Training in progress, step 160, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7497f6a0bf73eead2a998f776238be7dad0b28e21b30438effdfe392fd58a1
+oid sha256:5f506ea0a27d11213698935b80e6dfa359af22d511da08e50f3ed93d6008677f
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0372018a4be5540bc5abe6dc6460517fafa00663177aa4622b9d278e34d5efdc
+oid sha256:1fd844c79c32a67c4550bd5927f49b90e4581c3c63626897db1d09f6feb6e7fd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdb234aa059f58a6779d88484c835d370471c909d1d5f9115af25bb93e106804
+oid sha256:f8a626c58c869c9d1ca23eb9446f33bde15a185ae71e9f7e32d182b1648304b3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09687575684185033,
+  "epoch": 0.19375151368370067,
   "eval_steps": 55,
-  "global_step": 80,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -205,6 +205,203 @@
       "learning_rate": 7.303212252253162e-05,
       "loss": 0.0,
       "step": 78
+    },
+    {
+      "epoch": 0.09808670380237346,
+      "grad_norm": NaN,
+      "learning_rate": 7.101786141547828e-05,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.10171954468394284,
+      "grad_norm": NaN,
+      "learning_rate": 6.896127313264643e-05,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.10535238556551223,
+      "grad_norm": NaN,
+      "learning_rate": 6.686649936914152e-05,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.10898522644708161,
+      "grad_norm": NaN,
+      "learning_rate": 6.473775872054521e-05,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.11261806732865101,
+      "grad_norm": NaN,
+      "learning_rate": 6.257933818722543e-05,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.1162509082102204,
+      "grad_norm": NaN,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.11988374909178978,
+      "grad_norm": NaN,
+      "learning_rate": 5.819089557075689e-05,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.12351658997335917,
+      "grad_norm": NaN,
+      "learning_rate": 5.596971122701221e-05,
+      "loss": 0.0,
+      "step": 102
+    },
+    {
+      "epoch": 0.12714943085492855,
+      "grad_norm": NaN,
+      "learning_rate": 5.373650467932122e-05,
+      "loss": 0.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.13078227173649795,
+      "grad_norm": NaN,
+      "learning_rate": 5.149577330846993e-05,
+      "loss": 0.0,
+      "step": 108
+    },
+    {
+      "epoch": 0.1332041656575442,
+      "eval_loss": NaN,
+      "eval_runtime": 75.1898,
+      "eval_samples_per_second": 5.785,
+      "eval_steps_per_second": 2.899,
+      "step": 110
+    },
+    {
+      "epoch": 0.13441511261806732,
+      "grad_norm": NaN,
+      "learning_rate": 4.925202964923683e-05,
+      "loss": 0.0,
+      "step": 111
+    },
+    {
+      "epoch": 0.13804795349963672,
+      "grad_norm": NaN,
+      "learning_rate": 4.700979230274829e-05,
+      "loss": 0.0,
+      "step": 114
+    },
+    {
+      "epoch": 0.1416807943812061,
+      "grad_norm": NaN,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0,
+      "step": 117
+    },
+    {
+      "epoch": 0.1453136352627755,
+      "grad_norm": NaN,
+      "learning_rate": 4.254788669119127e-05,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.1489464761443449,
+      "grad_norm": NaN,
+      "learning_rate": 4.0337204110222346e-05,
+      "loss": 0.0,
+      "step": 123
+    },
+    {
+      "epoch": 0.15257931702591426,
+      "grad_norm": NaN,
+      "learning_rate": 3.814598111422513e-05,
+      "loss": 0.0,
+      "step": 126
+    },
+    {
+      "epoch": 0.15621215790748366,
+      "grad_norm": NaN,
+      "learning_rate": 3.597863053469987e-05,
+      "loss": 0.0,
+      "step": 129
+    },
+    {
+      "epoch": 0.15984499878905303,
+      "grad_norm": NaN,
+      "learning_rate": 3.383951712727701e-05,
+      "loss": 0.0,
+      "step": 132
+    },
+    {
+      "epoch": 0.16347783967062243,
+      "grad_norm": NaN,
+      "learning_rate": 3.173294878168025e-05,
+      "loss": 0.0,
+      "step": 135
+    },
+    {
+      "epoch": 0.1671106805521918,
+      "grad_norm": NaN,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.0,
+      "step": 138
+    },
+    {
+      "epoch": 0.1707435214337612,
+      "grad_norm": NaN,
+      "learning_rate": 2.7634342584218365e-05,
+      "loss": 0.0,
+      "step": 141
+    },
+    {
+      "epoch": 0.1743763623153306,
+      "grad_norm": NaN,
+      "learning_rate": 2.5650558779781635e-05,
+      "loss": 0.0,
+      "step": 144
+    },
+    {
+      "epoch": 0.17800920319689997,
+      "grad_norm": NaN,
+      "learning_rate": 2.371581150947476e-05,
+      "loss": 0.0,
+      "step": 147
+    },
+    {
+      "epoch": 0.18164204407846937,
+      "grad_norm": NaN,
+      "learning_rate": 2.1833997096818898e-05,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.18527488496003874,
+      "grad_norm": NaN,
+      "learning_rate": 2.0008905265604316e-05,
+      "loss": 0.0,
+      "step": 153
+    },
+    {
+      "epoch": 0.18890772584160814,
+      "grad_norm": NaN,
+      "learning_rate": 1.8244211507891063e-05,
+      "loss": 0.0,
+      "step": 156
+    },
+    {
+      "epoch": 0.19254056672317751,
+      "grad_norm": NaN,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0,
+      "step": 159
     }
   ],
   "logging_steps": 3,
@@ -224,7 +421,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.546654048465715e+16,
+  "total_flos": 7.09330809693143e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null