End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/tiny_bert_rand_5_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: tiny_bert_rand_5_v2_qqp
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QQP
+      type: glue
+      args: qqp
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8146178580262181
+    - name: F1
+      type: f1
+      value: 0.7371558828686656
 ---
 
 <!-- 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. -->
 
 # tiny_bert_rand_5_v2_qqp
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_rand_5_v2](https://huggingface.co/Hartunka/tiny_bert_rand_5_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_5_v2](https://huggingface.co/Hartunka/tiny_bert_rand_5_v2) on the GLUE QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5373
-- Accuracy: 0.8273
-- F1: 0.7644
-- Combined Score: 0.7959
+- Loss: 0.4161
+- Accuracy: 0.8146
+- F1: 0.7372
+- Combined Score: 0.7759
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.8146178580262181,
+    "eval_combined_score": 0.7758868704474419,
+    "eval_f1": 0.7371558828686656,
+    "eval_loss": 0.4161389470100403,
+    "eval_runtime": 11.4834,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 3520.736,
+    "eval_steps_per_second": 13.759,
+    "total_flos": 7.633075201391002e+16,
+    "train_loss": 0.30389826006024195,
+    "train_runtime": 1605.4025,
+    "train_samples": 363846,
+    "train_samples_per_second": 11331.925,
+    "train_steps_per_second": 44.288
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.8146178580262181,
+    "eval_combined_score": 0.7758868704474419,
+    "eval_f1": 0.7371558828686656,
+    "eval_loss": 0.4161389470100403,
+    "eval_runtime": 11.4834,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 3520.736,
+    "eval_steps_per_second": 13.759
+}

logs/events.out.tfevents.1745295128.s_005_m.2836625.97

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51ae01d6c09dccaf342333168e1a105d1e12a1ce63740b6953ab11564b766071
+size 467

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 7.633075201391002e+16,
+    "train_loss": 0.30389826006024195,
+    "train_runtime": 1605.4025,
+    "train_samples": 363846,
+    "train_samples_per_second": 11331.925,
+    "train_steps_per_second": 44.288
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_global_step": 4266,
+  "best_metric": 0.4161389470100403,
+  "best_model_checkpoint": "tiny_bert_rand_5_v2_qqp/checkpoint-4266",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 11376,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.7300523519515991,
+      "learning_rate": 4.9e-05,
+      "loss": 0.4948,
+      "step": 1422
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7834776156319565,
+      "eval_combined_score": 0.7347445466968965,
+      "eval_f1": 0.6860114777618365,
+      "eval_loss": 0.44807204604148865,
+      "eval_runtime": 11.998,
+      "eval_samples_per_second": 3369.732,
+      "eval_steps_per_second": 13.169,
+      "step": 1422
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.451735734939575,
+      "learning_rate": 4.8e-05,
+      "loss": 0.4052,
+      "step": 2844
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8023497402918625,
+      "eval_combined_score": 0.7576325672898148,
+      "eval_f1": 0.7129153942877672,
+      "eval_loss": 0.42114099860191345,
+      "eval_runtime": 11.4595,
+      "eval_samples_per_second": 3528.079,
+      "eval_steps_per_second": 13.788,
+      "step": 2844
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.203301429748535,
+      "learning_rate": 4.7e-05,
+      "loss": 0.3464,
+      "step": 4266
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8146178580262181,
+      "eval_combined_score": 0.7758868704474419,
+      "eval_f1": 0.7371558828686656,
+      "eval_loss": 0.4161389470100403,
+      "eval_runtime": 11.4612,
+      "eval_samples_per_second": 3527.559,
+      "eval_steps_per_second": 13.786,
+      "step": 4266
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.619699239730835,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.2996,
+      "step": 5688
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8190699975265892,
+      "eval_combined_score": 0.7806998865719529,
+      "eval_f1": 0.7423297756173166,
+      "eval_loss": 0.4293212294578552,
+      "eval_runtime": 12.0834,
+      "eval_samples_per_second": 3345.917,
+      "eval_steps_per_second": 13.076,
+      "step": 5688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.874742269515991,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2623,
+      "step": 7110
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8209992579767499,
+      "eval_combined_score": 0.789118259695161,
+      "eval_f1": 0.7572372614135722,
+      "eval_loss": 0.43629372119903564,
+      "eval_runtime": 11.5402,
+      "eval_samples_per_second": 3503.407,
+      "eval_steps_per_second": 13.691,
+      "step": 7110
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.806262731552124,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2317,
+      "step": 8532
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8217907494434825,
+      "eval_combined_score": 0.7909998776671268,
+      "eval_f1": 0.7602090058907711,
+      "eval_loss": 0.45417508482933044,
+      "eval_runtime": 11.5347,
+      "eval_samples_per_second": 3505.072,
+      "eval_steps_per_second": 13.698,
+      "step": 8532
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.6159353256225586,
+      "learning_rate": 4.3e-05,
+      "loss": 0.207,
+      "step": 9954
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8216423447934702,
+      "eval_combined_score": 0.7933131060407725,
+      "eval_f1": 0.7649838672880749,
+      "eval_loss": 0.4872119724750519,
+      "eval_runtime": 11.5245,
+      "eval_samples_per_second": 3508.174,
+      "eval_steps_per_second": 13.71,
+      "step": 9954
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.678138494491577,
+      "learning_rate": 4.2e-05,
+      "loss": 0.184,
+      "step": 11376
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8273311897106109,
+      "eval_combined_score": 0.7958507637890484,
+      "eval_f1": 0.7643703378674858,
+      "eval_loss": 0.5372677445411682,
+      "eval_runtime": 11.4885,
+      "eval_samples_per_second": 3519.164,
+      "eval_steps_per_second": 13.753,
+      "step": 11376
+    },
+    {
+      "epoch": 8.0,
+      "step": 11376,
+      "total_flos": 7.633075201391002e+16,
+      "train_loss": 0.30389826006024195,
+      "train_runtime": 1605.4025,
+      "train_samples_per_second": 11331.925,
+      "train_steps_per_second": 44.288
+    }
+  ],
+  "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": 7.633075201391002e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}