Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55b02ea69defa8e38e4e28e9fd29a0fcbd9acb8657681df97955e6f22f57da4c
+oid sha256:75ec05861f659e7a6bc56ce7bf9bd50a676348aad283328963d71c3bf8ca60e9
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8526d255608b3fb9a0c1e81123242e14069ced919150cb54aea2543ee82e25f7
+oid sha256:243de32689adb08d286c442730cfbd7424ad98232e10052f873ae5961321aa69
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb7e70944ee032b710f184512939412d316802644141141a5b9b23e848841cc1
+oid sha256:8aa4be861121341cc53f3c40e98a1feeecc92876a32bb3dc6eb154e58726a8e8
 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": 1.4063118696212769,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 1.7333333333333334,
+  "best_metric": 1.3972649574279785,
+  "best_model_checkpoint": "./outputs/checkpoint-1400",
+  "epoch": 1.8666666666666667,
   "eval_steps": 100,
-  "global_step": 1300,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,20 @@
       "eval_samples_per_second": 15.532,
       "eval_steps_per_second": 1.948,
       "step": 1300
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0002,
+      "loss": 1.1689,
+      "step": 1400
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 1.3972649574279785,
+      "eval_runtime": 93.3855,
+      "eval_samples_per_second": 15.538,
+      "eval_steps_per_second": 1.949,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
@@ -196,7 +210,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.595995991076864e+16,
+  "total_flos": 8.182893825921024e+16,
   "trial_name": null,
   "trial_params": null
 }