End of training

trainer_state.json

@@ -0,0 +1,165 @@
+{
+  "best_metric": 4.255077838897705,
+  "best_model_checkpoint": "deta-cd45rb-8ah-4l\\checkpoint-46060",
+  "epoch": 10.0,
+  "global_step": 46060,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.001085540599218e-07,
+      "loss": 4.0312,
+      "step": 4606
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 5.003675937652588,
+      "eval_runtime": 290.3174,
+      "eval_samples_per_second": 6.135,
+      "eval_steps_per_second": 0.768,
+      "step": 4606
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.001302648719061e-07,
+      "loss": 3.7212,
+      "step": 9212
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.078217506408691,
+      "eval_runtime": 292.8924,
+      "eval_samples_per_second": 6.081,
+      "eval_steps_per_second": 0.761,
+      "step": 9212
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7.001736864958749e-07,
+      "loss": 3.6768,
+      "step": 13818
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 5.191070556640625,
+      "eval_runtime": 287.498,
+      "eval_samples_per_second": 6.195,
+      "eval_steps_per_second": 0.776,
+      "step": 13818
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6.002171081198436e-07,
+      "loss": 3.5347,
+      "step": 18424
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 4.660577297210693,
+      "eval_runtime": 290.0214,
+      "eval_samples_per_second": 6.141,
+      "eval_steps_per_second": 0.769,
+      "step": 18424
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 5.002605297438124e-07,
+      "loss": 3.4744,
+      "step": 23030
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 4.628448963165283,
+      "eval_runtime": 290.2035,
+      "eval_samples_per_second": 6.137,
+      "eval_steps_per_second": 0.768,
+      "step": 23030
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.003256621797655e-07,
+      "loss": 3.4388,
+      "step": 27636
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 4.400201320648193,
+      "eval_runtime": 290.1419,
+      "eval_samples_per_second": 6.138,
+      "eval_steps_per_second": 0.769,
+      "step": 27636
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.003473729917499e-07,
+      "loss": 3.4019,
+      "step": 32242
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 4.3570098876953125,
+      "eval_runtime": 286.9928,
+      "eval_samples_per_second": 6.206,
+      "eval_steps_per_second": 0.777,
+      "step": 32242
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.00412505427703e-07,
+      "loss": 3.3708,
+      "step": 36848
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 4.308250904083252,
+      "eval_runtime": 290.8521,
+      "eval_samples_per_second": 6.123,
+      "eval_steps_per_second": 0.767,
+      "step": 36848
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 1.0045592705167173e-07,
+      "loss": 3.3474,
+      "step": 41454
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 4.273312568664551,
+      "eval_runtime": 290.6227,
+      "eval_samples_per_second": 6.128,
+      "eval_steps_per_second": 0.767,
+      "step": 41454
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4.993486756404689e-10,
+      "loss": 3.338,
+      "step": 46060
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 4.255077838897705,
+      "eval_runtime": 292.0237,
+      "eval_samples_per_second": 6.099,
+      "eval_steps_per_second": 0.764,
+      "step": 46060
+    },
+    {
+      "epoch": 10.0,
+      "step": 46060,
+      "total_flos": 8.85437678676096e+19,
+      "train_loss": 3.533535508202616,
+      "train_runtime": 51646.3651,
+      "train_samples_per_second": 3.567,
+      "train_steps_per_second": 0.892
+    }
+  ],
+  "max_steps": 46060,
+  "num_train_epochs": 10,
+  "total_flos": 8.85437678676096e+19,
+  "trial_name": null,
+  "trial_params": null
+}