Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03f824d0525967235999c9170fdb9a3afd4d4be45b9ae9a5f32ec56840844dd5
+oid sha256:001c00e359eb0b9b1214633c74d39980814ee406eb4408a6f9acfc116279ab1b
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d4a0e1d1b6c54ab0d837806d1286d6ceff0700371b812941f7de0be269e6a5
+oid sha256:88db0d92acad071a4e7023d936a83f6fef15535aa1440b4ef096092f7c50f98a
 size 1003002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27035ea1efd96357598ccd3bea9cecacd80035eaa6d3792153213c56e73abd54
+oid sha256:b12cb19739dc8815fca38fee9b664feb211b45b4f898b0912e895eff0e96da92
 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": 3.7473222259926763e-05,
+  "epoch": 4.1636913622140845e-05,
   "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": 58.733,
       "eval_steps_per_second": 29.367,
       "step": 9
+    },
+    {
+      "epoch": 4.1636913622140845e-05,
+      "grad_norm": 2.8738622665405273,
+      "learning_rate": 0.0002,
+      "loss": 10.0493,
+      "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": 4886913613824.0,
+  "total_flos": 5429904015360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null