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:da23ec3d4260e8a93b1bcbc0e61a478e3d8adf06a1eacede3a0f786a8ffd8528
+oid sha256:b8b22b96f4b8a071b7057ef279aa9e6cedd81611e0d602bc615c65a488ba158d
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d114e901f7999d81801baa995a76df40ce650cefe8e8a6ecb244d4128a697a6b
+oid sha256:064321f8d6a3de617d29729fb134d6d344b47a7ab8b424ee7769ddd5c2f64519
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200e6fcd481c16b4f3d1cbb24a0867b14067141b424637d8e0b176938ed6cbb2
+oid sha256:12652e548395ac54f34186413124cf818db17e2dae781e78f969b6d3fed44e53
 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": 0.00032863206901273447,
+  "epoch": 0.00036514674334748275,
   "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": 1.869,
       "eval_steps_per_second": 0.935,
       "step": 9
+    },
+    {
+      "epoch": 0.00036514674334748275,
+      "grad_norm": 0.8222519755363464,
+      "learning_rate": 0.0002,
+      "loss": 0.9516,
+      "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": 2351283906281472.0,
+  "total_flos": 2612537673646080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null