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:b3e877c04611b8f75953a97cd9238d7bdfaa53f751e3d1754916023d5933db54
+oid sha256:cfcd6ac223cc1cd192844d91d6333d67d86a2c7f27e9a36555cb6e0d34b3dc51
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b79f6b0195bac96d3f424b59f1c5bf7de3edcd06bfc93f77babdd7da8fadf3b
+oid sha256:15c93584783fb8ad6e79e1fd9c95ad967cd71f2b09f60a99e79629f9c763208b
 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": 2.5274579524993896,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.5100182149362478,
+  "best_metric": 2.506831645965576,
+  "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": 2.5141,
+      "step": 800
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 2.506831645965576,
+      "eval_runtime": 204.4886,
+      "eval_samples_per_second": 30.681,
+      "eval_steps_per_second": 3.839,
+      "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
 }