Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:346d485ed41ef925996fd17901bc67d55ee7d89137cb9d1a2bec2ad456654dcc
+oid sha256:7ddcdafea04effab8f5b704553e190bc8bf13c1d16da224177faf162404064da
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:673adfe9e3dec59931dab3dc444d6ca177dafa1c03ccbfb6dfb3ed3580abda1b
+oid sha256:736b4b5f1fc93aa34a96807bd8ca5284cd688e85f760e5cf6a662e5547cb2cdf
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b59954ca0801d56d659d9b748a6880456c339bd37c1bfc513909281d8ae0ffb
+oid sha256:51d3ad219d2064cf85163d881f4149c3e329c0ec00c353672cb88f2424bfa87b
 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": 0.0033635429318882555,
+  "epoch": 0.003737269924320284,
   "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": 343.325,
       "eval_steps_per_second": 171.815,
       "step": 9
+    },
+    {
+      "epoch": 0.003737269924320284,
+      "grad_norm": 1.8986198902130127,
+      "learning_rate": 0.0002,
+      "loss": 44.3314,
+      "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": 103681622016.0,
+  "total_flos": 115737624576.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null