End of training

runs/Feb28_15-54-30_7c779bfb7013/events.out.tfevents.1677599675.7c779bfb7013.343.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0a5fd7531b48f08d8e583a95477cbf4bd0b6aeeceb04582d97ac594bbb5cf31
-size 6243
+oid sha256:7020ef59b9f12b4d0db2ab12de3bf9ea99237937cb8f3ba2f219e4ca3f9bde9c
+size 6597

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
-  "global_step": 282,
+  "epoch": 7.0,
+  "global_step": 658,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -50,18 +50,74 @@
       "step": 282
     },
     {
-      "epoch": 3.0,
-      "step": 282,
-      "total_flos": 1.07525797056e+18,
-      "train_loss": 3.0334743202155363,
-      "train_runtime": 718.9206,
-      "train_samples_per_second": 3.13,
-      "train_steps_per_second": 0.392
+      "epoch": 4.0,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 2.7515,
+      "step": 376
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.964645504951477,
+      "eval_runtime": 35.4193,
+      "eval_samples_per_second": 5.647,
+      "eval_steps_per_second": 0.706,
+      "step": 376
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 2.724,
+      "step": 470
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.1284220218658447,
+      "eval_runtime": 34.8555,
+      "eval_samples_per_second": 5.738,
+      "eval_steps_per_second": 0.717,
+      "step": 470
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 2.6193,
+      "step": 564
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.9379758834838867,
+      "eval_runtime": 36.3088,
+      "eval_samples_per_second": 5.508,
+      "eval_steps_per_second": 0.689,
+      "step": 564
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.0,
+      "loss": 2.5032,
+      "step": 658
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.9285995960235596,
+      "eval_runtime": 35.9858,
+      "eval_samples_per_second": 5.558,
+      "eval_steps_per_second": 0.695,
+      "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
     }
   ],
-  "max_steps": 282,
-  "num_train_epochs": 3,
-  "total_flos": 1.07525797056e+18,
+  "max_steps": 658,
+  "num_train_epochs": 7,
+  "total_flos": 2.50893526464e+18,
   "trial_name": null,
   "trial_params": null
 }