End of training

README.md

@@ -1,15 +1,33 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: gokulsrinivasagan/bert_base_train_book_ent_15p_s_init
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_base_train_book_ent_15p_s_init_qqp
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QQP
+      type: glue
+      args: qqp
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6318327974276527
+    - name: F1
+      type: f1
+      value: 0.0
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,9 +35,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_train_book_ent_15p_s_init_qqp
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_train_book_ent_15p_s_init](https://huggingface.co/gokulsrinivasagan/bert_base_train_book_ent_15p_s_init) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_train_book_ent_15p_s_init](https://huggingface.co/gokulsrinivasagan/bert_base_train_book_ent_15p_s_init) on the GLUE QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6590
+- Loss: 0.6573
 - Accuracy: 0.6318
 - F1: 0.0
 - Combined Score: 0.3159

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6318327974276527,
+    "eval_combined_score": 0.3159163987138264,
+    "eval_f1": 0.0,
+    "eval_loss": 0.6573427319526672,
+    "eval_runtime": 34.38,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 1175.976,
+    "eval_steps_per_second": 4.596,
+    "total_flos": 3.3506166766980096e+17,
+    "train_loss": 0.6601989145185039,
+    "train_runtime": 4731.6615,
+    "train_samples": 363846,
+    "train_samples_per_second": 3844.802,
+    "train_steps_per_second": 15.026
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6318327974276527,
+    "eval_combined_score": 0.3159163987138264,
+    "eval_f1": 0.0,
+    "eval_loss": 0.6573427319526672,
+    "eval_runtime": 34.38,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 1175.976,
+    "eval_steps_per_second": 4.596
+}

logs/events.out.tfevents.1745517795.ki-g0008.3436350.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93b18ffb68e5244cc9ef108852f1c96df423e20398d3a1cf8d82b9a601f37b99
+size 515

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 3.3506166766980096e+17,
+    "train_loss": 0.6601989145185039,
+    "train_runtime": 4731.6615,
+    "train_samples": 363846,
+    "train_samples_per_second": 3844.802,
+    "train_steps_per_second": 15.026
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 2844,
+  "best_metric": 0.6573427319526672,
+  "best_model_checkpoint": "bert_base_train_book_ent_15p_s_init_qqp/checkpoint-2844",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 9954,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.648533046245575,
+      "learning_rate": 4.900070323488045e-05,
+      "loss": 0.662,
+      "step": 1422
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": 0.6601884365081787,
+      "eval_runtime": 34.2195,
+      "eval_samples_per_second": 1181.489,
+      "eval_steps_per_second": 4.617,
+      "step": 1422
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5813120007514954,
+      "learning_rate": 4.800070323488045e-05,
+      "loss": 0.6607,
+      "step": 2844
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": 0.6573427319526672,
+      "eval_runtime": 34.3016,
+      "eval_samples_per_second": 1178.661,
+      "eval_steps_per_second": 4.606,
+      "step": 2844
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.8131640553474426,
+      "learning_rate": 4.700070323488045e-05,
+      "loss": 0.6602,
+      "step": 4266
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": 0.6596799492835999,
+      "eval_runtime": 34.56,
+      "eval_samples_per_second": 1169.851,
+      "eval_steps_per_second": 4.572,
+      "step": 4266
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.0145621299743652,
+      "learning_rate": 4.600070323488046e-05,
+      "loss": 0.6601,
+      "step": 5688
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": 0.6594805717468262,
+      "eval_runtime": 34.272,
+      "eval_samples_per_second": 1179.681,
+      "eval_steps_per_second": 4.61,
+      "step": 5688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.3845888376235962,
+      "learning_rate": 4.500070323488045e-05,
+      "loss": 0.6595,
+      "step": 7110
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": 0.6581591367721558,
+      "eval_runtime": 34.2181,
+      "eval_samples_per_second": 1181.539,
+      "eval_steps_per_second": 4.617,
+      "step": 7110
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.6148237586021423,
+      "learning_rate": 4.400070323488045e-05,
+      "loss": 0.6595,
+      "step": 8532
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": 0.6577509641647339,
+      "eval_runtime": 34.2003,
+      "eval_samples_per_second": 1182.154,
+      "eval_steps_per_second": 4.62,
+      "step": 8532
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.7319674491882324,
+      "learning_rate": 4.300070323488045e-05,
+      "loss": 0.6594,
+      "step": 9954
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": 0.6589756011962891,
+      "eval_runtime": 34.2685,
+      "eval_samples_per_second": 1179.802,
+      "eval_steps_per_second": 4.611,
+      "step": 9954
+    },
+    {
+      "epoch": 7.0,
+      "step": 9954,
+      "total_flos": 3.3506166766980096e+17,
+      "train_loss": 0.6601989145185039,
+      "train_runtime": 4731.6615,
+      "train_samples_per_second": 3844.802,
+      "train_steps_per_second": 15.026
+    }
+  ],
+  "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": 3.3506166766980096e+17,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}