Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38f667f169ad688e25ac7c5407de2003cac6d1e4168f69a15fb61ba1a06681d7
+oid sha256:042feb5e0c533d7cebf3f96fde66bb552d8c58787c348e002784a0a16886fcb9
 size 50349441

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aac9303b6313dabec05560596d067d31e37caf3a02d16fdba574a9b8160764a
+oid sha256:1c1adb0241d72505ab60fa2b39ebb82e14f8176d45ac7e480ea997bfe5df7594
 size 100691721

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": 1.5348094701766968,
-  "best_model_checkpoint": "./outputs/checkpoint-1500",
-  "epoch": 1.092896174863388,
+  "best_metric": 1.515953540802002,
+  "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": 21.793,
       "eval_steps_per_second": 2.727,
       "step": 1500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002,
+      "loss": 1.506,
+      "step": 1600
+    },
+    {
+      "epoch": 1.17,
+      "eval_loss": 1.515953540802002,
+      "eval_runtime": 289.836,
+      "eval_samples_per_second": 21.647,
+      "eval_steps_per_second": 2.708,
+      "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
 }