Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1864cf3091cf4467b8b7646cb6c2701907bcef5eeb0590cf502a1695c05fe7
+oid sha256:a8235bb2e22c064f16733ebc1304fd6b601447307891cb7b03b2f0c3090632a0
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a286e2486538cd9f350461d8d7be3f7b1d4081d8d0cb89dccd60b2ccaeaac06b
+oid sha256:d29c98b1d022cc461df8fd5b3bef2deb4ccfa7a97633bfed3ff5cfc2d5157a15
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f537d6df07787c716bf4621ea221744763bd88e92a07f95d1fa6f6a06d8ac757
+oid sha256:0a016715ccb0112ab1394743f94acfb298ac9ccf9cd4cd745ca6d3b1bffe35a3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005441559913841968,
+  "epoch": 0.006976358863899959,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 41.052,
       "eval_steps_per_second": 20.527,
       "step": 39
+    },
+    {
+      "epoch": 0.005581087091119967,
+      "grad_norm": 0.2677469253540039,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1697,
+      "step": 40
+    },
+    {
+      "epoch": 0.005720614268397967,
+      "grad_norm": 0.21872298419475555,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 1.0556,
+      "step": 41
+    },
+    {
+      "epoch": 0.005860141445675966,
+      "grad_norm": 0.25124436616897583,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.9909,
+      "step": 42
+    },
+    {
+      "epoch": 0.005999668622953965,
+      "grad_norm": 0.23902897536754608,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 1.168,
+      "step": 43
+    },
+    {
+      "epoch": 0.006139195800231964,
+      "grad_norm": 0.21240876615047455,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.0213,
+      "step": 44
+    },
+    {
+      "epoch": 0.006278722977509963,
+      "grad_norm": 0.24014732241630554,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0644,
+      "step": 45
+    },
+    {
+      "epoch": 0.006418250154787962,
+      "grad_norm": 0.21955840289592743,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.952,
+      "step": 46
+    },
+    {
+      "epoch": 0.006557777332065961,
+      "grad_norm": 0.21186882257461548,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.9789,
+      "step": 47
+    },
+    {
+      "epoch": 0.0066973045093439605,
+      "grad_norm": 0.26049795746803284,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.993,
+      "step": 48
+    },
+    {
+      "epoch": 0.00683683168662196,
+      "grad_norm": 0.22005507349967957,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.9553,
+      "step": 49
+    },
+    {
+      "epoch": 0.006976358863899959,
+      "grad_norm": 0.21095995604991913,
+      "learning_rate": 0.0,
+      "loss": 1.0059,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.885320227107635e+16,
+  "total_flos": 3.69912849629184e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null