Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf08d649f6b53fa172c34f28cd7fa442b3105422afffb6e27d1da122806dee6e
+oid sha256:41749f7f165d9f2400e0c0e455ae911631502b72bc9e5d0e26da1b3e8d35061f
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:282c179f134a3cdd6b2754e4fa6d431e1da93103758369eddb00de7fc61cba97
-size 62950853
+oid sha256:dc43cb9f4bca58b5418445046da5f35b8c498ca07b60a9a7e0a25606eab11350
+size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf9f9827908bdf6f104fe6aded26cce430f267e7addfd8f51422961d9b7bad2e
+oid sha256:2239ab6c02f1029c9d0ff9b6f5166aaf1a373773586d6b550e1876cea1823c4c
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
+oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.131509304046631,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.14571948998178508,
+  "best_metric": 2.0894575119018555,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 0.2185792349726776,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,13 +35,27 @@
       "eval_samples_per_second": 11.41,
       "eval_steps_per_second": 1.428,
       "step": 200
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002,
+      "loss": 2.1088,
+      "step": 300
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 2.0894575119018555,
+      "eval_runtime": 550.3941,
+      "eval_samples_per_second": 11.399,
+      "eval_steps_per_second": 1.426,
+      "step": 300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.195287526080512e+16,
+  "total_flos": 7.809111892308787e+16,
   "trial_name": null,
   "trial_params": null
 }