Training in progress, step 1900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bff79a1886833cc728d86fecb7cea10054e4cc718ebf3f8cb04269b980303e9c
+oid sha256:b0ad383ff5c1ca432c7eb7f004459e86ec446f6336bbe22f7837fbc1622283e0
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bda85dfd1f0f2258ec1cbf31012e4a4d5cee688962db94252811c3cdceb0a3bb
+oid sha256:cbf975638616e1ce382f110c7bfdff8bbebaa42a491f319760ed57a5f0dda2df
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f3691462eb076e36147b1de487da24fc91bbb236e43e5130eee12dae621565f
+oid sha256:6921adec0cc9a9c9df2dc7b65fb0eb0e5c535cd65447579a8ab1f2c8e71d1dd4
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
+oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9806030988693237,
-  "best_model_checkpoint": "./outputs/checkpoint-1800",
-  "epoch": 2.5568181818181817,
+  "best_metric": 1.9745317697525024,
+  "best_model_checkpoint": "./outputs/checkpoint-1900",
+  "epoch": 2.6988636363636362,
   "eval_steps": 100,
-  "global_step": 1800,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -259,6 +259,20 @@
       "eval_samples_per_second": 28.593,
       "eval_steps_per_second": 3.584,
       "step": 1800
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.0002,
+      "loss": 2.0924,
+      "step": 1900
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 1.9745317697525024,
+      "eval_runtime": 52.0357,
+      "eval_samples_per_second": 28.673,
+      "eval_steps_per_second": 3.594,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
@@ -266,7 +280,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.22624542856192e+16,
+  "total_flos": 5.51482666140672e+16,
   "trial_name": null,
   "trial_params": null
 }