End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/distilbert_km_10_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: distilbert_km_10_v2_qnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6360973823906279
 ---
 
 <!-- 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. -->
 
 # distilbert_km_10_v2_qnli
 
-This model is a fine-tuned version of [Hartunka/distilbert_km_10_v2](https://huggingface.co/Hartunka/distilbert_km_10_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/distilbert_km_10_v2](https://huggingface.co/Hartunka/distilbert_km_10_v2) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2716
-- Accuracy: 0.6251
+- Loss: 0.6384
+- Accuracy: 0.6361
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6360973823906279,
+    "eval_loss": 0.63837730884552,
+    "eval_runtime": 2.2901,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 2385.466,
+    "eval_steps_per_second": 9.606,
+    "total_flos": 4.856261458098893e+16,
+    "train_loss": 0.4252281747213224,
+    "train_runtime": 690.7336,
+    "train_samples": 104743,
+    "train_samples_per_second": 7582.012,
+    "train_steps_per_second": 29.679
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6360973823906279,
+    "eval_loss": 0.63837730884552,
+    "eval_runtime": 2.2901,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 2385.466,
+    "eval_steps_per_second": 9.606
+}

logs/events.out.tfevents.1745315688.s_005_m.2850345.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e30a0969dc79c9239a579eab9eda76cd8390bba16458a2d51453e637031b70d
+size 363

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 4.856261458098893e+16,
+    "train_loss": 0.4252281747213224,
+    "train_runtime": 690.7336,
+    "train_samples": 104743,
+    "train_samples_per_second": 7582.012,
+    "train_steps_per_second": 29.679
+}

trainer_state.json

@@ -0,0 +1,164 @@
+{
+  "best_global_step": 820,
+  "best_metric": 0.63837730884552,
+  "best_model_checkpoint": "distilbert_km_10_v2_qnli/checkpoint-820",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 2870,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.971386194229126,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6659,
+      "step": 410
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6273110012813472,
+      "eval_loss": 0.6420336365699768,
+      "eval_runtime": 2.2776,
+      "eval_samples_per_second": 2398.613,
+      "eval_steps_per_second": 9.659,
+      "step": 410
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.879644751548767,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6251,
+      "step": 820
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6360973823906279,
+      "eval_loss": 0.63837730884552,
+      "eval_runtime": 2.2022,
+      "eval_samples_per_second": 2480.651,
+      "eval_steps_per_second": 9.99,
+      "step": 820
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.571931838989258,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5543,
+      "step": 1230
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6342668863261944,
+      "eval_loss": 0.6578118801116943,
+      "eval_runtime": 2.2708,
+      "eval_samples_per_second": 2405.759,
+      "eval_steps_per_second": 9.688,
+      "step": 1230
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.400623798370361,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.4359,
+      "step": 1640
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6313380926231008,
+      "eval_loss": 0.7432957887649536,
+      "eval_runtime": 2.1989,
+      "eval_samples_per_second": 2484.38,
+      "eval_steps_per_second": 10.005,
+      "step": 1640
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 7.518048286437988,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3151,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6348160351455244,
+      "eval_loss": 0.8895277976989746,
+      "eval_runtime": 2.2276,
+      "eval_samples_per_second": 2452.416,
+      "eval_steps_per_second": 9.876,
+      "step": 2050
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 6.723891258239746,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.221,
+      "step": 2460
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6262127036426872,
+      "eval_loss": 1.0872596502304077,
+      "eval_runtime": 2.2342,
+      "eval_samples_per_second": 2445.189,
+      "eval_steps_per_second": 9.847,
+      "step": 2460
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 10.113161087036133,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1593,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6251144060040271,
+      "eval_loss": 1.271634578704834,
+      "eval_runtime": 2.2465,
+      "eval_samples_per_second": 2431.798,
+      "eval_steps_per_second": 9.793,
+      "step": 2870
+    },
+    {
+      "epoch": 7.0,
+      "step": 2870,
+      "total_flos": 4.856261458098893e+16,
+      "train_loss": 0.4252281747213224,
+      "train_runtime": 690.7336,
+      "train_samples_per_second": 7582.012,
+      "train_steps_per_second": 29.679
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20500,
+  "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": 4.856261458098893e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}