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:ddc4b5bc54002691b761d783ab5d9269a8e5f5fa972f0f93ffaae9b3d5708e32
+oid sha256:b8a2f4965c8e5142d480e9cd53760dcecb4ca0fbd3f42aed02e08786bbcc0315
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02427cbcacb63ee2dabedd566d2aca1d5ad141577f85a84b8401aaa48f741ada
+oid sha256:1e790d9147d186dd1fbf9afeab6fc2a0dbb519e69b4844b9e8f4ce0bc6da1785
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:399171def2779bd0a4edea00ec815fe9bfd7f86cec979b7ea47ed048203a9783
+oid sha256:d67462133f0869238598f8229a8919771cd31c8c5b7561e7da6d0c8eaf56ea93
 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": 0.004678362573099415,
+  "epoch": 0.005198180636777128,
   "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": 80.122,
       "eval_steps_per_second": 40.11,
       "step": 9
+    },
+    {
+      "epoch": 0.005198180636777128,
+      "grad_norm": 24.867834091186523,
+      "learning_rate": 0.0002,
+      "loss": 6.5073,
+      "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": 157911418404864.0,
+  "total_flos": 175457131560960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null