Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd0c41d235f944ea27e73f7fbb57f49cb95419424ae3bfa63b9a290f2208f88
+oid sha256:b5e16c4531d20ba92dd8bd6a4ddc9c14f3e61944bcf8787ed3a1331bd8bf0c36
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b47a1dd2e0a8b7ec702b1afb86943c56747583da07e0d5a3047d95adf29f59f4
+oid sha256:07063a239b8f248d52b0d3757cc8b2b76ff11b2d25b5bc1c5ae7f33bc6a8a4e5
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d66b1a8c16da8ebf7970425c7c306a82ffa223990ce4f0cb56084c069e08e81
+oid sha256:741013df0f2c38258d3aad4259e56feb3245d57324e1c9624b55abdc9cee37a6
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
+oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.484386920928955,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 0.6557377049180327,
+  "best_metric": 2.4648232460021973,
+  "best_model_checkpoint": "./outputs/checkpoint-1000",
+  "epoch": 0.7285974499089253,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,13 +133,27 @@
       "eval_samples_per_second": 30.645,
       "eval_steps_per_second": 3.834,
       "step": 900
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002,
+      "loss": 2.4729,
+      "step": 1000
+    },
+    {
+      "epoch": 0.73,
+      "eval_loss": 2.4648232460021973,
+      "eval_runtime": 204.5514,
+      "eval_samples_per_second": 30.672,
+      "eval_steps_per_second": 3.838,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.562316410028032e+16,
+  "total_flos": 2.84738668720128e+16,
   "trial_name": null,
   "trial_params": null
 }