Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb225a59c974310143f5d17d604835d43b60874a8afd12b160443afb28b7a5c3
+oid sha256:4d33f338e1e9c39928855dff98bd185864db17a9257e3e67b608d3c2983b9c7b
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fec59b955900be9724e52e5ba1d6268f04cf008beb296419c5a2c8ae7389e45
+oid sha256:8034e399f236dac3e043878eb1d9b1537f45ffbb6d0bdb9c7067553d54818250
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e29e66817349158337df1bd41441f26d49ce5a4752ab84d525100d2ee478d1a6
+oid sha256:6f2d8633c0aa6b6a8b67d82ed27db4d43d78e0131786fdb9f59325ae79b03026
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
+oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2864296436309814,
-  "best_model_checkpoint": "./outputs/checkpoint-1900",
-  "epoch": 2.533333333333333,
+  "best_metric": 1.2813292741775513,
+  "best_model_checkpoint": "./outputs/checkpoint-2000",
+  "epoch": 2.6666666666666665,
   "eval_steps": 100,
-  "global_step": 1900,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,20 @@
       "eval_samples_per_second": 12.912,
       "eval_steps_per_second": 1.62,
       "step": 1900
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.0002,
+      "loss": 1.049,
+      "step": 2000
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 1.2813292741775513,
+      "eval_runtime": 112.6047,
+      "eval_samples_per_second": 12.886,
+      "eval_steps_per_second": 1.616,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -280,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.2086378107969536e+17,
+  "total_flos": 1.2725057626251264e+17,
   "trial_name": null,
   "trial_params": null
 }