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:d1ddcf6ea8f5ebbca5308a39e539f98bcc37e5b3b52ac6e3d6cb73f95e916a8e
+oid sha256:8d5d825604a999751abc205aa2360be9ac17ae2adf32df32ee1a962155b6acc4
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63ce3360450fa2beaefeaee64c056f8b8fc3435b5b40a0dde13dac0fce2f6779
+oid sha256:8f2339e6a163a447e287b8f491e1231c10c9a5adcb351a9fbb85b2332c6a6635
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:094837089fa2ed1c4f9dc6c25bac04422ed41c22630725ca5cdf86ffa65f03cf
+oid sha256:787ef78ee12881294c4aa83ed64603709fff88fc133de1a040e06eba2a245935
 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": 0.00034053501835105374,
+  "epoch": 0.00037837224261228196,
   "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": 2.34,
       "eval_steps_per_second": 2.34,
       "step": 9
+    },
+    {
+      "epoch": 0.00037837224261228196,
+      "grad_norm": 2.6987967491149902,
+      "learning_rate": 0.0002,
+      "loss": 2.6814,
+      "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": 6328165488132096.0,
+  "total_flos": 7031294986813440.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null