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_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6838235294117647
+    - name: F1
+      type: f1
+      value: 0.8122270742358079
 ---
 
 <!-- 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_mrpc
 
-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 MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6260
+- Loss: 0.6236
 - Accuracy: 0.6838
 - F1: 0.8122
 - Combined Score: 0.7480

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 12.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.6236213445663452,
+    "eval_runtime": 0.42,
+    "eval_samples": 408,
+    "eval_samples_per_second": 971.447,
+    "eval_steps_per_second": 4.762,
+    "total_flos": 5790548106362880.0,
+    "train_loss": 0.6358856678009033,
+    "train_runtime": 111.4221,
+    "train_samples": 3668,
+    "train_samples_per_second": 1645.993,
+    "train_steps_per_second": 6.731
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 12.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 0.6236213445663452,
+    "eval_runtime": 0.42,
+    "eval_samples": 408,
+    "eval_samples_per_second": 971.447,
+    "eval_steps_per_second": 4.762
+}

logs/events.out.tfevents.1745511664.ki-g0008.3436350.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3cdc9f3440749029907b479b114c1a8d2dc577d80d346f2dc85082f840760ea
+size 515

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 12.0,
+    "total_flos": 5790548106362880.0,
+    "train_loss": 0.6358856678009033,
+    "train_runtime": 111.4221,
+    "train_samples": 3668,
+    "train_samples_per_second": 1645.993,
+    "train_steps_per_second": 6.731
+}

trainer_state.json

@@ -0,0 +1,268 @@
+{
+  "best_global_step": 105,
+  "best_metric": 0.6236213445663452,
+  "best_model_checkpoint": "bert_base_train_book_ent_15p_s_init_mrpc/checkpoint-105",
+  "epoch": 12.0,
+  "eval_steps": 500,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7837658524513245,
+      "learning_rate": 4.906666666666667e-05,
+      "loss": 0.6428,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6254978775978088,
+      "eval_runtime": 0.3699,
+      "eval_samples_per_second": 1102.979,
+      "eval_steps_per_second": 5.407,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.680393934249878,
+      "learning_rate": 4.806666666666667e-05,
+      "loss": 0.6363,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6296674013137817,
+      "eval_runtime": 0.3745,
+      "eval_samples_per_second": 1089.444,
+      "eval_steps_per_second": 5.34,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.3696545362472534,
+      "learning_rate": 4.706666666666667e-05,
+      "loss": 0.6317,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6300982236862183,
+      "eval_runtime": 0.3764,
+      "eval_samples_per_second": 1084.091,
+      "eval_steps_per_second": 5.314,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.9995052814483643,
+      "learning_rate": 4.606666666666667e-05,
+      "loss": 0.6411,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6254978775978088,
+      "eval_runtime": 0.3663,
+      "eval_samples_per_second": 1113.836,
+      "eval_steps_per_second": 5.46,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.5899142026901245,
+      "learning_rate": 4.5066666666666667e-05,
+      "loss": 0.6336,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6254308223724365,
+      "eval_runtime": 0.363,
+      "eval_samples_per_second": 1123.901,
+      "eval_steps_per_second": 5.509,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.0961157083511353,
+      "learning_rate": 4.406666666666667e-05,
+      "loss": 0.6348,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6238797903060913,
+      "eval_runtime": 0.3681,
+      "eval_samples_per_second": 1108.448,
+      "eval_steps_per_second": 5.434,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.8835726976394653,
+      "learning_rate": 4.3066666666666665e-05,
+      "loss": 0.6346,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6236213445663452,
+      "eval_runtime": 0.3895,
+      "eval_samples_per_second": 1047.538,
+      "eval_steps_per_second": 5.135,
+      "step": 105
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.5998325943946838,
+      "learning_rate": 4.206666666666667e-05,
+      "loss": 0.6364,
+      "step": 120
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6241862177848816,
+      "eval_runtime": 0.3699,
+      "eval_samples_per_second": 1102.886,
+      "eval_steps_per_second": 5.406,
+      "step": 120
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 1.0318900346755981,
+      "learning_rate": 4.106666666666667e-05,
+      "loss": 0.6309,
+      "step": 135
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6320992112159729,
+      "eval_runtime": 0.3664,
+      "eval_samples_per_second": 1113.41,
+      "eval_steps_per_second": 5.458,
+      "step": 135
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.612123429775238,
+      "learning_rate": 4.006666666666667e-05,
+      "loss": 0.6392,
+      "step": 150
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.624152660369873,
+      "eval_runtime": 0.378,
+      "eval_samples_per_second": 1079.327,
+      "eval_steps_per_second": 5.291,
+      "step": 150
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 1.4060471057891846,
+      "learning_rate": 3.906666666666667e-05,
+      "loss": 0.6353,
+      "step": 165
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6270584464073181,
+      "eval_runtime": 0.3649,
+      "eval_samples_per_second": 1118.136,
+      "eval_steps_per_second": 5.481,
+      "step": 165
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.859621524810791,
+      "learning_rate": 3.8066666666666666e-05,
+      "loss": 0.6339,
+      "step": 180
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 0.6259621381759644,
+      "eval_runtime": 0.3756,
+      "eval_samples_per_second": 1086.399,
+      "eval_steps_per_second": 5.325,
+      "step": 180
+    },
+    {
+      "epoch": 12.0,
+      "step": 180,
+      "total_flos": 5790548106362880.0,
+      "train_loss": 0.6358856678009033,
+      "train_runtime": 111.4221,
+      "train_samples_per_second": 1645.993,
+      "train_steps_per_second": 6.731
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 750,
+  "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": 5790548106362880.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}