Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c23ff90a7c2ffe86382933b578e62c7468e1aca1d469095d6e2de7cff5356f18
+oid sha256:a128a2ff7aa220051a647440d1768b4452851577b371ceee1d053d5b6a7eceef
 size 36220072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b0b1915cc064079d38431eced60eae4347c96a95e4d00e10b474866c48345e
+oid sha256:56059925e64678dde01283e72b11a6c1b086d517e69b0c0c18f1fd0eb56c73e5
 size 18763860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e1ce9bb60ab00f99c593a82d96879a8e2a46d1d822f5dfb0aa269b464ba842
+oid sha256:e39beece3a04ad324e9d493363868b1a4ca42fb2d9c9e3591b853d4823466d89
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0009028892455858748,
+  "epoch": 0.0010032102728731941,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 45.376,
       "eval_steps_per_second": 22.688,
       "step": 9
+    },
+    {
+      "epoch": 0.0010032102728731941,
+      "grad_norm": 0.1082218587398529,
+      "learning_rate": 0.0002,
+      "loss": 0.5423,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 716528689348608.0,
+  "total_flos": 796142988165120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null