Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8134ea2a3eaa5cb8a90c61742125c2c2e16b8333660eceb4e0ac4bc87a9b3d4b
+oid sha256:551cc9e01e16c09a37e316823a86355686afecf4cd57ea8b7c486f40fec56032
 size 66103768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1da99327cd43626fd48e502e3477d741dae74d16bd42f85353a9f99068c0d9f
+oid sha256:62124b9ff570208b9761e925dffaac0b7c2146a62f66eb376ff826ad134adaa1
 size 33939412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0550373e8ab2cc5a61fc1c48c9e340c7375bbacfdfbd51c10d044332f8177330
+oid sha256:76713a142f1f54e59696c036a43b5e5cd041e21d5bbbb12d7a1ad0ac9254ae59
 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": 0.007733619763694952,
+  "epoch": 0.008592910848549946,
   "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": 18.546,
       "eval_steps_per_second": 9.273,
       "step": 9
+    },
+    {
+      "epoch": 0.008592910848549946,
+      "grad_norm": 1.9096448421478271,
+      "learning_rate": 0.0002,
+      "loss": 4.1353,
+      "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": 2088566084038656.0,
+  "total_flos": 2304624644456448.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null