Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30e932ed307d098aecdcddc90bb163858cec1216e8b7ab333cc70ddf4ff55e0a
+oid sha256:77f916cd72838e5a74c887b0f8491d580af88041208a33bf73a82f96ad192193
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cf7029a3047979a5b2692979f8b352fc366decc32d73c3591c1a790b04544c1
+oid sha256:c537483cedf4bf0185066bae5c81ff2e0992e039da70cb627db8437720c24997
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:957113e67ab11c2af45eb4aad3a4067ef1fc77a018bd85c77d56e6d10186026f
+oid sha256:55a434fa2478e58592908e5f1cc53dc10fd07fe28ea2b87f64160779bd08c4a0
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
+oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3044281005859375,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 0.9471766848816029,
+  "best_metric": 2.2812631130218506,
+  "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": 30.418,
       "eval_steps_per_second": 3.806,
       "step": 1300
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002,
+      "loss": 2.2788,
+      "step": 1400
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 2.2812631130218506,
+      "eval_runtime": 205.7511,
+      "eval_samples_per_second": 30.493,
+      "eval_steps_per_second": 3.815,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.817057293729792e+16,
+  "total_flos": 4.118366969063424e+16,
   "trial_name": null,
   "trial_params": null
 }