End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_rand_20_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_base_rand_20_v1_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7132352941176471
+    - name: F1
+      type: f1
+      value: 0.7958115183246073
 ---
 
 <!-- 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_20_v1_mrpc
 
-This model is a fine-tuned version of [Hartunka/bert_base_rand_20_v1](https://huggingface.co/Hartunka/bert_base_rand_20_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_rand_20_v1](https://huggingface.co/Hartunka/bert_base_rand_20_v1) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2892
-- Accuracy: 0.6618
-- F1: 0.7579
-- Combined Score: 0.7098
+- Loss: 0.5873
+- Accuracy: 0.7132
+- F1: 0.7958
+- Combined Score: 0.7545
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7132352941176471,
+    "eval_combined_score": 0.7545234062211272,
+    "eval_f1": 0.7958115183246073,
+    "eval_loss": 0.5872540473937988,
+    "eval_runtime": 0.3093,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1319.213,
+    "eval_steps_per_second": 6.467,
+    "total_flos": 3377819728711680.0,
+    "train_loss": 0.364438449768793,
+    "train_runtime": 57.7707,
+    "train_samples": 3668,
+    "train_samples_per_second": 3174.621,
+    "train_steps_per_second": 12.982
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7132352941176471,
+    "eval_combined_score": 0.7545234062211272,
+    "eval_f1": 0.7958115183246073,
+    "eval_loss": 0.5872540473937988,
+    "eval_runtime": 0.3093,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1319.213,
+    "eval_steps_per_second": 6.467
+}

logs/events.out.tfevents.1745147459.s_005_m.2796520.75

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21d60dee06760bcae731947d1f2121997410999fce625f69679c5cf7fd99315f
+size 459

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 3377819728711680.0,
+    "train_loss": 0.364438449768793,
+    "train_runtime": 57.7707,
+    "train_samples": 3668,
+    "train_samples_per_second": 3174.621,
+    "train_steps_per_second": 12.982
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 30,
+  "best_metric": 0.5872540473937988,
+  "best_model_checkpoint": "bert_base_rand_20_v1_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": 1.3199914693832397,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6376,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6911764705882353,
+      "eval_combined_score": 0.7459046909903202,
+      "eval_f1": 0.8006329113924051,
+      "eval_loss": 0.5899849534034729,
+      "eval_runtime": 0.2702,
+      "eval_samples_per_second": 1509.81,
+      "eval_steps_per_second": 7.401,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3427537679672241,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5782,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7132352941176471,
+      "eval_combined_score": 0.7545234062211272,
+      "eval_f1": 0.7958115183246073,
+      "eval_loss": 0.5872540473937988,
+      "eval_runtime": 0.2746,
+      "eval_samples_per_second": 1485.532,
+      "eval_steps_per_second": 7.282,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.3142318725585938,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5004,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7156862745098039,
+      "eval_combined_score": 0.7571486928104576,
+      "eval_f1": 0.7986111111111112,
+      "eval_loss": 0.5992395877838135,
+      "eval_runtime": 0.2778,
+      "eval_samples_per_second": 1468.862,
+      "eval_steps_per_second": 7.2,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.0415451526641846,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3709,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6936274509803921,
+      "eval_combined_score": 0.7329703739419264,
+      "eval_f1": 0.7723132969034608,
+      "eval_loss": 0.7209315299987793,
+      "eval_runtime": 0.2701,
+      "eval_samples_per_second": 1510.583,
+      "eval_steps_per_second": 7.405,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.19972562789917,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2326,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6813725490196079,
+      "eval_combined_score": 0.7212009803921569,
+      "eval_f1": 0.7610294117647058,
+      "eval_loss": 0.9644837975502014,
+      "eval_runtime": 0.2862,
+      "eval_samples_per_second": 1425.69,
+      "eval_steps_per_second": 6.989,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.0243194103240967,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1352,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.678921568627451,
+      "eval_combined_score": 0.7239405021267766,
+      "eval_f1": 0.7689594356261023,
+      "eval_loss": 1.1714582443237305,
+      "eval_runtime": 0.3123,
+      "eval_samples_per_second": 1306.239,
+      "eval_steps_per_second": 6.403,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 6.661202430725098,
+      "learning_rate": 4.3e-05,
+      "loss": 0.0961,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6617647058823529,
+      "eval_combined_score": 0.7098297213622291,
+      "eval_f1": 0.7578947368421053,
+      "eval_loss": 1.289219617843628,
+      "eval_runtime": 0.2745,
+      "eval_samples_per_second": 1486.328,
+      "eval_steps_per_second": 7.286,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "step": 105,
+      "total_flos": 3377819728711680.0,
+      "train_loss": 0.364438449768793,
+      "train_runtime": 57.7707,
+      "train_samples_per_second": 3174.621,
+      "train_steps_per_second": 12.982
+    }
+  ],
+  "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
+}