Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edd613c9ebde393fdab8e20d8204e4d152cf35089660f145f4dbef78cfb6b4f1
+oid sha256:8e5c4fba58c6bf9390a0338353e80e91f548009bff8fd02ccc563c1546569e22
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b628c7d707cfbb5143e133f23b9af2d0e02f5ef84cc25b954d4553b44098aa6
+oid sha256:92cf4e040cee5763a4b906acfa31515b86ab8d763bf97cb77d72691896e9b9ff
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef917bf1bec8cffeebbc0401af79a27e3570d44ae491f055da1b000fa1464589
+oid sha256:50dbb2327841dc1a7fe1a7d871fa34edd97692f38f48af326a03199ff55031f5
 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": 1.6627237796783447,
-  "best_model_checkpoint": "./outputs/checkpoint-1500",
-  "epoch": 1.092896174863388,
+  "best_metric": 1.6322499513626099,
+  "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": 11.32,
       "eval_steps_per_second": 1.416,
       "step": 1500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002,
+      "loss": 1.6016,
+      "step": 1600
+    },
+    {
+      "epoch": 1.17,
+      "eval_loss": 1.6322499513626099,
+      "eval_runtime": 554.3251,
+      "eval_samples_per_second": 11.318,
+      "eval_steps_per_second": 1.416,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.912157345269842e+17,
+  "total_flos": 4.172858875396915e+17,
   "trial_name": null,
   "trial_params": null
 }