Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b843ff0514e516f75c6f0635244524972cc7b6630377c14555d19e5b8bd5cf3
+oid sha256:e0fe4a3138a62a3bf41ab3a64cc34fa185a55b5eb85fd12f7368ae552e00acb4
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8345c63b5810e688fe6b2b75f25eec13ec443636b6d095097906c6a549e2e41
+oid sha256:f9370b9f25ae71c8002221b696dd4516399565215b085408197fbf1a66724cc6
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:660b7a5dfb51fff12ee01e67c8658d1f17ca6123b8cc1eb386148b5ee4e14a5f
+oid sha256:6dcf0a1d550e1486617643b9462f1d9eebdf9ddec6eafb10d0a8a79a9850919a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
+oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.188199758529663,
-  "best_model_checkpoint": "./outputs/checkpoint-2000",
-  "epoch": 1.4571948998178508,
+  "best_metric": 2.175708770751953,
+  "best_model_checkpoint": "./outputs/checkpoint-2100",
+  "epoch": 1.530054644808743,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,13 +287,27 @@
       "eval_samples_per_second": 30.493,
       "eval_steps_per_second": 3.815,
       "step": 2000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.0002,
+      "loss": 2.158,
+      "step": 2100
+    },
+    {
+      "epoch": 1.53,
+      "eval_loss": 2.175708770751953,
+      "eval_runtime": 206.3248,
+      "eval_samples_per_second": 30.408,
+      "eval_steps_per_second": 3.805,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.88204413088768e+16,
+  "total_flos": 6.174508048386048e+16,
   "trial_name": null,
   "trial_params": null
 }