End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_rand_100_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_rand_100_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: 0.6743287225386493
 ---
 
 <!-- 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_100_v2_mnli
 
-This model is a fine-tuned version of [Hartunka/bert_base_rand_100_v2](https://huggingface.co/Hartunka/bert_base_rand_100_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_rand_100_v2](https://huggingface.co/Hartunka/bert_base_rand_100_v2) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0930
-- Accuracy: 0.6595
+- Loss: 0.7597
+- Accuracy: 0.6743
 
 ## Model description
 

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 9.0,
+    "epoch_mm": 9.0,
+    "eval_accuracy": 0.6661232806928171,
+    "eval_accuracy_mm": 0.6743287225386493,
+    "eval_loss": 0.7633378505706787,
+    "eval_loss_mm": 0.7596884965896606,
+    "eval_runtime": 6.1967,
+    "eval_runtime_mm": 6.196,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 1583.9,
+    "eval_samples_per_second_mm": 1586.83,
+    "eval_steps_per_second": 6.294,
+    "eval_steps_per_second_mm": 6.294,
+    "total_flos": 4.6496324415879475e+17,
+    "train_loss": 0.6294902308029005,
+    "train_runtime": 5786.7639,
+    "train_samples": 392702,
+    "train_samples_per_second": 3393.105,
+    "train_steps_per_second": 13.254
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 9.0,
+    "epoch_mm": 9.0,
+    "eval_accuracy": 0.6661232806928171,
+    "eval_accuracy_mm": 0.6743287225386493,
+    "eval_loss": 0.7633378505706787,
+    "eval_loss_mm": 0.7596884965896606,
+    "eval_runtime": 6.1967,
+    "eval_runtime_mm": 6.196,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 1583.9,
+    "eval_samples_per_second_mm": 1586.83,
+    "eval_steps_per_second": 6.294,
+    "eval_steps_per_second_mm": 6.294
+}

logs/events.out.tfevents.1745523725.s_005_m.2892304.107

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a8cd5287dcf163e1e53de00296103ecfc1e277533610ef10a36acae92196bcb
+size 686

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "total_flos": 4.6496324415879475e+17,
+    "train_loss": 0.6294902308029005,
+    "train_runtime": 5786.7639,
+    "train_samples": 392702,
+    "train_samples_per_second": 3393.105,
+    "train_steps_per_second": 13.254
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_global_step": 6136,
+  "best_metric": 0.7633378505706787,
+  "best_model_checkpoint": "bert_base_rand_100_v2_mnli/checkpoint-6136",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 13806,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.271374225616455,
+      "learning_rate": 4.9e-05,
+      "loss": 0.9712,
+      "step": 1534
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5823739174732552,
+      "eval_loss": 0.8988065123558044,
+      "eval_runtime": 6.2909,
+      "eval_samples_per_second": 1560.178,
+      "eval_steps_per_second": 6.199,
+      "step": 1534
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.4784847497940063,
+      "learning_rate": 4.8e-05,
+      "loss": 0.861,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6276107997962302,
+      "eval_loss": 0.8349990248680115,
+      "eval_runtime": 6.2419,
+      "eval_samples_per_second": 1572.431,
+      "eval_steps_per_second": 6.248,
+      "step": 3068
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.2310168743133545,
+      "learning_rate": 4.7e-05,
+      "loss": 0.769,
+      "step": 4602
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6504330106979114,
+      "eval_loss": 0.7969886064529419,
+      "eval_runtime": 6.2276,
+      "eval_samples_per_second": 1576.04,
+      "eval_steps_per_second": 6.262,
+      "step": 4602
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.9881421327590942,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6896,
+      "step": 6136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6661232806928171,
+      "eval_loss": 0.7633378505706787,
+      "eval_runtime": 6.2198,
+      "eval_samples_per_second": 1578.024,
+      "eval_steps_per_second": 6.27,
+      "step": 6136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.077666759490967,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6191,
+      "step": 7670
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.673458991339786,
+      "eval_loss": 0.7851901054382324,
+      "eval_runtime": 6.2171,
+      "eval_samples_per_second": 1578.715,
+      "eval_steps_per_second": 6.273,
+      "step": 7670
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.732699394226074,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.5467,
+      "step": 9204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6729495669893021,
+      "eval_loss": 0.8340039849281311,
+      "eval_runtime": 6.2175,
+      "eval_samples_per_second": 1578.62,
+      "eval_steps_per_second": 6.273,
+      "step": 9204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.8983209133148193,
+      "learning_rate": 4.3e-05,
+      "loss": 0.4721,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6770249617931737,
+      "eval_loss": 0.8674674034118652,
+      "eval_runtime": 6.2313,
+      "eval_samples_per_second": 1575.123,
+      "eval_steps_per_second": 6.259,
+      "step": 10738
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.4001963138580322,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4013,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6663270504330107,
+      "eval_loss": 0.9629429578781128,
+      "eval_runtime": 6.2244,
+      "eval_samples_per_second": 1576.854,
+      "eval_steps_per_second": 6.266,
+      "step": 12272
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 4.502684116363525,
+      "learning_rate": 4.1e-05,
+      "loss": 0.3355,
+      "step": 13806
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6595007641365257,
+      "eval_loss": 1.0929573774337769,
+      "eval_runtime": 6.2219,
+      "eval_samples_per_second": 1577.486,
+      "eval_steps_per_second": 6.268,
+      "step": 13806
+    },
+    {
+      "epoch": 9.0,
+      "step": 13806,
+      "total_flos": 4.6496324415879475e+17,
+      "train_loss": 0.6294902308029005,
+      "train_runtime": 5786.7639,
+      "train_samples_per_second": 3393.105,
+      "train_steps_per_second": 13.254
+    }
+  ],
+  "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": 4.6496324415879475e+17,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}