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:b6b7a46adcb6e174f92393d7e4133b8f8f953976173d5c234c813a9a240ab938
+oid sha256:9230aadcb25ca0c5f82aab819b0891b6274c43bf17c5ae2ba26245aeda052815
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe7caeea59c7a74f5571c9f60dc019a72a17e22e83fef42036b0e46dc86db68e
+oid sha256:b775d6d5b52a1fd07398a5df50999f16da6e1a3d59b1cbd0de8c69369d7b54cf
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb449c5573d9c6849484b07e1e861c36ee7a050760fb8121ad74bad4bbd29319
+oid sha256:34769dc93a0f06a674a77a35bd545c2c3be7b1e200a5ef410c2ec61bc2e222b6
 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": 0.0003590735901374454,
+  "epoch": 0.0003989706557082727,
   "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": 17.648,
       "eval_steps_per_second": 8.824,
       "step": 9
+    },
+    {
+      "epoch": 0.0003989706557082727,
+      "grad_norm": 0.9276331067085266,
+      "learning_rate": 0.0002,
+      "loss": 1.9981,
+      "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": 1414583947100160.0,
+  "total_flos": 1578593680097280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null