Training in progress, step 102, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f220adf6445faa3084119deeca55d2d287f74f40538df7e9218a2aeee61a809a
+oid sha256:409506c2e743c0962472a80fbb6dcaf2cbc9c90ce5fb8329688b39a5b3cfa456
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ee335a62849ee2439378e9094b922b6e35c167d78196a6c3c8df14be4850d15
+oid sha256:609ac74381de893b35193cf51e9a6fce221b22031433fbd3b97539f9bac6436f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b383ad1d61ff4e9bbd86bd276c043e414782d2bb7de68ada3e289a786eb79681
+oid sha256:70670c442607259270e13afbef3aac28e38a58ddad6998414f76ed43ab7f41d4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0934001785591649,
+  "epoch": 0.11208021427099787,
   "eval_steps": 50,
-  "global_step": 85,
+  "global_step": 102,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -618,6 +618,133 @@
       "learning_rate": 0.00010669636963055245,
       "loss": 0.0,
       "step": 85
+    },
+    {
+      "epoch": 0.09449900418927272,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010550524823068502,
+      "loss": 0.0,
+      "step": 86
+    },
+    {
+      "epoch": 0.09559782981938053,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010430483463669551,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.09669665544948836,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001030954945061934,
+      "loss": 0.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.09779548107959618,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001018775962158975,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.098894306709704,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010065151074942516,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.09999313233981183,
+      "grad_norm": NaN,
+      "learning_rate": 9.941761158428674e-05,
+      "loss": 0.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.10109195796991965,
+      "grad_norm": NaN,
+      "learning_rate": 9.817627457812105e-05,
+      "loss": 0.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.10219078360002747,
+      "grad_norm": NaN,
+      "learning_rate": 9.692787785420525e-05,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.10328960923013529,
+      "grad_norm": NaN,
+      "learning_rate": 9.567280168627493e-05,
+      "loss": 0.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.10438843486024312,
+      "grad_norm": NaN,
+      "learning_rate": 9.441142838268905e-05,
+      "loss": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.10548726049035094,
+      "grad_norm": NaN,
+      "learning_rate": 9.314414216997507e-05,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.10658608612045876,
+      "grad_norm": NaN,
+      "learning_rate": 9.187132907578987e-05,
+      "loss": 0.0,
+      "step": 97
+    },
+    {
+      "epoch": 0.10768491175056658,
+      "grad_norm": NaN,
+      "learning_rate": 9.059337681133192e-05,
+      "loss": 0.0,
+      "step": 98
+    },
+    {
+      "epoch": 0.1087837373806744,
+      "grad_norm": NaN,
+      "learning_rate": 8.931067465324085e-05,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.10988256301078222,
+      "grad_norm": NaN,
+      "learning_rate": 8.802361332501978e-05,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.10988256301078222,
+      "eval_loss": NaN,
+      "eval_runtime": 637.0136,
+      "eval_samples_per_second": 4.813,
+      "eval_steps_per_second": 2.407,
+      "step": 100
+    },
+    {
+      "epoch": 0.11098138864089005,
+      "grad_norm": NaN,
+      "learning_rate": 8.673258487801731e-05,
+      "loss": 0.0,
+      "step": 101
+    },
+    {
+      "epoch": 0.11208021427099787,
+      "grad_norm": NaN,
+      "learning_rate": 8.54379825720049e-05,
+      "loss": 0.0,
+      "step": 102
     }
   ],
   "logging_steps": 1,
@@ -637,7 +764,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.978120149832827e+17,
+  "total_flos": 5.979003336114831e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null