Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4faca0ce7c610ea8d2d7107e2816ca9113cb5f7504e8e9a1721cdca46b0ddc66
+oid sha256:bf08d649f6b53fa172c34f28cd7fa442b3105422afffb6e27d1da122806dee6e
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efa0ba216ccc50c0e453d87666eb8ed06c052646ca27f8fb9025c55419a0cc0e
+oid sha256:282c179f134a3cdd6b2754e4fa6d431e1da93103758369eddb00de7fc61cba97
 size 62950853

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a2875ec1af5e31befdcddf3f498870dbf98226c5f675d226e5d742e2999595d
+oid sha256:bf9f9827908bdf6f104fe6aded26cce430f267e7addfd8f51422961d9b7bad2e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
+oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.1813676357269287,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.07285974499089254,
+  "best_metric": 2.131509304046631,
+  "best_model_checkpoint": "./outputs/checkpoint-200",
+  "epoch": 0.14571948998178508,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,13 +21,27 @@
       "eval_samples_per_second": 11.414,
       "eval_steps_per_second": 1.428,
       "step": 100
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0002,
+      "loss": 2.1547,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 2.131509304046631,
+      "eval_runtime": 549.883,
+      "eval_samples_per_second": 11.41,
+      "eval_steps_per_second": 1.428,
+      "step": 200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.603922911428608e+16,
+  "total_flos": 5.195287526080512e+16,
   "trial_name": null,
   "trial_params": null
 }