Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c359b92497808ce4769c6914822821e4d593169a636e78843c0ec74a54492011
+oid sha256:49a4fa94b63dc1733a36f8552f57e3cfee5eceffe5c940bfb37257d62e78332f
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7adb3d62a95c48f54ff24736ee67bea72cfd90cc1c65e7ba7b2306cae983cd6b
+oid sha256:d6ce47169592764a8d5f4dd7781fbe1214f92060d52f9d76a4ac669025391ec2
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d893120bfba3bcdf26c7a5f485519018e7cecd593a2d8ea3432449ab1d8daeb
+oid sha256:4d068296d3f9011b33a34c8187d97d4e5a695d49d324e8c6f6a7442a620b5590
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
+oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6063916683197021,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 0.8743169398907104,
+  "best_metric": 1.582713007926941,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 0.9471766848816029,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,13 +175,27 @@
       "eval_samples_per_second": 43.555,
       "eval_steps_per_second": 5.45,
       "step": 1200
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002,
+      "loss": 1.6104,
+      "step": 1300
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 1.582713007926941,
+      "eval_runtime": 144.0533,
+      "eval_samples_per_second": 43.553,
+      "eval_steps_per_second": 5.449,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.153237888539034e+16,
+  "total_flos": 7.750057637589811e+16,
   "trial_name": null,
   "trial_params": null
 }