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:a099db4a597bf3663563fd45eb81a3fbd24e931df3d358a78bbe8cff55d805b6
+oid sha256:eb0c6ad7bac22621efd8f7c6bfde56e44aa6c8f05d28dcecc3d1b696c0a48b6c
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb57a026e328ad1fa275fe7ceb29dd55f150ec16932f83f7a9370f8cd80671e8
-size 12639365
+oid sha256:d1a7658f18572bb6ac8360a86d3daa70f114f78a78fd88a7838d30a29cdcc619
+size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fba2ec29b727e3a0922186da9958dbfb3f3436d108f3953990b55b82bc253fb4
+oid sha256:adc62614d66705b8b13a0d65984d823126f5707ef0d8b71f73a02375c1eb0a11
 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": 1.319554328918457,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.26666666666666666,
+  "best_metric": 1.3056749105453491,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 0.4,
   "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": 15.286,
       "eval_steps_per_second": 1.917,
       "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002,
+      "loss": 1.1376,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.3056749105453491,
+      "eval_runtime": 126.1549,
+      "eval_samples_per_second": 15.299,
+      "eval_steps_per_second": 1.918,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7082689446199296.0,
+  "total_flos": 1.0639944335081472e+16,
   "trial_name": null,
   "trial_params": null
 }