End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/tiny_bert_rand_100_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: tiny_bert_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: 0.6838235294117647
+    - name: F1
+      type: f1
+      value: 0.7968503937007874
 ---
 
 <!-- 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_100_v2_mrpc
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_rand_100_v2](https://huggingface.co/Hartunka/tiny_bert_rand_100_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_100_v2](https://huggingface.co/Hartunka/tiny_bert_rand_100_v2) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0011
-- Accuracy: 0.625
-- F1: 0.7193
-- Combined Score: 0.6721
+- Loss: 0.5936
+- Accuracy: 0.6838
+- F1: 0.7969
+- Combined Score: 0.7403
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.740336961556276,
+    "eval_f1": 0.7968503937007874,
+    "eval_loss": 0.5935776829719543,
+    "eval_runtime": 0.156,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2614.887,
+    "eval_steps_per_second": 12.818,
+    "total_flos": 673316591603712.0,
+    "train_loss": 0.4635904698144822,
+    "train_runtime": 19.9755,
+    "train_samples": 3668,
+    "train_samples_per_second": 9181.264,
+    "train_steps_per_second": 37.546
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.740336961556276,
+    "eval_f1": 0.7968503937007874,
+    "eval_loss": 0.5935776829719543,
+    "eval_runtime": 0.156,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2614.887,
+    "eval_steps_per_second": 12.818
+}

logs/events.out.tfevents.1745321049.s_005_m.2850172.57

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:909bb39e0cb131f0fe27b2c7667e9a6b018d4d23ce5f4a6f623e6f94c77ec965
+size 459

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 673316591603712.0,
+    "train_loss": 0.4635904698144822,
+    "train_runtime": 19.9755,
+    "train_samples": 3668,
+    "train_samples_per_second": 9181.264,
+    "train_steps_per_second": 37.546
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 30,
+  "best_metric": 0.5935776829719543,
+  "best_model_checkpoint": "tiny_bert_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": 0.6582110524177551,
+      "learning_rate": 4.9e-05,
+      "loss": 0.627,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6985294117647058,
+      "eval_combined_score": 0.7545035348499954,
+      "eval_f1": 0.810477657935285,
+      "eval_loss": 0.6092624068260193,
+      "eval_runtime": 0.1324,
+      "eval_samples_per_second": 3080.744,
+      "eval_steps_per_second": 15.102,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1468154191970825,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5922,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.740336961556276,
+      "eval_f1": 0.7968503937007874,
+      "eval_loss": 0.5935776829719543,
+      "eval_runtime": 0.1385,
+      "eval_samples_per_second": 2945.235,
+      "eval_steps_per_second": 14.437,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.8627797961235046,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5576,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6862745098039216,
+      "eval_combined_score": 0.7440660474716203,
+      "eval_f1": 0.8018575851393189,
+      "eval_loss": 0.6135032773017883,
+      "eval_runtime": 0.1356,
+      "eval_samples_per_second": 3008.789,
+      "eval_steps_per_second": 14.749,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.542462110519409,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5114,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6348039215686274,
+      "eval_combined_score": 0.6727417666095564,
+      "eval_f1": 0.7106796116504854,
+      "eval_loss": 0.6668766736984253,
+      "eval_runtime": 0.1343,
+      "eval_samples_per_second": 3037.441,
+      "eval_steps_per_second": 14.889,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.4002983570098877,
+      "learning_rate": 4.5e-05,
+      "loss": 0.425,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6568627450980392,
+      "eval_combined_score": 0.7020775819353011,
+      "eval_f1": 0.7472924187725631,
+      "eval_loss": 0.7027082443237305,
+      "eval_runtime": 0.134,
+      "eval_samples_per_second": 3044.211,
+      "eval_steps_per_second": 14.923,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.386093616485596,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3145,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6372549019607843,
+      "eval_combined_score": 0.6815904139433551,
+      "eval_f1": 0.725925925925926,
+      "eval_loss": 0.8699068427085876,
+      "eval_runtime": 0.1332,
+      "eval_samples_per_second": 3064.085,
+      "eval_steps_per_second": 15.02,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 5.091856479644775,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2174,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.625,
+      "eval_combined_score": 0.6721330275229358,
+      "eval_f1": 0.7192660550458716,
+      "eval_loss": 1.0011260509490967,
+      "eval_runtime": 0.1461,
+      "eval_samples_per_second": 2792.042,
+      "eval_steps_per_second": 13.686,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "step": 105,
+      "total_flos": 673316591603712.0,
+      "train_loss": 0.4635904698144822,
+      "train_runtime": 19.9755,
+      "train_samples_per_second": 9181.264,
+      "train_steps_per_second": 37.546
+    }
+  ],
+  "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
+}