End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_rand_20_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_rand_20_v1_mnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6673108218063466
 ---
 
 <!-- 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. -->
 
 # bert_base_rand_20_v1_mnli
 
-This model is a fine-tuned version of [Hartunka/bert_base_rand_20_v1](https://huggingface.co/Hartunka/bert_base_rand_20_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_rand_20_v1](https://huggingface.co/Hartunka/bert_base_rand_20_v1) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1382
-- Accuracy: 0.6507
+- Loss: 0.7866
+- Accuracy: 0.6673
 
 ## Model description
 

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 10.0,
+    "epoch_mm": 10.0,
+    "eval_accuracy": 0.6617422312786552,
+    "eval_accuracy_mm": 0.6673108218063466,
+    "eval_loss": 0.7996456027030945,
+    "eval_loss_mm": 0.7866259217262268,
+    "eval_runtime": 6.1344,
+    "eval_runtime_mm": 6.1974,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 1599.984,
+    "eval_samples_per_second_mm": 1586.461,
+    "eval_steps_per_second": 6.358,
+    "eval_steps_per_second_mm": 6.293,
+    "total_flos": 5.166258268431053e+17,
+    "train_loss": 0.618427997773132,
+    "train_runtime": 6361.5043,
+    "train_samples": 392702,
+    "train_samples_per_second": 3086.55,
+    "train_steps_per_second": 12.057
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "epoch_mm": 10.0,
+    "eval_accuracy": 0.6617422312786552,
+    "eval_accuracy_mm": 0.6673108218063466,
+    "eval_loss": 0.7996456027030945,
+    "eval_loss_mm": 0.7866259217262268,
+    "eval_runtime": 6.1344,
+    "eval_runtime_mm": 6.1974,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 1599.984,
+    "eval_samples_per_second_mm": 1586.461,
+    "eval_steps_per_second": 6.358,
+    "eval_steps_per_second_mm": 6.293
+}

logs/events.out.tfevents.1745160477.s_005_m.2796520.89

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9c28e1853514c93b0f0294647a7865143fd0629229592d05fd0de76783c495
+size 686

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 5.166258268431053e+17,
+    "train_loss": 0.618427997773132,
+    "train_runtime": 6361.5043,
+    "train_samples": 392702,
+    "train_samples_per_second": 3086.55,
+    "train_steps_per_second": 12.057
+}

trainer_state.json

@@ -0,0 +1,212 @@
+{
+  "best_global_step": 7670,
+  "best_metric": 0.7996456027030945,
+  "best_model_checkpoint": "bert_base_rand_20_v1_mnli/checkpoint-7670",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 15340,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4270943403244019,
+      "learning_rate": 4.9e-05,
+      "loss": 0.9783,
+      "step": 1534
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.569332654100866,
+      "eval_loss": 0.9197439551353455,
+      "eval_runtime": 6.1778,
+      "eval_samples_per_second": 1588.757,
+      "eval_steps_per_second": 6.313,
+      "step": 1534
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.4544787406921387,
+      "learning_rate": 4.8e-05,
+      "loss": 0.8746,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6089658685685175,
+      "eval_loss": 0.8565420508384705,
+      "eval_runtime": 6.1223,
+      "eval_samples_per_second": 1603.168,
+      "eval_steps_per_second": 6.37,
+      "step": 3068
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.7756571769714355,
+      "learning_rate": 4.7e-05,
+      "loss": 0.7957,
+      "step": 4602
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6441161487519104,
+      "eval_loss": 0.8150185346603394,
+      "eval_runtime": 6.123,
+      "eval_samples_per_second": 1602.981,
+      "eval_steps_per_second": 6.369,
+      "step": 4602
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.0247035026550293,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.7173,
+      "step": 6136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6470708099847172,
+      "eval_loss": 0.8204519152641296,
+      "eval_runtime": 6.1456,
+      "eval_samples_per_second": 1597.076,
+      "eval_steps_per_second": 6.346,
+      "step": 6136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.3827614784240723,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6446,
+      "step": 7670
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6617422312786552,
+      "eval_loss": 0.7996456027030945,
+      "eval_runtime": 6.1393,
+      "eval_samples_per_second": 1598.706,
+      "eval_steps_per_second": 6.352,
+      "step": 7670
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.6881988048553467,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.5725,
+      "step": 9204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6644931227712685,
+      "eval_loss": 0.8414015769958496,
+      "eval_runtime": 6.1406,
+      "eval_samples_per_second": 1598.386,
+      "eval_steps_per_second": 6.351,
+      "step": 9204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.599024534225464,
+      "learning_rate": 4.3e-05,
+      "loss": 0.4995,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6592969943963322,
+      "eval_loss": 0.9118618369102478,
+      "eval_runtime": 6.1244,
+      "eval_samples_per_second": 1602.605,
+      "eval_steps_per_second": 6.368,
+      "step": 10738
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.8561458587646484,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4289,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6555272542027509,
+      "eval_loss": 0.9942179322242737,
+      "eval_runtime": 6.1281,
+      "eval_samples_per_second": 1601.65,
+      "eval_steps_per_second": 6.364,
+      "step": 12272
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 4.280539035797119,
+      "learning_rate": 4.1e-05,
+      "loss": 0.3647,
+      "step": 13806
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.648191543555782,
+      "eval_loss": 1.123213291168213,
+      "eval_runtime": 6.1617,
+      "eval_samples_per_second": 1592.912,
+      "eval_steps_per_second": 6.329,
+      "step": 13806
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 3.6000685691833496,
+      "learning_rate": 4e-05,
+      "loss": 0.3083,
+      "step": 15340
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6507386653082017,
+      "eval_loss": 1.138242483139038,
+      "eval_runtime": 6.1268,
+      "eval_samples_per_second": 1601.98,
+      "eval_steps_per_second": 6.365,
+      "step": 15340
+    },
+    {
+      "epoch": 10.0,
+      "step": 15340,
+      "total_flos": 5.166258268431053e+17,
+      "train_loss": 0.618427997773132,
+      "train_runtime": 6361.5043,
+      "train_samples_per_second": 3086.55,
+      "train_steps_per_second": 12.057
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 76700,
+  "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": 5.166258268431053e+17,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}