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:c169cce3b0f663a5f2b6c371f0316c0fb74184c18fe5a0d0b282b3e997c0cba2
+oid sha256:8415757a6e4a7d8892ce5eebf26ba96b974864c60d48c0d46ddb2afddfefd48f
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2985119935791e3e3e13ae825f74c7ee00883f099270dfdb09c0ea788ac950c0
+oid sha256:f9f369a42dfc8391f4981090380306256aa55113d1c7c13c7b33574c3612c7f3
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba9a87a902271a6450035455dc1f4df77fd809173f0ab0e7e6c52c6771e76140
+oid sha256:0d07875a2beaba1bd120398d3f1c16dc54dda0e8d32b8e1dd6579f1f939e66f8
 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": 1.1857892274856567,
-  "best_model_checkpoint": "./outputs/checkpoint-3700",
-  "epoch": 2.6958105646630237,
+  "best_metric": 1.1746346950531006,
+  "best_model_checkpoint": "./outputs/checkpoint-3800",
+  "epoch": 2.768670309653916,
   "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": 11.284,
       "eval_steps_per_second": 1.412,
       "step": 3700
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 0.0002,
+      "loss": 1.0989,
+      "step": 3800
+    },
+    {
+      "epoch": 2.77,
+      "eval_loss": 1.1746346950531006,
+      "eval_runtime": 556.1788,
+      "eval_samples_per_second": 11.281,
+      "eval_steps_per_second": 1.411,
+      "step": 3800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.631053618584617e+17,
+  "total_flos": 9.892167467357307e+17,
   "trial_name": null,
   "trial_params": null
 }