Training in progress, step 3800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:441b149a57263a8248572d94d37391f384b8fa25700a05990788b5dcffd89639
+oid sha256:331bfeb9a3801ff5597d93b76ec1d45414332859c8ac0f0c4f387e04adabc0d1
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c666938b20ce98db72835f06ea99a42af41580bfc404579afd773c498b70c15
+oid sha256:4d833a8a2463c550dc7714764408172507a53f68af97748bb4de0016326f8a18
 size 151032837

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f63f840c83291fc5960ae39fd8fa5846eb4ff5d9e718f5f03667b39592197864
+oid sha256:0b234d9d700f882ce9920f729494e9162825344c4091455e69b9d19ef11133c1
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c157d4508adfa804f177e78fb4986d5f3ffb3ec20ae255fb757aa13c0595fdb4
+oid sha256:3961d2f201ce99426ee113655da78d8214f6ef72fc082855daa3c565989888c2
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.123780369758606,
-  "best_model_checkpoint": "./outputs/checkpoint-3700",
-  "epoch": 2.6965391621129324,
+  "best_metric": 1.114593267440796,
+  "best_model_checkpoint": "./outputs/checkpoint-3800",
+  "epoch": 2.769398907103825,
   "eval_steps": 100,
-  "global_step": 3700,
+  "global_step": 3800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -525,13 +525,27 @@
       "eval_samples_per_second": 18.298,
       "eval_steps_per_second": 2.289,
       "step": 3700
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 0.0002,
+      "loss": 1.0954,
+      "step": 3800
+    },
+    {
+      "epoch": 2.77,
+      "eval_loss": 1.114593267440796,
+      "eval_runtime": 342.239,
+      "eval_samples_per_second": 18.332,
+      "eval_steps_per_second": 2.294,
+      "step": 3800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.1997718139609303e+18,
+  "total_flos": 1.2320766953801533e+18,
   "trial_name": null,
   "trial_params": null
 }