End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_rand_5_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_rand_5_v2_mnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6677176566314077
 ---
 
 <!-- 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_5_v2_mnli
 
-This model is a fine-tuned version of [Hartunka/bert_base_rand_5_v2](https://huggingface.co/Hartunka/bert_base_rand_5_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_rand_5_v2](https://huggingface.co/Hartunka/bert_base_rand_5_v2) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1639
-- Accuracy: 0.6609
+- Loss: 0.8059
+- Accuracy: 0.6677
 
 ## Model description
 

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 10.0,
+    "epoch_mm": 10.0,
+    "eval_accuracy": 0.6625573102394294,
+    "eval_accuracy_mm": 0.6677176566314077,
+    "eval_loss": 0.8058387637138367,
+    "eval_loss_mm": 0.8059132099151611,
+    "eval_runtime": 6.2028,
+    "eval_runtime_mm": 6.3195,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 1582.339,
+    "eval_samples_per_second_mm": 1555.808,
+    "eval_steps_per_second": 6.287,
+    "eval_steps_per_second_mm": 6.171,
+    "total_flos": 5.166258268431053e+17,
+    "train_loss": 0.6249743345974321,
+    "train_runtime": 6473.467,
+    "train_samples": 392702,
+    "train_samples_per_second": 3033.166,
+    "train_steps_per_second": 11.848
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "epoch_mm": 10.0,
+    "eval_accuracy": 0.6625573102394294,
+    "eval_accuracy_mm": 0.6677176566314077,
+    "eval_loss": 0.8058387637138367,
+    "eval_loss_mm": 0.8059132099151611,
+    "eval_runtime": 6.2028,
+    "eval_runtime_mm": 6.3195,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 1582.339,
+    "eval_samples_per_second_mm": 1555.808,
+    "eval_steps_per_second": 6.287,
+    "eval_steps_per_second_mm": 6.171
+}

logs/events.out.tfevents.1745469261.s_005_m.2892304.35

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb7127830a43026a90fd62ee38b8973b48c1fe01f55ee128ab107b21c71ec238
+size 686

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 5.166258268431053e+17,
+    "train_loss": 0.6249743345974321,
+    "train_runtime": 6473.467,
+    "train_samples": 392702,
+    "train_samples_per_second": 3033.166,
+    "train_steps_per_second": 11.848
+}

trainer_state.json

@@ -0,0 +1,212 @@
+{
+  "best_global_step": 7670,
+  "best_metric": 0.8058387637138367,
+  "best_model_checkpoint": "bert_base_rand_5_v2_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": 1.162489891052246,
+      "learning_rate": 4.9e-05,
+      "loss": 0.9841,
+      "step": 1534
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5655629139072847,
+      "eval_loss": 0.916408121585846,
+      "eval_runtime": 6.3023,
+      "eval_samples_per_second": 1557.363,
+      "eval_steps_per_second": 6.188,
+      "step": 1534
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.748944878578186,
+      "learning_rate": 4.8e-05,
+      "loss": 0.8816,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6031584309730005,
+      "eval_loss": 0.863948404788971,
+      "eval_runtime": 6.2592,
+      "eval_samples_per_second": 1568.093,
+      "eval_steps_per_second": 6.231,
+      "step": 3068
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.7005038261413574,
+      "learning_rate": 4.7e-05,
+      "loss": 0.802,
+      "step": 4602
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6224146714212939,
+      "eval_loss": 0.833983302116394,
+      "eval_runtime": 6.3985,
+      "eval_samples_per_second": 1533.944,
+      "eval_steps_per_second": 6.095,
+      "step": 4602
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.3252110481262207,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.7236,
+      "step": 6136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6466632705043301,
+      "eval_loss": 0.8122609257698059,
+      "eval_runtime": 6.399,
+      "eval_samples_per_second": 1533.828,
+      "eval_steps_per_second": 6.095,
+      "step": 6136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.2816672325134277,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6505,
+      "step": 7670
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6625573102394294,
+      "eval_loss": 0.8058387637138367,
+      "eval_runtime": 6.399,
+      "eval_samples_per_second": 1533.842,
+      "eval_steps_per_second": 6.095,
+      "step": 7670
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.778917074203491,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.5786,
+      "step": 9204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6624554253693327,
+      "eval_loss": 0.8320516347885132,
+      "eval_runtime": 6.4081,
+      "eval_samples_per_second": 1531.652,
+      "eval_steps_per_second": 6.086,
+      "step": 9204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.788456439971924,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5046,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6595007641365257,
+      "eval_loss": 0.8853159546852112,
+      "eval_runtime": 6.4161,
+      "eval_samples_per_second": 1529.748,
+      "eval_steps_per_second": 6.078,
+      "step": 10738
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.967282295227051,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4363,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.658380030565461,
+      "eval_loss": 0.9629728198051453,
+      "eval_runtime": 6.4118,
+      "eval_samples_per_second": 1530.769,
+      "eval_steps_per_second": 6.083,
+      "step": 12272
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 4.872507572174072,
+      "learning_rate": 4.1e-05,
+      "loss": 0.3721,
+      "step": 13806
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.650127356087621,
+      "eval_loss": 1.041638731956482,
+      "eval_runtime": 6.2088,
+      "eval_samples_per_second": 1580.814,
+      "eval_steps_per_second": 6.281,
+      "step": 13806
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 4.8294453620910645,
+      "learning_rate": 4e-05,
+      "loss": 0.3164,
+      "step": 15340
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6609271523178808,
+      "eval_loss": 1.1638540029525757,
+      "eval_runtime": 6.2489,
+      "eval_samples_per_second": 1570.688,
+      "eval_steps_per_second": 6.241,
+      "step": 15340
+    },
+    {
+      "epoch": 10.0,
+      "step": 15340,
+      "total_flos": 5.166258268431053e+17,
+      "train_loss": 0.6249743345974321,
+      "train_runtime": 6473.467,
+      "train_samples_per_second": 3033.166,
+      "train_steps_per_second": 11.848
+    }
+  ],
+  "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
+}