Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2174bcbfbd7eb0e49a26aefaff62055e293713180e9c445177b67f7588462e1d
+oid sha256:89e2a2f17c0d474d0773f238eca1de3eba62ca9cf27c2c5412a6d9a68d9d2825
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14a45d24d0add00c031074ef98f5be82a0ec2646a06d85a0079853489fca00c8
+oid sha256:0c6a81bd41e1af253887a6efe7de883d96b570282b0fc447149ef07a7e2b88f0
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db1fb422c59d5580726dafb7c0759e8ded729b26f46035e173f05331834f6b74
+oid sha256:fd66f2dc416a164022f9a63e90b05cd64c9e0e49360e1de46684b5ebbb8d3b1a
 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": 0.00459125111592909,
+  "epoch": 0.0051013901288101005,
   "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": 10.943,
       "eval_steps_per_second": 5.472,
       "step": 9
+    },
+    {
+      "epoch": 0.0051013901288101005,
+      "grad_norm": 0.4062849283218384,
+      "learning_rate": 0.0002,
+      "loss": 2.4832,
+      "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": 2788217673744384.0,
+  "total_flos": 3136744882962432.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null