Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a63d70ff2aedd429eee8ffa82e10c579494a24291c0f33a9de2fafd30cc56b3
+oid sha256:cf7249cf1b823ed7571aa3023c41d87191ce4d178dd08f8c002ddf57b28b69a3
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9386f11300018f520d4701b620154d3060b35b5fdf3b8e73a5ed88dac67195ad
+oid sha256:e2cfe5f31baec195884393abc71e2868ef7a2082dcf919f091c0d3522e4c5ff0
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef73aa36afabdfbf7be74c4769cba6429bbaaf8e4ecdfa5b7e9a2a21434f561
+oid sha256:9e651d14e7ee52a338fd24cd91e6b6490d38a4418546e878a83bea1f77d0d566
 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": 0.014908684308609765,
+  "epoch": 0.02236302646291465,
   "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": 1.6773,
       "step": 18
+    },
+    {
+      "epoch": 0.015654118524040254,
+      "grad_norm": 5.221904277801514,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.3178,
+      "step": 21
+    },
+    {
+      "epoch": 0.017890421170331718,
+      "grad_norm": 1.6797155141830444,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.0641,
+      "step": 24
+    },
+    {
+      "epoch": 0.017890421170331718,
+      "eval_loss": 1.0564405918121338,
+      "eval_runtime": 8.0102,
+      "eval_samples_per_second": 70.535,
+      "eval_steps_per_second": 35.33,
+      "step": 24
+    },
+    {
+      "epoch": 0.02012672381662318,
+      "grad_norm": 2.032195806503296,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.9839,
+      "step": 27
+    },
+    {
+      "epoch": 0.02236302646291465,
+      "grad_norm": 2.377633571624756,
+      "learning_rate": 0.0,
+      "loss": 0.9328,
+      "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": 138837586083840.0,
+  "total_flos": 208256379125760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null