Training in progress, step 3600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4bdfa5a211783e6b56d48fdca81908fbd9a24687a82f7cd9ea3763aeb259f37
+oid sha256:a3ab7bb8221aada9c42447d6358110b43c0830d69446e9c6f70a8b9f874fcc05
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a256f6595d9bf7df68b57cddeffb17fee277536bec4e4190e6e5f208d72eab5
+oid sha256:7dfa7fe5f18476d22e955034a5b9b03a2ae298bff9940c273462e7bd56e191e2
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3d019d07e324ed5f5738dc62eb5b60bf9fc48fa141a0dac4fa6bde2ae658c81
+oid sha256:8385871146a99c13f93d55ba812cf95e05bc8a01606813404732f408c6340885
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31f466e63f2d702a9646f61d3cb0499d7a443ca833cfea51694a53eaa24cfd01
+oid sha256:43e3cf8d56a3f083d00cc85544d76ada2f884a1018c8752332d96f2799911117
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2722229957580566,
-  "best_model_checkpoint": "./outputs/checkpoint-3500",
-  "epoch": 2.5500910746812386,
+  "best_metric": 1.2600913047790527,
+  "best_model_checkpoint": "./outputs/checkpoint-3600",
+  "epoch": 2.6229508196721314,
   "eval_steps": 100,
-  "global_step": 3500,
+  "global_step": 3600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -497,13 +497,27 @@
       "eval_samples_per_second": 43.632,
       "eval_steps_per_second": 5.459,
       "step": 3500
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 0.0002,
+      "loss": 1.2425,
+      "step": 3600
+    },
+    {
+      "epoch": 2.62,
+      "eval_loss": 1.2600913047790527,
+      "eval_runtime": 143.6927,
+      "eval_samples_per_second": 43.663,
+      "eval_steps_per_second": 5.463,
+      "step": 3600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.086425749233582e+17,
+  "total_flos": 2.14592454630826e+17,
   "trial_name": null,
   "trial_params": null
 }