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:db183b4c240300319ba21d9a5823241fc654924489ebdf0da8ead35bf7d33afd
+oid sha256:e3974bb77f58dcea05df80c79e66342750567daec3ecbf2106e35d5f97a2177c
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f5840e72070e9b33956e918331e004b3085de49cd62b51c13689a4058d9bb4a
+oid sha256:973c6bb5c184e9b9342f44226a0a59583c08895a580f2779692ff7fe1675fe88
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f84b7eed8ce383f213fa2c01c69e8fe6d926bcb9bee31ed27ce8dad8d9e48e50
+oid sha256:19a32067fb5f557237726e10d4e5248eee478b9f21bf82db1c657e481f64a127
 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": 0.041429311237700675,
+  "epoch": 0.06214396685655101,
   "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": 4.0307,
       "step": 18
+    },
+    {
+      "epoch": 0.04350077679958571,
+      "grad_norm": 1.498288631439209,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 4.1272,
+      "step": 21
+    },
+    {
+      "epoch": 0.04971517348524081,
+      "grad_norm": 1.7765750885009766,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 4.0162,
+      "step": 24
+    },
+    {
+      "epoch": 0.04971517348524081,
+      "eval_loss": 4.141704082489014,
+      "eval_runtime": 1.7416,
+      "eval_samples_per_second": 117.134,
+      "eval_steps_per_second": 58.567,
+      "step": 24
+    },
+    {
+      "epoch": 0.055929570170895906,
+      "grad_norm": 1.6882319450378418,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.9876,
+      "step": 27
+    },
+    {
+      "epoch": 0.06214396685655101,
+      "grad_norm": 1.9130908250808716,
+      "learning_rate": 0.0,
+      "loss": 4.1616,
+      "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