End of training

runs/Feb26_18-29-17_952abec28ae3/events.out.tfevents.1677436161.952abec28ae3.204.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47b8ce2ecfd4ea0646b6a2771ecb5c1c17ca6e19c253c96811f71af2cf36b482
-size 6617
+oid sha256:d6099c14cce2e1a1454759cbb614ad70a9ead42d2cb64b1752fac545f3bf5b15
+size 6971

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
-  "global_step": 470,
+  "epoch": 10.0,
+  "global_step": 940,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -78,18 +78,88 @@
       "step": 470
     },
     {
-      "epoch": 5.0,
-      "step": 470,
-      "total_flos": 1.7920966176e+18,
-      "train_loss": 2.7582357853016957,
-      "train_runtime": 1233.6665,
-      "train_samples_per_second": 3.04,
-      "train_steps_per_second": 0.381
+      "epoch": 6.0,
+      "learning_rate": 4e-05,
+      "loss": 2.5099,
+      "step": 564
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.029414415359497,
+      "eval_runtime": 36.8084,
+      "eval_samples_per_second": 5.434,
+      "eval_steps_per_second": 0.679,
+      "step": 564
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3e-05,
+      "loss": 2.5365,
+      "step": 658
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.8844919204711914,
+      "eval_runtime": 36.3496,
+      "eval_samples_per_second": 5.502,
+      "eval_steps_per_second": 0.688,
+      "step": 658
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2e-05,
+      "loss": 2.4593,
+      "step": 752
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.869893193244934,
+      "eval_runtime": 36.7235,
+      "eval_samples_per_second": 5.446,
+      "eval_steps_per_second": 0.681,
+      "step": 752
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 1e-05,
+      "loss": 2.4248,
+      "step": 846
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.794630765914917,
+      "eval_runtime": 37.5145,
+      "eval_samples_per_second": 5.331,
+      "eval_steps_per_second": 0.666,
+      "step": 846
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 2.4017,
+      "step": 940
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.7905255556106567,
+      "eval_runtime": 37.4985,
+      "eval_samples_per_second": 5.334,
+      "eval_steps_per_second": 0.667,
+      "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
     }
   ],
-  "max_steps": 470,
-  "num_train_epochs": 5,
-  "total_flos": 1.7920966176e+18,
+  "max_steps": 940,
+  "num_train_epochs": 10,
+  "total_flos": 3.5841932352e+18,
   "trial_name": null,
   "trial_params": null
 }