End of training

runs/Feb28_16-17-43_7c779bfb7013/events.out.tfevents.1677601069.7c779bfb7013.343.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:996954c7aaa28e8501661f0720e61563de446b6e1d499b7b0cbbc4f339136b4a
-size 7956
+oid sha256:866915fec5e91db69625be44827d9b6dd3cb6a3bcfa477ca370cd0cabcd4e0d6
+size 8310

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.0,
-  "global_step": 658,
+  "epoch": 15.0,
+  "global_step": 1410,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -106,18 +106,130 @@
       "step": 658
     },
     {
-      "epoch": 7.0,
-      "step": 658,
-      "total_flos": 2.50893526464e+18,
-      "train_loss": 1.5139910805189138,
-      "train_runtime": 964.856,
-      "train_samples_per_second": 5.441,
-      "train_steps_per_second": 0.682
+      "epoch": 8.0,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 2.5342,
+      "step": 752
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.9365949630737305,
+      "eval_runtime": 35.1567,
+      "eval_samples_per_second": 5.689,
+      "eval_steps_per_second": 0.711,
+      "step": 752
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4e-05,
+      "loss": 2.5519,
+      "step": 846
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.9736474752426147,
+      "eval_runtime": 35.9727,
+      "eval_samples_per_second": 5.56,
+      "eval_steps_per_second": 0.695,
+      "step": 846
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 2.4988,
+      "step": 940
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.881581425666809,
+      "eval_runtime": 35.6769,
+      "eval_samples_per_second": 5.606,
+      "eval_steps_per_second": 0.701,
+      "step": 940
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 2.5101,
+      "step": 1034
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.8453679084777832,
+      "eval_runtime": 33.4013,
+      "eval_samples_per_second": 5.988,
+      "eval_steps_per_second": 0.748,
+      "step": 1034
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 2e-05,
+      "loss": 2.4441,
+      "step": 1128
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.8143038749694824,
+      "eval_runtime": 34.7625,
+      "eval_samples_per_second": 5.753,
+      "eval_steps_per_second": 0.719,
+      "step": 1128
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.3857,
+      "step": 1222
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 1.7919152975082397,
+      "eval_runtime": 33.975,
+      "eval_samples_per_second": 5.887,
+      "eval_steps_per_second": 0.736,
+      "step": 1222
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.2877,
+      "step": 1316
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 1.7400457859039307,
+      "eval_runtime": 34.7007,
+      "eval_samples_per_second": 5.764,
+      "eval_steps_per_second": 0.72,
+      "step": 1316
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 0.0,
+      "loss": 2.3013,
+      "step": 1410
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 1.7408628463745117,
+      "eval_runtime": 34.5398,
+      "eval_samples_per_second": 5.79,
+      "eval_steps_per_second": 0.724,
+      "step": 1410
+    },
+    {
+      "epoch": 15.0,
+      "step": 1410,
+      "total_flos": 5.3762898528e+18,
+      "train_loss": 1.3009196721070202,
+      "train_runtime": 1911.8077,
+      "train_samples_per_second": 5.884,
+      "train_steps_per_second": 0.738
     }
   ],
-  "max_steps": 658,
-  "num_train_epochs": 7,
-  "total_flos": 2.50893526464e+18,
+  "max_steps": 1410,
+  "num_train_epochs": 15,
+  "total_flos": 5.3762898528e+18,
   "trial_name": null,
   "trial_params": null
 }