End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/tiny_bert_rand_5_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: tiny_bert_rand_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: 0.00705908192371065
+    - name: Accuracy
+      type: accuracy
+      value: 0.6855225563049316
 ---
 
 <!-- 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_rand_5_v2_cola
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_rand_5_v2](https://huggingface.co/Hartunka/tiny_bert_rand_5_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_5_v2](https://huggingface.co/Hartunka/tiny_bert_rand_5_v2) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7743
-- Matthews Correlation: 0.0624
-- Accuracy: 0.6232
+- Loss: 0.6145
+- Matthews Correlation: 0.0071
+- Accuracy: 0.6855
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.6855225563049316,
+    "eval_loss": 0.6145429015159607,
+    "eval_matthews_correlation": 0.00705908192371065,
+    "eval_runtime": 0.335,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 3112.989,
+    "eval_steps_per_second": 14.923,
+    "total_flos": 1793902531485696.0,
+    "train_loss": 0.5206848488134497,
+    "train_runtime": 46.5092,
+    "train_samples": 8551,
+    "train_samples_per_second": 9192.807,
+    "train_steps_per_second": 36.552
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.6855225563049316,
+    "eval_loss": 0.6145429015159607,
+    "eval_matthews_correlation": 0.00705908192371065,
+    "eval_runtime": 0.335,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 3112.989,
+    "eval_steps_per_second": 14.923
+}

logs/events.out.tfevents.1745292946.s_005_m.2836625.91

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51ac656de8cbe0e635c596bcf6fa0ac45c4f5eb4d6cdbd11f9679b410bad68b4
+size 427

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 1793902531485696.0,
+    "train_loss": 0.5206848488134497,
+    "train_runtime": 46.5092,
+    "train_samples": 8551,
+    "train_samples_per_second": 9192.807,
+    "train_steps_per_second": 36.552
+}

trainer_state.json

@@ -0,0 +1,188 @@
+{
+  "best_global_step": 102,
+  "best_metric": 0.6145429015159607,
+  "best_model_checkpoint": "tiny_bert_rand_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": 0.8452883362770081,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6181,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6160077452659607,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3718,
+      "eval_samples_per_second": 2805.608,
+      "eval_steps_per_second": 13.45,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8655800819396973,
+      "learning_rate": 4.8e-05,
+      "loss": 0.603,
+      "step": 68
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6145668029785156,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3713,
+      "eval_samples_per_second": 2809.048,
+      "eval_steps_per_second": 13.466,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.1405643224716187,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5863,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6855225563049316,
+      "eval_loss": 0.6145429015159607,
+      "eval_matthews_correlation": 0.00705908192371065,
+      "eval_runtime": 0.3536,
+      "eval_samples_per_second": 2949.298,
+      "eval_steps_per_second": 14.139,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.808847188949585,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5473,
+      "step": 136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6874400973320007,
+      "eval_loss": 0.6423367857933044,
+      "eval_matthews_correlation": 0.10902881882069253,
+      "eval_runtime": 0.3704,
+      "eval_samples_per_second": 2815.547,
+      "eval_steps_per_second": 13.497,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.500699758529663,
+      "learning_rate": 4.5e-05,
+      "loss": 0.5062,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.666347086429596,
+      "eval_loss": 0.6451377272605896,
+      "eval_matthews_correlation": 0.10306039540521846,
+      "eval_runtime": 0.3793,
+      "eval_samples_per_second": 2749.921,
+      "eval_steps_per_second": 13.183,
+      "step": 170
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.465254068374634,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.4682,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6596356630325317,
+      "eval_loss": 0.705679714679718,
+      "eval_matthews_correlation": 0.09426976277858662,
+      "eval_runtime": 0.3315,
+      "eval_samples_per_second": 3146.266,
+      "eval_steps_per_second": 15.083,
+      "step": 204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.8560423851013184,
+      "learning_rate": 4.3e-05,
+      "loss": 0.4321,
+      "step": 238
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6356663703918457,
+      "eval_loss": 0.751916229724884,
+      "eval_matthews_correlation": 0.09149005382699188,
+      "eval_runtime": 0.3112,
+      "eval_samples_per_second": 3351.864,
+      "eval_steps_per_second": 16.068,
+      "step": 238
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.6627018451690674,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4043,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6232023239135742,
+      "eval_loss": 0.774285078048706,
+      "eval_matthews_correlation": 0.0624246376945414,
+      "eval_runtime": 0.3429,
+      "eval_samples_per_second": 3041.373,
+      "eval_steps_per_second": 14.58,
+      "step": 272
+    },
+    {
+      "epoch": 8.0,
+      "step": 272,
+      "total_flos": 1793902531485696.0,
+      "train_loss": 0.5206848488134497,
+      "train_runtime": 46.5092,
+      "train_samples_per_second": 9192.807,
+      "train_steps_per_second": 36.552
+    }
+  ],
+  "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
+}