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:ae49914fcc93989bdccb11990212af15823109d70ef12ec90fef966f12737bf9
+oid sha256:167d873c59501328a42a3046761dce41eec044ca3a5217c07ab59532e84e25d6
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5127fb311c6254e94ced7c5124a302f160cf6c5f0beb82d8d7a504f049b201e
+oid sha256:853fe16aaf6e1ee0e8cc941850763130d51478ee13ecef1b7c7521abbaafc502
 size 113416442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d650a30743ff2256b9a7a9184b0fa1154e6213fc98bfe3cebb6834924450b024
+oid sha256:2b860c3df50b7a6a512ae0beb7baaea7a20c512c23c5be3da8a18d49485dede3
 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": 0.01132342533616419,
+  "epoch": 0.016985138004246284,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 5.0813,
       "step": 18
+    },
+    {
+      "epoch": 0.0118895966029724,
+      "grad_norm": 6.950047969818115,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 4.321,
+      "step": 21
+    },
+    {
+      "epoch": 0.013588110403397028,
+      "grad_norm": 5.376028060913086,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.8397,
+      "step": 24
+    },
+    {
+      "epoch": 0.013588110403397028,
+      "eval_loss": 0.756127119064331,
+      "eval_runtime": 47.9128,
+      "eval_samples_per_second": 15.528,
+      "eval_steps_per_second": 7.764,
+      "step": 24
+    },
+    {
+      "epoch": 0.015286624203821656,
+      "grad_norm": 4.770466327667236,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.4694,
+      "step": 27
+    },
+    {
+      "epoch": 0.016985138004246284,
+      "grad_norm": 4.77080774307251,
+      "learning_rate": 0.0,
+      "loss": 2.7841,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1217045672755200.0,
+  "total_flos": 1833081136742400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null