Training in progress, step 3500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94f60540ceba67b43edb961d9eb68ceeb8df14ff6b8a52a2435f2d6f547b8032
+oid sha256:766823c3351c436a73f412e2d52b8493d7080a8306cdf3fd6d37c248da77694a
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9be048dbcb5cff8f9e3dcee217ddeb6360f254536160be606b4b70ca5c2ea750
+oid sha256:b91c4e67a8aa750e8008400aa454f6ceb88e26b5e996d2c8b5f67663947fb71d
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49538dce3facebf1422d6e704db43c3d118b4ba238927a55894a7f6c90e7b58f
+oid sha256:55cc1817d8def71a3bc8f24bf4582f8ab4532c2542185ddc75da7e42fa5e372c
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb3309524185001782da002e1efb7406e18966db2aee795c24a16a9ee18dd8d0
+oid sha256:31f466e63f2d702a9646f61d3cb0499d7a443ca833cfea51694a53eaa24cfd01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2918113470077515,
-  "best_model_checkpoint": "./outputs/checkpoint-3400",
-  "epoch": 2.477231329690346,
+  "best_metric": 1.2808809280395508,
+  "best_model_checkpoint": "./outputs/checkpoint-3500",
+  "epoch": 2.5500910746812386,
   "eval_steps": 100,
-  "global_step": 3400,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -483,13 +483,27 @@
       "eval_samples_per_second": 43.579,
       "eval_steps_per_second": 5.453,
       "step": 3400
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.0002,
+      "loss": 1.2629,
+      "step": 3500
+    },
+    {
+      "epoch": 2.55,
+      "eval_loss": 1.2808809280395508,
+      "eval_runtime": 143.992,
+      "eval_samples_per_second": 43.572,
+      "eval_steps_per_second": 5.452,
+      "step": 3500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.026581552041902e+17,
+  "total_flos": 2.0862010999423795e+17,
   "trial_name": null,
   "trial_params": null
 }