End of training

runs/Feb28_20-00-28_d566756ae0ad/events.out.tfevents.1677614434.d566756ae0ad.260.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d64a92f1aae6476ba510b884c34955f2b8221f2223f42521e94afe1daf291e43
-size 6286
+oid sha256:6843aa41620fdd9e8b04e96303208928d4a5a6057ff4f38c819f5b5918f12a81
+size 6640

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
-  "global_step": 470,
+  "epoch": 10.0,
+  "global_step": 940,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -78,18 +78,88 @@
       "step": 470
     },
     {
-      "epoch": 5.0,
-      "step": 470,
-      "total_flos": 1.1450900938752e+17,
-      "train_loss": 3.4047226276803526,
-      "train_runtime": 644.0168,
-      "train_samples_per_second": 5.823,
-      "train_steps_per_second": 0.73
+      "epoch": 6.0,
+      "learning_rate": 4e-05,
+      "loss": 3.2959,
+      "step": 564
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.6477155685424805,
+      "eval_runtime": 21.1835,
+      "eval_samples_per_second": 9.441,
+      "eval_steps_per_second": 1.18,
+      "step": 564
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3e-05,
+      "loss": 3.2286,
+      "step": 658
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.6884500980377197,
+      "eval_runtime": 20.3071,
+      "eval_samples_per_second": 9.849,
+      "eval_steps_per_second": 1.231,
+      "step": 658
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2e-05,
+      "loss": 3.1364,
+      "step": 752
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.6582536697387695,
+      "eval_runtime": 21.3174,
+      "eval_samples_per_second": 9.382,
+      "eval_steps_per_second": 1.173,
+      "step": 752
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 1e-05,
+      "loss": 3.0872,
+      "step": 846
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 2.666731595993042,
+      "eval_runtime": 20.761,
+      "eval_samples_per_second": 9.633,
+      "eval_steps_per_second": 1.204,
+      "step": 846
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 3.0935,
+      "step": 940
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 2.616997718811035,
+      "eval_runtime": 21.3962,
+      "eval_samples_per_second": 9.347,
+      "eval_steps_per_second": 1.168,
+      "step": 940
+    },
+    {
+      "epoch": 10.0,
+      "step": 940,
+      "total_flos": 2.2901801877504e+17,
+      "train_loss": 1.5841756617769283,
+      "train_runtime": 646.9821,
+      "train_samples_per_second": 11.592,
+      "train_steps_per_second": 1.453
     }
   ],
-  "max_steps": 470,
-  "num_train_epochs": 5,
-  "total_flos": 1.1450900938752e+17,
+  "max_steps": 940,
+  "num_train_epochs": 10,
+  "total_flos": 2.2901801877504e+17,
   "trial_name": null,
   "trial_params": null
 }