Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:550418b495e642138ff57ea22146a0a2dc37e240ea5f7cf71efbbdd110848571
+oid sha256:a8071137b43324f66fad92dcbcca890f1f249e011d1a47ec6be285c188b7ba57
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bbc3b609937acfe962edc49ad7033863f023f761460e7e85762f694a90c992d
+oid sha256:7027c56520b0e180bf33387ab058f9ab27b5c3e753140e5684714f326337095b
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edfa7fbe1d7912aca33dd309a581d2fa813033a87d47ee3c156ce7f7d42fa719
+oid sha256:a9dfc0ac726fa37ee99e3992cf3283d3071da98575ab0ad545adbfc30185469f
 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": 0.0026996625421822273,
+  "epoch": 0.0029996250468691415,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 14.495,
       "eval_steps_per_second": 7.248,
       "step": 9
+    },
+    {
+      "epoch": 0.0029996250468691415,
+      "grad_norm": 0.5097793340682983,
+      "learning_rate": 0.0002,
+      "loss": 0.9937,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2931719644643328.0,
+  "total_flos": 3257466271825920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null