End of training

README.md

@@ -1,14 +1,29 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: google/bert_uncased_L-4_H-256_A-4
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_uncased_L-4_H-256_A-4_qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8412959912136189
 ---
 
 <!-- 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-4_H-256_A-4_qnli
 
-This model is a fine-tuned version of [google/bert_uncased_L-4_H-256_A-4](https://huggingface.co/google/bert_uncased_L-4_H-256_A-4) on an unknown dataset.
+This model is a fine-tuned version of [google/bert_uncased_L-4_H-256_A-4](https://huggingface.co/google/bert_uncased_L-4_H-256_A-4) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4672
-- Accuracy: 0.8365
+- Loss: 0.3597
+- Accuracy: 0.8413
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.8412959912136189,
+    "eval_loss": 0.35965824127197266,
+    "eval_runtime": 1.913,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 2855.764,
+    "eval_steps_per_second": 11.5,
+    "total_flos": 4151943714742272.0,
+    "train_loss": 0.32248923138874336,
+    "train_runtime": 408.6184,
+    "train_samples": 104743,
+    "train_samples_per_second": 12816.725,
+    "train_steps_per_second": 50.169
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.8412959912136189,
+    "eval_loss": 0.35965824127197266,
+    "eval_runtime": 1.913,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 2855.764,
+    "eval_steps_per_second": 11.5
+}

logs/events.out.tfevents.1733330802.ki-g0008.1761130.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b74d22eccb1043cf944b82ef54cbc9afd266712d3eeba380d0295f522e9b3b
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 4151943714742272.0,
+    "train_loss": 0.32248923138874336,
+    "train_runtime": 408.6184,
+    "train_samples": 104743,
+    "train_samples_per_second": 12816.725,
+    "train_steps_per_second": 50.169
+}

trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": 0.35965824127197266,
+  "best_model_checkpoint": "bert_uncased_L-4_H-256_A-4_qnli/checkpoint-1230",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 3280,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.336244106292725,
+      "learning_rate": 4.9e-05,
+      "loss": 0.4733,
+      "step": 410
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8301299652205748,
+      "eval_loss": 0.3914959132671356,
+      "eval_runtime": 1.867,
+      "eval_samples_per_second": 2926.104,
+      "eval_steps_per_second": 11.784,
+      "step": 410
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.451577663421631,
+      "learning_rate": 4.8e-05,
+      "loss": 0.4054,
+      "step": 820
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8372688998718653,
+      "eval_loss": 0.3684421479701996,
+      "eval_runtime": 1.9519,
+      "eval_samples_per_second": 2798.797,
+      "eval_steps_per_second": 11.271,
+      "step": 820
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.1921000480651855,
+      "learning_rate": 4.7e-05,
+      "loss": 0.3655,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8412959912136189,
+      "eval_loss": 0.35965824127197266,
+      "eval_runtime": 1.94,
+      "eval_samples_per_second": 2816.032,
+      "eval_steps_per_second": 11.34,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.697085380554199,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3295,
+      "step": 1640
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8383671975105254,
+      "eval_loss": 0.3784671127796173,
+      "eval_runtime": 2.0609,
+      "eval_samples_per_second": 2650.759,
+      "eval_steps_per_second": 10.675,
+      "step": 1640
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.71102237701416,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2935,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8383671975105254,
+      "eval_loss": 0.38417768478393555,
+      "eval_runtime": 1.9381,
+      "eval_samples_per_second": 2818.791,
+      "eval_steps_per_second": 11.352,
+      "step": 2050
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.5562968254089355,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2649,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.838184147904082,
+      "eval_loss": 0.40549930930137634,
+      "eval_runtime": 1.9053,
+      "eval_samples_per_second": 2867.244,
+      "eval_steps_per_second": 11.547,
+      "step": 2460
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.949692249298096,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2359,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8332418085301116,
+      "eval_loss": 0.4253882169723511,
+      "eval_runtime": 1.9373,
+      "eval_samples_per_second": 2819.861,
+      "eval_steps_per_second": 11.356,
+      "step": 2870
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 9.953798294067383,
+      "learning_rate": 4.2e-05,
+      "loss": 0.212,
+      "step": 3280
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8365367014460919,
+      "eval_loss": 0.46724265813827515,
+      "eval_runtime": 1.9425,
+      "eval_samples_per_second": 2812.307,
+      "eval_steps_per_second": 11.325,
+      "step": 3280
+    },
+    {
+      "epoch": 8.0,
+      "step": 3280,
+      "total_flos": 4151943714742272.0,
+      "train_loss": 0.32248923138874336,
+      "train_runtime": 408.6184,
+      "train_samples_per_second": 12816.725,
+      "train_steps_per_second": 50.169
+    }
+  ],
+  "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": 4151943714742272.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}