Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:337612f9b6571afb6fe92280c365b4bc2aeaabb8c4618482ff5588c23cb28ea1
+oid sha256:2916542850cb3a1bfd3428cb351518b7299e1cfc90b2a936c28a2e59ead9b69c
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db14898209a8514bbe5d353646005316687f146443f6722b329f76737597a5fb
+oid sha256:0a355ca3f58f6f73922516892e75ae61b07dee45e5976dd457f40c48846484f0
 size 202110330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd82b1b2b5a7eb490891b2d5563f9814fe936f9107e77b2d0a228ed834690ec3
+oid sha256:92d16bcd5c35eb3199903ce2303be691b57bda8555271b4c33c02091fd117f0b
 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": 0.05399290576167194,
+  "epoch": 0.055220017256255395,
   "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": 14.593,
       "eval_steps_per_second": 7.296,
       "step": 88
+    },
+    {
+      "epoch": 0.055220017256255395,
+      "grad_norm": 0.4225621521472931,
+      "learning_rate": 0.0,
+      "loss": 0.9957,
+      "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": 1.176158883324887e+17,
+  "total_flos": 1.2037658013125837e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null