+    "train_steps_per_second": 60.367
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.8799901063566659,
+    "eval_combined_score": 0.8606206257473684,
+    "eval_f1": 0.841251145138071,
+    "eval_loss": 0.2816171944141388,
+    "eval_runtime": 8.7095,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 4642.071,
+    "eval_steps_per_second": 18.141
+}

logs/events.out.tfevents.1739306330.ki-g0009.35827.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87ce2d410740dd92d9632d2e5282fc9272fe23d411d347e1561d1ad80ec640f8
+size 515

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 7.633075201391002e+16,
+    "train_loss": 0.19880325113503072,
+    "train_runtime": 1177.802,
+    "train_samples": 363846,
+    "train_samples_per_second": 15445.975,
+    "train_steps_per_second": 60.367
+}

trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.2816171944141388,
+  "best_model_checkpoint": "bert_tiny_olda_book_10_v1_qqp/checkpoint-4266",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 11376,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.653726100921631,
+      "learning_rate": 4.9e-05,
+      "loss": 0.3941,
+      "step": 1422
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8495671531041306,
+      "eval_combined_score": 0.8165937373603761,
+      "eval_f1": 0.7836203216166217,
+      "eval_loss": 0.336513489484787,
+      "eval_runtime": 8.7955,
+      "eval_samples_per_second": 4596.684,
+      "eval_steps_per_second": 17.964,
+      "step": 1422
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.036668300628662,
+      "learning_rate": 4.8e-05,
+      "loss": 0.2912,
+      "step": 2844
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.871036359139253,
+      "eval_combined_score": 0.8516432680452716,
+      "eval_f1": 0.8322501769512901,
+      "eval_loss": 0.2904755473136902,
+      "eval_runtime": 8.7935,
+      "eval_samples_per_second": 4597.69,
+      "eval_steps_per_second": 17.968,
+      "step": 2844
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.329303741455078,
+      "learning_rate": 4.7e-05,
+      "loss": 0.2365,
+      "step": 4266
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8799901063566659,
+      "eval_combined_score": 0.8606206257473684,
+      "eval_f1": 0.841251145138071,
+      "eval_loss": 0.2816171944141388,
+      "eval_runtime": 8.738,
+      "eval_samples_per_second": 4626.891,
+      "eval_steps_per_second": 18.082,
+      "step": 4266
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.775084495544434,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.1917,
+      "step": 5688
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8807073954983923,
+      "eval_combined_score": 0.8578104836468514,
+      "eval_f1": 0.8349135717953107,
+      "eval_loss": 0.29652276635169983,
+      "eval_runtime": 8.7166,
+      "eval_samples_per_second": 4638.258,
+      "eval_steps_per_second": 18.126,
+      "step": 5688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.788520812988281,
+      "learning_rate": 4.5e-05,
+      "loss": 0.157,
+      "step": 7110
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8831313381152609,
+      "eval_combined_score": 0.8652846319584087,
+      "eval_f1": 0.8474379258015563,
+      "eval_loss": 0.30863726139068604,
+      "eval_runtime": 8.6769,
+      "eval_samples_per_second": 4659.482,
+      "eval_steps_per_second": 18.209,
+      "step": 7110
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.376418352127075,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1268,
+      "step": 8532
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8849121939154093,
+      "eval_combined_score": 0.8672451571846468,
+      "eval_f1": 0.8495781204538843,
+      "eval_loss": 0.32399794459342957,
+      "eval_runtime": 8.6806,
+      "eval_samples_per_second": 4657.523,
+      "eval_steps_per_second": 18.202,
+      "step": 8532
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.879223346710205,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1053,
+      "step": 9954
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8877813504823151,
+      "eval_combined_score": 0.8686826389052493,
+      "eval_f1": 0.8495839273281836,
+      "eval_loss": 0.35125985741615295,
+      "eval_runtime": 8.7172,
+      "eval_samples_per_second": 4637.939,
+      "eval_steps_per_second": 18.125,
+      "step": 9954
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.2115604877471924,
+      "learning_rate": 4.2e-05,
+      "loss": 0.0878,
+      "step": 11376
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8864457086322038,
+      "eval_combined_score": 0.8692007331332958,
+      "eval_f1": 0.8519557576343878,
+      "eval_loss": 0.38166430592536926,
+      "eval_runtime": 8.7563,
+      "eval_samples_per_second": 4617.233,
+      "eval_steps_per_second": 18.044,
+      "step": 11376
+    },
+    {
+      "epoch": 8.0,
+      "step": 11376,
+      "total_flos": 7.633075201391002e+16,
+      "train_loss": 0.19880325113503072,
+      "train_runtime": 1177.802,
+      "train_samples_per_second": 15445.975,
+      "train_steps_per_second": 60.367
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 71100,
+  "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": 7.633075201391002e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}