Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2146169b4fb1058d0986a3326fd72dc0dfe47b976290869ebf399fddbb50c31f
+oid sha256:303302bb77c38c22100c73f59cea60538f44f68a9655bba7ef66ab356f04fcf6
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c049a1a89951687ef2f25fd4c200917ca7b44158d62446e72c444137f6d51aea
+oid sha256:b028707927e34488d3ef15b823b8e93f6c69a067e39b1892a43ff75ff4996a43
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:849c2735d9f3711d3b45cd02f417d920a694e6d10391da18f0c884120cdb6f60
+oid sha256:77987d1aa285679a5104248e7fb7b9ed531b5e9fc37be752c17bd4076014e0e6
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
+oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.072767734527588,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.2840909090909091,
+  "best_metric": 2.044309616088867,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 0.42613636363636365,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,20 @@
       "eval_samples_per_second": 27.568,
       "eval_steps_per_second": 3.455,
       "step": 200
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002,
+      "loss": 2.2227,
+      "step": 300
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 2.044309616088867,
+      "eval_runtime": 54.0469,
+      "eval_samples_per_second": 27.606,
+      "eval_steps_per_second": 3.46,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6049717237186560.0,
+  "total_flos": 9097682005278720.0,
   "trial_name": null,
   "trial_params": null
 }