Training in progress, step 2500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab59c9621500fbdec068f8056aca83d7369f37820e8231811b0a833edff61759
+oid sha256:149a09998bf83e31819b4090132c2d9eb7a95f79fbfd79d14ca99701afb2b106
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c707b0da0a3afb3da76e81c534469fb17f542718e6e4595df7d3fd75c5d0485
+oid sha256:fac0da93c6ac2a9191052ef608e652b77666a46926201a5e53e599744f601fa1
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58ea747baffcc60dbc2ddb0ad42496c65ba93dc6eb544acc3c718b399777b2b4
+oid sha256:c5fcc107cd0de5799df59f0bf6b3a9f6637359068ab89f890c741b49034e80db
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a78e728336b77d3305afe2734acb1241c76f8f2c33b35460bc07397abc49ba2
+oid sha256:bd37581d93a41fc457d899cacb7a67009a6909f6dbf72b467de55158ef91ac94
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4125311374664307,
-  "best_model_checkpoint": "./outputs/checkpoint-2400",
-  "epoch": 1.748633879781421,
+  "best_metric": 1.3995251655578613,
+  "best_model_checkpoint": "./outputs/checkpoint-2500",
+  "epoch": 1.8214936247723132,
   "eval_steps": 100,
-  "global_step": 2400,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -343,13 +343,27 @@
       "eval_samples_per_second": 43.601,
       "eval_steps_per_second": 5.455,
       "step": 2400
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.0002,
+      "loss": 1.3915,
+      "step": 2500
+    },
+    {
+      "epoch": 1.82,
+      "eval_loss": 1.3995251655578613,
+      "eval_runtime": 143.9086,
+      "eval_samples_per_second": 43.597,
+      "eval_steps_per_second": 5.455,
+      "step": 2500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.4306308718896742e+17,
+  "total_flos": 1.4900150729136538e+17,
   "trial_name": null,
   "trial_params": null
 }