Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12333fd57f2f21090aca8b249467fa97c1937b804c5deaff197a3ca89bf3c167
+oid sha256:0847e2ed74e1f3fb53cdfa53b289636e6fa5b8c7585688840248c4df886ccd5e
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:206c08064e77b6fd4711b3629983506999a7c2b690874afb1bc85c9ac345d6e2
+oid sha256:8228687184710ba76325585120de3122ce5e800618ccd5197c1611a6bfab37a3
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2888a62db6bbbdd9fb6379059149f22a64e1c46675f5da47d0742f8805f53809
+oid sha256:1a21671a73f6dd028dc229518951bc93c2491b077773a47299b6d42a86ae0659
 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": 0.0013343217197924388,
+  "epoch": 0.0014825796886582653,
   "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": 52.233,
       "eval_steps_per_second": 26.117,
       "step": 9
+    },
+    {
+      "epoch": 0.0014825796886582653,
+      "grad_norm": 0.8482385277748108,
+      "learning_rate": 0.0002,
+      "loss": 1.421,
+      "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": 140235107991552.0,
+  "total_flos": 155816786657280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null