Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dcc963b9974429fbf17295871d0585952e3d747883cf04ea7c1dba83c12409d
+oid sha256:c6e958e05b0965c7138e5f666f0572cf0a90f63954bef91b7ea692a4dd09edcb
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:253d535f3400ed76c0ab226fbcb367b601a0c99d61a8257b5061b804144b6a23
+oid sha256:95dd9193f1ea644242c1cfdf13f630d74089a1f52954caa69d7af1fda5b0e9ca
 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": 2.2731645107269287,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 1.1657559198542806,
+  "best_metric": 2.25679087638855,
+  "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": 30.599,
       "eval_steps_per_second": 3.829,
       "step": 1600
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0002,
+      "loss": 2.2527,
+      "step": 1700
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 2.25679087638855,
+      "eval_runtime": 205.2907,
+      "eval_samples_per_second": 30.562,
+      "eval_steps_per_second": 3.824,
+      "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
 }