Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d3ba3e8b753262e1b13be84e7cbd10128448f0c3899d5a976391d9e1754ec1d
+oid sha256:2c5033f79d9749477f10e6e7a3a9c3cac3f4e145332f835d10178c9cd2dbf88b
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e99a7b91e312cae393077747f948e7c8da4c279b1ca76f1f4e28c8d9160428bd
+oid sha256:4146124c8b0eb95748ab763a25f518de884bcc1135c1ad6352ce115b8ab13c5d
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c24a5519079f5affefa77bc221612f519ec2d7b465daf634e60b03336ade4e2c
+oid sha256:957113e67ab11c2af45eb4aad3a4067ef1fc77a018bd85c77d56e6d10186026f
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
+oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3209476470947266,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 0.8743169398907104,
+  "best_metric": 2.3050100803375244,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 0.9471766848816029,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,13 +175,27 @@
       "eval_samples_per_second": 30.454,
       "eval_steps_per_second": 3.81,
       "step": 1200
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002,
+      "loss": 2.3272,
+      "step": 1300
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 2.3050100803375244,
+      "eval_runtime": 205.8768,
+      "eval_samples_per_second": 30.475,
+      "eval_steps_per_second": 3.813,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.523768039636992e+16,
+  "total_flos": 3.817057293729792e+16,
   "trial_name": null,
   "trial_params": null
 }