Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:801dc6ce35e23ac85938e3e746e50141afe5c3ebcbd20eb271e3e2f0a1c15a21
+oid sha256:5dde7cd716056ff6ad9f748a7f0e5aeafa78a5433a8d282c758bf8e3cb6a0579
 size 50349441

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb8383a7e5dea0980760e4a24e9c9ec131778f81424b7b42bfb040a417d5a9e2
+oid sha256:0c6384db839da64131ffbc3f4c33fdea56a5d379727db42e65240499b5840e61
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab823abb115c32fa0673f758e0b0199bf6d5f3e43f5557dbadcc612729790b53
+oid sha256:cd0e92abf050d4ab2ae03dc05823099af1cb99bab8778b951d8b18b05768e217
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
+oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5355615615844727,
-  "best_model_checkpoint": "./outputs/checkpoint-1500",
-  "epoch": 1.092896174863388,
+  "best_metric": 1.5179370641708374,
+  "best_model_checkpoint": "./outputs/checkpoint-1600",
+  "epoch": 1.1657559198542806,
   "eval_steps": 100,
-  "global_step": 1500,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,13 +217,27 @@
       "eval_samples_per_second": 43.557,
       "eval_steps_per_second": 5.45,
       "step": 1500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002,
+      "loss": 1.5062,
+      "step": 1600
+    },
+    {
+      "epoch": 1.17,
+      "eval_loss": 1.5179370641708374,
+      "eval_runtime": 144.0242,
+      "eval_samples_per_second": 43.562,
+      "eval_steps_per_second": 5.45,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.943146869488845e+16,
+  "total_flos": 9.539236838063309e+16,
   "trial_name": null,
   "trial_params": null
 }