Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c17e1d6b6bca144e823670d17283e3490132c6ec0fcfec5a7816908b3aec050c
+oid sha256:f7f96df7bd3e5349d9b49a62d34bd8d027187e64e2eb7dc3e3ac0c4297d69fa7
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44816feb214487997972088393fa104dbe4c7d180e758a92b1325f95902b76a9
+oid sha256:1260b98c53015862559a109342940a588476d9d02238617f300208dcf4e19807
 size 100692937

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b75a5f452b9ade4a1758634b2d34804b2f90e784cbbb361df59d00d4923a6ba1
+oid sha256:548719e8fcb17ef09c89c53de77f37623dd6f564e0e5fd5f6e820e579f2f66b5
 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": 0.8566448092460632,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.5333333333333333,
+  "best_metric": 0.8006419539451599,
+  "best_model_checkpoint": "./outputs/checkpoint-200",
+  "epoch": 1.0666666666666667,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,20 @@
       "eval_samples_per_second": 8.41,
       "eval_steps_per_second": 1.054,
       "step": 100
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 0.8856,
+      "step": 200
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 0.8006419539451599,
+      "eval_runtime": 229.5751,
+      "eval_samples_per_second": 8.407,
+      "eval_steps_per_second": 1.054,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -28,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.03402868736e+16,
+  "total_flos": 1.40647601737728e+17,
   "trial_name": null,
   "trial_params": null
 }