End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: google-bert/bert-base-uncased
 tags:
 - generated_from_trainer
+metrics:
+- f1
 model-index:
 - name: nano_cls-2-no-bf16
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # nano_cls-2-no-bf16
 
 This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5383
+- F1: 0.8169
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_f1": 0.8169250744672726,
+    "eval_loss": 0.538325846195221,
+    "eval_runtime": 17.3733,
+    "eval_samples": 20000,
+    "eval_samples_per_second": 1151.19,
+    "eval_steps_per_second": 18.016,
+    "total_flos": 4.216512416894157e+16,
+    "train_loss": 0.4463165575703874,
+    "train_runtime": 453.3701,
+    "train_samples": 160000,
+    "train_samples_per_second": 352.913,
+    "train_steps_per_second": 0.69,
+    "train_tokens_per_second": 22622.54
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_f1": 0.8169250744672726,
+    "eval_loss": 0.538325846195221,
+    "eval_runtime": 17.3733,
+    "eval_samples": 20000,
+    "eval_samples_per_second": 1151.19,
+    "eval_steps_per_second": 18.016
+}

runs/Jun27_09-32-02_x3006c0s13b1n0/events.out.tfevents.1719481227.x3006c0s13b1n0.3074043.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da5c2461ffda80c2f73435f5f0a0a4beab8c1067f8e9a4d3a8eb855ca35d4df2
+size 405

train_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 1.0,
+    "total_flos": 4.216512416894157e+16,
+    "train_loss": 0.4463165575703874,
+    "train_runtime": 453.3701,
+    "train_samples": 160000,
+    "train_samples_per_second": 352.913,
+    "train_steps_per_second": 0.69,
+    "train_tokens_per_second": 22622.54
+}

trainer_state.json

@@ -0,0 +1,43 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 313,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "step": 313,
+      "total_flos": 4.216512416894157e+16,
+      "train_loss": 0.4463165575703874,
+      "train_runtime": 453.3701,
+      "train_samples_per_second": 352.913,
+      "train_steps_per_second": 0.69,
+      "train_tokens_per_second": 22622.54
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 313,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.216512416894157e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}