Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a647617668747d3f7f19605c845ca3f8fa4976ad76247969aebf53e4b49ea26
+oid sha256:dbf6870bf675c8cb2cba9537e9d21d55fb91664725167cb5d439619920f800ef
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14f358a9fa0ae121102ba80c501c67a7ee6bc09b0966ed2af678564c9e4605b9
+oid sha256:6aadb2534a2025fff6f558cafdd7e78ad26d52df63f2e49206cf7e8bd68a7133
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be78a4950643aa2c0f7f3e14329f834829bfe49fb52a0d080a54375bd9ada6a0
+oid sha256:ad8deb18f625e20e598fde86410ebc6bf9ded1508a486c75694db51ede76751e
 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": 2.3795337677001953,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 0.6557377049180327,
+  "best_metric": 2.3618950843811035,
+  "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": 30.435,
       "eval_steps_per_second": 3.808,
       "step": 900
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002,
+      "loss": 2.3664,
+      "step": 1000
+    },
+    {
+      "epoch": 0.73,
+      "eval_loss": 2.3618950843811035,
+      "eval_runtime": 205.9336,
+      "eval_samples_per_second": 30.466,
+      "eval_steps_per_second": 3.812,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.64265735974912e+16,
+  "total_flos": 2.936670420934656e+16,
   "trial_name": null,
   "trial_params": null
 }