End of training

runs/Feb26_20-34-17_952abec28ae3/events.out.tfevents.1677443662.952abec28ae3.204.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87e0f9091ca844e9978d01d0f5e372c356c7bbbd503480010dcb11b07edf6b07
-size 6618
+oid sha256:cf0a8abba9725965319b9f228c4a042b03c24398a5b81e9bc29c14029388c9f5
+size 6972

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 30.0,
-  "global_step": 2820,
+  "epoch": 35.0,
+  "global_step": 3290,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -428,18 +428,88 @@
       "step": 2820
     },
     {
-      "epoch": 30.0,
-      "step": 2820,
-      "total_flos": 1.07525797056e+19,
-      "train_loss": 0.3677567448176391,
-      "train_runtime": 1223.17,
-      "train_samples_per_second": 18.395,
-      "train_steps_per_second": 2.305
+      "epoch": 31.0,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 2.1863,
+      "step": 2914
+    },
+    {
+      "epoch": 31.0,
+      "eval_loss": 1.6801691055297852,
+      "eval_runtime": 37.7204,
+      "eval_samples_per_second": 5.302,
+      "eval_steps_per_second": 0.663,
+      "step": 2914
+    },
+    {
+      "epoch": 32.0,
+      "learning_rate": 8.571428571428573e-06,
+      "loss": 2.2009,
+      "step": 3008
+    },
+    {
+      "epoch": 32.0,
+      "eval_loss": 1.6939789056777954,
+      "eval_runtime": 37.6669,
+      "eval_samples_per_second": 5.31,
+      "eval_steps_per_second": 0.664,
+      "step": 3008
+    },
+    {
+      "epoch": 33.0,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 2.1894,
+      "step": 3102
+    },
+    {
+      "epoch": 33.0,
+      "eval_loss": 1.6720386743545532,
+      "eval_runtime": 38.2727,
+      "eval_samples_per_second": 5.226,
+      "eval_steps_per_second": 0.653,
+      "step": 3102
+    },
+    {
+      "epoch": 34.0,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 2.1759,
+      "step": 3196
+    },
+    {
+      "epoch": 34.0,
+      "eval_loss": 1.6699862480163574,
+      "eval_runtime": 37.7344,
+      "eval_samples_per_second": 5.3,
+      "eval_steps_per_second": 0.663,
+      "step": 3196
+    },
+    {
+      "epoch": 35.0,
+      "learning_rate": 0.0,
+      "loss": 2.1575,
+      "step": 3290
+    },
+    {
+      "epoch": 35.0,
+      "eval_loss": 1.6713430881500244,
+      "eval_runtime": 36.971,
+      "eval_samples_per_second": 5.41,
+      "eval_steps_per_second": 0.676,
+      "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
     }
   ],
-  "max_steps": 2820,
-  "num_train_epochs": 30,
-  "total_flos": 1.07525797056e+19,
+  "max_steps": 3290,
+  "num_train_epochs": 35,
+  "total_flos": 1.25446763232e+19,
   "trial_name": null,
   "trial_params": null
 }