Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8cdd28be9549af1d5bae665c6e126d72e4da1f2ba57ad65c7b14a6a4a333524
+oid sha256:91b838f0603e6e34285dc2b3133f011cc7bcbf22aed025ac31257814f960c862
 size 37965300

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e767df46c90584f75b1e6b6257ff8fcd692290b2ffd0de4529d0298f5cd31d24
+oid sha256:36e45c974a6190b6de9fc6c10b60e823a61222efeac9ea8accdba774d381a9de
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d87a1a565de8d9454ec5b84c8c49d8c31a26f884bf198b921051cab4aead55b
+oid sha256:0332385199679d6956d83344338db2c830a95ac88db6fd32d53aa1116f8c2d69
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7584ce9d7e86e7470dbb7669c7bdd8e57a5b4e1e70b8320491fe89e5e06fec20
+oid sha256:8cc77b5278492484e5ec4d2755d1c49247cfe16cc960a700a9e6220b24674bea
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:789264f785683542d0f42ae9ec4e080a45d30fc0072fb7c515425e498d63a077
+oid sha256:728d17c396539440de64e4c8ce7b4c070eba3f067afd200a91d62210f5ff6272
 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": 0.0131916452913155,
+  "epoch": 0.014657383657017223,
   "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": 43.222,
       "eval_steps_per_second": 5.412,
       "step": 9
+    },
+    {
+      "epoch": 0.014657383657017223,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "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": 9405135625125888.0,
+  "total_flos": 1.045015069458432e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null