Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dc81b83385f0873edd595e3f2e7700a0a297fcef54df6adaa568e56b1debcb0
+oid sha256:7ed6580e9dfd8448ca12de150c8c27a9545f63c3b82e8e7f849549cf4bee6168
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab4e8c09339af63c475e60c79d932f99d4fa0b65d723a1b9f03446a26715bfc4
+oid sha256:4c3157eeed37ec8309aed89eb544fb49a47c250b10a377a93a17904fd21851d2
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57d82a3d3954cfc244134be1298ae6e4cf994607d25c2af293db3cc713fa7126
+oid sha256:fd6ce35db78642b81a936d63e81073fe945f996b3d85633986eb9a2d8c6d6f07
 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": 0.0035152817107704324,
+  "epoch": 0.0039058685675227027,
   "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": 11.271,
       "eval_steps_per_second": 5.635,
       "step": 9
+    },
+    {
+      "epoch": 0.0039058685675227027,
+      "grad_norm": 4.768134593963623,
+      "learning_rate": 0.0002,
+      "loss": 5.6721,
+      "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": 2035936552550400.0,
+  "total_flos": 2239530207805440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null