Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:207b0f93334913f1d85a200490bf415cb7cc3d623c0827fc64386b06007481de
+oid sha256:2085afabcc8603cadcaa31b244d07e69fb3454ee29aee7230098b904c129aafc
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c3ac062c2696643ce5b31bd8ac6d6654ff117c7f45bee59c8aaeeeb8fc00714
+oid sha256:f16d851a52d02b98de7f43aacd3a878e51fd8767ec4b4c183d7d35e179bb655d
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8662557b50cc51438eaa14c2b2a247b688b19166e0ce09334733e3489595dd32
+oid sha256:ccf766ab7ef9d49860555347a36c059234d6eb124336b64a64b99fa4b6999389
 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": 1.0080314874649048,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.9943181818181818,
+  "best_metric": 1.0012787580490112,
+  "best_model_checkpoint": "./outputs/checkpoint-800",
+  "epoch": 1.1363636363636362,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -105,6 +105,20 @@
       "eval_samples_per_second": 12.006,
       "eval_steps_per_second": 1.505,
       "step": 700
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002,
+      "loss": 1.1391,
+      "step": 800
+    },
+    {
+      "epoch": 1.14,
+      "eval_loss": 1.0012787580490112,
+      "eval_runtime": 124.3175,
+      "eval_samples_per_second": 12.002,
+      "eval_steps_per_second": 1.504,
+      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -112,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.933519820038144e+16,
+  "total_flos": 4.49771803278336e+16,
   "trial_name": null,
   "trial_params": null
 }