Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69bd38a6824b8993452d505e4408561587238b148f02bbe67a76d88dd1d4187e
+oid sha256:6276eddecf379fbee81e5e4607405891ba79cc0d26b96dcaf32eed76d637f990
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f42340889903b234c9abe77e01510015ba3cc24f6c6908cbf48be031b0b04ff3
+oid sha256:38d272dc77b1fbb167af9826d761883e22b8e3060bc7c84dd4c5ffc933bb909f
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf306a9b1914534d727644260ec730fedc7b57bd2d8fd998953572a924983513
+oid sha256:e18e668860aa083adef211013189cd3d58c25adbb67cd9b0e99f8ed5231c4495
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a4e7013bdf0cfef44b18348c4082377d680816016af2638e8995bf0bb3c8d9
+oid sha256:cf6a9a1e39c0655c6941309388d2a028b5b8dbbca031ca2500bdfcdc9f2c01aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.031781143489154236,
+  "epoch": 0.03250344220481683,
   "eval_steps": 8,
-  "global_step": 88,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -306,6 +306,13 @@
       "eval_samples_per_second": 9.359,
       "eval_steps_per_second": 4.68,
       "step": 88
+    },
+    {
+      "epoch": 0.03250344220481683,
+      "grad_norm": 0.26352646946907043,
+      "learning_rate": 0.0,
+      "loss": 1.9889,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -320,12 +327,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.681769044200653e+17,
+  "total_flos": 4.788172886114304e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null