Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c5033f79d9749477f10e6e7a3a9c3cac3f4e145332f835d10178c9cd2dbf88b
+oid sha256:28f5a2178236c0b47df536e1b431584b0b052ee27175697529b9286f1d64e8a4
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4146124c8b0eb95748ab763a25f518de884bcc1135c1ad6352ce115b8ab13c5d
+oid sha256:cfa994e29f25a46581c29d6e3b3184132e3f1d8582959b76e1c6c3f2037b3e0e
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:957113e67ab11c2af45eb4aad3a4067ef1fc77a018bd85c77d56e6d10186026f
+oid sha256:55a434fa2478e58592908e5f1cc53dc10fd07fe28ea2b87f64160779bd08c4a0
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
+oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3050100803375244,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 0.9471766848816029,
+  "best_metric": 2.2802278995513916,
+  "best_model_checkpoint": "./outputs/checkpoint-1400",
+  "epoch": 1.0200364298724955,
   "eval_steps": 100,
-  "global_step": 1300,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,13 +189,27 @@
       "eval_samples_per_second": 30.475,
       "eval_steps_per_second": 3.813,
       "step": 1300
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002,
+      "loss": 2.2787,
+      "step": 1400
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 2.2802278995513916,
+      "eval_runtime": 206.0479,
+      "eval_samples_per_second": 30.449,
+      "eval_steps_per_second": 3.81,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.817057293729792e+16,
+  "total_flos": 4.118366969063424e+16,
   "trial_name": null,
   "trial_params": null
 }