Training in progress, step 3900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b17718f7d65cf0fc510cf7915ee9df388ef233dc5d8660162644867534c15761
+oid sha256:ab20ce49c0884a18e6d7777cc389963329dc1ca289eba549c3cc09de3f8b40c9
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb29170c14de688303ce5de2d20820edc02017393c019a2d1c47a7ef9e2d2a8a
+oid sha256:a1d4ab94ab1808efbe80c1333519bd55cd0ecb2c672c323516df8c330d413aff
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0625d44593f9a35a65bd6a0c353b2ee783deaa835a908009e34809ad32c4166a
+oid sha256:33ac3d2b522a45fffa5206c5d7a821c451a2d4e38cb61393c89b930eaeff3109
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb592c268b6f8eab99358b5a12e18084bc178639195f5911973b566c7c32da81
+oid sha256:794a0a668693664bb45fb10418080981a1873b71841f3a55ed72c5aa6d455597
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2479283809661865,
-  "best_model_checkpoint": "./outputs/checkpoint-3800",
-  "epoch": 2.768670309653916,
+  "best_metric": 1.234686255455017,
+  "best_model_checkpoint": "./outputs/checkpoint-3900",
+  "epoch": 2.841530054644809,
   "eval_steps": 100,
-  "global_step": 3800,
+  "global_step": 3900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -539,13 +539,27 @@
       "eval_samples_per_second": 43.695,
       "eval_steps_per_second": 5.467,
       "step": 3800
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 0.0002,
+      "loss": 1.2207,
+      "step": 3900
+    },
+    {
+      "epoch": 2.84,
+      "eval_loss": 1.234686255455017,
+      "eval_runtime": 143.5291,
+      "eval_samples_per_second": 43.712,
+      "eval_steps_per_second": 5.469,
+      "step": 3900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.2648457919379046e+17,
+  "total_flos": 2.3245805220581376e+17,
   "trial_name": null,
   "trial_params": null
 }