End of training

README.md

@@ -3,6 +3,8 @@ license: mit
 base_model: roberta-large
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: HorAI-V2-47k-large-e1-lr-6
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # HorAI-V2-47k-large-e1-lr-6
 
 This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3896
+- Accuracy: 0.8309
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.830948121645796,
+    "eval_loss": 0.38962292671203613,
+    "eval_runtime": 19.7419,
+    "eval_samples": 2236,
+    "eval_samples_per_second": 113.261,
+    "eval_steps_per_second": 14.183,
+    "train_loss": 0.4227196282855535,
+    "train_runtime": 1206.6968,
+    "train_samples": 47198,
+    "train_samples_per_second": 39.113,
+    "train_steps_per_second": 2.445
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.830948121645796,
+    "eval_loss": 0.38962292671203613,
+    "eval_runtime": 19.7419,
+    "eval_samples": 2236,
+    "eval_samples_per_second": 113.261,
+    "eval_steps_per_second": 14.183
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.4227196282855535,
+    "train_runtime": 1206.6968,
+    "train_samples": 47198,
+    "train_samples_per_second": 39.113,
+    "train_steps_per_second": 2.445
+}

trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2950,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "learning_rate": 8.305084745762712e-07,
+      "loss": 0.634,
+      "step": 500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 6.610169491525423e-07,
+      "loss": 0.4411,
+      "step": 1000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.915254237288136e-07,
+      "loss": 0.3908,
+      "step": 1500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.220338983050847e-07,
+      "loss": 0.3642,
+      "step": 2000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.5254237288135593e-07,
+      "loss": 0.3506,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "step": 2950,
+      "total_flos": 5498162060794368.0,
+      "train_loss": 0.4227196282855535,
+      "train_runtime": 1206.6968,
+      "train_samples_per_second": 39.113,
+      "train_steps_per_second": 2.445
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2950,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 5498162060794368.0,
+  "trial_name": null,
+  "trial_params": null
+}