Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93d570904a9ed66b27b0d20dda89f24b58971cda22ecab11a2b0ae03b9ea1efa
+oid sha256:e24d2d1ad2df16f2f1b088f805bf7bcf3ec2dec633cba613d2caa5bccc5d2158
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27bc898c119c3fea3cb54fcc7edad7b860a8405779467bbe4ef27d71ba6adddc
+oid sha256:b4bf312b2f38cdc0ddf775e268f308a86142df562d6e8a1fdfd46f4a84e2ff51
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98929920e2becfcab04e82aa93e81382f3a01ef05c01842148a47548a3a1eeff
+oid sha256:af8292635fc0a9138cfafa7bef595d7bbe98e9032fb05191e1709e2b37772f52
 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": 0.0015218769816106531,
+  "epoch": 0.0016909744240118367,
   "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": 29.179,
       "eval_steps_per_second": 14.59,
       "step": 9
+    },
+    {
+      "epoch": 0.0016909744240118367,
+      "grad_norm": 5.289436340332031,
+      "learning_rate": 0.0002,
+      "loss": 3.5508,
+      "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": 1096970617749504.0,
+  "total_flos": 1199811613163520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null