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:f1c14eff221190bd740731b86d954f0a405232b25cfefb8bebaec23d20b0db1c
+oid sha256:1b0ae9ae528aa63bb0322ea36b031d7ba17cf3d4e51fb1f0c7793bc784209ad5
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e8c768ec4aabe5423653cc2ffb8bab262aca036facc4c67f97b67880e397b02
+oid sha256:b6cdfeefca76fc362e2e072bb8410b8873e36c23414ee280c0fd7e13c4e0e5ca
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:156d65e08be6ed2e70634b9e6879f6f7a9d819dc52b2483d64024b159beaf208
+oid sha256:e9ed9626ba6e412f40126198b85320c11d70caab3bee87c19069e3aea6dd4f83
 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": 0.00024773255893970465,
+  "epoch": 0.00027525839882189403,
   "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": 18.406,
       "eval_steps_per_second": 9.204,
       "step": 9
+    },
+    {
+      "epoch": 0.00027525839882189403,
+      "grad_norm": 0.17171159386634827,
+      "learning_rate": 0.0002,
+      "loss": 0.073,
+      "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": 2959302797033472.0,
+  "total_flos": 3329215646662656.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null