End of training

runs/Feb26_20-37-41_b0051077c075/events.out.tfevents.1677443867.b0051077c075.1132.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:653ec58812d01357f0bef34a643c676f75245050fc0eddcfd9c24b4740aea982
-size 6237
+oid sha256:11757cbf9ba59602aa24e51edeb00edacc835d725b37b4fb667ca0ed9cd569b5
+size 6591

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": 1.1450900938752e+17,
-      "train_loss": 3.3688572660405587,
-      "train_runtime": 692.9876,
-      "train_samples_per_second": 5.411,
-      "train_steps_per_second": 0.678
+      "epoch": 6.0,
+      "learning_rate": 4e-05,
+      "loss": 3.2701,
+      "step": 564
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.648871421813965,
+      "eval_runtime": 23.3072,
+      "eval_samples_per_second": 8.581,
+      "eval_steps_per_second": 1.073,
+      "step": 564
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3e-05,
+      "loss": 3.1847,
+      "step": 658
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.699300765991211,
+      "eval_runtime": 22.1301,
+      "eval_samples_per_second": 9.037,
+      "eval_steps_per_second": 1.13,
+      "step": 658
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2e-05,
+      "loss": 3.0959,
+      "step": 752
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.636422634124756,
+      "eval_runtime": 21.8919,
+      "eval_samples_per_second": 9.136,
+      "eval_steps_per_second": 1.142,
+      "step": 752
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 1e-05,
+      "loss": 3.0506,
+      "step": 846
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 2.6463677883148193,
+      "eval_runtime": 22.9819,
+      "eval_samples_per_second": 8.702,
+      "eval_steps_per_second": 1.088,
+      "step": 846
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 3.0497,
+      "step": 940
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 2.63041615486145,
+      "eval_runtime": 23.2242,
+      "eval_samples_per_second": 8.612,
+      "eval_steps_per_second": 1.076,
+      "step": 940
+    },
+    {
+      "epoch": 10.0,
+      "step": 940,
+      "total_flos": 2.2901801877504e+17,
+      "train_loss": 1.5650983120532747,
+      "train_runtime": 702.8978,
+      "train_samples_per_second": 10.67,
+      "train_steps_per_second": 1.337
     }
   ],
-  "max_steps": 470,
-  "num_train_epochs": 5,
-  "total_flos": 1.1450900938752e+17,
+  "max_steps": 940,
+  "num_train_epochs": 10,
+  "total_flos": 2.2901801877504e+17,
   "trial_name": null,
   "trial_params": null
 }