Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f2a852a249b4fe890f73d6aa8620fef80511c40875a5dc82dbe87f5a9c929e0
+oid sha256:450095aa5c5465158557762d47903a143e90c0a66d68de92d95d75fa2ec4389d
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8345d25dd466077002c6dab5b9d182ec26a0beb1fc1fb91f97a38c563769336f
+oid sha256:c95be57b1ce63a56f8c9b301c6552bc014a53b16f1ac072041ccfacc6eb37422
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0b94d1122471aca26c892d9b2d4a4e37ccc99bccd12a642f92316f84a6a18ef
+oid sha256:f4f1181e0e3e2c9c9c4867f3c8fa0bba665e663473833a2ab7b385cf778c0261
 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": 1.203295350074768,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.4,
+  "best_metric": 1.190936803817749,
+  "best_model_checkpoint": "./outputs/checkpoint-400",
+  "epoch": 0.5333333333333333,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,6 +49,20 @@
       "eval_samples_per_second": 10.879,
       "eval_steps_per_second": 1.364,
       "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002,
+      "loss": 0.992,
+      "step": 400
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.190936803817749,
+      "eval_runtime": 177.5627,
+      "eval_samples_per_second": 10.869,
+      "eval_steps_per_second": 1.363,
+      "step": 400
     }
   ],
   "logging_steps": 100,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.242334722424832e+16,
+  "total_flos": 2.9915995189248e+16,
   "trial_name": null,
   "trial_params": null
 }