Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87cd665d5194b58daf9f076f0d70da138f72bfb986db877d8c94f22a71986ac2
+oid sha256:e76c97b27b51d837fe269cdda525be6be9c4d7a31602f78d2f350e2e4c055475
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b027afa43f63b2c5b25975008932c91acea891890d801200412531e83645d762
+oid sha256:4104c3726537a5faa74893845e9bfab56b36655aba99fddca711a343e68399f2
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec5cd6f4135325d74cbe93521ed6f759304f9780c6d6678a798b7bcfeb74b23f
+oid sha256:33e579106e8f865507506805b7ed42146d38e63f436a4089773e539eb4028c15
 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": 1.905383586883545,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 1.8465909090909092,
+  "best_metric": 1.8999686241149902,
+  "best_model_checkpoint": "./outputs/checkpoint-1400",
+  "epoch": 1.9886363636363638,
   "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": 19.873,
       "eval_steps_per_second": 2.491,
       "step": 1300
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.0002,
+      "loss": 2.0463,
+      "step": 1400
+    },
+    {
+      "epoch": 1.99,
+      "eval_loss": 1.8999686241149902,
+      "eval_runtime": 75.2179,
+      "eval_samples_per_second": 19.836,
+      "eval_steps_per_second": 2.486,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
@@ -196,7 +210,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.957240059265024e+16,
+  "total_flos": 4.261985771323392e+16,
   "trial_name": null,
   "trial_params": null
 }