Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e8c69a22c4024e6d6f615d58e2c795cd699118f945dcb1c8aee1912f18478f9
+oid sha256:7dcc96e88dbbe67e2aba75e1410e8be8368740094647756f3aeda0648e40eda2
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be9a796192f42eeebc4da2a1e5fe69a123bf78d995f0b205e0d2d8ed980cf541
+oid sha256:92cc3d88eb1cd631988dadbb911dbf04d254cc8a4175f59317397b0d8cc53e57
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd0e92abf050d4ab2ae03dc05823099af1cb99bab8778b951d8b18b05768e217
+oid sha256:1389c8fb4da5b08654d5ecff1c857ae43115866bad194f9289834fc2a0b6a9c8
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
+oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5172873735427856,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 1.1657559198542806,
+  "best_metric": 1.501122236251831,
+  "best_model_checkpoint": "./outputs/checkpoint-1700",
+  "epoch": 1.238615664845173,
   "eval_steps": 100,
-  "global_step": 1600,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,13 +231,27 @@
       "eval_samples_per_second": 43.676,
       "eval_steps_per_second": 5.465,
       "step": 1600
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002,
+      "loss": 1.5042,
+      "step": 1700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.501122236251831,
+      "eval_runtime": 145.0647,
+      "eval_samples_per_second": 43.25,
+      "eval_steps_per_second": 5.411,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.539236838063309e+16,
+  "total_flos": 1.0135854358789325e+17,
   "trial_name": null,
   "trial_params": null
 }