Training in progress, step 3500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f90a2da63f348434e3f45b718dce2b3f87a252225c3397aa8a051d7ece42cc6
+oid sha256:027649fdc9bb39375f7877e818837eec9151d245c636ff7645c95d33d3a52732
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c503eadb83102e83f532a9055aebab231aec2a0f1357cdec5c679711330825
+oid sha256:7ff7270ada9cf8cf5634d4915d2aa34fa7bf7f529feeec57587911f95fff17cb
 size 151034501

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a46f0218404e0c30dbd1af232f5ed9fc7773078be75008ba1a070be2f38d151
+oid sha256:5111e44aa3c7fb3d2679f29ed14de9b378a43fa023e1e3c7c0e2bac399b6ea6f
 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": 1.1388046741485596,
-  "best_model_checkpoint": "./outputs/checkpoint-3400",
-  "epoch": 2.477231329690346,
+  "best_metric": 1.128933310508728,
+  "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": 14.984,
       "eval_steps_per_second": 1.875,
       "step": 3400
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.0002,
+      "loss": 1.1112,
+      "step": 3500
+    },
+    {
+      "epoch": 2.55,
+      "eval_loss": 1.128933310508728,
+      "eval_runtime": 418.5353,
+      "eval_samples_per_second": 14.99,
+      "eval_steps_per_second": 1.876,
+      "step": 3500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.1022399703988951e+18,
+  "total_flos": 1.134669408060162e+18,
   "trial_name": null,
   "trial_params": null
 }