End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/tiny_bert_rand_5_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: tiny_bert_rand_5_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: 0.7058823529411765
+    - name: F1
+      type: f1
+      value: 0.8119122257053292
 ---
 
 <!-- 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_v1_mrpc
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_rand_5_v1](https://huggingface.co/Hartunka/tiny_bert_rand_5_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_5_v1](https://huggingface.co/Hartunka/tiny_bert_rand_5_v1) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8375
-- Accuracy: 0.7108
-- F1: 0.7966
-- Combined Score: 0.7537
+- Loss: 0.5841
+- Accuracy: 0.7059
+- F1: 0.8119
+- Combined Score: 0.7589
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7058823529411765,
+    "eval_combined_score": 0.7588972893232528,
+    "eval_f1": 0.8119122257053292,
+    "eval_loss": 0.5841196179389954,
+    "eval_runtime": 0.1406,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2900.91,
+    "eval_steps_per_second": 14.22,
+    "total_flos": 673316591603712.0,
+    "train_loss": 0.46603998910813105,
+    "train_runtime": 20.2822,
+    "train_samples": 3668,
+    "train_samples_per_second": 9042.414,
+    "train_steps_per_second": 36.978
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7058823529411765,
+    "eval_combined_score": 0.7588972893232528,
+    "eval_f1": 0.8119122257053292,
+    "eval_loss": 0.5841196179389954,
+    "eval_runtime": 0.1406,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2900.91,
+    "eval_steps_per_second": 14.22
+}

logs/events.out.tfevents.1744642985.s_005_m.2701049.57

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:896896b7103e34561c587099bac212291fc2f9eb57f19c250d8536c0e8bde77f
+size 459

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 673316591603712.0,
+    "train_loss": 0.46603998910813105,
+    "train_runtime": 20.2822,
+    "train_samples": 3668,
+    "train_samples_per_second": 9042.414,
+    "train_steps_per_second": 36.978
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 30,
+  "best_metric": 0.5841196179389954,
+  "best_model_checkpoint": "tiny_bert_rand_5_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": 0.7388980984687805,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6249,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_combined_score": 0.7606334841628959,
+      "eval_f1": 0.8153846153846154,
+      "eval_loss": 0.5954541563987732,
+      "eval_runtime": 0.1354,
+      "eval_samples_per_second": 3013.176,
+      "eval_steps_per_second": 14.77,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.493939995765686,
+      "learning_rate": 4.8e-05,
+      "loss": 0.585,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_combined_score": 0.7588972893232528,
+      "eval_f1": 0.8119122257053292,
+      "eval_loss": 0.5841196179389954,
+      "eval_runtime": 0.1408,
+      "eval_samples_per_second": 2898.493,
+      "eval_steps_per_second": 14.208,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.9635825157165527,
+      "learning_rate": 4.7e-05,
+      "loss": 0.547,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_combined_score": 0.7606334841628959,
+      "eval_f1": 0.8153846153846154,
+      "eval_loss": 0.5992072820663452,
+      "eval_runtime": 0.1638,
+      "eval_samples_per_second": 2491.274,
+      "eval_steps_per_second": 12.212,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.4762623310089111,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5109,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.696078431372549,
+      "eval_combined_score": 0.7377189309887656,
+      "eval_f1": 0.7793594306049823,
+      "eval_loss": 0.607634961605072,
+      "eval_runtime": 0.1497,
+      "eval_samples_per_second": 2725.895,
+      "eval_steps_per_second": 13.362,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.124079465866089,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4274,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7009803921568627,
+      "eval_combined_score": 0.744218419074947,
+      "eval_f1": 0.7874564459930313,
+      "eval_loss": 0.6408296227455139,
+      "eval_runtime": 0.1462,
+      "eval_samples_per_second": 2791.55,
+      "eval_steps_per_second": 13.684,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.5391898155212402,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.33,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6642156862745098,
+      "eval_combined_score": 0.7091275917907558,
+      "eval_f1": 0.7540394973070018,
+      "eval_loss": 0.7433287501335144,
+      "eval_runtime": 0.1462,
+      "eval_samples_per_second": 2791.25,
+      "eval_steps_per_second": 13.683,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.578379154205322,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2371,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7107843137254902,
+      "eval_combined_score": 0.7536680189317106,
+      "eval_f1": 0.7965517241379311,
+      "eval_loss": 0.8374699354171753,
+      "eval_runtime": 0.1537,
+      "eval_samples_per_second": 2654.104,
+      "eval_steps_per_second": 13.01,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "step": 105,
+      "total_flos": 673316591603712.0,
+      "train_loss": 0.46603998910813105,
+      "train_runtime": 20.2822,
+      "train_samples_per_second": 9042.414,
+      "train_steps_per_second": 36.978
+    }
+  ],
+  "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
+}