End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/tiny_bert_rand_20_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: tiny_bert_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: 0.6936274509803921
+    - name: F1
+      type: f1
+      value: 0.8073959938366718
 ---
 
 <!-- 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_20_v1_mrpc
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_rand_20_v1](https://huggingface.co/Hartunka/tiny_bert_rand_20_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_20_v1](https://huggingface.co/Hartunka/tiny_bert_rand_20_v1) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9934
-- Accuracy: 0.6593
-- F1: 0.7495
-- Combined Score: 0.7044
+- Loss: 0.5944
+- Accuracy: 0.6936
+- F1: 0.8074
+- Combined Score: 0.7505
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6936274509803921,
+    "eval_combined_score": 0.750511722408532,
+    "eval_f1": 0.8073959938366718,
+    "eval_loss": 0.5944022536277771,
+    "eval_runtime": 0.1365,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2989.531,
+    "eval_steps_per_second": 14.655,
+    "total_flos": 673316591603712.0,
+    "train_loss": 0.42778842335655576,
+    "train_runtime": 20.3796,
+    "train_samples": 3668,
+    "train_samples_per_second": 8999.196,
+    "train_steps_per_second": 36.802
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6936274509803921,
+    "eval_combined_score": 0.750511722408532,
+    "eval_f1": 0.8073959938366718,
+    "eval_loss": 0.5944022536277771,
+    "eval_runtime": 0.1365,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2989.531,
+    "eval_steps_per_second": 14.655
+}

logs/events.out.tfevents.1744652255.s_005_m.2701049.93

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6683ff6c7824724d19d8f052c435462e11d9c7ca6575664134df937973e64f38
+size 459

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 673316591603712.0,
+    "train_loss": 0.42778842335655576,
+    "train_runtime": 20.3796,
+    "train_samples": 3668,
+    "train_samples_per_second": 8999.196,
+    "train_steps_per_second": 36.802
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 30,
+  "best_metric": 0.5944022536277771,
+  "best_model_checkpoint": "tiny_bert_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": 0.9935017824172974,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6234,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.696078431372549,
+      "eval_combined_score": 0.7505549389567148,
+      "eval_f1": 0.8050314465408805,
+      "eval_loss": 0.6027568578720093,
+      "eval_runtime": 0.1391,
+      "eval_samples_per_second": 2932.205,
+      "eval_steps_per_second": 14.374,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.6997376680374146,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5729,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6936274509803921,
+      "eval_combined_score": 0.750511722408532,
+      "eval_f1": 0.8073959938366718,
+      "eval_loss": 0.5944022536277771,
+      "eval_runtime": 0.1517,
+      "eval_samples_per_second": 2688.703,
+      "eval_steps_per_second": 13.18,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.3739608526229858,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5187,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6985294117647058,
+      "eval_combined_score": 0.7539158686730506,
+      "eval_f1": 0.8093023255813954,
+      "eval_loss": 0.6136234998703003,
+      "eval_runtime": 0.1551,
+      "eval_samples_per_second": 2631.36,
+      "eval_steps_per_second": 12.899,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.9833365678787231,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4667,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_combined_score": 0.7555385790679909,
+      "eval_f1": 0.8051948051948052,
+      "eval_loss": 0.6241942644119263,
+      "eval_runtime": 0.1447,
+      "eval_samples_per_second": 2819.352,
+      "eval_steps_per_second": 13.82,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.4283900260925293,
+      "learning_rate": 4.5e-05,
+      "loss": 0.372,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6764705882352942,
+      "eval_combined_score": 0.7220381110190555,
+      "eval_f1": 0.7676056338028169,
+      "eval_loss": 0.6986564993858337,
+      "eval_runtime": 0.1456,
+      "eval_samples_per_second": 2801.852,
+      "eval_steps_per_second": 13.735,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.3482108116149902,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2679,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6862745098039216,
+      "eval_combined_score": 0.7300630499549643,
+      "eval_f1": 0.773851590106007,
+      "eval_loss": 0.8146053552627563,
+      "eval_runtime": 0.1899,
+      "eval_samples_per_second": 2148.306,
+      "eval_steps_per_second": 10.531,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.3743345737457275,
+      "learning_rate": 4.3e-05,
+      "loss": 0.173,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6593137254901961,
+      "eval_combined_score": 0.7044316375198728,
+      "eval_f1": 0.7495495495495496,
+      "eval_loss": 0.9934117794036865,
+      "eval_runtime": 0.1543,
+      "eval_samples_per_second": 2643.408,
+      "eval_steps_per_second": 12.958,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "step": 105,
+      "total_flos": 673316591603712.0,
+      "train_loss": 0.42778842335655576,
+      "train_runtime": 20.3796,
+      "train_samples_per_second": 8999.196,
+      "train_steps_per_second": 36.802
+    }
+  ],
+  "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
+}