Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c41b3cf5565659f656d9e5056f1787a96e63005ae72bb4295f5db1c95f53bfc
+oid sha256:6ef5b32a8a62931908755623e87d3799e1ace0bcc5a82ca5b0cb42f174abf39b
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2f3b4d25ae5daadf0abdb6ec47256de41113032409bf71de448b8a79d68cd21
+oid sha256:148884d6c7ff51efadcf36692dc5ec40e8973c725d4ff1efefd7557427a285d8
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2e345d54e3592c532aab61b6f38d436e78a3ad0f3965019c9f4db88ef50bdb0
+oid sha256:a4060886c8f06325a105271f5ee9d3973327355c66ff72bbab33ee261ed68656
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f824d8dfbbf15687dfe61700fabfa8a5a0ff71ab4fbfbc90093d11204ca3eae
+oid sha256:41639d1994829bc2ee2cf4bcf82d4fb746380cad20e3d593102982ecf4be7313
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6430609226226807,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 1.1657559198542806,
+  "best_metric": 1.6253100633621216,
+  "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": 41.662,
       "eval_steps_per_second": 5.213,
       "step": 1600
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002,
+      "loss": 1.6298,
+      "step": 1700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.6253100633621216,
+      "eval_runtime": 143.5003,
+      "eval_samples_per_second": 43.721,
+      "eval_steps_per_second": 5.47,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.528438138605568e+16,
+  "total_flos": 1.0124498798727168e+17,
   "trial_name": null,
   "trial_params": null
 }