Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76581b06bf5f732e9c7358f572ce6381f474e5580722329670c5d55d8083e367
+oid sha256:0c70ef2189b74ba1f23416866f20524005a5a63cc364dffc41f0ac4dacfd8d69
 size 28348936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a236b8451cd1b998e34fd46c848e8857e4812d62203b366a2630a70fc4bed44f
+oid sha256:3c911e392ae69b71a092d1cef2bddb695f6f2c87b5f55b7f3463aa9ad0378e5c
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16175748798ebd7e55ba83d6c76d4f9b9828c7b45b2602fa6b62af224a20f7b0
+oid sha256:333b626330e710affe324a7a8c9d61c47568ef0fae6f60e5a179319d189d9a9e
 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": 0.015384615384615385,
+  "epoch": 0.017094017094017096,
   "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": 52.82,
       "eval_steps_per_second": 26.517,
       "step": 9
+    },
+    {
+      "epoch": 0.017094017094017096,
+      "grad_norm": 0.4381785988807678,
+      "learning_rate": 0.0002,
+      "loss": 3.6834,
+      "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": 421881031163904.0,
+  "total_flos": 470559611682816.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null