Training in progress, step 100, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d6e3e3f8da5ca34e31e7e1da106d1a2de25558024735de31f395304b7ea671c
+oid sha256:06ee945e16ae22c9075277531a6f8bc0ec708f7e7d0f7f18b4a9e5b5ec85eb27
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13045082dd395ff23ec01ea62abb7ab1984d0af8f8c2441c419760ff666be782
+oid sha256:d6516708bef1a97795da04892fd3df3bf2305ac978924d9e7083e4eed6ef52b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.133973428603327,
+  "epoch": 0.17863123813776935,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 16.827,
       "eval_steps_per_second": 8.422,
       "step": 75
+    },
+    {
+      "epoch": 0.1357597409847047,
+      "grad_norm": NaN,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0,
+      "step": 76
+    },
+    {
+      "epoch": 0.1375460533660824,
+      "grad_norm": NaN,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0,
+      "step": 77
+    },
+    {
+      "epoch": 0.13933236574746008,
+      "grad_norm": NaN,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.14111867812883777,
+      "grad_norm": NaN,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0,
+      "step": 79
+    },
+    {
+      "epoch": 0.14290499051021546,
+      "grad_norm": NaN,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.14469130289159315,
+      "grad_norm": NaN,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 33.7649,
+      "step": 81
+    },
+    {
+      "epoch": 0.14647761527297087,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 82
+    },
+    {
+      "epoch": 0.14826392765434857,
+      "grad_norm": NaN,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 5.1139,
+      "step": 83
+    },
+    {
+      "epoch": 0.15005024003572626,
+      "grad_norm": NaN,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.15183655241710395,
+      "grad_norm": NaN,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.15362286479848164,
+      "grad_norm": NaN,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0,
+      "step": 86
+    },
+    {
+      "epoch": 0.15540917717985933,
+      "grad_norm": NaN,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.15719548956123702,
+      "grad_norm": NaN,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.15898180194261471,
+      "grad_norm": NaN,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.1607681143239924,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.1625544267053701,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.1643407390867478,
+      "grad_norm": NaN,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.16612705146812548,
+      "grad_norm": NaN,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.16791336384950317,
+      "grad_norm": NaN,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.16969967623088086,
+      "grad_norm": NaN,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.17148598861225856,
+      "grad_norm": NaN,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 15.2213,
+      "step": 96
+    },
+    {
+      "epoch": 0.17327230099363627,
+      "grad_norm": NaN,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0,
+      "step": 97
+    },
+    {
+      "epoch": 0.17505861337501397,
+      "grad_norm": NaN,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0,
+      "step": 98
+    },
+    {
+      "epoch": 0.17684492575639166,
+      "grad_norm": NaN,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.17863123813776935,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.17863123813776935,
+      "eval_loss": NaN,
+      "eval_runtime": 58.95,
+      "eval_samples_per_second": 15.997,
+      "eval_steps_per_second": 8.007,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -578,12 +761,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.9753146179584e+16,
+  "total_flos": 9.238916716560384e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null