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:f4a8e6d50d3d5733441317f16e8b76d7ec1cc35e048b73f557c7ebf1dd4eee73
+oid sha256:691c9c34b7b3de4453f20ae541c5992c2e962849c95813dee494250da2b6ddb8
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cea90ed8df089a0d01447cb677526bd26ed1053099839eb65d4599b0e4a82903
+oid sha256:74ba0889b3f6feb501af66830ba0c843ce4933fed04b6b5a888e0d47d28dbdf6
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:307a22d558182f4e20431c7770e3d51d2b15eef6ae18cfe9bc109ea0c11f4dcb
+oid sha256:0c709cc36c11f689009db74b712a1bf9cf00d7cd21dc17a14550bc188bd9fc06
 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": 2.1278133392333984,
-  "best_model_checkpoint": "./outputs/checkpoint-3400",
-  "epoch": 2.477231329690346,
+  "best_metric": 2.1079277992248535,
+  "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": 30.56,
       "eval_steps_per_second": 3.824,
       "step": 3400
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.0002,
+      "loss": 2.0761,
+      "step": 3500
+    },
+    {
+      "epoch": 2.55,
+      "eval_loss": 2.1079277992248535,
+      "eval_runtime": 205.5563,
+      "eval_samples_per_second": 30.522,
+      "eval_steps_per_second": 3.819,
+      "step": 3500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.681643263043584e+16,
+  "total_flos": 9.966757754677248e+16,
   "trial_name": null,
   "trial_params": null
 }