Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a985ffa60e09abc725388dfad2fa38e67a248fe3507fad8b773b770daebd360
+oid sha256:08596d303f9e6af776386bc4504771dde765e90876d1f140cdf69fee48983f40
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2770642f711890de03dde93b01a86a5793b3203c1816ac379fc5d7437022a47
+oid sha256:ba49de804724a2fec300f63bc0637393553a6f42cf16cda89b6e7e0e3c0ab621
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d2d6e14904128a443b518d8e76a7926f8a1af0669bd545e4ac0538a858cbbe
+oid sha256:aa942a2735f9e77fcdf287283c57bd6296771ce4bb160fffb501c94085817c55
 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": 1.7718570232391357,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.36429872495446264,
+  "best_metric": 1.742559790611267,
+  "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": 43.657,
       "eval_steps_per_second": 5.462,
       "step": 500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002,
+      "loss": 1.7567,
+      "step": 600
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 1.742559790611267,
+      "eval_runtime": 143.6984,
+      "eval_samples_per_second": 43.661,
+      "eval_steps_per_second": 5.463,
+      "step": 600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.9834861985890304e+16,
+  "total_flos": 3.5797901188694016e+16,
   "trial_name": null,
   "trial_params": null
 }