Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7058d2d28f94132f811065a11eccfe0e87ab97817242e51576d7d894b42d34c5
+oid sha256:aaec534c9c956137335b09eb59b327721b092ed133ffbf5c5a10b22e11fcb92c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34a8fcd8247048abdffc77226ad646a77dc686037c052ace6e1989da6cbe9a24
+oid sha256:fa2c8993adbe1fa9045831a3bf631445dcdf6c39af324db5db352200f5afe732
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bdac87cf390cb72252ff25e1e6d2db6b4f49d909074ff854f1cf9f55613c368
+oid sha256:27a4d0444cea84908b7e4779227a0c900d659ffeadefb9a6c6042092ef92188b
 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": 0.02909090909090909,
+  "epoch": 0.04363636363636364,
   "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": 0.0604,
       "step": 18
+    },
+    {
+      "epoch": 0.030545454545454546,
+      "grad_norm": 0.5574419498443604,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0659,
+      "step": 21
+    },
+    {
+      "epoch": 0.03490909090909091,
+      "grad_norm": 0.3288589119911194,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0638,
+      "step": 24
+    },
+    {
+      "epoch": 0.03490909090909091,
+      "eval_loss": 0.05812034755945206,
+      "eval_runtime": 37.5038,
+      "eval_samples_per_second": 7.733,
+      "eval_steps_per_second": 3.866,
+      "step": 24
+    },
+    {
+      "epoch": 0.03927272727272727,
+      "grad_norm": 0.7242821455001831,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0807,
+      "step": 27
+    },
+    {
+      "epoch": 0.04363636363636364,
+      "grad_norm": 0.5137593746185303,
+      "learning_rate": 0.0,
+      "loss": 0.0329,
+      "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": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null