Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2531756f227f698c4295ca3a793aab3b065333ee1e7adbde9f17815af9b24f60
+oid sha256:4a1edeea60c23fc58fe80cc59f69db405d973e9f0a2e827d8e166793f7286aa8
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b58b9129afc59b4cd3581d2b56cf173515653c5022cc8e95e5641bfd1c5b5023
+oid sha256:260836b2258c3c7464635ae0427fc8bcb3cf62577bec2af4e375566cc7b3e551
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c784a60f4659800f3c4472f150d377d77a69d88547c6e5e024a7e54b3ef12b
+oid sha256:1ae59499d6fa89d93656a32994352236f76ecdb3c0d5d7d01bbf5e497aa8ee6c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02723463687150838,
+  "epoch": 0.034916201117318434,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 322.194,
       "eval_steps_per_second": 161.364,
       "step": 39
+    },
+    {
+      "epoch": 0.027932960893854747,
+      "grad_norm": 0.42409539222717285,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 44.3033,
+      "step": 40
+    },
+    {
+      "epoch": 0.02863128491620112,
+      "grad_norm": 0.48222002387046814,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 44.3052,
+      "step": 41
+    },
+    {
+      "epoch": 0.029329608938547486,
+      "grad_norm": 0.49725550413131714,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 44.2809,
+      "step": 42
+    },
+    {
+      "epoch": 0.030027932960893854,
+      "grad_norm": 0.4729093909263611,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 44.2818,
+      "step": 43
+    },
+    {
+      "epoch": 0.030726256983240222,
+      "grad_norm": 0.5070559978485107,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 44.2813,
+      "step": 44
+    },
+    {
+      "epoch": 0.031424581005586594,
+      "grad_norm": 0.4928998351097107,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 44.2873,
+      "step": 45
+    },
+    {
+      "epoch": 0.03212290502793296,
+      "grad_norm": 0.44889867305755615,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 44.2844,
+      "step": 46
+    },
+    {
+      "epoch": 0.03282122905027933,
+      "grad_norm": 0.4408016502857208,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 44.2798,
+      "step": 47
+    },
+    {
+      "epoch": 0.0335195530726257,
+      "grad_norm": 0.4764954149723053,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 44.2815,
+      "step": 48
+    },
+    {
+      "epoch": 0.034217877094972066,
+      "grad_norm": 0.4159543812274933,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 44.3073,
+      "step": 49
+    },
+    {
+      "epoch": 0.034916201117318434,
+      "grad_norm": 0.46668875217437744,
+      "learning_rate": 0.0,
+      "loss": 44.2862,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 54912614400.0,
+  "total_flos": 70415155200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null