End of training

runs/Feb26_21-20-11_952abec28ae3/events.out.tfevents.1677446416.952abec28ae3.204.16

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5773efbe8444e97cdb238cd3c6f28fb766aaedacd0dc8d5f54f15d165e5c625
-size 6618
+oid sha256:c5ff3d76639c247548a4c32b73959bb298a318234473af15b449cf8b7ede5ace
+size 6972

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 35.0,
-  "global_step": 3290,
+  "epoch": 45.0,
+  "global_step": 4230,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -498,18 +498,158 @@
       "step": 3290
     },
     {
-      "epoch": 35.0,
-      "step": 3290,
-      "total_flos": 1.25446763232e+19,
-      "train_loss": 0.31171516024233,
-      "train_runtime": 1243.3871,
-      "train_samples_per_second": 21.112,
-      "train_steps_per_second": 2.646
+      "epoch": 36.0,
+      "learning_rate": 1e-05,
+      "loss": 2.1715,
+      "step": 3384
+    },
+    {
+      "epoch": 36.0,
+      "eval_loss": 1.7286556959152222,
+      "eval_runtime": 37.366,
+      "eval_samples_per_second": 5.352,
+      "eval_steps_per_second": 0.669,
+      "step": 3384
+    },
+    {
+      "epoch": 37.0,
+      "learning_rate": 7.5e-06,
+      "loss": 2.2125,
+      "step": 3478
+    },
+    {
+      "epoch": 37.0,
+      "eval_loss": 1.6994493007659912,
+      "eval_runtime": 36.8702,
+      "eval_samples_per_second": 5.424,
+      "eval_steps_per_second": 0.678,
+      "step": 3478
+    },
+    {
+      "epoch": 38.0,
+      "learning_rate": 5e-06,
+      "loss": 2.2032,
+      "step": 3572
+    },
+    {
+      "epoch": 38.0,
+      "eval_loss": 1.6896188259124756,
+      "eval_runtime": 37.5355,
+      "eval_samples_per_second": 5.328,
+      "eval_steps_per_second": 0.666,
+      "step": 3572
+    },
+    {
+      "epoch": 39.0,
+      "learning_rate": 2.5e-06,
+      "loss": 2.21,
+      "step": 3666
+    },
+    {
+      "epoch": 39.0,
+      "eval_loss": 1.6792980432510376,
+      "eval_runtime": 37.2056,
+      "eval_samples_per_second": 5.376,
+      "eval_steps_per_second": 0.672,
+      "step": 3666
+    },
+    {
+      "epoch": 40.0,
+      "learning_rate": 0.0,
+      "loss": 2.1837,
+      "step": 3760
+    },
+    {
+      "epoch": 40.0,
+      "eval_loss": 1.6746587753295898,
+      "eval_runtime": 37.0982,
+      "eval_samples_per_second": 5.391,
+      "eval_steps_per_second": 0.674,
+      "step": 3760
+    },
+    {
+      "epoch": 41.0,
+      "learning_rate": 8.88888888888889e-06,
+      "loss": 2.2136,
+      "step": 3854
+    },
+    {
+      "epoch": 41.0,
+      "eval_loss": 1.6727588176727295,
+      "eval_runtime": 36.6175,
+      "eval_samples_per_second": 5.462,
+      "eval_steps_per_second": 0.683,
+      "step": 3854
+    },
+    {
+      "epoch": 42.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.1825,
+      "step": 3948
+    },
+    {
+      "epoch": 42.0,
+      "eval_loss": 1.6641244888305664,
+      "eval_runtime": 36.4688,
+      "eval_samples_per_second": 5.484,
+      "eval_steps_per_second": 0.686,
+      "step": 3948
+    },
+    {
+      "epoch": 43.0,
+      "learning_rate": 4.444444444444445e-06,
+      "loss": 2.1419,
+      "step": 4042
+    },
+    {
+      "epoch": 43.0,
+      "eval_loss": 1.6828693151474,
+      "eval_runtime": 36.8137,
+      "eval_samples_per_second": 5.433,
+      "eval_steps_per_second": 0.679,
+      "step": 4042
+    },
+    {
+      "epoch": 44.0,
+      "learning_rate": 2.2222222222222225e-06,
+      "loss": 2.1695,
+      "step": 4136
+    },
+    {
+      "epoch": 44.0,
+      "eval_loss": 1.6625133752822876,
+      "eval_runtime": 37.3227,
+      "eval_samples_per_second": 5.359,
+      "eval_steps_per_second": 0.67,
+      "step": 4136
+    },
+    {
+      "epoch": 45.0,
+      "learning_rate": 0.0,
+      "loss": 2.1478,
+      "step": 4230
+    },
+    {
+      "epoch": 45.0,
+      "eval_loss": 1.667972445487976,
+      "eval_runtime": 37.5388,
+      "eval_samples_per_second": 5.328,
+      "eval_steps_per_second": 0.666,
+      "step": 4230
+    },
+    {
+      "epoch": 45.0,
+      "step": 4230,
+      "total_flos": 1.61288695584e+19,
+      "train_loss": 0.2412280865031213,
+      "train_runtime": 1234.9371,
+      "train_samples_per_second": 27.329,
+      "train_steps_per_second": 3.425
     }
   ],
-  "max_steps": 3290,
-  "num_train_epochs": 35,
-  "total_flos": 1.25446763232e+19,
+  "max_steps": 4230,
+  "num_train_epochs": 45,
+  "total_flos": 1.61288695584e+19,
   "trial_name": null,
   "trial_params": null
 }