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:de643c3817c0c5fda27f4e69bf374cc439726b27645d95125203aae1fcfc6cb7
+oid sha256:44b915f2bcccce73b01a7c62aa183d7f993ae32c6ebc0a767862d2569a00a14c
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dadbed77aefdfb05b28636afafb43b0246943e371a124647e6ed47c398399687
+oid sha256:1c77b5a1915d755adfd68955c079f4f1648f057aa2a022296d2f0865217ed57d
 size 12639365

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfdba55c43769059e866e73758c51b067ee153060eb661a7b796b5c001f2fe30
+oid sha256:fba2ec29b727e3a0922186da9958dbfb3f3436d108f3953990b55b82bc253fb4
 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": 1.360513687133789,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.13333333333333333,
+  "best_metric": 1.3187366724014282,
+  "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": 15.116,
       "eval_steps_per_second": 1.895,
       "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002,
+      "loss": 1.1616,
+      "step": 200
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 1.3187366724014282,
+      "eval_runtime": 126.439,
+      "eval_samples_per_second": 15.264,
+      "eval_steps_per_second": 1.914,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -28,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3546752647888896.0,
+  "total_flos": 7082689446199296.0,
   "trial_name": null,
   "trial_params": null
 }