Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f8acc8e4583671b90ee55d4dda63885eb7fa29a9a3f70d98501f1851852feb3
+oid sha256:e475ef66d57f4c7e969e4b4c2e0874139ab6bd169ab6b7ece6941318486e88fe
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3226ae37fb90e8fc8e19c1e5d48d7bffcf5eb041f5cd91967b8bed92ba350dbd
+oid sha256:f8ecb9f1782ef033a338e68df8a2676a95848bfe12f315f9827c6d9357b4602e
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
+oid sha256:c06cc185129710fbc4aefbd4aecab61cbe55d72872505d4a12d4f40835976880
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000559331040076069,
+  "epoch": 0.0008389965601141035,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 8.208,
       "eval_steps_per_second": 4.104,
       "step": 20
+    },
+    {
+      "epoch": 0.0005872975920798725,
+      "grad_norm": 0.5474965572357178,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.1812,
+      "step": 21
+    },
+    {
+      "epoch": 0.0006711972480912829,
+      "grad_norm": 0.45622146129608154,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.1839,
+      "step": 24
+    },
+    {
+      "epoch": 0.0006991638000950863,
+      "eval_loss": 1.191240668296814,
+      "eval_runtime": 1835.1225,
+      "eval_samples_per_second": 8.204,
+      "eval_steps_per_second": 4.102,
+      "step": 25
+    },
+    {
+      "epoch": 0.0007550969041026932,
+      "grad_norm": 0.4854365885257721,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.1041,
+      "step": 27
+    },
+    {
+      "epoch": 0.0008389965601141035,
+      "grad_norm": 0.43934768438339233,
+      "learning_rate": 0.0,
+      "loss": 1.1416,
+      "step": 30
+    },
+    {
+      "epoch": 0.0008389965601141035,
+      "eval_loss": 1.188349962234497,
+      "eval_runtime": 1836.1198,
+      "eval_samples_per_second": 8.2,
+      "eval_steps_per_second": 4.1,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6610941168844800.0,
+  "total_flos": 9916411753267200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null