End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_rand_100_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: bert_base_rand_100_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: 0.696078431372549
+    - name: F1
+      type: f1
+      value: 0.7832167832167832
 ---
 
 <!-- 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_100_v2_mrpc
 
-This model is a fine-tuned version of [Hartunka/bert_base_rand_100_v2](https://huggingface.co/Hartunka/bert_base_rand_100_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_rand_100_v2](https://huggingface.co/Hartunka/bert_base_rand_100_v2) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3472
-- Accuracy: 0.6544
-- F1: 0.7413
-- Combined Score: 0.6978
+- Loss: 0.5916
+- Accuracy: 0.6961
+- F1: 0.7832
+- Combined Score: 0.7396
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.696078431372549,
+    "eval_combined_score": 0.739647607294666,
+    "eval_f1": 0.7832167832167832,
+    "eval_loss": 0.5916197896003723,
+    "eval_runtime": 0.2949,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1383.704,
+    "eval_steps_per_second": 6.783,
+    "total_flos": 3377819728711680.0,
+    "train_loss": 0.3715402500970023,
+    "train_runtime": 58.9919,
+    "train_samples": 3668,
+    "train_samples_per_second": 3108.901,
+    "train_steps_per_second": 12.714
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.696078431372549,
+    "eval_combined_score": 0.739647607294666,
+    "eval_f1": 0.7832167832167832,
+    "eval_loss": 0.5916197896003723,
+    "eval_runtime": 0.2949,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1383.704,
+    "eval_steps_per_second": 6.783
+}

logs/events.out.tfevents.1745511137.s_005_m.2892304.93

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5bd0a06463a93437a6d089f22f051567ad580c479857505d96b25246c69277b
+size 459

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 3377819728711680.0,
+    "train_loss": 0.3715402500970023,
+    "train_runtime": 58.9919,
+    "train_samples": 3668,
+    "train_samples_per_second": 3108.901,
+    "train_steps_per_second": 12.714
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 30,
+  "best_metric": 0.5916197896003723,
+  "best_model_checkpoint": "bert_base_rand_100_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": 1.281264305114746,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6254,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6764705882352942,
+      "eval_combined_score": 0.7331397527163732,
+      "eval_f1": 0.7898089171974523,
+      "eval_loss": 0.6039632558822632,
+      "eval_runtime": 0.2748,
+      "eval_samples_per_second": 1484.839,
+      "eval_steps_per_second": 7.279,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3976408243179321,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5783,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.696078431372549,
+      "eval_combined_score": 0.739647607294666,
+      "eval_f1": 0.7832167832167832,
+      "eval_loss": 0.5916197896003723,
+      "eval_runtime": 0.287,
+      "eval_samples_per_second": 1421.764,
+      "eval_steps_per_second": 6.969,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.8759346008300781,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5106,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7009803921568627,
+      "eval_combined_score": 0.7463946329384996,
+      "eval_f1": 0.7918088737201365,
+      "eval_loss": 0.6092804670333862,
+      "eval_runtime": 0.2935,
+      "eval_samples_per_second": 1390.011,
+      "eval_steps_per_second": 6.814,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.080292224884033,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3753,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6642156862745098,
+      "eval_combined_score": 0.7112965556593007,
+      "eval_f1": 0.7583774250440917,
+      "eval_loss": 0.7310943603515625,
+      "eval_runtime": 0.2812,
+      "eval_samples_per_second": 1450.786,
+      "eval_steps_per_second": 7.112,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.867292404174805,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2454,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6200980392156863,
+      "eval_combined_score": 0.6553584008453681,
+      "eval_f1": 0.6906187624750499,
+      "eval_loss": 1.023072600364685,
+      "eval_runtime": 0.2737,
+      "eval_samples_per_second": 1490.503,
+      "eval_steps_per_second": 7.306,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 8.217503547668457,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.158,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6200980392156863,
+      "eval_combined_score": 0.6559734728881612,
+      "eval_f1": 0.6918489065606361,
+      "eval_loss": 1.261865496635437,
+      "eval_runtime": 0.2788,
+      "eval_samples_per_second": 1463.421,
+      "eval_steps_per_second": 7.174,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.351443290710449,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1077,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6544117647058824,
+      "eval_combined_score": 0.6978480841878036,
+      "eval_f1": 0.7412844036697248,
+      "eval_loss": 1.3472307920455933,
+      "eval_runtime": 0.2766,
+      "eval_samples_per_second": 1475.05,
+      "eval_steps_per_second": 7.231,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "step": 105,
+      "total_flos": 3377819728711680.0,
+      "train_loss": 0.3715402500970023,
+      "train_runtime": 58.9919,
+      "train_samples_per_second": 3108.901,
+      "train_steps_per_second": 12.714
+    }
+  ],
+  "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
+}