Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79e65ebd5bd32a68ee4307c9312ea9f01c438f4a8c1284133bdf083404663bbd
+oid sha256:72a9790771c08c053dff44467034d102742b1be32e6d9cf61f14bfae0ac8eb2b
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07837251be8eece079ce4157b5861d07efc6d5e2ee237aa3a74af9d159d84c53
+oid sha256:cab12edcb69549c97d5f09d906eaaa5e1e5e213967364b8aaec0f4b04e4cdd8a
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9cc803867fe7245ea681fe699d560af7aae2d3d848fa96a72508a4d1886494c
+oid sha256:ef7673e25e51a98aec78b64117d84341dadb6882fc8441f1b2fd4ab47394cd16
 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": 0.0189873417721519,
+  "epoch": 0.02109704641350211,
   "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": 21.918,
       "eval_steps_per_second": 10.959,
       "step": 9
+    },
+    {
+      "epoch": 0.02109704641350211,
+      "grad_norm": 9.600102424621582,
+      "learning_rate": 0.0002,
+      "loss": 13.624,
+      "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": 537430264381440.0,
+  "total_flos": 597144738201600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null