Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15ed418657f68a5be1dc0577e90c9a66b3902dd8fb14e117b39f263458221fca
+oid sha256:c5eb592577ebfd87bc8bd2d2bb51a660761c2d02ebf2209412e4510bba09e2ca
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:231a45e5f2979d9bb537e959733a4acd4b99dfe05123ddfbd74f41fa2d931734
+oid sha256:42bc8b231d035894e8d24a747505d8e0d1f39f2c0033ce5b821c47472e84d56c
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d227d827271d8d15bc26d6aba03cf1a188b8f58dd30bd17277eebb7d8088fcbb
+oid sha256:ccb076adb8aad74200d54ce93f610ab7a81728e7152e5eb3895f0e3d7d771e86
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0061562139284340135,
+  "epoch": 0.00923432089265102,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 11.692,
       "eval_steps_per_second": 5.846,
       "step": 20
+    },
+    {
+      "epoch": 0.006464024624855714,
+      "grad_norm": 0.8741333484649658,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.7784,
+      "step": 21
+    },
+    {
+      "epoch": 0.007387456714120816,
+      "grad_norm": 0.6359958648681641,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.7055,
+      "step": 24
+    },
+    {
+      "epoch": 0.007695267410542516,
+      "eval_loss": 0.7582727670669556,
+      "eval_runtime": 117.031,
+      "eval_samples_per_second": 11.689,
+      "eval_steps_per_second": 5.845,
+      "step": 25
+    },
+    {
+      "epoch": 0.008310888803385917,
+      "grad_norm": 0.6420719623565674,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.8814,
+      "step": 27
+    },
+    {
+      "epoch": 0.00923432089265102,
+      "grad_norm": 0.6477676033973694,
+      "learning_rate": 0.0,
+      "loss": 0.8694,
+      "step": 30
+    },
+    {
+      "epoch": 0.00923432089265102,
+      "eval_loss": 0.7546724081039429,
+      "eval_runtime": 116.9888,
+      "eval_samples_per_second": 11.693,
+      "eval_steps_per_second": 5.847,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7511608746049536.0,
+  "total_flos": 1.1313781074296832e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null