Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:674184f8eb7aee2542031af2c791f143ad919a4395ebf613fa8f7051b3975bec
+oid sha256:4ee4e64169efb7e102717f2fc3b1f3d9460bbbdf0f2aed418c63b9e15014651e
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12e01e60c58d4374e09f1dbefcada5e314c817f612f8e399617d8db5f0c00eee
+oid sha256:4f0882eaab11a947976a2295ef8ffc4344a235b04323135892fb582f3e309f2d
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f397672f6504655cdaf62d3edac072359c0fa5bc9ab3b2804e87306f7e7d5e1
+oid sha256:b5135fd3f6237f90bfceaba9437fdc000a5d68c604b4ea5bf8dd2565a49d402e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
+oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0435657501220703,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.29143897996357016,
+  "best_metric": 2.0031208992004395,
+  "best_model_checkpoint": "./outputs/checkpoint-500",
+  "epoch": 0.36429872495446264,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,13 +63,27 @@
       "eval_samples_per_second": 11.393,
       "eval_steps_per_second": 1.425,
       "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002,
+      "loss": 2.0241,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 2.0031208992004395,
+      "eval_runtime": 550.5855,
+      "eval_samples_per_second": 11.395,
+      "eval_steps_per_second": 1.426,
+      "step": 500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0422007089758208e+17,
+  "total_flos": 1.3026351030789734e+17,
   "trial_name": null,
   "trial_params": null
 }