Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0461a9617d9f9dd277ef637f7fb067a4e4ab45293d071942bcd84da9c1c0e6
+oid sha256:eb60e94ca7dd7e2db4671ad6e44c3d1c09ad724157dcbae30e331d36a4a520c3
 size 228140600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc2ecdc163215d8d22ff0d3dfa949bc3648659239933c57e85f69e44d114a943
+oid sha256:04b0f9d438477373c26551c6c45f695198021b39f1af011b0d02bc3f6c06dc33
 size 116472340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03ad0c4652463f1096182a18d963eb133233e4b3378834bfb14790c18a607c56
+oid sha256:cff7a7bf575bf735c43664a9f3e7d6224b8e0f70881552070db80cfa952aae28
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03903496882624018,
+  "epoch": 0.04337218758471131,
   "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": 4.739,
       "eval_steps_per_second": 2.375,
       "step": 9
+    },
+    {
+      "epoch": 0.04337218758471131,
+      "grad_norm": 192.78652954101562,
+      "learning_rate": 0.0001,
+      "loss": 53.0197,
+      "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": 8.234209697071104e+16,
+  "total_flos": 9.14912188563456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null