Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f0d9ae747d73d46e771dd5be015db65c9e868b05ab212f319ee9d08281eceb2
+oid sha256:cf0a4442aa0a763dafbf4bedf69d830e4462a5301d509c74f861a0650a8e7c10
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f987e048123dc6f8b7da1a180149daacc0106d753c5a533998e015ffa414dfc2
+oid sha256:653dd159470540e86c71e1df496a0bd8f22dd33ae2f8945676cb28458067b3b8
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e09a8c59c3f41f2c2255af0db63699659ef41692967df867b13af0b15265b56
+oid sha256:3b7c6677e9fd19b893b86f757fb71bc5cb4e3de7673f44d725a75c5216e2c901
 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": 0.10762331838565023,
+  "epoch": 0.11958146487294469,
   "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": 21.704,
       "eval_steps_per_second": 10.929,
       "step": 9
+    },
+    {
+      "epoch": 0.11958146487294469,
+      "grad_norm": 15.960527420043945,
+      "learning_rate": 0.0001,
+      "loss": 30.5932,
+      "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": 1.140113195139072e+16,
+  "total_flos": 1.2704118460121088e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null