Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d1eecfce2ce5a475d07c9b8d9eb490cee69fc05e91981dadd1f816a6309af85
+oid sha256:3d194b2f665e442bb00b11490c0edf1a28ada39517ca0bccda6e160fbdf0b424
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb91d3aa2dba6985bbfda47e627d674a4cf84633222b447d5b948daf9f8c346
+oid sha256:c4385a46b9189b97f4df02efacc679455dd021f37e162ebbe9c3e1d35b72d299
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b79569914b66c8a8adae97b253e826ad354a54341d167ae1705fdfccf06f3e4
+oid sha256:6279e2d6d30b2ce7f2189e648e383ab146d51fb0fecf44d1e16d05504562e6f8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4178454842219804,
+  "epoch": 0.5223068552774756,
   "eval_steps": 8,
-  "global_step": 24,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -207,6 +207,48 @@
       "eval_samples_per_second": 179.407,
       "eval_steps_per_second": 90.628,
       "step": 24
+    },
+    {
+      "epoch": 0.4352557127312296,
+      "grad_norm": 0.05406927689909935,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.762,
+      "step": 25
+    },
+    {
+      "epoch": 0.45266594124047876,
+      "grad_norm": 0.0536014661192894,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.7623,
+      "step": 26
+    },
+    {
+      "epoch": 0.470076169749728,
+      "grad_norm": 0.05207870528101921,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 11.7614,
+      "step": 27
+    },
+    {
+      "epoch": 0.48748639825897716,
+      "grad_norm": 0.05782800912857056,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 11.7621,
+      "step": 28
+    },
+    {
+      "epoch": 0.5048966267682263,
+      "grad_norm": 0.05422654375433922,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 11.7636,
+      "step": 29
+    },
+    {
+      "epoch": 0.5223068552774756,
+      "grad_norm": 0.06374860554933548,
+      "learning_rate": 0.0,
+      "loss": 11.7614,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -221,12 +263,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 39110408404992.0,
+  "total_flos": 48888010506240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null