Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ca77649e3368ae1c0bd32dc226df5f76f4d9d8fe751580a203a95fd3792a0fb
+oid sha256:b3d2315e33bc525bbe5675682c58b3ede77b52403224cbd3771dd7c97823feca
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6dd552f4679b27941858ea30e31850cdef2c9fc7e20d4d8c5a36da9ebff4507
+oid sha256:350fab16db68303418646f37a3c86cdabe1c0046a7ea290c25893eaf039335b7
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45e73149cee834f63e198fb7c5baf040c22ac8eb1ad042c43b2bf6a76aaddb1d
+oid sha256:2d956bbe29389d803201f795b58c63ed565fec24e0e84b4e6a37f67b9223d2da
 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": 2.038727045059204,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.5681818181818182,
+  "best_metric": 2.0150375366210938,
+  "best_model_checkpoint": "./outputs/checkpoint-500",
+  "epoch": 0.7102272727272727,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,20 @@
       "eval_samples_per_second": 27.84,
       "eval_steps_per_second": 3.489,
       "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002,
+      "loss": 2.1811,
+      "step": 500
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 2.0150375366210938,
+      "eval_runtime": 53.7081,
+      "eval_samples_per_second": 27.78,
+      "eval_steps_per_second": 3.482,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.209137761714176e+16,
+  "total_flos": 1.51321534414848e+16,
   "trial_name": null,
   "trial_params": null
 }