End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_km_20_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_base_km_20_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: 0.6644629780309195
 ---
 
 <!-- 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_km_20_v2_mnli
 
-This model is a fine-tuned version of [Hartunka/bert_base_km_20_v2](https://huggingface.co/Hartunka/bert_base_km_20_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_km_20_v2](https://huggingface.co/Hartunka/bert_base_km_20_v2) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2364
-- Accuracy: 0.6570
+- Loss: 0.7873
+- Accuracy: 0.6645
 
 ## Model description
 

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 10.0,
+    "epoch_mm": 10.0,
+    "eval_accuracy": 0.6616403464085583,
+    "eval_accuracy_mm": 0.6644629780309195,
+    "eval_loss": 0.7950525283813477,
+    "eval_loss_mm": 0.7872781157493591,
+    "eval_runtime": 6.136,
+    "eval_runtime_mm": 6.2093,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 1599.567,
+    "eval_samples_per_second_mm": 1583.433,
+    "eval_steps_per_second": 6.356,
+    "eval_steps_per_second_mm": 6.281,
+    "total_flos": 5.166258268431053e+17,
+    "train_loss": 0.6059419873174198,
+    "train_runtime": 6356.9891,
+    "train_samples": 392702,
+    "train_samples_per_second": 3088.742,
+    "train_steps_per_second": 12.065
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "epoch_mm": 10.0,
+    "eval_accuracy": 0.6616403464085583,
+    "eval_accuracy_mm": 0.6644629780309195,
+    "eval_loss": 0.7950525283813477,
+    "eval_loss_mm": 0.7872781157493591,
+    "eval_runtime": 6.136,
+    "eval_runtime_mm": 6.2093,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 1599.567,
+    "eval_samples_per_second_mm": 1583.433,
+    "eval_steps_per_second": 6.356,
+    "eval_steps_per_second_mm": 6.281
+}

logs/events.out.tfevents.1745411568.s_005_m.2876923.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0448cf573663cd4afade6f8b5a25857efe5f0c23ff0214db93c5a8e1a334bb39
+size 686

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 5.166258268431053e+17,
+    "train_loss": 0.6059419873174198,
+    "train_runtime": 6356.9891,
+    "train_samples": 392702,
+    "train_samples_per_second": 3088.742,
+    "train_steps_per_second": 12.065
+}

trainer_state.json

@@ -0,0 +1,212 @@
+{
+  "best_global_step": 7670,
+  "best_metric": 0.7950525283813477,
+  "best_model_checkpoint": "bert_base_km_20_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": 1.5084047317504883,
+      "learning_rate": 4.9e-05,
+      "loss": 0.9876,
+      "step": 1534
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5726948548140601,
+      "eval_loss": 0.9146076440811157,
+      "eval_runtime": 6.2209,
+      "eval_samples_per_second": 1577.745,
+      "eval_steps_per_second": 6.269,
+      "step": 1534
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.318026065826416,
+      "learning_rate": 4.8e-05,
+      "loss": 0.8776,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6045848191543556,
+      "eval_loss": 0.8655351400375366,
+      "eval_runtime": 6.1821,
+      "eval_samples_per_second": 1587.653,
+      "eval_steps_per_second": 6.309,
+      "step": 3068
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.7010105848312378,
+      "learning_rate": 4.7e-05,
+      "loss": 0.7975,
+      "step": 4602
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6417727967396841,
+      "eval_loss": 0.8097133636474609,
+      "eval_runtime": 6.175,
+      "eval_samples_per_second": 1589.479,
+      "eval_steps_per_second": 6.316,
+      "step": 4602
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.1400508880615234,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.7185,
+      "step": 6136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6566479877738156,
+      "eval_loss": 0.7999866604804993,
+      "eval_runtime": 6.1668,
+      "eval_samples_per_second": 1591.585,
+      "eval_steps_per_second": 6.324,
+      "step": 6136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.2893998622894287,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6415,
+      "step": 7670
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6616403464085583,
+      "eval_loss": 0.7950525283813477,
+      "eval_runtime": 6.1727,
+      "eval_samples_per_second": 1590.054,
+      "eval_steps_per_second": 6.318,
+      "step": 7670
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.949033737182617,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.5611,
+      "step": 9204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6600101884870097,
+      "eval_loss": 0.8546719551086426,
+      "eval_runtime": 6.1536,
+      "eval_samples_per_second": 1594.997,
+      "eval_steps_per_second": 6.338,
+      "step": 9204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.00984263420105,
+      "learning_rate": 4.3e-05,
+      "loss": 0.4782,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6601120733571064,
+      "eval_loss": 0.9199888110160828,
+      "eval_runtime": 6.1882,
+      "eval_samples_per_second": 1586.096,
+      "eval_steps_per_second": 6.302,
+      "step": 10738
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.925968885421753,
+      "learning_rate": 4.2e-05,
+      "loss": 0.3996,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6586856851757514,
+      "eval_loss": 1.010155200958252,
+      "eval_runtime": 6.1772,
+      "eval_samples_per_second": 1588.907,
+      "eval_steps_per_second": 6.314,
+      "step": 12272
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 4.3679399490356445,
+      "learning_rate": 4.1e-05,
+      "loss": 0.3293,
+      "step": 13806
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6507386653082017,
+      "eval_loss": 1.1860852241516113,
+      "eval_runtime": 6.1801,
+      "eval_samples_per_second": 1588.158,
+      "eval_steps_per_second": 6.311,
+      "step": 13806
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 4.252954006195068,
+      "learning_rate": 4e-05,
+      "loss": 0.2684,
+      "step": 15340
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6569536423841059,
+      "eval_loss": 1.236405372619629,
+      "eval_runtime": 6.2163,
+      "eval_samples_per_second": 1578.923,
+      "eval_steps_per_second": 6.274,
+      "step": 15340
+    },
+    {
+      "epoch": 10.0,
+      "step": 15340,
+      "total_flos": 5.166258268431053e+17,
+      "train_loss": 0.6059419873174198,
+      "train_runtime": 6356.9891,
+      "train_samples_per_second": 3088.742,
+      "train_steps_per_second": 12.065
+    }
+  ],
+  "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
+}