Training in progress, step 3400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd537153891e7d185e0d81b0c7c4520e46b21a784002f3f0f8719e9c47277e3f
+oid sha256:6085aeb77559c11612b8cfd556b3dbfe14c49a23ebf22659ca8a5747b68d19cb
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3070a7891b7a52dbf791e23ef3b13f6ec33aec9b98a072e22cbbd8c297697fa
+oid sha256:819cf24064f698172cabc52a3fa76c7f54fb1dabbb6165bbc289ac54d330ea28
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b32db0a2b713dd6b1e7016c32489b8ad860f5a342471d86c52b5af270bb99a
+oid sha256:298e8871de8745e7586904db3da51f0731b6797e7faf72bed74b5f5a5c7425f5
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad85ddedbe158ea4b6f60faba10617b6fb17a69c778e6d7c0a8e4338dd95e31f
+oid sha256:cb3309524185001782da002e1efb7406e18966db2aee795c24a16a9ee18dd8d0
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0311737060546875,
-  "best_model_checkpoint": "./outputs/checkpoint-3300",
-  "epoch": 2.4043715846994536,
+  "best_metric": 2.0267181396484375,
+  "best_model_checkpoint": "./outputs/checkpoint-3400",
+  "epoch": 2.477231329690346,
   "eval_steps": 100,
-  "global_step": 3300,
+  "global_step": 3400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -469,13 +469,27 @@
       "eval_samples_per_second": 10.916,
       "eval_steps_per_second": 1.366,
       "step": 3300
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.0002,
+      "loss": 1.9862,
+      "step": 3400
+    },
+    {
+      "epoch": 2.48,
+      "eval_loss": 2.0267181396484375,
+      "eval_runtime": 538.138,
+      "eval_samples_per_second": 11.659,
+      "eval_steps_per_second": 1.459,
+      "step": 3400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.691971842875392e+16,
+  "total_flos": 9.98463226908672e+16,
   "trial_name": null,
   "trial_params": null
 }