Training in progress, step 100, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d1a8dd3bb56efc8f5d013240ca65922a8ce332d515e5abf941b96f4e177e540
+oid sha256:dbb8068738de5d1b22ae9f99110fe2b7311193b82a1c9a83c09f8d4747c18186
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b516262e611e64feed373fc0a19148dd159b868c8d52c53d4e4b202d27f26b1e
+oid sha256:67afef3268769f9df8e8bd28497ea0d8633cc51fc4807d23d80268c5de0a09db
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feed204db996a9f7ac3167cc4686c04dccd6605b9b2a7d539da6ff57c605983d
+oid sha256:beccfaf9bab963f178f24d893fd68585ea073339edab1cdcc5698c989a1dd81e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5016722408026756,
+  "epoch": 0.6688963210702341,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,205 @@
       "learning_rate": 3.5721239031346067e-06,
       "loss": 0.0,
       "step": 75
+    },
+    {
+      "epoch": 0.5083612040133779,
+      "grad_norm": NaN,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.0,
+      "step": 76
+    },
+    {
+      "epoch": 0.5150501672240803,
+      "grad_norm": NaN,
+      "learning_rate": 3.0534162954100264e-06,
+      "loss": 0.0,
+      "step": 77
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": NaN,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.5284280936454849,
+      "grad_norm": NaN,
+      "learning_rate": 2.5685517452260566e-06,
+      "loss": 0.0,
+      "step": 79
+    },
+    {
+      "epoch": 0.5351170568561873,
+      "grad_norm": NaN,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.5418060200668896,
+      "grad_norm": NaN,
+      "learning_rate": 2.119892463932781e-06,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.5418060200668896,
+      "eval_loss": NaN,
+      "eval_runtime": 4.1778,
+      "eval_samples_per_second": 30.16,
+      "eval_steps_per_second": 3.83,
+      "step": 81
+    },
+    {
+      "epoch": 0.5484949832775919,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.0,
+      "step": 82
+    },
+    {
+      "epoch": 0.5551839464882943,
+      "grad_norm": NaN,
+      "learning_rate": 1.709624274449584e-06,
+      "loss": 0.0,
+      "step": 83
+    },
+    {
+      "epoch": 0.5618729096989966,
+      "grad_norm": NaN,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.568561872909699,
+      "grad_norm": NaN,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.5752508361204013,
+      "grad_norm": NaN,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 0.0,
+      "step": 86
+    },
+    {
+      "epoch": 0.5819397993311036,
+      "grad_norm": NaN,
+      "learning_rate": 1.012059537008332e-06,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.5886287625418061,
+      "grad_norm": NaN,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.5953177257525084,
+      "grad_norm": NaN,
+      "learning_rate": 7.281614543321269e-07,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.6020066889632107,
+      "grad_norm": NaN,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.6020066889632107,
+      "eval_loss": NaN,
+      "eval_runtime": 4.1709,
+      "eval_samples_per_second": 30.209,
+      "eval_steps_per_second": 3.836,
+      "step": 90
+    },
+    {
+      "epoch": 0.6086956521739131,
+      "grad_norm": NaN,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": NaN,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 0.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.6220735785953178,
+      "grad_norm": NaN,
+      "learning_rate": 2.970427372400353e-07,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.6287625418060201,
+      "grad_norm": NaN,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 0.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.6354515050167224,
+      "grad_norm": NaN,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.6421404682274248,
+      "grad_norm": NaN,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.6488294314381271,
+      "grad_norm": NaN,
+      "learning_rate": 5.4781046317267103e-08,
+      "loss": 0.0,
+      "step": 97
+    },
+    {
+      "epoch": 0.6555183946488294,
+      "grad_norm": NaN,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 0.0,
+      "step": 98
+    },
+    {
+      "epoch": 0.6622073578595318,
+      "grad_norm": NaN,
+      "learning_rate": 6.091729809042379e-09,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.6622073578595318,
+      "eval_loss": NaN,
+      "eval_runtime": 4.1935,
+      "eval_samples_per_second": 30.047,
+      "eval_steps_per_second": 3.815,
+      "step": 99
+    },
+    {
+      "epoch": 0.6688963210702341,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -618,12 +817,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8183481737674752.0,
+  "total_flos": 1.0911308983566336e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null