Training in progress, step 3900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38acc6e27c9e910592a3928094223ff54a296092f8bcb05d0ad3a8b0184c65c9
+oid sha256:d949b8f9f8167d5ba7b401703d84c6d353cf22473acb4b2aa2a100c9a985fe58
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fb0ecdec215ce19ff9fa28f7e8a359fc57fec9788315b4eb61ac30cac2280e8
+oid sha256:14f08122247da99ed8e28880f02e7bd81fd7e698a2fe282e14df568bda6ee5cf
 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 sha256:3961d2f201ce99426ee113655da78d8214f6ef72fc082855daa3c565989888c2
+oid sha256:a42424f90eb68391066979b79f87ab18e2fce2a0abc640b46cf1b3f4c12c720a
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2465852499008179,
-  "best_model_checkpoint": "./outputs/checkpoint-3800",
-  "epoch": 2.768670309653916,
+  "best_metric": 1.2340775728225708,
+  "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": 43.565,
       "eval_steps_per_second": 5.451,
       "step": 3800
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 0.0002,
+      "loss": 1.221,
+      "step": 3900
+    },
+    {
+      "epoch": 2.84,
+      "eval_loss": 1.2340775728225708,
+      "eval_runtime": 144.91,
+      "eval_samples_per_second": 43.296,
+      "eval_steps_per_second": 5.417,
+      "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
 }