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:d645fe07bc1b1643959142a3b6b98de72bb992fc8297c8ff8f014fab0a56a890
+oid sha256:8e35174dd40422a40426a4e41cf7840ec7fac79e45bb80949a45c2cde28a1ac3
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:036e21991ebc9b60e5015554062babf78c22feb9c6aa1d392e2dae2646602c8c
+oid sha256:3088c8b0ec2320ddcf63abfaf562c9e933ce3911fae930797203e7edbb150db9
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f821cd4a85f081d11b51cd13f90ea849d7c4ecdb1f73ca599d9604f19ebea037
+oid sha256:a9b90d357685719c57fa133e4a1df8bf3bcfd50a3a24b52028d35927fe9cc447
 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": 2.231445789337158,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 1.238615664845173,
+  "best_metric": 2.2156155109405518,
+  "best_model_checkpoint": "./outputs/checkpoint-1800",
+  "epoch": 1.3114754098360657,
   "eval_steps": 100,
-  "global_step": 1700,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,13 +245,27 @@
       "eval_samples_per_second": 30.457,
       "eval_steps_per_second": 3.811,
       "step": 1700
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002,
+      "loss": 2.193,
+      "step": 1800
+    },
+    {
+      "epoch": 1.31,
+      "eval_loss": 2.2156155109405518,
+      "eval_runtime": 217.8526,
+      "eval_samples_per_second": 28.799,
+      "eval_steps_per_second": 3.603,
+      "step": 1800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.002024074356736e+16,
+  "total_flos": 5.2948760965632e+16,
   "trial_name": null,
   "trial_params": null
 }