Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99b254caa8faa6f1e0acb2d97f06455fc5f113d44678677e3130eccd3b5d7a6f
+oid sha256:c916ffe701f41ea7196c774dda4a18104a2fb8e72a8fd98f29449cb700ee1f47
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f0907150f1cf0518c712b6eba1454343571fc1ae5368cd20634f898356a0dd4
+oid sha256:9a2d9372517c402f17e896fa8c70ccda4680c69229e87544fac6f419e69c1157
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:836b92a3bc8c991adee049fba1895711a4f510235c95414c287849672ddf25b0
+oid sha256:fe1d98121dec1e10b89cbbf79fb7433fce4fe8fbe36ae0274a84026345108858
 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": 1.7239936590194702,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.5100182149362478,
+  "best_metric": 1.695021390914917,
+  "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": 42.704,
       "eval_steps_per_second": 5.343,
       "step": 700
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 1.7092,
+      "step": 800
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 1.695021390914917,
+      "eval_runtime": 143.2343,
+      "eval_samples_per_second": 43.802,
+      "eval_steps_per_second": 5.481,
+      "step": 800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.17362919826391e+16,
+  "total_flos": 4.770481186612838e+16,
   "trial_name": null,
   "trial_params": null
 }