End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/tiny_bert_rand_50_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: tiny_bert_rand_50_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: 0.6985294117647058
+    - name: F1
+      type: f1
+      value: 0.8098918083462133
 ---
 
 <!-- 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_50_v2_mrpc
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_rand_50_v2](https://huggingface.co/Hartunka/tiny_bert_rand_50_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_50_v2](https://huggingface.co/Hartunka/tiny_bert_rand_50_v2) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9303
-- Accuracy: 0.6740
-- F1: 0.7734
-- Combined Score: 0.7237
+- Loss: 0.5925
+- Accuracy: 0.6985
+- F1: 0.8099
+- Combined Score: 0.7542
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6985294117647058,
+    "eval_combined_score": 0.7542106100554595,
+    "eval_f1": 0.8098918083462133,
+    "eval_loss": 0.5925365090370178,
+    "eval_runtime": 0.1745,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2338.055,
+    "eval_steps_per_second": 11.461,
+    "total_flos": 673316591603712.0,
+    "train_loss": 0.4740510032290504,
+    "train_runtime": 20.1601,
+    "train_samples": 3668,
+    "train_samples_per_second": 9097.158,
+    "train_steps_per_second": 37.202
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6985294117647058,
+    "eval_combined_score": 0.7542106100554595,
+    "eval_f1": 0.8098918083462133,
+    "eval_loss": 0.5925365090370178,
+    "eval_runtime": 0.1745,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2338.055,
+    "eval_steps_per_second": 11.461
+}

logs/events.out.tfevents.1745316466.s_005_m.2850172.39

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fce36034ffcbd71be4b742f0fa8bb49393169b1cdca4263bb60f9718f544c16
+size 459

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 673316591603712.0,
+    "train_loss": 0.4740510032290504,
+    "train_runtime": 20.1601,
+    "train_samples": 3668,
+    "train_samples_per_second": 9097.158,
+    "train_steps_per_second": 37.202
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 30,
+  "best_metric": 0.5925365090370178,
+  "best_model_checkpoint": "tiny_bert_rand_50_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": 0.746475338935852,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6271,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.696078431372549,
+      "eval_combined_score": 0.7526546003016591,
+      "eval_f1": 0.8092307692307692,
+      "eval_loss": 0.6033073663711548,
+      "eval_runtime": 0.1315,
+      "eval_samples_per_second": 3102.082,
+      "eval_steps_per_second": 15.206,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.2179274559020996,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5912,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6985294117647058,
+      "eval_combined_score": 0.7542106100554595,
+      "eval_f1": 0.8098918083462133,
+      "eval_loss": 0.5925365090370178,
+      "eval_runtime": 0.1343,
+      "eval_samples_per_second": 3037.538,
+      "eval_steps_per_second": 14.89,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.8887869715690613,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5551,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6862745098039216,
+      "eval_combined_score": 0.7428237752781364,
+      "eval_f1": 0.799373040752351,
+      "eval_loss": 0.6018652319908142,
+      "eval_runtime": 0.1392,
+      "eval_samples_per_second": 2931.211,
+      "eval_steps_per_second": 14.369,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.3352513313293457,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5148,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6421568627450981,
+      "eval_combined_score": 0.6817654542733125,
+      "eval_f1": 0.7213740458015268,
+      "eval_loss": 0.6426445245742798,
+      "eval_runtime": 0.2016,
+      "eval_samples_per_second": 2023.814,
+      "eval_steps_per_second": 9.921,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.087498426437378,
+      "learning_rate": 4.5e-05,
+      "loss": 0.43,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6225490196078431,
+      "eval_combined_score": 0.6665376676986584,
+      "eval_f1": 0.7105263157894737,
+      "eval_loss": 0.6741282343864441,
+      "eval_runtime": 0.1361,
+      "eval_samples_per_second": 2998.698,
+      "eval_steps_per_second": 14.7,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.535114765167236,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3406,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6372549019607843,
+      "eval_combined_score": 0.6897075903532144,
+      "eval_f1": 0.7421602787456446,
+      "eval_loss": 0.8507905006408691,
+      "eval_runtime": 0.1912,
+      "eval_samples_per_second": 2134.365,
+      "eval_steps_per_second": 10.463,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.9563608169555664,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2595,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6740196078431373,
+      "eval_combined_score": 0.7237218993219094,
+      "eval_f1": 0.7734241908006815,
+      "eval_loss": 0.9303423762321472,
+      "eval_runtime": 0.1535,
+      "eval_samples_per_second": 2657.434,
+      "eval_steps_per_second": 13.027,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "step": 105,
+      "total_flos": 673316591603712.0,
+      "train_loss": 0.4740510032290504,
+      "train_runtime": 20.1601,
+      "train_samples_per_second": 9097.158,
+      "train_steps_per_second": 37.202
+    }
+  ],
+  "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": 673316591603712.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}