End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: distilbert-base-multilingual-cased
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: text-classification-model-multilingual
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # text-classification-model-multilingual
 
 This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2706
+- Accuracy: 0.9373
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9373333333333334,
+    "eval_loss": 0.2706108093261719,
+    "eval_runtime": 11.0779,
+    "eval_samples": 3000,
+    "eval_samples_per_second": 270.809,
+    "eval_steps_per_second": 33.851,
+    "train_loss": 0.8795227316481558,
+    "train_runtime": 626.0855,
+    "train_samples": 15000,
+    "train_samples_per_second": 71.875,
+    "train_steps_per_second": 4.495
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9373333333333334,
+    "eval_loss": 0.2706108093261719,
+    "eval_runtime": 11.0779,
+    "eval_samples": 3000,
+    "eval_samples_per_second": 270.809,
+    "eval_steps_per_second": 33.851
+}

runs/Dec07_09-39-39_19e0ce5cd803/events.out.tfevents.1701942656.19e0ce5cd803.1409.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:417e07558071dd435859a7914b26e599270b8e2da7ec266b7fcee3d12f125fa8
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.8795227316481558,
+    "train_runtime": 626.0855,
+    "train_samples": 15000,
+    "train_samples_per_second": 71.875,
+    "train_steps_per_second": 4.495
+}

trainer_state.json

@@ -0,0 +1,59 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2814,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.111584932480455e-05,
+      "loss": 3.3646,
+      "step": 500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 3.2231698649609096e-05,
+      "loss": 0.932,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.3347547974413646e-05,
+      "loss": 0.3383,
+      "step": 1500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.4463397299218195e-05,
+      "loss": 0.1763,
+      "step": 2000
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 5.579246624022743e-06,
+      "loss": 0.0893,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "step": 2814,
+      "total_flos": 1494191577600000.0,
+      "train_loss": 0.8795227316481558,
+      "train_runtime": 626.0855,
+      "train_samples_per_second": 71.875,
+      "train_steps_per_second": 4.495
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2814,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1494191577600000.0,
+  "trial_name": null,
+  "trial_params": null
+}