Training in progress, step 2900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9062d82bf6c01714a8bc139e57048e0a1408dd46d29692e4adfab81c12c11212
+oid sha256:68e0b1fef53fbc69911cd92159f9059982797ff42b186214825643b0794e877e
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3239a64ba59b650079a5eeb1487a17c6f209297a21c5a4da5197a9ef2106bf89
+oid sha256:3a3be646d4fe647f6e3c445baf08bbb4edeebf19cda2b119a2d4a12644acd0d6
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70168052704796a5abb9d0b9c508a9b89ab3a8963fa20bba019e60bdebdc9e90
+oid sha256:e112b2c9c2407506fce8eaea80850d63f91d65bd32e87553852af1558f3c8da5
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c08a7148c570c3d4c87a735e3acef3af52d256eb019f3a3f3feeab8a656949
+oid sha256:097f95efaf3ced711759e9e49c3b8b3ef906ff28483e958d227db85b3ea360b9
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3511581420898438,
-  "best_model_checkpoint": "./outputs/checkpoint-2800",
-  "epoch": 2.040072859744991,
+  "best_metric": 1.3384917974472046,
+  "best_model_checkpoint": "./outputs/checkpoint-2900",
+  "epoch": 2.1129326047358834,
   "eval_steps": 100,
-  "global_step": 2800,
+  "global_step": 2900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -399,13 +399,27 @@
       "eval_samples_per_second": 43.642,
       "eval_steps_per_second": 5.46,
       "step": 2800
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.0002,
+      "loss": 1.3051,
+      "step": 2900
+    },
+    {
+      "epoch": 2.11,
+      "eval_loss": 1.3384917974472046,
+      "eval_runtime": 143.684,
+      "eval_samples_per_second": 43.665,
+      "eval_steps_per_second": 5.463,
+      "step": 2900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.669167753668444e+17,
+  "total_flos": 1.72867124009558e+17,
   "trial_name": null,
   "trial_params": null
 }