End of training

runs/Feb26_18-51-23_952abec28ae3/events.out.tfevents.1677437488.952abec28ae3.204.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26ec7dec2fbabd5ec43049311c9a9f89072555ae4808103ab135dcc5c10dac46
-size 6617
+oid sha256:f53389cf87d70d5578e1c3eb5f7eb0c8c516640e7cb31903ab34200db8471bcc
+size 6971

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
-  "global_step": 940,
+  "epoch": 15.0,
+  "global_step": 1410,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,18 +148,88 @@
       "step": 940
     },
     {
-      "epoch": 10.0,
-      "step": 940,
-      "total_flos": 3.5841932352e+18,
-      "train_loss": 1.233215185936461,
-      "train_runtime": 1242.3857,
-      "train_samples_per_second": 6.037,
-      "train_steps_per_second": 0.757
+      "epoch": 11.0,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 2.4523,
+      "step": 1034
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.8318734169006348,
+      "eval_runtime": 36.8394,
+      "eval_samples_per_second": 5.429,
+      "eval_steps_per_second": 0.679,
+      "step": 1034
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 2e-05,
+      "loss": 2.4407,
+      "step": 1128
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.8369686603546143,
+      "eval_runtime": 37.09,
+      "eval_samples_per_second": 5.392,
+      "eval_steps_per_second": 0.674,
+      "step": 1128
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.3727,
+      "step": 1222
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 1.8001278638839722,
+      "eval_runtime": 36.6653,
+      "eval_samples_per_second": 5.455,
+      "eval_steps_per_second": 0.682,
+      "step": 1222
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.317,
+      "step": 1316
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 1.7492361068725586,
+      "eval_runtime": 37.2728,
+      "eval_samples_per_second": 5.366,
+      "eval_steps_per_second": 0.671,
+      "step": 1316
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 0.0,
+      "loss": 2.3292,
+      "step": 1410
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 1.7530813217163086,
+      "eval_runtime": 36.325,
+      "eval_samples_per_second": 5.506,
+      "eval_steps_per_second": 0.688,
+      "step": 1410
+    },
+    {
+      "epoch": 15.0,
+      "step": 1410,
+      "total_flos": 5.3762898528e+18,
+      "train_loss": 0.7941258856590758,
+      "train_runtime": 1222.3381,
+      "train_samples_per_second": 9.204,
+      "train_steps_per_second": 1.154
     }
   ],
-  "max_steps": 940,
-  "num_train_epochs": 10,
-  "total_flos": 3.5841932352e+18,
+  "max_steps": 1410,
+  "num_train_epochs": 15,
+  "total_flos": 5.3762898528e+18,
   "trial_name": null,
   "trial_params": null
 }