Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03a0a3336547a47bdfc6a8dd5e2e5239f4d20da2eca8e885ef3d03c4fe74b91a
+oid sha256:5a12857bd943ebd53e96ef314e7001e588a2a17d5407b30ef9f3371065c53c6d
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a39a41f912d3765e4194e7bf2d118cba79dcbe423e3417f95fa83853160b690
+oid sha256:fdde6ac87a64995609da02d0ac08c227f29316a78167a5224ca4e6df927f97ad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011333585190782017,
+  "epoch": 0.01511144692104269,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 12.888,
       "eval_steps_per_second": 6.444,
       "step": 15
+    },
+    {
+      "epoch": 0.012089157536834151,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.012844729882886286,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 460.4789,
+      "step": 17
+    },
+    {
+      "epoch": 0.01360030222893842,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 8.2432,
+      "step": 18
+    },
+    {
+      "epoch": 0.014355874574990555,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 580.8181,
+      "step": 19
+    },
+    {
+      "epoch": 0.01511144692104269,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 988.7248,
+      "step": 20
+    },
+    {
+      "epoch": 0.01511144692104269,
+      "eval_loss": NaN,
+      "eval_runtime": 172.6591,
+      "eval_samples_per_second": 12.916,
+      "eval_steps_per_second": 6.458,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.8038397855596544e+16,
+  "total_flos": 2.4309082437451776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null