End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_km_20_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_km_20_v2_qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6293245469522241
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_km_20_v2_qnli
 
-This model is a fine-tuned version of [Hartunka/bert_base_km_20_v2](https://huggingface.co/Hartunka/bert_base_km_20_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_km_20_v2](https://huggingface.co/Hartunka/bert_base_km_20_v2) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9490
-- Accuracy: 0.6443
+- Loss: 0.6412
+- Accuracy: 0.6293
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.6293245469522241,
+    "eval_loss": 0.6411793231964111,
+    "eval_runtime": 3.4701,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 1574.315,
+    "eval_steps_per_second": 6.34,
+    "total_flos": 8.267712381471744e+16,
+    "train_loss": 0.4771146355605707,
+    "train_runtime": 1039.7534,
+    "train_samples": 104743,
+    "train_samples_per_second": 5036.915,
+    "train_steps_per_second": 19.716
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.6293245469522241,
+    "eval_loss": 0.6411793231964111,
+    "eval_runtime": 3.4701,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 1574.315,
+    "eval_steps_per_second": 6.34
+}

logs/events.out.tfevents.1745294238.s_005_m.2836894.41

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae2acc774c45ba123b4ee83b065391d75ee1c61098dff136088be19da062c81e
+size 363

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 8.267712381471744e+16,
+    "train_loss": 0.4771146355605707,
+    "train_runtime": 1039.7534,
+    "train_samples": 104743,
+    "train_samples_per_second": 5036.915,
+    "train_steps_per_second": 19.716
+}

trainer_state.json

@@ -0,0 +1,148 @@
+{
+  "best_global_step": 410,
+  "best_metric": 0.6411793231964111,
+  "best_model_checkpoint": "bert_base_km_20_v2_qnli/checkpoint-410",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 2460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.804979681968689,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6649,
+      "step": 410
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6293245469522241,
+      "eval_loss": 0.6411793231964111,
+      "eval_runtime": 3.4619,
+      "eval_samples_per_second": 1578.034,
+      "eval_steps_per_second": 6.355,
+      "step": 410
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7831207513809204,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6275,
+      "step": 820
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6415888705839282,
+      "eval_loss": 0.6414221525192261,
+      "eval_runtime": 3.4274,
+      "eval_samples_per_second": 1593.916,
+      "eval_steps_per_second": 6.419,
+      "step": 820
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.2202813625335693,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5633,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6231008603331503,
+      "eval_loss": 0.6846280694007874,
+      "eval_runtime": 3.4529,
+      "eval_samples_per_second": 1582.135,
+      "eval_steps_per_second": 6.371,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.440066337585449,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4529,
+      "step": 1640
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6436024162548051,
+      "eval_loss": 0.7028859853744507,
+      "eval_runtime": 3.4448,
+      "eval_samples_per_second": 1585.874,
+      "eval_steps_per_second": 6.386,
+      "step": 1640
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 7.325146675109863,
+      "learning_rate": 4.5e-05,
+      "loss": 0.328,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6346329855390811,
+      "eval_loss": 0.7875908017158508,
+      "eval_runtime": 3.4063,
+      "eval_samples_per_second": 1603.806,
+      "eval_steps_per_second": 6.459,
+      "step": 2050
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 6.193163871765137,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2262,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6443346146805784,
+      "eval_loss": 0.9489961862564087,
+      "eval_runtime": 3.4487,
+      "eval_samples_per_second": 1584.054,
+      "eval_steps_per_second": 6.379,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "step": 2460,
+      "total_flos": 8.267712381471744e+16,
+      "train_loss": 0.4771146355605707,
+      "train_runtime": 1039.7534,
+      "train_samples_per_second": 5036.915,
+      "train_steps_per_second": 19.716
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20500,
+  "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": 8.267712381471744e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}