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:b64a37e3f5ea1bd47c4e48763e3d7bfaa3e2d681615294d062bdbb121679a335
+oid sha256:bec696f1e60176b56ab402461dc7c9a95653c288ee77a23c2273c0c4ff25ce1e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d6738830c3d3a05031700e3c5d9e856b12eedcb9ac9c1236e01e441750d7b88
+oid sha256:3f3ed11d3ba7a817e7b83f2ab3a8b8ca1dfea7841dedaddc0d54c52026de998d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f299d7d715a9da57119827362cd20a3ee73249d6a1cc12c0e77d7674bfec06b3
+oid sha256:8cde9ca23dfe033d10028cbe0dd91dfa734d0be4761346f37da51e83a1e32cda
 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": 0.00031887755102040814,
+  "epoch": 0.00035430839002267573,
   "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": 28.779,
       "eval_steps_per_second": 14.389,
       "step": 9
+    },
+    {
+      "epoch": 0.00035430839002267573,
+      "grad_norm": 2.5194461345672607,
+      "learning_rate": 0.0002,
+      "loss": 1.7139,
+      "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": 1988281566756864.0,
+  "total_flos": 2173237991571456.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null