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:e47a73708d6733a3a4722170bf05dd396f7a42640ce961173c53900d441b9b39
+oid sha256:cf3c2685b5a54ee5eb7eeb51cdf525b938175f023aedc6bff3897f87fd8c7dd6
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd0d2a6c985825dd91d914ba1b5ee0e15153e8022036de5122cfdbb0c81cb3af
+oid sha256:58818c092fa372e81eb272432f3e7b70892874e593e0c6c670fccc79847fbaeb
 size 74188650

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2e9db38d4c1da0d5d5ef197285e15c71a7f2c782732a3ab7e0af12207119eb5
+oid sha256:69965ee7f2e6825bca03ff6693076ba82a5181c358a0bd4c33454b2e1bc24eb6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.046735796699284356,
+  "epoch": 0.05841974587410545,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,92 @@
       "eval_samples_per_second": 23.131,
       "eval_steps_per_second": 11.582,
       "step": 40
+    },
+    {
+      "epoch": 0.04790419161676647,
+      "grad_norm": 0.4715648293495178,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 1.2266,
+      "step": 41
+    },
+    {
+      "epoch": 0.04907258653424858,
+      "grad_norm": 0.3626469075679779,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.3755,
+      "step": 42
+    },
+    {
+      "epoch": 0.050240981451730685,
+      "grad_norm": 0.3921823799610138,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 1.3125,
+      "step": 43
+    },
+    {
+      "epoch": 0.05140937636921279,
+      "grad_norm": 0.35432127118110657,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.2351,
+      "step": 44
+    },
+    {
+      "epoch": 0.052577771286694906,
+      "grad_norm": 0.4417038559913635,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.7417,
+      "step": 45
+    },
+    {
+      "epoch": 0.052577771286694906,
+      "eval_loss": 1.1834783554077148,
+      "eval_runtime": 31.2195,
+      "eval_samples_per_second": 23.095,
+      "eval_steps_per_second": 11.563,
+      "step": 45
+    },
+    {
+      "epoch": 0.053746166204177014,
+      "grad_norm": 0.3598865866661072,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 1.4514,
+      "step": 46
+    },
+    {
+      "epoch": 0.05491456112165912,
+      "grad_norm": 0.43709179759025574,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 1.5828,
+      "step": 47
+    },
+    {
+      "epoch": 0.05608295603914123,
+      "grad_norm": 0.32742375135421753,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 1.5362,
+      "step": 48
+    },
+    {
+      "epoch": 0.057251350956623336,
+      "grad_norm": 0.31574079394340515,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 1.5458,
+      "step": 49
+    },
+    {
+      "epoch": 0.05841974587410545,
+      "grad_norm": 0.3892696797847748,
+      "learning_rate": 0.0,
+      "loss": 1.5221,
+      "step": 50
+    },
+    {
+      "epoch": 0.05841974587410545,
+      "eval_loss": 1.1832040548324585,
+      "eval_runtime": 31.1605,
+      "eval_samples_per_second": 23.138,
+      "eval_steps_per_second": 11.585,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -373,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0442403924148224e+16,
+  "total_flos": 1.3069219818110976e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null