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:a1ec088f4fa09729549619be3383c35daf7301e2f67ed6c482674b8984894288
+oid sha256:bad6f322e28ea35ea661d270bf6a7100a5599f65cf6717a244a7b602dadee6d9
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81c041afed3ff3ddbeb18461be75189fe89e384134b34aa15d4ba4d7d5bb3375
+oid sha256:6afe61b98cc9cf1b9f79c61427b5b166dad9fa9ef2bf96ce8f81edc1bc4140fc
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daf57e31af47133854b198d2ed1bf061cf80e24e56fc7a49ef63f0f861ee6fba
+oid sha256:40c4d8d467fbb472343878358435ceadbe4bf072a336c5e0d605631e57f10697
 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": 0.001463057790782736,
+  "epoch": 0.0016256197675363732,
   "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": 20.34,
       "eval_steps_per_second": 10.174,
       "step": 9
+    },
+    {
+      "epoch": 0.0016256197675363732,
+      "grad_norm": 0.3359471261501312,
+      "learning_rate": 0.0002,
+      "loss": 0.7936,
+      "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": 3007893964062720.0,
+  "total_flos": 3324514381332480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null