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:de736a267c35db52f11d9f6e095d31985bebbff0877d5b8eab970c18b7c032ab
+oid sha256:3e7f996d423e000d1a022b2978f938d534110ef3e36a44f80b429c6fbb1e54d8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06a869dd62362728749d978d7c5ae1df4fbf66dc225c664dc1b38496e6e9925f
+oid sha256:395077dd7060ae550c6e8a43c2693c031b8fa339590f2f3b7c5713fb37c7cbab
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a74f0fa67ad2ea453853ea9c83fafb9413743a4d7deb09428e0f1e45b1df8364
+oid sha256:da70fcbf4bc000d633bdd59ff5bb75c3f527ccd5147f13a7552f0015370d4e68
 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": 0.0006456935825232271,
+  "epoch": 0.0007174373139146967,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 13.953,
       "eval_steps_per_second": 6.978,
       "step": 9
+    },
+    {
+      "epoch": 0.0007174373139146967,
+      "grad_norm": 4.515064716339111,
+      "learning_rate": 0.0002,
+      "loss": 1.3864,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3156197184110592.0,
+  "total_flos": 3506885760122880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null