Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dde7cd716056ff6ad9f748a7f0e5aeafa78a5433a8d282c758bf8e3cb6a0579
+oid sha256:9c3694b9769451b4e7587f8afd0bf460e687c5c552683b2b6a8832e5d0943cd6
 size 50349441

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c6384db839da64131ffbc3f4c33fdea56a5d379727db42e65240499b5840e61
+oid sha256:f211b36881b86340c0e1c1926f46a2a99a1d45eb54e2a242690a4e07cddb2cf6
 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": 1.5179370641708374,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 1.1657559198542806,
+  "best_metric": 1.5012134313583374,
+  "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": 43.562,
       "eval_steps_per_second": 5.45,
       "step": 1600
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002,
+      "loss": 1.5038,
+      "step": 1700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.5012134313583374,
+      "eval_runtime": 144.0166,
+      "eval_samples_per_second": 43.564,
+      "eval_steps_per_second": 5.451,
+      "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
 }