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:a23f6369e6a19c8a9602744a77b467db1123a931c836f7ce81adc1cbd8417b22
+oid sha256:3be22b182f4881c8e9422eac1a64078955ac1d093a138316de88f655680159a8
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae6b07a4ab0a70e1bec7de0b3de8b0e76a8691d90e446fcacaa092f95bd09483
+oid sha256:9ae825836365514438b97ce8a8bbbb97ce11207eb4aa1c60347033b615e7c084
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56c7d9acd97a65ba6f52bddd9c1a7be0b5f95308e5fa05bcc7a62b6822eb6d6f
+oid sha256:fb0990d8cdbc2bdd1880b9951298cbfae149ae47de29db9d5d340de0693addfd
 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": 2.523040533065796,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.29143897996357016,
+  "best_metric": 2.497437000274658,
+  "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": 30.6,
       "eval_steps_per_second": 3.829,
       "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002,
+      "loss": 2.4938,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 2.497437000274658,
+      "eval_runtime": 204.8026,
+      "eval_samples_per_second": 30.634,
+      "eval_steps_per_second": 3.833,
+      "step": 500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.167856193839104e+16,
+  "total_flos": 1.459702746464256e+16,
   "trial_name": null,
   "trial_params": null
 }