Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acb38c4bdaf385e847c23f6426861762fc30c396ffe396929419ea17e2f54a7b
+oid sha256:78f6f6b9ad614902a5a49e1304497a9a06437fa5602ff9430a7dd4decc0764f9
 size 1101572914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8045872fca2455adab861fcdd8ffebe0c1674421c3ca38a87bb2ec3128286bd5
+oid sha256:767e0cac1b239989c6b172c32fe0276a900c0406513da6be5624daee594e472c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef593f391c66ba3ea6e8dea3b2aa8e19ae1f574e3c6a18c96ee14293016120aa
+oid sha256:0f6003820aa1d9b0e6aa1d70309948568223b16abb8759408bc4ed8976518161
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00856971462850287,
+  "epoch": 0.012854571942754306,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 5.244,
       "eval_steps_per_second": 2.623,
       "step": 50
+    },
+    {
+      "epoch": 0.008741108921072929,
+      "grad_norm": NaN,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.008912503213642986,
+      "grad_norm": NaN,
+      "learning_rate": 1.1567509791329401e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.009083897506213042,
+      "grad_norm": NaN,
+      "learning_rate": 1.0660589091223855e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.009255291798783101,
+      "grad_norm": NaN,
+      "learning_rate": 9.780964274781984e-06,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.009426686091353158,
+      "grad_norm": NaN,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.009598080383923215,
+      "grad_norm": NaN,
+      "learning_rate": 8.110244809608495e-06,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.009769474676493273,
+      "grad_norm": NaN,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.00994086896906333,
+      "grad_norm": NaN,
+      "learning_rate": 6.568066579746901e-06,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.010112263261633388,
+      "grad_norm": NaN,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.010283657554203445,
+      "grad_norm": NaN,
+      "learning_rate": 5.166166492719124e-06,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.010455051846773502,
+      "grad_norm": NaN,
+      "learning_rate": 4.521198892775203e-06,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.01062644613934356,
+      "grad_norm": NaN,
+      "learning_rate": 3.9152138546778625e-06,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.010797840431913617,
+      "grad_norm": NaN,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.010969234724483674,
+      "grad_norm": NaN,
+      "learning_rate": 2.8247291705444575e-06,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.011140629017053733,
+      "grad_norm": NaN,
+      "learning_rate": 2.3423053240837515e-06,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.01131202330962379,
+      "grad_norm": NaN,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.011483417602193846,
+      "grad_norm": NaN,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.011654811894763905,
+      "grad_norm": NaN,
+      "learning_rate": 1.1570762312943295e-06,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.011826206187333961,
+      "grad_norm": NaN,
+      "learning_rate": 8.51854342773295e-07,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.01199760047990402,
+      "grad_norm": NaN,
+      "learning_rate": 5.925998220016659e-07,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.012168994772474077,
+      "grad_norm": NaN,
+      "learning_rate": 3.7980617469479953e-07,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.012340389065044133,
+      "grad_norm": NaN,
+      "learning_rate": 2.1387846565474045e-07,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.012511783357614192,
+      "grad_norm": NaN,
+      "learning_rate": 9.513254770636137e-08,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.012683177650184249,
+      "grad_norm": NaN,
+      "learning_rate": 2.3794460453555047e-08,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.012854571942754306,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.012854571942754306,
+      "eval_loss": NaN,
+      "eval_runtime": 468.897,
+      "eval_samples_per_second": 5.24,
+      "eval_steps_per_second": 2.621,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.94473109536768e+16,
+  "total_flos": 1.041709664305152e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null