Training in progress, step 55, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69c30a91dfe450570125c38ead8325c3181ce4dfa0ff79da1572183a9b969bc8
+oid sha256:782df2de62314fd00a07f609128e636a2bb63700d6cc7f3fda63949faaa70072
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27b143646ed979c314d570266e9b3640d3b565f36fa46d2756fafb2c49ba765b
+oid sha256:fc37a2a8c4de21936d2710e3ab1be80a3c2169df853d6d59404bb8fd01208b87
 size 75471860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eb415ea26e870302de4384a029ef7ff77e384ddb696ca258894875114dc0a21
+oid sha256:cf45e4402320c6640eb2293e0130379c33d21f14d23e9f891e48da3b5a649f0e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43352a0ea01b8f309df99bb65027960564fe5f2f452a04b8b6c955b0ecfed4cf
+oid sha256:8b16062161cca6c6d42c840fa02f9c59f431931479788fa87a822481c8e65827
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.031878557874762806,
+  "epoch": 0.04174573055028463,
   "eval_steps": 14,
-  "global_step": 42,
+  "global_step": 55,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,13 @@
       "eval_samples_per_second": 49.397,
       "eval_steps_per_second": 24.699,
       "step": 42
+    },
+    {
+      "epoch": 0.03795066413662239,
+      "grad_norm": 3.2989048957824707,
+      "learning_rate": 0.0002,
+      "loss": 1.1103,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -81,12 +88,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 695320732237824.0,
+  "total_flos": 910539054120960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null