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-1
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # nano_cls-1
 
 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: 0.5919
+- F1: 0.8216
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_f1": 0.8215811965811965,
+    "eval_loss": 0.5918742418289185,
+    "eval_runtime": 18.3513,
+    "eval_samples": 20000,
+    "eval_samples_per_second": 1089.842,
+    "eval_steps_per_second": 17.056,
+    "total_flos": 4.209776888119296e+16,
+    "train_loss": 0.4081730590820313,
+    "train_runtime": 544.5651,
+    "train_samples": 160000,
+    "train_samples_per_second": 293.812,
+    "train_steps_per_second": 1.148,
+    "train_tokens_per_second": 18803.995
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_f1": 0.8215811965811965,
+    "eval_loss": 0.5918742418289185,
+    "eval_runtime": 18.3513,
+    "eval_samples": 20000,
+    "eval_samples_per_second": 1089.842,
+    "eval_steps_per_second": 17.056
+}

runs/Jun26_20-33-53_x3005c0s25b1n0/events.out.tfevents.1719434678.x3005c0s25b1n0.2293679.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7304b0ad2adb9801ed77fdad9426dd041038a0bcef0ebdfee3d5f2100b2fe3be
+size 405

train_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 1.0,
+    "total_flos": 4.209776888119296e+16,
+    "train_loss": 0.4081730590820313,
+    "train_runtime": 544.5651,
+    "train_samples": 160000,
+    "train_samples_per_second": 293.812,
+    "train_steps_per_second": 1.148,
+    "train_tokens_per_second": 18803.995
+}

trainer_state.json

@@ -0,0 +1,50 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 625,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.995232582092285,
+      "learning_rate": 5e-05,
+      "loss": 0.4298,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "step": 625,
+      "total_flos": 4.209776888119296e+16,
+      "train_loss": 0.4081730590820313,
+      "train_runtime": 544.5651,
+      "train_samples_per_second": 293.812,
+      "train_steps_per_second": 1.148,
+      "train_tokens_per_second": 18803.995
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 625,
+  "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": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.209776888119296e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}