Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:564000152e04f34ad9cff380fb4b4d07e96b2901edc2e7c66cb072a2ec50b829
+oid sha256:3898b881437b494d33bcbd0be6deac28fc4f0ceab8f5e7159c92533c69f2c1ce
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ca718b881699e51c73349b0ef9642ba4daf6b2d09966e7ce7f852ac6cf4ef61
+oid sha256:c64724c77f86875831f0dc3f9e73f358382113e6d2ee84dbd31d50e46c9970e6
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c0ff0504c317a650346ee57e6218cab84ea2865e8a3e9847fe8a9d7e5cc0868
+oid sha256:3ea4c478403fb988737e59309edf8e8423663fefe3eb2b8c49cf8b79c121891b
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09921ec2b52ed1c6b0f6ed69eeab044aae49b679e52ca9804dd8ad029e7ac795
+oid sha256:1fa67daeb64419974086372ba8aca20c65ba993b273167e2568257f8e5992653
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8469738960266113,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.5100182149362478,
+  "best_metric": 1.8184312582015991,
+  "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": 43.73,
       "eval_steps_per_second": 5.471,
       "step": 700
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 1.8337,
+      "step": 800
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 1.8184312582015991,
+      "eval_runtime": 143.5016,
+      "eval_samples_per_second": 43.721,
+      "eval_steps_per_second": 5.47,
+      "step": 800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.169402919360922e+16,
+  "total_flos": 4.765730286403584e+16,
   "trial_name": null,
   "trial_params": null
 }