End of training

trainer_state.json

@@ -0,0 +1,165 @@
+{
+  "best_metric": 4.117910861968994,
+  "best_model_checkpoint": "deta-cd45rb-2ah-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": 9.00065132435953e-07,
+      "loss": 4.5965,
+      "step": 4606
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 6.677134037017822,
+      "eval_runtime": 279.3645,
+      "eval_samples_per_second": 6.375,
+      "eval_steps_per_second": 0.798,
+      "step": 4606
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.001302648719061e-07,
+      "loss": 4.4496,
+      "step": 9212
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 6.5967535972595215,
+      "eval_runtime": 277.6199,
+      "eval_samples_per_second": 6.415,
+      "eval_steps_per_second": 0.803,
+      "step": 9212
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7.001736864958749e-07,
+      "loss": 4.0734,
+      "step": 13818
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 6.080860137939453,
+      "eval_runtime": 277.602,
+      "eval_samples_per_second": 6.416,
+      "eval_steps_per_second": 0.803,
+      "step": 13818
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6.00238818931828e-07,
+      "loss": 3.7428,
+      "step": 18424
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 5.441587924957275,
+      "eval_runtime": 284.1842,
+      "eval_samples_per_second": 6.267,
+      "eval_steps_per_second": 0.785,
+      "step": 18424
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 5.002822405557968e-07,
+      "loss": 3.6307,
+      "step": 23030
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 5.47948694229126,
+      "eval_runtime": 284.3229,
+      "eval_samples_per_second": 6.264,
+      "eval_steps_per_second": 0.784,
+      "step": 23030
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.003256621797655e-07,
+      "loss": 3.6208,
+      "step": 27636
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 5.01987886428833,
+      "eval_runtime": 283.9545,
+      "eval_samples_per_second": 6.272,
+      "eval_steps_per_second": 0.785,
+      "step": 27636
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.0036908380373426e-07,
+      "loss": 3.7471,
+      "step": 32242
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 4.527164459228516,
+      "eval_runtime": 283.6165,
+      "eval_samples_per_second": 6.28,
+      "eval_steps_per_second": 0.786,
+      "step": 32242
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.00412505427703e-07,
+      "loss": 3.6253,
+      "step": 36848
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 4.254842281341553,
+      "eval_runtime": 283.2692,
+      "eval_samples_per_second": 6.287,
+      "eval_steps_per_second": 0.787,
+      "step": 36848
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 1.0047763786365609e-07,
+      "loss": 3.5243,
+      "step": 41454
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 4.140212059020996,
+      "eval_runtime": 283.7636,
+      "eval_samples_per_second": 6.276,
+      "eval_steps_per_second": 0.786,
+      "step": 41454
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 5.210594876248372e-10,
+      "loss": 3.4963,
+      "step": 46060
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 4.117910861968994,
+      "eval_runtime": 284.2168,
+      "eval_samples_per_second": 6.266,
+      "eval_steps_per_second": 0.785,
+      "step": 46060
+    },
+    {
+      "epoch": 10.0,
+      "step": 46060,
+      "total_flos": 8.69730749237376e+19,
+      "train_loss": 3.850683614951965,
+      "train_runtime": 47276.3436,
+      "train_samples_per_second": 3.896,
+      "train_steps_per_second": 0.974
+    }
+  ],
+  "max_steps": 46060,
+  "num_train_epochs": 10,
+  "total_flos": 8.69730749237376e+19,
+  "trial_name": null,
+  "trial_params": null
+}