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:f5dea9e7e89a6bf18b878a15e13f9282ce800849b126959b875bddf33ad982d3
+oid sha256:99fbd51dcd47174d553f48ab7d42ce4d8ad6e942ebdb2ac2e1dbfb0380934150
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e490e0d662d181caab427c4e262671341bb4b505334095951eb01cd37ecaec5d
+oid sha256:51ece5744645b0a3b7e51c5288eb01a6ca188d183c4c8beccc8d680e42518c5f
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ac91903c5cac39d373ba152e89eaf571f71e7cdfdd359d038b6afb1f47557a7
+oid sha256:dc1986f965434487f282c921cd047de83fc5378b905a800ea6f7e406812d0ef0
 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": 43.195,
       "eval_steps_per_second": 21.606,
       "step": 9
+    },
+    {
+      "epoch": 0.0016256197675363732,
+      "grad_norm": 2.4515552520751953,
+      "learning_rate": 0.0002,
+      "loss": 2.0185,
+      "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": 697505855569920.0,
+  "total_flos": 770927524577280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null