Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:002af32a590093290e0a9c7729b92a84afdc00e85030308f849817d0b9c1650a
+oid sha256:09a1711d7b86f22d286b4dab8611d43229feed130c1301c24013f4a77c4f82b0
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d26c640d748af893d72dae69a12269eee1396b9138b5268c9efd67369847392a
+oid sha256:24f2a31f49f1da9f22016c2775f4af6f48af5e79930730ff414dcea9f92b55ef
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6806389118ec16be45f91f2597dc80c85380e866e2552fc0b165cbd873f66c65
+oid sha256:0bb344c1a46ab1ca05a5243802d67b36bd798bd1c0d66d53e1472c53d4e2344c
 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": 0.0012503473186996387,
+  "epoch": 0.0013892747985551543,
   "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": 16.331,
       "eval_steps_per_second": 8.168,
       "step": 9
+    },
+    {
+      "epoch": 0.0013892747985551543,
+      "grad_norm": 1.2583094835281372,
+      "learning_rate": 0.0002,
+      "loss": 5.2049,
+      "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": 2809592442519552.0,
+  "total_flos": 3094623559876608.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null