Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:110bca5766adb8d423e9bf795b6c6fe25cc8c6984d61d131492a592d3a013eb9
+oid sha256:a50dd62149d8fa5130dab9c47840780adecc7fe832f5a78cdfa1c472ea332452
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1433bd821eee7bfb22aec6100cf421da3fb94a9ac15530afc970cb9f8e79ad2a
+oid sha256:e7ee16962f8ddf2bc5bd916ebd4a947447a25b62cdb819e2432b9882d0799628
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6598ba8d28457ca982679bb4678b929548195f1692dc85503bc0d791879d46e
+oid sha256:207198ff45c079aff8e96fb155ce64eadd6265eb7e7f1ba1f48dca470b10a3e3
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
+oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.384419560432434,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 2.2666666666666666,
+  "best_metric": 1.3802986145019531,
+  "best_model_checkpoint": "./outputs/checkpoint-1800",
+  "epoch": 2.4,
   "eval_steps": 100,
-  "global_step": 1700,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,6 +245,20 @@
       "eval_samples_per_second": 15.559,
       "eval_steps_per_second": 1.952,
       "step": 1700
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0002,
+      "loss": 1.1295,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 1.3802986145019531,
+      "eval_runtime": 93.2911,
+      "eval_samples_per_second": 15.553,
+      "eval_steps_per_second": 1.951,
+      "step": 1800
     }
   ],
   "logging_steps": 100,
@@ -252,7 +266,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.940658531844096e+16,
+  "total_flos": 1.0524178054397952e+17,
   "trial_name": null,
   "trial_params": null
 }