Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7a78a6aaaca928eca24508a754a5ff2ef2041a6a73cad7f060f54fa764f1897
+oid sha256:75dd46ee53440b400db35c75d29ef47eea8eb6cf00f2617d0bb67ff0df7f49a2
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d29e2d9958f1c8a5d22033bec8b6286f98436d4031882de4cae34c3568ee1115
+oid sha256:f95671948202b7d6defc2801d4092688f173d13aad3d53842c38013ebc5657e2
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1b5277d5cea8e100a686288ddedae2c0ea0218b333df76e463fb0a545514396
+oid sha256:97951a03649ecfce2fa477a94503377d7d9a1a56dc63144e563f1bf217b06b64
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0015218769816106531,
+  "epoch": 0.0016909744240118367,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 51.383,
       "eval_steps_per_second": 25.691,
       "step": 9
+    },
+    {
+      "epoch": 0.0016909744240118367,
+      "grad_norm": 11.172967910766602,
+      "learning_rate": 0.0002,
+      "loss": 1.3211,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 95716026089472.0,
+  "total_flos": 104619842469888.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null