Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84507a980b24d17e266f5639939a8b3f41e5f457a4c72e56ec956bfd67e3fd03
+oid sha256:4ff1f6a2d30326c9619949fd8731fee5b899b196f95c743d3625c4254865045f
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e298cdf7181ed00a5253701178fe3a741538e2bd701304280a3231ffc9b907b
+oid sha256:8e303cc6ce79c3da42024e9ac891d7c346bd8f68cf338ffa70ef94914c8aa81f
 size 151034501

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d08f4bbf51a6a6932d1b8245d602743b6b47c3167169e34a3aac6c4f5ce559b
+oid sha256:459728dd7fd8fb6703264413047ab4e7d8161f4fe6db1d499f282289a066f3b6
 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": 1.5300686359405518,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.29143897996357016,
+  "best_metric": 1.5074832439422607,
+  "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": 15.01,
       "eval_steps_per_second": 1.878,
       "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002,
+      "loss": 1.5114,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.5074832439422607,
+      "eval_runtime": 417.962,
+      "eval_samples_per_second": 15.011,
+      "eval_steps_per_second": 1.878,
+      "step": 500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.298292292791122e+17,
+  "total_flos": 1.6226839540486656e+17,
   "trial_name": null,
   "trial_params": null
 }