Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ee4e64169efb7e102717f2fc3b1f3d9460bbbdf0f2aed418c63b9e15014651e
+oid sha256:610ba9980a82114bff6956c9ff90959aa6e9376248c7df34a4bd522af37a0de8
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f0882eaab11a947976a2295ef8ffc4344a235b04323135892fb582f3e309f2d
+oid sha256:2ab77640d2a05a648a25a7c0d95839fed11feeefdaf0a6b9667805717e06a555
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5135fd3f6237f90bfceaba9437fdc000a5d68c604b4ea5bf8dd2565a49d402e
+oid sha256:f4cfe991b3ad712baa288a77dd6f044c8861d31b30f3c0de8fe14a274bb7d623
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
+oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0031208992004395,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.36429872495446264,
+  "best_metric": 1.9635978937149048,
+  "best_model_checkpoint": "./outputs/checkpoint-600",
+  "epoch": 0.4371584699453552,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,13 +77,27 @@
       "eval_samples_per_second": 11.395,
       "eval_steps_per_second": 1.426,
       "step": 500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002,
+      "loss": 1.9755,
+      "step": 600
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 1.9635978937149048,
+      "eval_runtime": 552.4575,
+      "eval_samples_per_second": 11.357,
+      "eval_steps_per_second": 1.421,
+      "step": 600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.3026351030789734e+17,
+  "total_flos": 1.5637373372419277e+17,
   "trial_name": null,
   "trial_params": null
 }