Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5daa46155fb7b0cc263ef1799291136a05796a67b8b1434be1d8bfbd73a1d0b9
+oid sha256:f37f1189244a8f029d3deea43582f8e03bdc63fbc8044b9c3f838c542d94bbfa
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89cc0e06f1e3c8ec34237abddcdadcb5dd413df45bc76eb9e1b8ef2caf4402c5
+oid sha256:e0063649cb6aad4fa4841b4b5d1e564d3e2af52add38362194e223a3b639db36
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f303dbdb6e91e8d3f652bf7aa35cf837fd0e49b11625945338e0249a07acebc
+oid sha256:b69581977c408b91d3848576bb21889db5cb5adcd56b4f7643e57271d9c33de5
 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": 0.0009804989650288702,
+  "epoch": 0.0010894432944765224,
   "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": 21.932,
       "eval_steps_per_second": 10.969,
       "step": 9
+    },
+    {
+      "epoch": 0.0010894432944765224,
+      "grad_norm": 5.113893985748291,
+      "learning_rate": 0.0002,
+      "loss": 7.6312,
+      "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": 2897648504537088.0,
+  "total_flos": 3142520209145856.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null