Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3898b881437b494d33bcbd0be6deac28fc4f0ceab8f5e7159c92533c69f2c1ce
+oid sha256:251f0d23e7cc7ff7b02b7f89375964c7785569584b8c7171f1241c1d0e2a663a
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c64724c77f86875831f0dc3f9e73f358382113e6d2ee84dbd31d50e46c9970e6
+oid sha256:e3cea6b935081f89ad900a908bab0539f9e0331029e1a7be684cc13797049c52
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ea4c478403fb988737e59309edf8e8423663fefe3eb2b8c49cf8b79c121891b
+oid sha256:c9252c51de1df31c7fa9db77b24072fda5aaa497928e7fedd7c0f01cfbd17906
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fa67daeb64419974086372ba8aca20c65ba993b273167e2568257f8e5992653
+oid sha256:5cf3d71e92538f8852c28d0ab56db4f9cd9e4b98c0e807cde568075961dd5196
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8184312582015991,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 0.5828779599271403,
+  "best_metric": 1.7926479578018188,
+  "best_model_checkpoint": "./outputs/checkpoint-900",
+  "epoch": 0.6557377049180327,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,13 +119,27 @@
       "eval_samples_per_second": 43.721,
       "eval_steps_per_second": 5.47,
       "step": 800
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 1.7964,
+      "step": 900
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 1.7926479578018188,
+      "eval_runtime": 143.5332,
+      "eval_samples_per_second": 43.711,
+      "eval_steps_per_second": 5.469,
+      "step": 900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.765730286403584e+16,
+  "total_flos": 5.359923998077747e+16,
   "trial_name": null,
   "trial_params": null
 }