Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:166e5102d78e4a721e258cc684235bdb1d1677dbef752199158ef451d1c42f50
+oid sha256:8500ac0c8d08fbe45f39206aff8beab2a62d16294af9d7b7d8fc8e07f4c03b6b
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98ad8d5df014fbf4264c3dbe4daaa94a17049ba03a1b9df708499135eeba31bc
+oid sha256:d2a67432ca150a7cbadda19d56b7d11060a5e5f63b8ab91cf6829afe29ffa04e
 size 51418196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:447b434cc689129a2fc58a5d22ab93c7be9acad4d1c2ce5af2991789642cd017
+oid sha256:0063ba01d1b812463ec3e12bc2caab6e3dca1a1ea5593584dda6aa30d370f6ce
 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": 0.0474191158310694,
+  "epoch": 0.059273894788836747,
   "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": 5.863,
       "eval_steps_per_second": 2.935,
       "step": 24
+    },
+    {
+      "epoch": 0.04939491232403063,
+      "grad_norm": 4.943809509277344,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 17.7916,
+      "step": 25
+    },
+    {
+      "epoch": 0.05137070881699185,
+      "grad_norm": 5.202208518981934,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 16.5579,
+      "step": 26
+    },
+    {
+      "epoch": 0.05334650530995307,
+      "grad_norm": 2.9827098846435547,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 16.4835,
+      "step": 27
+    },
+    {
+      "epoch": 0.0553223018029143,
+      "grad_norm": 5.730014324188232,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 16.5029,
+      "step": 28
+    },
+    {
+      "epoch": 0.057298098295875524,
+      "grad_norm": 3.476895570755005,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 16.4587,
+      "step": 29
+    },
+    {
+      "epoch": 0.059273894788836747,
+      "grad_norm": 3.6241424083709717,
+      "learning_rate": 0.0,
+      "loss": 17.1663,
+      "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": 7.073631392130662e+16,
+  "total_flos": 8.842039240163328e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null