End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/distilbert_rand_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: distilbert_rand_100_v1_rte
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5415162454873647
 ---
 
 <!-- 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_100_v1_rte
 
-This model is a fine-tuned version of [Hartunka/distilbert_rand_100_v1](https://huggingface.co/Hartunka/distilbert_rand_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/distilbert_rand_100_v1](https://huggingface.co/Hartunka/distilbert_rand_100_v1) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6374
-- Accuracy: 0.4910
+- Loss: 0.6875
+- Accuracy: 0.5415
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5415162454873647,
+    "eval_loss": 0.687450647354126,
+    "eval_runtime": 0.1547,
+    "eval_samples": 277,
+    "eval_samples_per_second": 1790.766,
+    "eval_steps_per_second": 12.93,
+    "total_flos": 989531467960320.0,
+    "train_loss": 0.5249984780947368,
+    "train_runtime": 22.3739,
+    "train_samples": 2490,
+    "train_samples_per_second": 5564.514,
+    "train_steps_per_second": 22.347
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5415162454873647,
+    "eval_loss": 0.687450647354126,
+    "eval_runtime": 0.1547,
+    "eval_samples": 277,
+    "eval_samples_per_second": 1790.766,
+    "eval_steps_per_second": 12.93
+}

logs/events.out.tfevents.1744946676.s_005_m.2758941.99

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59553e4e6b51a9cfa50e7fce44c1afed60d40c2e56cb81c4708aa3c1c3443049
+size 357

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 989531467960320.0,
+    "train_loss": 0.5249984780947368,
+    "train_runtime": 22.3739,
+    "train_samples": 2490,
+    "train_samples_per_second": 5564.514,
+    "train_steps_per_second": 22.347
+}

trainer_state.json

@@ -0,0 +1,148 @@
+{
+  "best_global_step": 10,
+  "best_metric": 0.687450647354126,
+  "best_model_checkpoint": "distilbert_rand_100_v1_rte/checkpoint-10",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.1372756958007812,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6961,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5415162454873647,
+      "eval_loss": 0.687450647354126,
+      "eval_runtime": 0.1289,
+      "eval_samples_per_second": 2148.94,
+      "eval_steps_per_second": 15.516,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5947099924087524,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6818,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5234657039711191,
+      "eval_loss": 0.7027230858802795,
+      "eval_runtime": 0.133,
+      "eval_samples_per_second": 2082.749,
+      "eval_steps_per_second": 15.038,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.5024683475494385,
+      "learning_rate": 4.7e-05,
+      "loss": 0.6342,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5126353790613718,
+      "eval_loss": 0.7948302626609802,
+      "eval_runtime": 0.1396,
+      "eval_samples_per_second": 1984.86,
+      "eval_steps_per_second": 14.331,
+      "step": 30
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.120546340942383,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5249,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4981949458483754,
+      "eval_loss": 0.9894155859947205,
+      "eval_runtime": 0.1291,
+      "eval_samples_per_second": 2145.535,
+      "eval_steps_per_second": 15.491,
+      "step": 40
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.601308584213257,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3703,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.47653429602888087,
+      "eval_loss": 1.246387243270874,
+      "eval_runtime": 0.1282,
+      "eval_samples_per_second": 2161.441,
+      "eval_steps_per_second": 15.606,
+      "step": 50
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 7.120133399963379,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.2426,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.49097472924187724,
+      "eval_loss": 1.6374201774597168,
+      "eval_runtime": 0.1519,
+      "eval_samples_per_second": 1824.134,
+      "eval_steps_per_second": 13.171,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "step": 60,
+      "total_flos": 989531467960320.0,
+      "train_loss": 0.5249984780947368,
+      "train_runtime": 22.3739,
+      "train_samples_per_second": 5564.514,
+      "train_steps_per_second": 22.347
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 500,
+  "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": 989531467960320.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}