Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c3963d02ebc5c564f675c9c4b6b695d331697a94cc66b96824b5ca5ce26e515
+oid sha256:7722eb15b6265cfdf28201106478444d57f5408a4f21a67af71a50a68e8e3b0e
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87d23b295cfc208984b15b45dde7a870c8327bb8dae689f22d940c0249641843
+oid sha256:b6a6d5e3f4f004b58048fce8a3abe578638bbaec20ada2638e7004b65eebcbda
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f00106cbfb8c632beca164b78975f9a67d424eb8a9d2ed6a5beb4029b939428
+oid sha256:abc09d070fafc67ab86d5788e460f0fb5e7514aafabd32570046dbac5764487b
 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": 2.083603858947754,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.2840909090909091,
+  "best_metric": 2.054030656814575,
+  "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": 27.777,
       "eval_steps_per_second": 3.481,
       "step": 200
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002,
+      "loss": 2.2344,
+      "step": 300
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 2.054030656814575,
+      "eval_runtime": 53.5493,
+      "eval_samples_per_second": 27.862,
+      "eval_steps_per_second": 3.492,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6019766034186240.0,
+  "total_flos": 9052943521628160.0,
   "trial_name": null,
   "trial_params": null
 }