End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_km_20_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: bert_base_km_20_v1_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. -->
 
 # bert_base_km_20_v1_cola
 
-This model is a fine-tuned version of [Hartunka/bert_base_km_20_v1](https://huggingface.co/Hartunka/bert_base_km_20_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_km_20_v1](https://huggingface.co/Hartunka/bert_base_km_20_v1) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8696
-- Matthews Correlation: 0.0963
-- Accuracy: 0.6366
+- Loss: 0.6226
+- Matthews Correlation: 0.0
+- Accuracy: 0.6913
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6225768327713013,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 0.6888,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 1514.181,
+    "eval_steps_per_second": 7.259,
+    "total_flos": 6749587903150080.0,
+    "train_loss": 0.484881274840411,
+    "train_runtime": 99.6839,
+    "train_samples": 8551,
+    "train_samples_per_second": 4289.056,
+    "train_steps_per_second": 17.054
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6225768327713013,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 0.6888,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 1514.181,
+    "eval_steps_per_second": 7.259
+}

logs/events.out.tfevents.1745028397.s_005_m.2780655.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbab77ef36fece1c46737dd832828f65f01a007ff6fbff7445bf5cbe6efaef5e
+size 427

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 6749587903150080.0,
+    "train_loss": 0.484881274840411,
+    "train_runtime": 99.6839,
+    "train_samples": 8551,
+    "train_samples_per_second": 4289.056,
+    "train_steps_per_second": 17.054
+}

trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_global_step": 34,
+  "best_metric": 0.6225768327713013,
+  "best_model_checkpoint": "bert_base_km_20_v1_cola/checkpoint-34",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 204,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3155686855316162,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6182,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6225768327713013,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7082,
+      "eval_samples_per_second": 1472.699,
+      "eval_steps_per_second": 7.06,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.696873426437378,
+      "learning_rate": 4.8e-05,
+      "loss": 0.591,
+      "step": 68
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6893576383590698,
+      "eval_loss": 0.6297030448913574,
+      "eval_matthews_correlation": 0.07656947466775693,
+      "eval_runtime": 0.6837,
+      "eval_samples_per_second": 1525.417,
+      "eval_steps_per_second": 7.313,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.9348201751708984,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5432,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6797698736190796,
+      "eval_loss": 0.6300162076950073,
+      "eval_matthews_correlation": 0.08088406701239864,
+      "eval_runtime": 0.6712,
+      "eval_samples_per_second": 1553.855,
+      "eval_steps_per_second": 7.449,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.5529346466064453,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4606,
+      "step": 136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6519654989242554,
+      "eval_loss": 0.6926795244216919,
+      "eval_matthews_correlation": 0.14975092131840292,
+      "eval_runtime": 0.6975,
+      "eval_samples_per_second": 1495.386,
+      "eval_steps_per_second": 7.169,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.714582681655884,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3815,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6567593216896057,
+      "eval_loss": 0.7553606033325195,
+      "eval_matthews_correlation": 0.09193331749307261,
+      "eval_runtime": 0.6706,
+      "eval_samples_per_second": 1555.292,
+      "eval_steps_per_second": 7.456,
+      "step": 170
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.6072070598602295,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3147,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6366251111030579,
+      "eval_loss": 0.8696136474609375,
+      "eval_matthews_correlation": 0.09631786888423775,
+      "eval_runtime": 0.6847,
+      "eval_samples_per_second": 1523.185,
+      "eval_steps_per_second": 7.302,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "step": 204,
+      "total_flos": 6749587903150080.0,
+      "train_loss": 0.484881274840411,
+      "train_runtime": 99.6839,
+      "train_samples_per_second": 4289.056,
+      "train_steps_per_second": 17.054
+    }
+  ],
+  "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": 6749587903150080.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}