Training in progress, step 100, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa114a7a12a40badac7216ec0ffb4d495b02cb3b49d33b42799b881c94f94baf
+oid sha256:d9bb6116680e2898f3938ed7578c9f5c01762abaa5cfd7354acc3112b5da790c
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb12056bde6db464c4c3afc4902afb0a96960a35a41004b8be823383da375106
+oid sha256:5e8f7683e7ad9e943930097231479802eb09e943440f3ab35a9e5018fc6dd4bd
 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": 0.12468827930174564,
+  "epoch": 0.1662510390689942,
   "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": 0.12635078969243557,
+      "grad_norm": NaN,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.0,
+      "step": 76
+    },
+    {
+      "epoch": 0.12801330008312553,
+      "grad_norm": NaN,
+      "learning_rate": 3.0534162954100264e-06,
+      "loss": 0.0,
+      "step": 77
+    },
+    {
+      "epoch": 0.12967581047381546,
+      "grad_norm": NaN,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.1313383208645054,
+      "grad_norm": NaN,
+      "learning_rate": 2.5685517452260566e-06,
+      "loss": 0.0,
+      "step": 79
+    },
+    {
+      "epoch": 0.13300083125519535,
+      "grad_norm": NaN,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.13466334164588528,
+      "grad_norm": NaN,
+      "learning_rate": 2.119892463932781e-06,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.13466334164588528,
+      "eval_loss": NaN,
+      "eval_runtime": 96.6256,
+      "eval_samples_per_second": 5.247,
+      "eval_steps_per_second": 0.662,
+      "step": 81
+    },
+    {
+      "epoch": 0.13632585203657524,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.0,
+      "step": 82
+    },
+    {
+      "epoch": 0.13798836242726517,
+      "grad_norm": NaN,
+      "learning_rate": 1.709624274449584e-06,
+      "loss": 0.0,
+      "step": 83
+    },
+    {
+      "epoch": 0.1396508728179551,
+      "grad_norm": NaN,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.14131338320864506,
+      "grad_norm": NaN,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.142975893599335,
+      "grad_norm": NaN,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 0.0,
+      "step": 86
+    },
+    {
+      "epoch": 0.14463840399002495,
+      "grad_norm": NaN,
+      "learning_rate": 1.012059537008332e-06,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.14630091438071488,
+      "grad_norm": NaN,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.1479634247714048,
+      "grad_norm": NaN,
+      "learning_rate": 7.281614543321269e-07,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.14962593516209477,
+      "grad_norm": NaN,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.14962593516209477,
+      "eval_loss": NaN,
+      "eval_runtime": 96.6211,
+      "eval_samples_per_second": 5.247,
+      "eval_steps_per_second": 0.662,
+      "step": 90
+    },
+    {
+      "epoch": 0.1512884455527847,
+      "grad_norm": NaN,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.15295095594347466,
+      "grad_norm": NaN,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 0.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.1546134663341646,
+      "grad_norm": NaN,
+      "learning_rate": 2.970427372400353e-07,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.15627597672485452,
+      "grad_norm": NaN,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 0.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.15793848711554448,
+      "grad_norm": NaN,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.1596009975062344,
+      "grad_norm": NaN,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.16126350789692437,
+      "grad_norm": NaN,
+      "learning_rate": 5.4781046317267103e-08,
+      "loss": 0.0,
+      "step": 97
+    },
+    {
+      "epoch": 0.1629260182876143,
+      "grad_norm": NaN,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 0.0,
+      "step": 98
+    },
+    {
+      "epoch": 0.16458852867830423,
+      "grad_norm": NaN,
+      "learning_rate": 6.091729809042379e-09,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.16458852867830423,
+      "eval_loss": NaN,
+      "eval_runtime": 96.6138,
+      "eval_samples_per_second": 5.248,
+      "eval_steps_per_second": 0.662,
+      "step": 99
+    },
+    {
+      "epoch": 0.1662510390689942,
+      "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": 1.0369999835234304e+17,
+  "total_flos": 1.3869079534239744e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null