Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:180cee1c455a43b8b52b5de10aae102b005052c94b746f60911d70ae213aec21
+oid sha256:8f225d8ae8f69d55bf001f6132d299f58dc2026159676b83b56cd491cbf09165
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:738537358f8baac5a712631d8a814198eccc3e123f864ac99d39d42501880843
+oid sha256:fb9a9196e18f947229f8d19996e0b02da11c24b427a684e279b592d59d0c94ba
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10290e2d4f04e9723337ac6f941d80a3c552e6f9467b309d39eaa1b78fdecaf0
+oid sha256:98d55838b2a5d2cc02e664d55f8af0bd999b1640f076d9cd2e5f34a26e5a2e02
 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": 1.4976259469985962,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.13333333333333333,
+  "best_metric": 1.4663879871368408,
+  "best_model_checkpoint": "./outputs/checkpoint-200",
+  "epoch": 0.26666666666666666,
   "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": 30.694,
       "eval_steps_per_second": 3.85,
       "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002,
+      "loss": 1.5891,
+      "step": 200
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 1.4663879871368408,
+      "eval_runtime": 47.1865,
+      "eval_samples_per_second": 30.75,
+      "eval_steps_per_second": 3.857,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -28,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3353748701184000.0,
+  "total_flos": 6707497402368000.0,
   "trial_name": null,
   "trial_params": null
 }