End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.6842443729903537,
+    "eval_loss": 0.5816319584846497,
+    "eval_runtime": 111.7033,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 361.941,
+    "eval_steps_per_second": 11.316,
+    "train_loss": 0.5902769758531864,
+    "train_runtime": 11488.0766,
+    "train_samples": 363846,
+    "train_samples_per_second": 126.686,
+    "train_steps_per_second": 0.99
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.6842443729903537,
+    "eval_loss": 0.5816319584846497,
+    "eval_runtime": 111.7033,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 361.941,
+    "eval_steps_per_second": 11.316
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.5902769758531864,
+    "train_runtime": 11488.0766,
+    "train_samples": 363846,
+    "train_samples_per_second": 126.686,
+    "train_steps_per_second": 0.99
+}

trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.999120531199156,
+  "global_step": 11368,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.792839549612949e-05,
+      "loss": 0.659,
+      "step": 500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.572923997185081e-05,
+      "loss": 0.611,
+      "step": 1000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.3530084447572136e-05,
+      "loss": 0.6055,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.1335327234342017e-05,
+      "loss": 0.6116,
+      "step": 2000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.9136171710063336e-05,
+      "loss": 0.6019,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6733860994311155,
+      "eval_loss": 0.5970579385757446,
+      "eval_runtime": 112.0914,
+      "eval_samples_per_second": 360.688,
+      "eval_steps_per_second": 11.277,
+      "step": 2842
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.693701618578466e-05,
+      "loss": 0.5947,
+      "step": 3000
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 3.473786066150598e-05,
+      "loss": 0.5897,
+      "step": 3500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 3.253870513722731e-05,
+      "loss": 0.5881,
+      "step": 4000
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 3.033954961294863e-05,
+      "loss": 0.5853,
+      "step": 4500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.814479239971851e-05,
+      "loss": 0.5839,
+      "step": 5000
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 2.5945636875439833e-05,
+      "loss": 0.5849,
+      "step": 5500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6843185753153599,
+      "eval_loss": 0.5835733413696289,
+      "eval_runtime": 111.952,
+      "eval_samples_per_second": 361.137,
+      "eval_steps_per_second": 11.291,
+      "step": 5685
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 2.3746481351161152e-05,
+      "loss": 0.5784,
+      "step": 6000
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.154732582688248e-05,
+      "loss": 0.5803,
+      "step": 6500
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.93481703026038e-05,
+      "loss": 0.58,
+      "step": 7000
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 1.715341308937368e-05,
+      "loss": 0.5807,
+      "step": 7500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.4954257565095003e-05,
+      "loss": 0.5813,
+      "step": 8000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 1.2755102040816327e-05,
+      "loss": 0.5819,
+      "step": 8500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6855305466237942,
+      "eval_loss": 0.5815231204032898,
+      "eval_runtime": 111.9533,
+      "eval_samples_per_second": 361.133,
+      "eval_steps_per_second": 11.29,
+      "step": 8527
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 1.055594651653765e-05,
+      "loss": 0.5771,
+      "step": 9000
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 8.356790992258972e-06,
+      "loss": 0.5794,
+      "step": 9500
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 6.162033779028853e-06,
+      "loss": 0.5802,
+      "step": 10000
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 3.962878254750176e-06,
+      "loss": 0.5831,
+      "step": 10500
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 1.7637227304714988e-06,
+      "loss": 0.5768,
+      "step": 11000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6842443729903537,
+      "eval_loss": 0.5816319584846497,
+      "eval_runtime": 111.9533,
+      "eval_samples_per_second": 361.133,
+      "eval_steps_per_second": 11.29,
+      "step": 11368
+    },
+    {
+      "epoch": 4.0,
+      "step": 11368,
+      "total_flos": 5.063018043612856e+17,
+      "train_loss": 0.5902769758531864,
+      "train_runtime": 11488.0766,
+      "train_samples_per_second": 126.686,
+      "train_steps_per_second": 0.99
+    }
+  ],
+  "max_steps": 11368,
+  "num_train_epochs": 4,
+  "total_flos": 5.063018043612856e+17,
+  "trial_name": null,
+  "trial_params": null
+}