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-lr1-5-batch8
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # HorAI-V2-47k-large-lr1-5-batch8
 
 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: 0.3406
+- Accuracy: 0.8573
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.8573345259391771,
+    "eval_loss": 0.3406178951263428,
+    "eval_runtime": 8.5441,
+    "eval_samples": 2236,
+    "eval_samples_per_second": 261.7,
+    "eval_steps_per_second": 32.771,
+    "train_loss": 0.368828774145094,
+    "train_runtime": 1338.0666,
+    "train_samples": 47198,
+    "train_samples_per_second": 35.273,
+    "train_steps_per_second": 4.409
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.8573345259391771,
+    "eval_loss": 0.3406178951263428,
+    "eval_runtime": 8.5441,
+    "eval_samples": 2236,
+    "eval_samples_per_second": 261.7,
+    "eval_steps_per_second": 32.771
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.368828774145094,
+    "train_runtime": 1338.0666,
+    "train_samples": 47198,
+    "train_samples_per_second": 35.273,
+    "train_steps_per_second": 4.409
+}

trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 5900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.152542372881356e-06,
+      "loss": 0.5256,
+      "step": 500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 8.305084745762712e-06,
+      "loss": 0.4113,
+      "step": 1000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 7.4576271186440685e-06,
+      "loss": 0.3918,
+      "step": 1500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 6.610169491525424e-06,
+      "loss": 0.3881,
+      "step": 2000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 5.7627118644067805e-06,
+      "loss": 0.3572,
+      "step": 2500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.915254237288136e-06,
+      "loss": 0.3509,
+      "step": 3000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.067796610169492e-06,
+      "loss": 0.3447,
+      "step": 3500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.2203389830508473e-06,
+      "loss": 0.3426,
+      "step": 4000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.372881355932204e-06,
+      "loss": 0.3318,
+      "step": 4500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.5254237288135596e-06,
+      "loss": 0.3324,
+      "step": 5000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.779661016949153e-07,
+      "loss": 0.3303,
+      "step": 5500
+    },
+    {
+      "epoch": 1.0,
+      "step": 5900,
+      "total_flos": 5498162060794368.0,
+      "train_loss": 0.368828774145094,
+      "train_runtime": 1338.0666,
+      "train_samples_per_second": 35.273,
+      "train_steps_per_second": 4.409
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5900,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 5498162060794368.0,
+  "trial_name": null,
+  "trial_params": null
+}