End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/distilbert_rand_5_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: distilbert_rand_5_v1_mnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6682262001627339
 ---
 
 <!-- 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_5_v1_mnli
 
-This model is a fine-tuned version of [Hartunka/distilbert_rand_5_v1](https://huggingface.co/Hartunka/distilbert_rand_5_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/distilbert_rand_5_v1](https://huggingface.co/Hartunka/distilbert_rand_5_v1) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1851
-- Accuracy: 0.6563
+- Loss: 0.7899
+- Accuracy: 0.6682
 
 ## Model description
 

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 10.0,
+    "epoch_mm": 10.0,
+    "eval_accuracy": 0.669587366276108,
+    "eval_accuracy_mm": 0.6682262001627339,
+    "eval_loss": 0.7916574478149414,
+    "eval_loss_mm": 0.789862871170044,
+    "eval_runtime": 3.9499,
+    "eval_runtime_mm": 4.0564,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 2484.887,
+    "eval_samples_per_second_mm": 2423.819,
+    "eval_steps_per_second": 9.874,
+    "eval_steps_per_second_mm": 9.614,
+    "total_flos": 2.6010570046823424e+17,
+    "train_loss": 0.6276591274853325,
+    "train_runtime": 3596.4786,
+    "train_samples": 392702,
+    "train_samples_per_second": 5459.535,
+    "train_steps_per_second": 21.326
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "epoch_mm": 10.0,
+    "eval_accuracy": 0.669587366276108,
+    "eval_accuracy_mm": 0.6682262001627339,
+    "eval_loss": 0.7916574478149414,
+    "eval_loss_mm": 0.789862871170044,
+    "eval_runtime": 3.9499,
+    "eval_runtime_mm": 4.0564,
+    "eval_samples": 9815,
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 2484.887,
+    "eval_samples_per_second_mm": 2423.819,
+    "eval_steps_per_second": 9.874,
+    "eval_steps_per_second_mm": 9.614
+}

logs/events.out.tfevents.1744920138.s_005_m.2758941.35

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f398c70e29883492b71bd0a9590cdfeb3d520c02aab75ac0493bcc4065dfc32
+size 686

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 2.6010570046823424e+17,
+    "train_loss": 0.6276591274853325,
+    "train_runtime": 3596.4786,
+    "train_samples": 392702,
+    "train_samples_per_second": 5459.535,
+    "train_steps_per_second": 21.326
+}

trainer_state.json

@@ -0,0 +1,212 @@
+{
+  "best_global_step": 7670,
+  "best_metric": 0.7916574478149414,
+  "best_model_checkpoint": "distilbert_rand_5_v1_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": 1.3144339323043823,
+      "learning_rate": 4.9e-05,
+      "loss": 0.9796,
+      "step": 1534
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5718797758532858,
+      "eval_loss": 0.915686309337616,
+      "eval_runtime": 4.0109,
+      "eval_samples_per_second": 2447.097,
+      "eval_steps_per_second": 9.724,
+      "step": 1534
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9763035774230957,
+      "learning_rate": 4.8e-05,
+      "loss": 0.877,
+      "step": 3068
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6139582272032603,
+      "eval_loss": 0.846189558506012,
+      "eval_runtime": 3.9391,
+      "eval_samples_per_second": 2491.667,
+      "eval_steps_per_second": 9.901,
+      "step": 3068
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.0250139236450195,
+      "learning_rate": 4.7e-05,
+      "loss": 0.7859,
+      "step": 4602
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.648700967906266,
+      "eval_loss": 0.802159309387207,
+      "eval_runtime": 3.9687,
+      "eval_samples_per_second": 2473.098,
+      "eval_steps_per_second": 9.827,
+      "step": 4602
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.045177459716797,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.7113,
+      "step": 6136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6530820173204279,
+      "eval_loss": 0.8008774518966675,
+      "eval_runtime": 3.9424,
+      "eval_samples_per_second": 2489.599,
+      "eval_steps_per_second": 9.892,
+      "step": 6136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.0712034702301025,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6457,
+      "step": 7670
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.669587366276108,
+      "eval_loss": 0.7916574478149414,
+      "eval_runtime": 3.9372,
+      "eval_samples_per_second": 2492.914,
+      "eval_steps_per_second": 9.906,
+      "step": 7670
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.8154921531677246,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.5791,
+      "step": 9204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6712175241976567,
+      "eval_loss": 0.8462638854980469,
+      "eval_runtime": 3.9489,
+      "eval_samples_per_second": 2485.527,
+      "eval_steps_per_second": 9.876,
+      "step": 9204
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.6073708534240723,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5132,
+      "step": 10738
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6599083036169129,
+      "eval_loss": 0.8748463988304138,
+      "eval_runtime": 3.9565,
+      "eval_samples_per_second": 2480.731,
+      "eval_steps_per_second": 9.857,
+      "step": 10738
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.182267665863037,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4509,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.660825267447784,
+      "eval_loss": 0.9892714619636536,
+      "eval_runtime": 3.9483,
+      "eval_samples_per_second": 2485.86,
+      "eval_steps_per_second": 9.878,
+      "step": 12272
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 3.359374761581421,
+      "learning_rate": 4.1e-05,
+      "loss": 0.3924,
+      "step": 13806
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6580743759551707,
+      "eval_loss": 1.0943820476531982,
+      "eval_runtime": 3.9881,
+      "eval_samples_per_second": 2461.092,
+      "eval_steps_per_second": 9.779,
+      "step": 13806
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 4.142611503601074,
+      "learning_rate": 4e-05,
+      "loss": 0.3413,
+      "step": 15340
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6563423331635252,
+      "eval_loss": 1.1850701570510864,
+      "eval_runtime": 3.9408,
+      "eval_samples_per_second": 2490.639,
+      "eval_steps_per_second": 9.897,
+      "step": 15340
+    },
+    {
+      "epoch": 10.0,
+      "step": 15340,
+      "total_flos": 2.6010570046823424e+17,
+      "train_loss": 0.6276591274853325,
+      "train_runtime": 3596.4786,
+      "train_samples_per_second": 5459.535,
+      "train_steps_per_second": 21.326
+    }
+  ],
+  "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": 2.6010570046823424e+17,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}