End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/tiny_bert_rand_20_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: tiny_bert_rand_20_v2_rte
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5703971119133574
 ---
 
 <!-- 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. -->
 
 # tiny_bert_rand_20_v2_rte
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_rand_20_v2](https://huggingface.co/Hartunka/tiny_bert_rand_20_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_20_v2](https://huggingface.co/Hartunka/tiny_bert_rand_20_v2) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1315
-- Accuracy: 0.4982
+- Loss: 0.6859
+- Accuracy: 0.5704
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.5703971119133574,
+    "eval_loss": 0.6859487891197205,
+    "eval_runtime": 0.1259,
+    "eval_samples": 277,
+    "eval_samples_per_second": 2199.6,
+    "eval_steps_per_second": 15.882,
+    "total_flos": 457076966492160.0,
+    "train_loss": 0.595053608076913,
+    "train_runtime": 15.2908,
+    "train_samples": 2490,
+    "train_samples_per_second": 8142.147,
+    "train_steps_per_second": 32.699
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.5703971119133574,
+    "eval_loss": 0.6859487891197205,
+    "eval_runtime": 0.1259,
+    "eval_samples": 277,
+    "eval_samples_per_second": 2199.6,
+    "eval_steps_per_second": 15.882
+}

logs/events.out.tfevents.1745313879.s_005_m.2850172.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9721a4aa81b486a42ca76be9f2035bbd3933ccee8ea50c347709edd5dff99a7
+size 357

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 457076966492160.0,
+    "train_loss": 0.595053608076913,
+    "train_runtime": 15.2908,
+    "train_samples": 2490,
+    "train_samples_per_second": 8142.147,
+    "train_steps_per_second": 32.699
+}

trainer_state.json

@@ -0,0 +1,164 @@
+{
+  "best_global_step": 20,
+  "best_metric": 0.6859487891197205,
+  "best_model_checkpoint": "tiny_bert_rand_20_v2_rte/checkpoint-20",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 70,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.596297025680542,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6973,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5451263537906137,
+      "eval_loss": 0.6897563338279724,
+      "eval_runtime": 0.0983,
+      "eval_samples_per_second": 2818.254,
+      "eval_steps_per_second": 20.348,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6815950870513916,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6885,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5703971119133574,
+      "eval_loss": 0.6859487891197205,
+      "eval_runtime": 0.1168,
+      "eval_samples_per_second": 2371.569,
+      "eval_steps_per_second": 17.123,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5316508412361145,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6679,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5703971119133574,
+      "eval_loss": 0.7017534971237183,
+      "eval_runtime": 0.0972,
+      "eval_samples_per_second": 2848.546,
+      "eval_steps_per_second": 20.567,
+      "step": 30
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.6141400337219238,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6325,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5487364620938628,
+      "eval_loss": 0.7494218349456787,
+      "eval_runtime": 0.0989,
+      "eval_samples_per_second": 2802.11,
+      "eval_steps_per_second": 20.232,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.5151808261871338,
+      "learning_rate": 4.5e-05,
+      "loss": 0.58,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5379061371841155,
+      "eval_loss": 0.8294788002967834,
+      "eval_runtime": 0.1094,
+      "eval_samples_per_second": 2531.153,
+      "eval_steps_per_second": 18.275,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.656488060951233,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.5061,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.8910938501358032,
+      "eval_runtime": 0.1145,
+      "eval_samples_per_second": 2419.934,
+      "eval_steps_per_second": 17.472,
+      "step": 60
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.2175965309143066,
+      "learning_rate": 4.3e-05,
+      "loss": 0.3931,
+      "step": 70
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.4981949458483754,
+      "eval_loss": 1.1315115690231323,
+      "eval_runtime": 0.1083,
+      "eval_samples_per_second": 2556.99,
+      "eval_steps_per_second": 18.462,
+      "step": 70
+    },
+    {
+      "epoch": 7.0,
+      "step": 70,
+      "total_flos": 457076966492160.0,
+      "train_loss": 0.595053608076913,
+      "train_runtime": 15.2908,
+      "train_samples_per_second": 8142.147,
+      "train_steps_per_second": 32.699
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 500,
+  "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": 457076966492160.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}