End of training

README.md

@@ -1,14 +1,29 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: google/bert_uncased_L-2_H-128_A-2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_uncased_L-2_H-128_A-2_qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8004759289767527
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_uncased_L-2_H-128_A-2_qnli
 
-This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on an unknown dataset.
+This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4981
-- Accuracy: 0.7842
+- Loss: 0.4352
+- Accuracy: 0.8005
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 12.0,
+    "eval_accuracy": 0.8004759289767527,
+    "eval_loss": 0.43515709042549133,
+    "eval_runtime": 1.8126,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 3013.979,
+    "eval_steps_per_second": 12.138,
+    "total_flos": 798447744184320.0,
+    "train_loss": 0.40839064063095465,
+    "train_runtime": 496.9363,
+    "train_samples": 104743,
+    "train_samples_per_second": 10538.875,
+    "train_steps_per_second": 41.253
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 12.0,
+    "eval_accuracy": 0.8004759289767527,
+    "eval_loss": 0.43515709042549133,
+    "eval_runtime": 1.8126,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 3013.979,
+    "eval_steps_per_second": 12.138
+}

logs/events.out.tfevents.1733343833.ki-g0008.1759256.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:502b841a6a92e48da29363e0561032086492979b8b41592d21e9e616748829dd
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 12.0,
+    "total_flos": 798447744184320.0,
+    "train_loss": 0.40839064063095465,
+    "train_runtime": 496.9363,
+    "train_samples": 104743,
+    "train_samples_per_second": 10538.875,
+    "train_steps_per_second": 41.253
+}

trainer_state.json

@@ -0,0 +1,243 @@
+{
+  "best_metric": 0.43515709042549133,
+  "best_model_checkpoint": "bert_uncased_L-2_H-128_A-2_qnli/checkpoint-2870",
+  "epoch": 12.0,
+  "eval_steps": 500,
+  "global_step": 4920,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.511760950088501,
+      "learning_rate": 4.9e-05,
+      "loss": 0.5442,
+      "step": 410
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.767893099029837,
+      "eval_loss": 0.4932023286819458,
+      "eval_runtime": 1.826,
+      "eval_samples_per_second": 2991.779,
+      "eval_steps_per_second": 12.048,
+      "step": 410
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.8159499168396,
+      "learning_rate": 4.8e-05,
+      "loss": 0.4861,
+      "step": 820
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7691744462749405,
+      "eval_loss": 0.4810234010219574,
+      "eval_runtime": 1.8114,
+      "eval_samples_per_second": 3015.851,
+      "eval_steps_per_second": 12.145,
+      "step": 820
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.060815811157227,
+      "learning_rate": 4.7e-05,
+      "loss": 0.4609,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7882116053450485,
+      "eval_loss": 0.45270103216171265,
+      "eval_runtime": 1.7984,
+      "eval_samples_per_second": 3037.631,
+      "eval_steps_per_second": 12.233,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.754549264907837,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4422,
+      "step": 1640
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7803404722679846,
+      "eval_loss": 0.4639158546924591,
+      "eval_runtime": 1.8537,
+      "eval_samples_per_second": 2947.02,
+      "eval_steps_per_second": 11.868,
+      "step": 1640
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.4434049129486084,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4256,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7770455793520044,
+      "eval_loss": 0.47440072894096375,
+      "eval_runtime": 1.7223,
+      "eval_samples_per_second": 3171.84,
+      "eval_steps_per_second": 12.773,
+      "step": 2050
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.349808692932129,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.409,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7808896210873146,
+      "eval_loss": 0.4701761305332184,
+      "eval_runtime": 1.7288,
+      "eval_samples_per_second": 3160.033,
+      "eval_steps_per_second": 12.726,
+      "step": 2460
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.3617963790893555,
+      "learning_rate": 4.3e-05,
+      "loss": 0.392,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8004759289767527,
+      "eval_loss": 0.43515709042549133,
+      "eval_runtime": 1.775,
+      "eval_samples_per_second": 3077.761,
+      "eval_steps_per_second": 12.394,
+      "step": 2870
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 4.656054973602295,
+      "learning_rate": 4.2e-05,
+      "loss": 0.3772,
+      "step": 3280
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7969979864543292,
+      "eval_loss": 0.4428509771823883,
+      "eval_runtime": 1.7207,
+      "eval_samples_per_second": 3174.797,
+      "eval_steps_per_second": 12.785,
+      "step": 3280
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 4.831632614135742,
+      "learning_rate": 4.1e-05,
+      "loss": 0.3608,
+      "step": 3690
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7874794069192751,
+      "eval_loss": 0.4629783034324646,
+      "eval_runtime": 1.7551,
+      "eval_samples_per_second": 3112.654,
+      "eval_steps_per_second": 12.535,
+      "step": 3690
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 4.578758716583252,
+      "learning_rate": 4e-05,
+      "loss": 0.3459,
+      "step": 4100
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7688083470620538,
+      "eval_loss": 0.5137489438056946,
+      "eval_runtime": 1.9152,
+      "eval_samples_per_second": 2852.478,
+      "eval_steps_per_second": 11.487,
+      "step": 4100
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 6.495868682861328,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.3354,
+      "step": 4510
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.7880285557386052,
+      "eval_loss": 0.48358291387557983,
+      "eval_runtime": 1.7898,
+      "eval_samples_per_second": 3052.237,
+      "eval_steps_per_second": 12.292,
+      "step": 4510
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 5.4473795890808105,
+      "learning_rate": 3.8e-05,
+      "loss": 0.3213,
+      "step": 4920
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.7841845140032949,
+      "eval_loss": 0.4980739951133728,
+      "eval_runtime": 1.8138,
+      "eval_samples_per_second": 3011.856,
+      "eval_steps_per_second": 12.129,
+      "step": 4920
+    },
+    {
+      "epoch": 12.0,
+      "step": 4920,
+      "total_flos": 798447744184320.0,
+      "train_loss": 0.40839064063095465,
+      "train_runtime": 496.9363,
+      "train_samples_per_second": 10538.875,
+      "train_steps_per_second": 41.253
+    }
+  ],
+  "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": 798447744184320.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}