End of training

README.md

@@ -3,6 +3,8 @@ license: mit
 base_model: roberta-base
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: HorAI-medium-17k-roberta-V2
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # HorAI-medium-17k-roberta-V2
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3179
+- Accuracy: 0.8314
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8314176245210728,
+    "eval_loss": 1.317917823791504,
+    "eval_runtime": 11.9903,
+    "eval_samples": 1566,
+    "eval_samples_per_second": 130.606,
+    "eval_steps_per_second": 2.752,
+    "train_loss": 0.13995733648127837,
+    "train_runtime": 3316.8175,
+    "train_samples": 15658,
+    "train_samples_per_second": 47.208,
+    "train_steps_per_second": 1.969
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8314176245210728,
+    "eval_loss": 1.317917823791504,
+    "eval_runtime": 11.9903,
+    "eval_samples": 1566,
+    "eval_samples_per_second": 130.606,
+    "eval_steps_per_second": 2.752
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.13995733648127837,
+    "train_runtime": 3316.8175,
+    "train_samples": 15658,
+    "train_samples_per_second": 47.208,
+    "train_steps_per_second": 1.969
+}

trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 6530,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.8468606431852987e-05,
+      "loss": 0.434,
+      "step": 500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.6937212863705975e-05,
+      "loss": 0.3029,
+      "step": 1000
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.540581929555896e-05,
+      "loss": 0.266,
+      "step": 1500
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 1.3874425727411946e-05,
+      "loss": 0.2028,
+      "step": 2000
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 1.2343032159264931e-05,
+      "loss": 0.1468,
+      "step": 2500
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 1.081163859111792e-05,
+      "loss": 0.1093,
+      "step": 3000
+    },
+    {
+      "epoch": 5.36,
+      "learning_rate": 9.280245022970904e-06,
+      "loss": 0.0966,
+      "step": 3500
+    },
+    {
+      "epoch": 6.13,
+      "learning_rate": 7.748851454823891e-06,
+      "loss": 0.0746,
+      "step": 4000
+    },
+    {
+      "epoch": 6.89,
+      "learning_rate": 6.217457886676877e-06,
+      "loss": 0.062,
+      "step": 4500
+    },
+    {
+      "epoch": 7.66,
+      "learning_rate": 4.686064318529863e-06,
+      "loss": 0.0457,
+      "step": 5000
+    },
+    {
+      "epoch": 8.42,
+      "learning_rate": 3.1546707503828488e-06,
+      "loss": 0.0361,
+      "step": 5500
+    },
+    {
+      "epoch": 9.19,
+      "learning_rate": 1.6232771822358347e-06,
+      "loss": 0.0299,
+      "step": 6000
+    },
+    {
+      "epoch": 9.95,
+      "learning_rate": 9.188361408882085e-08,
+      "loss": 0.0196,
+      "step": 6500
+    },
+    {
+      "epoch": 10.0,
+      "step": 6530,
+      "total_flos": 1.02994822620672e+16,
+      "train_loss": 0.13995733648127837,
+      "train_runtime": 3316.8175,
+      "train_samples_per_second": 47.208,
+      "train_steps_per_second": 1.969
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6530,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.02994822620672e+16,
+  "trial_name": null,
+  "trial_params": null
+}