Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16ef960926e6179cfb6f49eaa48d656ff7a40ae934128696394d1a6072a34105
+oid sha256:ce8d36c0bd87bf8ae8bdcb20921b8caf35b86cdffe827d7bd03f32a2723d46b7
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:717bf92d5df6bb3a00ce8cebf8fba878e595f2877fc6555db086ebefdd0f20b6
+oid sha256:10ad15c86ce0d35acdac7ffab5ef1be85f7bbaf83fa208863bebc20371166117
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b0e12247d9d10f7e64c8c089eb113909ad8bbe42725f30cb59f2c8d990744bd
+oid sha256:9c84e8b4a8c776f86051b75aa3685560455029395d582d469c76653ad7d97caf
 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": 0.00976933514246947,
+  "epoch": 0.010854816824966078,
   "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": 63.195,
       "eval_steps_per_second": 31.598,
       "step": 9
+    },
+    {
+      "epoch": 0.010854816824966078,
+      "grad_norm": 9.76582145690918,
+      "learning_rate": 0.0002,
+      "loss": 3.9622,
+      "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": 282640980639744.0,
+  "total_flos": 312709170069504.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null