Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6556801eea3deb91b9f458803724a80f379721eebffcfd2e1962d926e6220f52
+oid sha256:bb7f79a5b3e10e9ac94f2ab9dec1edb67a313fe7409d96d6557a8b17228176e0
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89396b2c278f8e8f8bb83e8f719c87a47d3c08adeb9acc2837b6c041ced22960
+oid sha256:aa01ddab5b3448b50be9dd715f1cb202b01c440c4daf62f719b7eee2eed1060a
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9013865ce1db6c56389ad8c81d9da591edccc22d595720deba33a4baadab4fc1
+oid sha256:b8c9268a88f9a768a56781b2f922982dd8b112b100e2229d10de13e4538eb16e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3fb62e1a686af03a6294538f23b0512dc4df0d77f62afb535a9f3732c29458d
+oid sha256:eb0b2196e2f29a6683acf49e9b6eb98e7393791df29402c783d469811f16cf26
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9101046323776245,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.36429872495446264,
+  "best_metric": 1.8801190853118896,
+  "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": 43.578,
       "eval_steps_per_second": 5.452,
       "step": 500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002,
+      "loss": 1.8971,
+      "step": 600
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 1.8801190853118896,
+      "eval_runtime": 143.9079,
+      "eval_samples_per_second": 43.597,
+      "eval_steps_per_second": 5.455,
+      "step": 600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.9805494916120576e+16,
+  "total_flos": 3.576193971702989e+16,
   "trial_name": null,
   "trial_params": null
 }