Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:820d01be5a6b44cb2bba830db51c2d55caa147263e00ed937c2ce7a626ae0adb
+oid sha256:b9c67c0a5a8a6973079665278f8b4a493769bafbc5cb7a655c29401784ad09a5
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19c29a5b504e561230992463937333d2b9056f92f246eb125d546954f42e48ba
+oid sha256:dfce265431541d4b2d4b1ecd41c03fe1631b51321eb87f8654322608e36947f7
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63dc2d8608fa8b36d01cc06ffb7d3c3b355455dfe67158233e553a478a7c7c1d
+oid sha256:6d9abb419b80aead609e3d25aa188a530b509237800785868036d93ad22750d1
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fc56f953d372e16c8b68954ff13e9f4409f9a42678d3b33dea6fba4610a0519
+oid sha256:7e41ec466e37d3e777474b32690d472b15b70497f93b8ea178e488be3afc4f79
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7012412548065186,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 0.9471766848816029,
+  "best_metric": 1.679748773574829,
+  "best_model_checkpoint": "./outputs/checkpoint-1400",
+  "epoch": 1.0200364298724955,
   "eval_steps": 100,
-  "global_step": 1300,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,13 +189,27 @@
       "eval_samples_per_second": 43.73,
       "eval_steps_per_second": 5.472,
       "step": 1300
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002,
+      "loss": 1.6814,
+      "step": 1400
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 1.679748773574829,
+      "eval_runtime": 143.4782,
+      "eval_samples_per_second": 43.728,
+      "eval_steps_per_second": 5.471,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.742035914040934e+16,
+  "total_flos": 8.337729485790413e+16,
   "trial_name": null,
   "trial_params": null
 }