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:b5da0cef3be7e5d0088d66fdf5cb75a2f2d87fb1b762de5aa84ba302b7987745
+oid sha256:3ae1d5e5a6a80dff6aeb23e41a64dca9f81c75330526fd385bf6bc55cdbf2a49
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3b12076f1ae9ac221385aaf4c9674595e9e5e8a00c4f61f2b25d1b585d0052f
+oid sha256:8c3e09c571410529d69db7be5f028e2d1ba9d805682e17e3be00fce0ac338974
 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": 1.2932065725326538,
-  "best_model_checkpoint": "./outputs/checkpoint-3400",
-  "epoch": 2.477231329690346,
+  "best_metric": 1.28367018699646,
+  "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": 43.689,
       "eval_steps_per_second": 5.466,
       "step": 3400
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.0002,
+      "loss": 1.2635,
+      "step": 3500
+    },
+    {
+      "epoch": 2.55,
+      "eval_loss": 1.28367018699646,
+      "eval_runtime": 143.5245,
+      "eval_samples_per_second": 43.714,
+      "eval_steps_per_second": 5.469,
+      "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
 }