End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_rand_5_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_base_rand_5_v2_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7083333333333334
+    - name: F1
+      type: f1
+      value: 0.797274275979557
 ---
 
 <!-- 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_base_rand_5_v2_mrpc
 
-This model is a fine-tuned version of [Hartunka/bert_base_rand_5_v2](https://huggingface.co/Hartunka/bert_base_rand_5_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_rand_5_v2](https://huggingface.co/Hartunka/bert_base_rand_5_v2) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2410
-- Accuracy: 0.6863
-- F1: 0.7754
-- Combined Score: 0.7309
+- Loss: 0.5794
+- Accuracy: 0.7083
+- F1: 0.7973
+- Combined Score: 0.7528
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7083333333333334,
+    "eval_combined_score": 0.7528038046564451,
+    "eval_f1": 0.797274275979557,
+    "eval_loss": 0.5793828368186951,
+    "eval_runtime": 0.2953,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1381.715,
+    "eval_steps_per_second": 6.773,
+    "total_flos": 3377819728711680.0,
+    "train_loss": 0.3609652462459746,
+    "train_runtime": 59.4323,
+    "train_samples": 3668,
+    "train_samples_per_second": 3085.865,
+    "train_steps_per_second": 12.619
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7083333333333334,
+    "eval_combined_score": 0.7528038046564451,
+    "eval_f1": 0.797274275979557,
+    "eval_loss": 0.5793828368186951,
+    "eval_runtime": 0.2953,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1381.715,
+    "eval_steps_per_second": 6.773
+}

logs/events.out.tfevents.1745456039.s_005_m.2892304.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38e7095631eee6e521e8f674f6c270f0414322af49a65e06f8fbc0ecebd1ecb6
+size 459

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 3377819728711680.0,
+    "train_loss": 0.3609652462459746,
+    "train_runtime": 59.4323,
+    "train_samples": 3668,
+    "train_samples_per_second": 3085.865,
+    "train_steps_per_second": 12.619
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 30,
+  "best_metric": 0.5793828368186951,
+  "best_model_checkpoint": "bert_base_rand_5_v2_mrpc/checkpoint-30",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 105,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0964593887329102,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6383,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.678921568627451,
+      "eval_combined_score": 0.7311963215038082,
+      "eval_f1": 0.7834710743801653,
+      "eval_loss": 0.6041474938392639,
+      "eval_runtime": 0.2742,
+      "eval_samples_per_second": 1487.791,
+      "eval_steps_per_second": 7.293,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.5544981956481934,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5729,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7083333333333334,
+      "eval_combined_score": 0.7528038046564451,
+      "eval_f1": 0.797274275979557,
+      "eval_loss": 0.5793828368186951,
+      "eval_runtime": 0.2826,
+      "eval_samples_per_second": 1443.592,
+      "eval_steps_per_second": 7.076,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.8892422914505005,
+      "learning_rate": 4.7e-05,
+      "loss": 0.4918,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6985294117647058,
+      "eval_combined_score": 0.7455547564725722,
+      "eval_f1": 0.7925801011804384,
+      "eval_loss": 0.6017581820487976,
+      "eval_runtime": 0.2854,
+      "eval_samples_per_second": 1429.653,
+      "eval_steps_per_second": 7.008,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.4752492904663086,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3574,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7034313725490197,
+      "eval_combined_score": 0.7450137462392364,
+      "eval_f1": 0.7865961199294532,
+      "eval_loss": 0.6998467445373535,
+      "eval_runtime": 0.2899,
+      "eval_samples_per_second": 1407.306,
+      "eval_steps_per_second": 6.899,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.615607738494873,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2336,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.696078431372549,
+      "eval_combined_score": 0.7373249299719888,
+      "eval_f1": 0.7785714285714286,
+      "eval_loss": 0.8754630088806152,
+      "eval_runtime": 0.2825,
+      "eval_samples_per_second": 1444.27,
+      "eval_steps_per_second": 7.08,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 6.541562557220459,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1407,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6740196078431373,
+      "eval_combined_score": 0.7171899841017488,
+      "eval_f1": 0.7603603603603604,
+      "eval_loss": 1.1302683353424072,
+      "eval_runtime": 0.2888,
+      "eval_samples_per_second": 1412.857,
+      "eval_steps_per_second": 6.926,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 5.691794395446777,
+      "learning_rate": 4.3e-05,
+      "loss": 0.0921,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6862745098039216,
+      "eval_combined_score": 0.7308565531475748,
+      "eval_f1": 0.775438596491228,
+      "eval_loss": 1.2410293817520142,
+      "eval_runtime": 0.2854,
+      "eval_samples_per_second": 1429.474,
+      "eval_steps_per_second": 7.007,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "step": 105,
+      "total_flos": 3377819728711680.0,
+      "train_loss": 0.3609652462459746,
+      "train_runtime": 59.4323,
+      "train_samples_per_second": 3085.865,
+      "train_steps_per_second": 12.619
+    }
+  ],
+  "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": 3377819728711680.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}