End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/distilbert_rand_10_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: distilbert_rand_10_v1_wnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE WNLI
+      type: glue
+      args: wnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.323943661971831
 ---
 
 <!-- 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_rand_10_v1_wnli
 
-This model is a fine-tuned version of [Hartunka/distilbert_rand_10_v1](https://huggingface.co/Hartunka/distilbert_rand_10_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/distilbert_rand_10_v1](https://huggingface.co/Hartunka/distilbert_rand_10_v1) on the GLUE WNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7966
-- Accuracy: 0.3099
+- Loss: 0.7145
+- Accuracy: 0.3239
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.323943661971831,
+    "eval_loss": 0.7144585847854614,
+    "eval_runtime": 0.0712,
+    "eval_samples": 71,
+    "eval_samples_per_second": 996.669,
+    "eval_steps_per_second": 14.038,
+    "total_flos": 252350394439680.0,
+    "train_loss": 0.7009861336814033,
+    "train_runtime": 11.3483,
+    "train_samples": 635,
+    "train_samples_per_second": 2797.77,
+    "train_steps_per_second": 13.218
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.323943661971831,
+    "eval_loss": 0.7144585847854614,
+    "eval_runtime": 0.0712,
+    "eval_samples": 71,
+    "eval_samples_per_second": 996.669,
+    "eval_steps_per_second": 14.038
+}

logs/events.out.tfevents.1744924164.s_005_m.2758941.51

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8db1b19ab1f684115b5c4e9f82ef94ea30bf53ed18d08934387fc43138a168ca
+size 357

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 252350394439680.0,
+    "train_loss": 0.7009861336814033,
+    "train_runtime": 11.3483,
+    "train_samples": 635,
+    "train_samples_per_second": 2797.77,
+    "train_steps_per_second": 13.218
+}

trainer_state.json

@@ -0,0 +1,148 @@
+{
+  "best_global_step": 3,
+  "best_metric": 0.7144585847854614,
+  "best_model_checkpoint": "distilbert_rand_10_v1_wnli/checkpoint-3",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.6102161407470703,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7125,
+      "step": 3
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.323943661971831,
+      "eval_loss": 0.7144585847854614,
+      "eval_runtime": 0.0404,
+      "eval_samples_per_second": 1759.501,
+      "eval_steps_per_second": 24.782,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0894246101379395,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7065,
+      "step": 6
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.38028169014084506,
+      "eval_loss": 0.7247469425201416,
+      "eval_runtime": 0.0395,
+      "eval_samples_per_second": 1798.359,
+      "eval_steps_per_second": 25.329,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.388277530670166,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6998,
+      "step": 9
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.29577464788732394,
+      "eval_loss": 0.7582525014877319,
+      "eval_runtime": 0.0394,
+      "eval_samples_per_second": 1803.827,
+      "eval_steps_per_second": 25.406,
+      "step": 9
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.0093088150024414,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6882,
+      "step": 12
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5211267605633803,
+      "eval_loss": 0.745296061038971,
+      "eval_runtime": 0.0424,
+      "eval_samples_per_second": 1674.58,
+      "eval_steps_per_second": 23.586,
+      "step": 12
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.0113441944122314,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6992,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.2676056338028169,
+      "eval_loss": 0.7629843354225159,
+      "eval_runtime": 0.0457,
+      "eval_samples_per_second": 1555.093,
+      "eval_steps_per_second": 21.903,
+      "step": 15
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.0279693603515625,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6998,
+      "step": 18
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.30985915492957744,
+      "eval_loss": 0.796627402305603,
+      "eval_runtime": 0.0388,
+      "eval_samples_per_second": 1827.684,
+      "eval_steps_per_second": 25.742,
+      "step": 18
+    },
+    {
+      "epoch": 6.0,
+      "step": 18,
+      "total_flos": 252350394439680.0,
+      "train_loss": 0.7009861336814033,
+      "train_runtime": 11.3483,
+      "train_samples_per_second": 2797.77,
+      "train_steps_per_second": 13.218
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "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": 252350394439680.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}