Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe38d557f4213975dcf91685bf9d39c920c343c3f58f6b90023cabe8ad68dbfd
+oid sha256:2fcbe9bdda2410d6e7bac72d128922f0a6f97341a6b1df2aad6c0655e442004e
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9097e840707fb0d3863cee16747ffce7adb7daac69da1dfcc302dce65debf596
+oid sha256:ef44c4d032640d06a9129c2dde08f2d53538b984c5b30dd2f2ac61a370327c9e
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4933eabcc84eee1438f9d6f8169b5cecd886b53e4de0afe6e5bf4f525371b890
+oid sha256:6691656f59836e679b0b16a9e5fb6259737616134b8601994c32a922f156d9a2
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
+oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.5280492305755615,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.5100182149362478,
+  "best_metric": 2.507997512817383,
+  "best_model_checkpoint": "./outputs/checkpoint-800",
+  "epoch": 0.5828779599271403,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -105,13 +105,27 @@
       "eval_samples_per_second": 30.63,
       "eval_steps_per_second": 3.832,
       "step": 700
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 2.5165,
+      "step": 800
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 2.507997512817383,
+      "eval_runtime": 204.6726,
+      "eval_samples_per_second": 30.654,
+      "eval_steps_per_second": 3.835,
+      "step": 800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.993348357668864e+16,
+  "total_flos": 2.277701378039808e+16,
   "trial_name": null,
   "trial_params": null
 }