Training in progress, step 102, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c755a8afd91ffba478a86b1819c20d2a43b7da45950356efc27abffb3b3be7b
+oid sha256:12376e4db748a376237b65e445862fb6b6c7d941478ada47e104846caae0b43c
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33b475a076fd9434f2dd13dd7dd07097656597c66a04650e8cfe678812f89c14
+oid sha256:707aa91b200109054a6c52a5711067948760aa86788680f27a286fc28a3c81da
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f4e77fd2a3bb3f08929494d77da2f57f8781f91a45852bcf8f71a5777dd088c
+oid sha256:70670c442607259270e13afbef3aac28e38a58ddad6998414f76ed43ab7f41d4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013567861128950798,
+  "epoch": 0.020351791693426196,
   "eval_steps": 50,
-  "global_step": 68,
+  "global_step": 102,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -499,6 +499,252 @@
       "learning_rate": 0.00012518479547691435,
       "loss": 0.0,
       "step": 68
+    },
+    {
+      "epoch": 0.013767388498494192,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012420442717428804,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.013966915868037586,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012320907072649044,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.01416644323758098,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001221990293287378,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.014365970607124374,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012117461064942435,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.014565497976667768,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012013612673640363,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.014765025346211161,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011908389392193547,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.014964552715754557,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011801823272632844,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.015164080085297951,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011693946776030599,
+      "loss": 0.0,
+      "step": 76
+    },
+    {
+      "epoch": 0.015363607454841345,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011584792762612703,
+      "loss": 0.0,
+      "step": 77
+    },
+    {
+      "epoch": 0.015563134824384739,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011474394481749035,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.015762662193928134,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011362785561825406,
+      "loss": 0.0,
+      "step": 79
+    },
+    {
+      "epoch": 0.015962189563471528,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001125,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.016161716933014922,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011136072151847529,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.016361244302558316,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011021036720894179,
+      "loss": 0.0,
+      "step": 82
+    },
+    {
+      "epoch": 0.01656077167210171,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010904928748046599,
+      "loss": 0.0,
+      "step": 83
+    },
+    {
+      "epoch": 0.016760299041645103,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001078778360091808,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.016959826411188497,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010669636963055245,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.01715935378073189,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010550524823068502,
+      "loss": 0.0,
+      "step": 86
+    },
+    {
+      "epoch": 0.017358881150275285,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010430483463669551,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.01755840851981868,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001030954945061934,
+      "loss": 0.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.017757935889362073,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001018775962158975,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.017957463258905466,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010065151074942516,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.01815699062844886,
+      "grad_norm": NaN,
+      "learning_rate": 9.941761158428674e-05,
+      "loss": 0.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.018356517997992258,
+      "grad_norm": NaN,
+      "learning_rate": 9.817627457812105e-05,
+      "loss": 0.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.01855604536753565,
+      "grad_norm": NaN,
+      "learning_rate": 9.692787785420525e-05,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.018755572737079045,
+      "grad_norm": NaN,
+      "learning_rate": 9.567280168627493e-05,
+      "loss": 0.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.01895510010662244,
+      "grad_norm": NaN,
+      "learning_rate": 9.441142838268905e-05,
+      "loss": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.019154627476165833,
+      "grad_norm": NaN,
+      "learning_rate": 9.314414216997507e-05,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.019354154845709227,
+      "grad_norm": NaN,
+      "learning_rate": 9.187132907578987e-05,
+      "loss": 0.0,
+      "step": 97
+    },
+    {
+      "epoch": 0.01955368221525262,
+      "grad_norm": NaN,
+      "learning_rate": 9.059337681133192e-05,
+      "loss": 0.0,
+      "step": 98
+    },
+    {
+      "epoch": 0.019753209584796014,
+      "grad_norm": NaN,
+      "learning_rate": 8.931067465324085e-05,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.01995273695433941,
+      "grad_norm": NaN,
+      "learning_rate": 8.802361332501978e-05,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.01995273695433941,
+      "eval_loss": NaN,
+      "eval_runtime": 2915.8692,
+      "eval_samples_per_second": 5.79,
+      "eval_steps_per_second": 2.895,
+      "step": 100
+    },
+    {
+      "epoch": 0.020152264323882802,
+      "grad_norm": NaN,
+      "learning_rate": 8.673258487801731e-05,
+      "loss": 0.0,
+      "step": 101
+    },
+    {
+      "epoch": 0.020351791693426196,
+      "grad_norm": NaN,
+      "learning_rate": 8.54379825720049e-05,
+      "loss": 0.0,
+      "step": 102
     }
   ],
   "logging_steps": 1,
@@ -518,7 +764,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.0582968597754675e+17,
+  "total_flos": 6.087445289663201e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null