Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41749f7f165d9f2400e0c0e455ae911631502b72bc9e5d0e26da1b3e8d35061f
+oid sha256:674184f8eb7aee2542031af2c791f143ad919a4395ebf613fa8f7051b3975bec
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc43cb9f4bca58b5418445046da5f35b8c498ca07b60a9a7e0a25606eab11350
+oid sha256:12e01e60c58d4374e09f1dbefcada5e314c817f612f8e399617d8db5f0c00eee
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2239ab6c02f1029c9d0ff9b6f5166aaf1a373773586d6b550e1876cea1823c4c
+oid sha256:9f397672f6504655cdaf62d3edac072359c0fa5bc9ab3b2804e87306f7e7d5e1
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
+oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0894575119018555,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.2185792349726776,
+  "best_metric": 2.0435657501220703,
+  "best_model_checkpoint": "./outputs/checkpoint-400",
+  "epoch": 0.29143897996357016,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,13 +49,27 @@
       "eval_samples_per_second": 11.399,
       "eval_steps_per_second": 1.426,
       "step": 300
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002,
+      "loss": 2.0681,
+      "step": 400
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 2.0435657501220703,
+      "eval_runtime": 550.6916,
+      "eval_samples_per_second": 11.393,
+      "eval_steps_per_second": 1.425,
+      "step": 400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.809111892308787e+16,
+  "total_flos": 1.0422007089758208e+17,
   "trial_name": null,
   "trial_params": null
 }