End of training

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8333333333333334,
+    "eval_loss": 0.701846718788147,
+    "eval_runtime": 5.0813,
+    "eval_samples_per_second": 80.295,
+    "eval_steps_per_second": 10.037,
+    "train_loss": 1.276922034557303,
+    "train_runtime": 342.3245,
+    "train_samples_per_second": 33.725,
+    "train_steps_per_second": 4.221
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8333333333333334,
+    "eval_loss": 0.701846718788147,
+    "eval_runtime": 5.0813,
+    "eval_samples_per_second": 80.295,
+    "eval_steps_per_second": 10.037
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.0,
+    "train_loss": 1.276922034557303,
+    "train_runtime": 342.3245,
+    "train_samples_per_second": 33.725,
+    "train_steps_per_second": 4.221
+}

trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 1445,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8615916955017305e-05,
+      "loss": 2.2312,
+      "step": 100
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7231833910034604e-05,
+      "loss": 1.9053,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7132352941176471,
+      "eval_loss": 1.368030309677124,
+      "eval_runtime": 5.1707,
+      "eval_samples_per_second": 78.907,
+      "eval_steps_per_second": 9.863,
+      "step": 289
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.5847750865051904e-05,
+      "loss": 1.6154,
+      "step": 300
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.4463667820069205e-05,
+      "loss": 1.4013,
+      "step": 400
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 1.3079584775086506e-05,
+      "loss": 1.2788,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7965686274509803,
+      "eval_loss": 0.949878990650177,
+      "eval_runtime": 5.1726,
+      "eval_samples_per_second": 78.878,
+      "eval_steps_per_second": 9.86,
+      "step": 578
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.1695501730103806e-05,
+      "loss": 1.2022,
+      "step": 600
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.0311418685121109e-05,
+      "loss": 1.1687,
+      "step": 700
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 8.92733564013841e-06,
+      "loss": 1.1232,
+      "step": 800
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7279411764705882,
+      "eval_loss": 0.8679393529891968,
+      "eval_runtime": 5.1694,
+      "eval_samples_per_second": 78.925,
+      "eval_steps_per_second": 9.866,
+      "step": 867
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 7.5432525951557104e-06,
+      "loss": 1.0408,
+      "step": 900
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 6.159169550173011e-06,
+      "loss": 1.0277,
+      "step": 1000
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 4.775086505190312e-06,
+      "loss": 1.0373,
+      "step": 1100
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8088235294117647,
+      "eval_loss": 0.732408344745636,
+      "eval_runtime": 5.1695,
+      "eval_samples_per_second": 78.924,
+      "eval_steps_per_second": 9.865,
+      "step": 1156
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 3.3910034602076125e-06,
+      "loss": 1.0172,
+      "step": 1200
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 2.0069204152249138e-06,
+      "loss": 0.9715,
+      "step": 1300
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 6.228373702422146e-07,
+      "loss": 0.9658,
+      "step": 1400
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8333333333333334,
+      "eval_loss": 0.701846718788147,
+      "eval_runtime": 5.1658,
+      "eval_samples_per_second": 78.982,
+      "eval_steps_per_second": 9.873,
+      "step": 1445
+    },
+    {
+      "epoch": 5.0,
+      "step": 1445,
+      "total_flos": 8.947091674631578e+17,
+      "train_loss": 1.276922034557303,
+      "train_runtime": 342.3245,
+      "train_samples_per_second": 33.725,
+      "train_steps_per_second": 4.221
+    }
+  ],
+  "max_steps": 1445,
+  "num_train_epochs": 5,
+  "total_flos": 8.947091674631578e+17,
+  "trial_name": null,
+  "trial_params": null
+}