Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53f2f3446a19634c906c9137244712d5a2609909611892760d48690b617313f8
+oid sha256:a00de4730e203ecf5b16400bd5eb819068fd7f8a9ee0d798adc4ea1377a02c48
 size 684272496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94e44a3abfc1262f53fe89de4ddd92295861ad567c79f8beded210a2854535f9
+oid sha256:fff53219e119c8471408238f114e3467015775b3b86e06c41535d00fc8ea19d1
 size 81730196

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23b1cdc93839cf3d1839ae8fbc0a092fe54b0e38a1fa2ef42fb2cb7ea1f38aa8
+oid sha256:b9cc97840e396f9967fd8f9e4ef92a2ce3e8dfe687ad4f22259913bb1a1605d5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f9c8d472a9fcb528aad7900cb24b90313f284110ca432406a71ead59cbde1f3
+oid sha256:f74435840181ef5be67cebc46f6421ff7fb7533a96f7855fe36586ff3b95c263
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8245d8d3d3816dd284f4381705afc1ac7d7e6002a14fe01153bec7adf5280188
+oid sha256:edfcdc8ec38ecceb363a6724b6b40828a842365deb928ebadcb5c58b2d9fa751
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e01e0573ae2aa58b2e2ae712e76a15ee28e34fab0d7c2da6f89be4395d3de6b5
+oid sha256:62f93d329bdcf7d3756dec05f7e91ade831fa62b19bfbd47c2dc342f6c816929
 size 15024

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": 0.07100591715976332,
+  "epoch": 0.07889546351084813,
   "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": 19.909,
       "eval_steps_per_second": 2.512,
       "step": 9
+    },
+    {
+      "epoch": 0.07889546351084813,
+      "grad_norm": 2.467024087905884,
+      "learning_rate": 0.0002,
+      "loss": 0.331,
+      "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": 4.704901952805274e+16,
+  "total_flos": 5.227668836450304e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null