Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bace564bbcc291f674cbc41ee5f877f143659d6f3b39aaeed80e4752f6af931f
+oid sha256:746165a2764849c8c6dbde4fda8fe622a44314bd48f356b3e382f5155ed976b3
 size 50349441

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d891ed6f8c26f1586111b2539c9499c27082792140e557b95580ba50106ab5
+oid sha256:d97d38cb88545389354c4173ee03c29c858dfb4d72c7c126d90e1d145c165349
 size 100692937

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e90988831b9db998648b371e860ead99285474d492b68b6640c993b33227e49
+oid sha256:a8cca4050b412069a5a574ef82deadd3fd628d6acb7444705fb5ae44f31ae444
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
+oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0125839710235596,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.07285974499089254,
+  "best_metric": 1.9195271730422974,
+  "best_model_checkpoint": "./outputs/checkpoint-200",
+  "epoch": 0.14571948998178508,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,13 +21,27 @@
       "eval_samples_per_second": 43.527,
       "eval_steps_per_second": 5.446,
       "step": 100
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0002,
+      "loss": 1.9626,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 1.9195271730422974,
+      "eval_runtime": 144.2253,
+      "eval_samples_per_second": 43.501,
+      "eval_steps_per_second": 5.443,
+      "step": 200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5959170487025664.0,
+  "total_flos": 1.1917344486653952e+16,
   "trial_name": null,
   "trial_params": null
 }