Training in progress, step 3500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1377f63ed2c9dadb7c619e577650e3cc38d7909b724c9f720375231f368e5d93
+oid sha256:a4bdfa5a211783e6b56d48fdca81908fbd9a24687a82f7cd9ea3763aeb259f37
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f860865ef7a337fe0cf9a0ab83db43be9374f836cf79de539d50c0381c00bdff
+oid sha256:3a256f6595d9bf7df68b57cddeffb17fee277536bec4e4190e6e5f208d72eab5
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2833d6a72f9c2dcc8e1caf553d9c58d438680ada5c3bfdcab9d366a01af971e9
+oid sha256:b3d019d07e324ed5f5738dc62eb5b60bf9fc48fa141a0dac4fa6bde2ae658c81
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb3309524185001782da002e1efb7406e18966db2aee795c24a16a9ee18dd8d0
+oid sha256:31f466e63f2d702a9646f61d3cb0499d7a443ca833cfea51694a53eaa24cfd01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2834123373031616,
-  "best_model_checkpoint": "./outputs/checkpoint-3400",
-  "epoch": 2.477231329690346,
+  "best_metric": 1.2722229957580566,
+  "best_model_checkpoint": "./outputs/checkpoint-3500",
+  "epoch": 2.5500910746812386,
   "eval_steps": 100,
-  "global_step": 3400,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -483,13 +483,27 @@
       "eval_samples_per_second": 43.619,
       "eval_steps_per_second": 5.458,
       "step": 3400
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.0002,
+      "loss": 1.2554,
+      "step": 3500
+    },
+    {
+      "epoch": 2.55,
+      "eval_loss": 1.2722229957580566,
+      "eval_runtime": 143.7943,
+      "eval_samples_per_second": 43.632,
+      "eval_steps_per_second": 5.459,
+      "step": 3500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.0268000465580032e+17,
+  "total_flos": 2.086425749233582e+17,
   "trial_name": null,
   "trial_params": null
 }