End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/tiny_bert_km_5_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: tiny_bert_km_5_v2_cola
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.0
+    - name: Accuracy
+      type: accuracy
+      value: 0.6912751793861389
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,11 +34,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tiny_bert_km_5_v2_cola
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_km_5_v2](https://huggingface.co/Hartunka/tiny_bert_km_5_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_km_5_v2](https://huggingface.co/Hartunka/tiny_bert_km_5_v2) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7225
-- Matthews Correlation: 0.0664
-- Accuracy: 0.6433
+- Loss: 0.6132
+- Matthews Correlation: 0.0
+- Accuracy: 0.6913
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6132072806358337,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 0.3395,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 3072.424,
+    "eval_steps_per_second": 14.729,
+    "total_flos": 1793902531485696.0,
+    "train_loss": 0.5503367466085097,
+    "train_runtime": 45.4021,
+    "train_samples": 8551,
+    "train_samples_per_second": 9416.971,
+    "train_steps_per_second": 37.443
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6132072806358337,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 0.3395,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 3072.424,
+    "eval_steps_per_second": 14.729
+}

logs/events.out.tfevents.1745267843.s_005_m.2836251.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26438fc82a3ba3f83c389f5544ec4816cdb31dcd619c692249efeba7a13b6336
+size 427

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 1793902531485696.0,
+    "train_loss": 0.5503367466085097,
+    "train_runtime": 45.4021,
+    "train_samples": 8551,
+    "train_samples_per_second": 9416.971,
+    "train_steps_per_second": 37.443
+}

trainer_state.json

@@ -0,0 +1,188 @@
+{
+  "best_global_step": 102,
+  "best_metric": 0.6132072806358337,
+  "best_model_checkpoint": "tiny_bert_km_5_v2_cola/checkpoint-102",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 272,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7630343437194824,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6164,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6185938119888306,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.325,
+      "eval_samples_per_second": 3208.865,
+      "eval_steps_per_second": 15.383,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.778609037399292,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6071,
+      "step": 68
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6137447357177734,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3406,
+      "eval_samples_per_second": 3062.365,
+      "eval_steps_per_second": 14.681,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.3126204013824463,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6025,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6132072806358337,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3117,
+      "eval_samples_per_second": 3346.424,
+      "eval_steps_per_second": 16.042,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.9153343439102173,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5865,
+      "step": 136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6922339200973511,
+      "eval_loss": 0.6316416263580322,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 0.3269,
+      "eval_samples_per_second": 3190.096,
+      "eval_steps_per_second": 15.293,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.5319900512695312,
+      "learning_rate": 4.5e-05,
+      "loss": 0.5525,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7027804255485535,
+      "eval_loss": 0.6342248916625977,
+      "eval_matthews_correlation": 0.17712606131822545,
+      "eval_runtime": 0.3079,
+      "eval_samples_per_second": 3387.574,
+      "eval_steps_per_second": 16.24,
+      "step": 170
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.82542884349823,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.5122,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6318312287330627,
+      "eval_loss": 0.6609932780265808,
+      "eval_matthews_correlation": 0.08825845093702572,
+      "eval_runtime": 0.3339,
+      "eval_samples_per_second": 3123.819,
+      "eval_steps_per_second": 14.975,
+      "step": 204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.6594173908233643,
+      "learning_rate": 4.3e-05,
+      "loss": 0.4796,
+      "step": 238
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6778523325920105,
+      "eval_loss": 0.7212586998939514,
+      "eval_matthews_correlation": 0.07130170780284954,
+      "eval_runtime": 0.3491,
+      "eval_samples_per_second": 2987.563,
+      "eval_steps_per_second": 14.322,
+      "step": 238
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.2772269248962402,
+      "learning_rate": 4.2e-05,
+      "loss": 0.446,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6433365345001221,
+      "eval_loss": 0.7225203514099121,
+      "eval_matthews_correlation": 0.06635583278930876,
+      "eval_runtime": 0.3177,
+      "eval_samples_per_second": 3283.145,
+      "eval_steps_per_second": 15.739,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "step": 272,
+      "total_flos": 1793902531485696.0,
+      "train_loss": 0.5503367466085097,
+      "train_runtime": 45.4021,
+      "train_samples_per_second": 9416.971,
+      "train_steps_per_second": 37.443
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1700,
+  "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": 1793902531485696.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}