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:bf687c97c3048bda787509502aed0e6ab284be422fe9eef3ef690305aead055b
+oid sha256:3dd2e3ff998164e6d132e68b13922830c77637b16a88fadb2d877fac7badc034
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aff1308a34b67de55723805f953720e3704453befa5478fc610c164b45dbbfbf
+oid sha256:fcc5658dc293ed3e1c51d43bbb67bdbd8715c80977ee4439712ee92d08456621
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ddfe3e8ead907e4700160b9adbd3b9aa0e0e74fb68787d737dcd6fedac9227f
+oid sha256:ba67d73136c5c38f7e153edca2789ac2d86c9d6910093eb36e53443c625f07ff
 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": 0.005491153142159854,
+  "epoch": 0.006101281269066504,
   "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": 29.051,
       "eval_steps_per_second": 14.547,
       "step": 9
+    },
+    {
+      "epoch": 0.006101281269066504,
+      "grad_norm": 6.60803747177124,
+      "learning_rate": 0.0002,
+      "loss": 15.7592,
+      "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": 1465859822321664.0,
+  "total_flos": 1628733135912960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null