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:ff718802a67f448c18641ec9f12db89e54c03969e5d7fac720c5081393b9fc13
+oid sha256:8ebe09c52a3f04365975892320a186aa239c700677b4d63769c678493ae9e292
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6015f026b6a7d9de5040c97c3c51a15e848b2e026bbba62e15d890c7a6e8bb4c
+oid sha256:dd60fd7ae2ede17c16bf972d0976f1d8d156f3be75031330a456cce6bcc23fa5
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3f14f26e1c82af1569197c946ee60a682af9d056666c7fed1d76396f3ef87dc
+oid sha256:4c638f15cd58032f947d87dcc068e20509a398cb8780976d061ac887a6986b8a
 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": 2.275839328765869,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 1.1657559198542806,
+  "best_metric": 2.2586843967437744,
+  "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": 30.302,
       "eval_steps_per_second": 3.791,
       "step": 1600
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002,
+      "loss": 2.2529,
+      "step": 1700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 2.2586843967437744,
+      "eval_runtime": 207.0741,
+      "eval_samples_per_second": 30.298,
+      "eval_steps_per_second": 3.791,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.676360009803776e+16,
+  "total_flos": 4.969767169124352e+16,
   "trial_name": null,
   "trial_params": null
 }