End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/tiny_bert_rand_50_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: tiny_bert_rand_50_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: 0.6124839831594362
 ---
 
 <!-- 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_50_v2_qnli
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_rand_50_v2](https://huggingface.co/Hartunka/tiny_bert_rand_50_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_50_v2](https://huggingface.co/Hartunka/tiny_bert_rand_50_v2) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9106
-- Accuracy: 0.6110
+- Loss: 0.6521
+- Accuracy: 0.6125
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.6124839831594362,
+    "eval_loss": 0.6520935893058777,
+    "eval_runtime": 1.6136,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 3385.561,
+    "eval_steps_per_second": 13.634,
+    "total_flos": 1.6480417453111296e+16,
+    "train_loss": 0.5487746634134432,
+    "train_runtime": 343.7213,
+    "train_samples": 104743,
+    "train_samples_per_second": 15236.618,
+    "train_steps_per_second": 59.641
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.6124839831594362,
+    "eval_loss": 0.6520935893058777,
+    "eval_runtime": 1.6136,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 3385.561,
+    "eval_steps_per_second": 13.634
+}

logs/events.out.tfevents.1745316843.s_005_m.2850172.41

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22f4c7ff464e7b46700354cfa1db4cce230c8da13c5a1e45f5adad0ead43394b
+size 363

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 1.6480417453111296e+16,
+    "train_loss": 0.5487746634134432,
+    "train_runtime": 343.7213,
+    "train_samples": 104743,
+    "train_samples_per_second": 15236.618,
+    "train_steps_per_second": 59.641
+}

trainer_state.json

@@ -0,0 +1,148 @@
+{
+  "best_global_step": 410,
+  "best_metric": 0.6520935893058777,
+  "best_model_checkpoint": "tiny_bert_rand_50_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": 1.406223177909851,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6655,
+      "step": 410
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6124839831594362,
+      "eval_loss": 0.6520935893058777,
+      "eval_runtime": 1.6245,
+      "eval_samples_per_second": 3362.889,
+      "eval_steps_per_second": 13.543,
+      "step": 410
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.5263471603393555,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6359,
+      "step": 820
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6188907193849533,
+      "eval_loss": 0.6523372530937195,
+      "eval_runtime": 1.5602,
+      "eval_samples_per_second": 3501.394,
+      "eval_steps_per_second": 14.1,
+      "step": 820
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.781379461288452,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5935,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6203551162365001,
+      "eval_loss": 0.6675785779953003,
+      "eval_runtime": 1.5826,
+      "eval_samples_per_second": 3451.962,
+      "eval_steps_per_second": 13.901,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.04308819770813,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5338,
+      "step": 1640
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6214534138751602,
+      "eval_loss": 0.7060788869857788,
+      "eval_runtime": 1.5593,
+      "eval_samples_per_second": 3503.427,
+      "eval_steps_per_second": 14.109,
+      "step": 1640
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.421135425567627,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4667,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6157788760754165,
+      "eval_loss": 0.7881438732147217,
+      "eval_runtime": 1.5868,
+      "eval_samples_per_second": 3442.677,
+      "eval_steps_per_second": 13.864,
+      "step": 2050
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.98477029800415,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3973,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6110195863078894,
+      "eval_loss": 0.9105799794197083,
+      "eval_runtime": 1.5608,
+      "eval_samples_per_second": 3500.038,
+      "eval_steps_per_second": 14.095,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "step": 2460,
+      "total_flos": 1.6480417453111296e+16,
+      "train_loss": 0.5487746634134432,
+      "train_runtime": 343.7213,
+      "train_samples_per_second": 15236.618,
+      "train_steps_per_second": 59.641
+    }
+  ],
+  "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": 1.6480417453111296e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}