End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_rand_10_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_rand_10_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: 0.6695484133441822
 ---
 
 <!-- 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_10_v2_mnli
 
-This model is a fine-tuned version of [Hartunka/bert_base_rand_10_v2](https://huggingface.co/Hartunka/bert_base_rand_10_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_rand_10_v2](https://huggingface.co/Hartunka/bert_base_rand_10_v2) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1209
-- Accuracy: 0.6675
+- Loss: 0.7912
+- Accuracy: 0.6695
 
 ## Model description
 

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 10.0,
+    "epoch_mm": 10.0,
+    "eval_accuracy": 0.6669383596535915,
+    "eval_accuracy_mm": 0.6695484133441822,
+    "eval_loss": 0.7891020178794861,
+    "eval_loss_mm": 0.7911800146102905,
+    "eval_runtime": 6.2116,
+    "eval_runtime_mm": 6.2435,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 1580.114,
+    "eval_samples_per_second_mm": 1574.76,
+    "eval_steps_per_second": 6.279,
+    "eval_steps_per_second_mm": 6.247,
+    "total_flos": 5.166258268431053e+17,
+    "train_loss": 0.6272336599257965,
+    "train_runtime": 6425.3808,
+    "train_samples": 392702,
+    "train_samples_per_second": 3055.866,
+    "train_steps_per_second": 11.937
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "epoch_mm": 10.0,
+    "eval_accuracy": 0.6669383596535915,
+    "eval_accuracy_mm": 0.6695484133441822,
+    "eval_loss": 0.7891020178794861,
+    "eval_loss_mm": 0.7911800146102905,
+    "eval_runtime": 6.2116,
+    "eval_runtime_mm": 6.2435,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 1580.114,
+    "eval_samples_per_second_mm": 1574.76,
+    "eval_steps_per_second": 6.279,
+    "eval_steps_per_second_mm": 6.247
+}

logs/events.out.tfevents.1745483328.s_005_m.2892304.53

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b3882b02c349b55606528455d9b5a1591a37d7ff1ee52b2008c61ed59610db3
+size 686

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 5.166258268431053e+17,
+    "train_loss": 0.6272336599257965,
+    "train_runtime": 6425.3808,
+    "train_samples": 392702,
+    "train_samples_per_second": 3055.866,
+    "train_steps_per_second": 11.937
+}

trainer_state.json

@@ -0,0 +1,212 @@
+{
+  "best_global_step": 7670,
+  "best_metric": 0.7891020178794861,
+  "best_model_checkpoint": "bert_base_rand_10_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": 1.2558138370513916,
+      "learning_rate": 4.9e-05,
+      "loss": 0.9824,
+      "step": 1534
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5699439633214468,
+      "eval_loss": 0.9110311269760132,
+      "eval_runtime": 6.3612,
+      "eval_samples_per_second": 1542.943,
+      "eval_steps_per_second": 6.131,
+      "step": 1534
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.4911693334579468,
+      "learning_rate": 4.8e-05,
+      "loss": 0.8805,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6046867040244523,
+      "eval_loss": 0.8597168922424316,
+      "eval_runtime": 6.247,
+      "eval_samples_per_second": 1571.154,
+      "eval_steps_per_second": 6.243,
+      "step": 3068
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.8992587327957153,
+      "learning_rate": 4.7e-05,
+      "loss": 0.7993,
+      "step": 4602
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6384105960264901,
+      "eval_loss": 0.8155638575553894,
+      "eval_runtime": 6.2198,
+      "eval_samples_per_second": 1578.016,
+      "eval_steps_per_second": 6.27,
+      "step": 4602
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.442138671875,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.7199,
+      "step": 6136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6514518593988793,
+      "eval_loss": 0.8102550506591797,
+      "eval_runtime": 6.2207,
+      "eval_samples_per_second": 1577.808,
+      "eval_steps_per_second": 6.269,
+      "step": 6136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.2134199142456055,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6507,
+      "step": 7670
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6669383596535915,
+      "eval_loss": 0.7891020178794861,
+      "eval_runtime": 6.2158,
+      "eval_samples_per_second": 1579.049,
+      "eval_steps_per_second": 6.274,
+      "step": 7670
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.173543930053711,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.5825,
+      "step": 9204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6738665308201732,
+      "eval_loss": 0.8292580842971802,
+      "eval_runtime": 6.2207,
+      "eval_samples_per_second": 1577.791,
+      "eval_steps_per_second": 6.269,
+      "step": 9204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.7192294597625732,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5126,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6684666327050433,
+      "eval_loss": 0.840766191482544,
+      "eval_runtime": 6.2289,
+      "eval_samples_per_second": 1575.729,
+      "eval_steps_per_second": 6.261,
+      "step": 10738
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.465540647506714,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4443,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6673458991339786,
+      "eval_loss": 0.9585584998130798,
+      "eval_runtime": 6.225,
+      "eval_samples_per_second": 1576.709,
+      "eval_steps_per_second": 6.265,
+      "step": 12272
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 4.3748555183410645,
+      "learning_rate": 4.1e-05,
+      "loss": 0.3792,
+      "step": 13806
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6593988792664289,
+      "eval_loss": 1.07344651222229,
+      "eval_runtime": 6.2298,
+      "eval_samples_per_second": 1575.481,
+      "eval_steps_per_second": 6.26,
+      "step": 13806
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 4.201927661895752,
+      "learning_rate": 4e-05,
+      "loss": 0.3211,
+      "step": 15340
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6675496688741722,
+      "eval_loss": 1.1208546161651611,
+      "eval_runtime": 6.2157,
+      "eval_samples_per_second": 1579.058,
+      "eval_steps_per_second": 6.274,
+      "step": 15340
+    },
+    {
+      "epoch": 10.0,
+      "step": 15340,
+      "total_flos": 5.166258268431053e+17,
+      "train_loss": 0.6272336599257965,
+      "train_runtime": 6425.3808,
+      "train_samples_per_second": 3055.866,
+      "train_steps_per_second": 11.937
+    }
+  ],
+  "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
+}