Training in progress, step 3500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6085aeb77559c11612b8cfd556b3dbfe14c49a23ebf22659ca8a5747b68d19cb
+oid sha256:ed5ecffef9dd0df6bf95f4a8a538762232a42aab3c1a55dbce4541bf35d59f38
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:819cf24064f698172cabc52a3fa76c7f54fb1dabbb6165bbc289ac54d330ea28
+oid sha256:28aa8c4e74acbda7b67d8e9591080a1756af988995d1c49f602b3994144236f5
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:298e8871de8745e7586904db3da51f0731b6797e7faf72bed74b5f5a5c7425f5
+oid sha256:1d52ff8f30c089f48a02ba0fe7032248959728b72ac67b9908d20208c82868df
 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": 2.0267181396484375,
-  "best_model_checkpoint": "./outputs/checkpoint-3400",
-  "epoch": 2.477231329690346,
+  "best_metric": 2.013442039489746,
+  "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": 11.659,
       "eval_steps_per_second": 1.459,
       "step": 3400
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.0002,
+      "loss": 1.9811,
+      "step": 3500
+    },
+    {
+      "epoch": 2.55,
+      "eval_loss": 2.013442039489746,
+      "eval_runtime": 547.6149,
+      "eval_samples_per_second": 11.457,
+      "eval_steps_per_second": 1.433,
+      "step": 3500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.98463226908672e+16,
+  "total_flos": 1.0278664981143552e+17,
   "trial_name": null,
   "trial_params": null
 }