Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5165b11ade523eb79c90e6ce36f7d39e418c544743a16dd10a02883c9b59b159
+oid sha256:a7b766d6d4f43feacee29d2e89f32664bdb7e3cd00b10f010023335ed3ee80b3
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ecb5daa6230b9221a1b6263ac0b2b154144bd7d2ecfba1bed683f966d362e87
+oid sha256:b1df308f1e5635a54bf4d7db14f37d53868b7a80be9a07787f04380f3c4b23a8
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
+oid sha256:574c700717b33f47ad8a70b47083271e5db120d9e87ae1c83258d7702c5eeb81
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0038801465833153696,
+  "epoch": 0.004311273981461522,
   "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": 12.929,
       "eval_steps_per_second": 12.929,
       "step": 9
+    },
+    {
+      "epoch": 0.004311273981461522,
+      "grad_norm": 21.4761905670166,
+      "learning_rate": 0.00012,
+      "loss": 10.1439,
+      "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": 1664607823331328.0,
+  "total_flos": 1849564248145920.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null