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:ce80b425795190903fb3ef7f4a458bb3e944828f724d90fffdff0952230f5af3
+oid sha256:5920b62f27764a1e25cd64b405d9ae271f4733ed869dc1a45a7853eec61fcb04
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30fecc5ea90faada7cf690a12b7e55363b32c900d50b03067f483cffe92b3b6e
+oid sha256:8ec35b633299dcdc744486f0cc64c6655fb2e84e1a6ede69dbd77b7c0f43b068
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e366af8effa8e611032ee14d35d0beb9af6ce001f26b03eb553dccb7c9dcb689
+oid sha256:91d824b928e00e7e10a6b6eaf4cc8a97628d3bdc510fd7dfbf624534dba47e02
 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": 0.02140309155766944,
+  "epoch": 0.023781212841854936,
   "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": 49.781,
       "eval_steps_per_second": 24.891,
       "step": 9
+    },
+    {
+      "epoch": 0.023781212841854936,
+      "grad_norm": 4.394505500793457,
+      "learning_rate": 0.0002,
+      "loss": 9.1061,
+      "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": 750891722342400.0,
+  "total_flos": 816186654720000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null