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:fe1a9afd93f5adfc339e8b64839ea9cd1badc6da6cdf955be8603fb8a03aab1b
+oid sha256:7ff2c6951e123eafafc9099890b6cc5cba851ca8a33e0159a54a540cc7cbd3e7
 size 14293800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:368852d5287812b078f9615ffc02b84af3192a6907d483e7fcc701d413473f84
+oid sha256:6cfb3b8234e1da34ef400e47d325ecec319a1204ac8c8fcbc6dc20c179924dd8
 size 7579748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:147f86daa998915c5d165d9ceed625464a9087a004ce02c3508f4ce18620367b
+oid sha256:0eae09f5992b9191e6859a0c4198a500ead3dc67c84e9514e1372d46a7764a5b
 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": 0.0035849432383987254,
+  "epoch": 0.003983270264887473,
   "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": 71.399,
       "eval_steps_per_second": 35.7,
       "step": 9
+    },
+    {
+      "epoch": 0.003983270264887473,
+      "grad_norm": 16.190603256225586,
+      "learning_rate": 0.0002,
+      "loss": 25.933,
+      "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": 67886118862848.0,
+  "total_flos": 75429020958720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null