End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: google-bert/bert-base-multilingual-uncased
 tags:
 - generated_from_trainer
+metrics:
+- f1
 model-index:
 - name: bert-multilingual-sdg-classification
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # bert-multilingual-sdg-classification
 
 This model is a fine-tuned version of [google-bert/bert-base-multilingual-uncased](https://huggingface.co/google-bert/bert-base-multilingual-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6998
+- F1: 0.7966
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_f1": 0.7966137307268389,
+    "eval_loss": 0.6998273134231567,
+    "eval_runtime": 2255.012,
+    "eval_samples": 12908,
+    "eval_samples_per_second": 5.724,
+    "eval_steps_per_second": 0.716,
+    "total_flos": 2.377533515518771e+16,
+    "train_loss": 0.9355160604532273,
+    "train_runtime": 47353.9083,
+    "train_samples": 30117,
+    "train_samples_per_second": 1.908,
+    "train_steps_per_second": 0.06
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_f1": 0.7966137307268389,
+    "eval_loss": 0.6998273134231567,
+    "eval_runtime": 2255.012,
+    "eval_samples": 12908,
+    "eval_samples_per_second": 5.724,
+    "eval_steps_per_second": 0.716
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2.377533515518771e+16,
+    "train_loss": 0.9355160604532273,
+    "train_runtime": 47353.9083,
+    "train_samples": 30117,
+    "train_samples_per_second": 1.908,
+    "train_steps_per_second": 0.06
+}

trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 300.0,
+  "global_step": 2826,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5307855626326964,
+      "grad_norm": 10.279387474060059,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.9545,
+      "step": 500
+    },
+    {
+      "epoch": 1.0615711252653928,
+      "grad_norm": 7.024175643920898,
+      "learning_rate": 1.6406109613656783e-05,
+      "loss": 0.9557,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5923566878980893,
+      "grad_norm": 7.754688262939453,
+      "learning_rate": 1.1913746630727763e-05,
+      "loss": 0.7767,
+      "step": 1500
+    },
+    {
+      "epoch": 2.1231422505307855,
+      "grad_norm": 9.531620979309082,
+      "learning_rate": 7.421383647798742e-06,
+      "loss": 0.6899,
+      "step": 2000
+    },
+    {
+      "epoch": 2.653927813163482,
+      "grad_norm": 6.811396598815918,
+      "learning_rate": 2.929020664869722e-06,
+      "loss": 0.5649,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "step": 2826,
+      "total_flos": 2.377533515518771e+16,
+      "train_loss": 0.9355160604532273,
+      "train_runtime": 47353.9083,
+      "train_samples_per_second": 1.908,
+      "train_steps_per_second": 0.06
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2826,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.377533515518771e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}