Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f78309ef133c6197d30fc6f94cee4186403bf7ca6899cba372e554335fc3b5f
+oid sha256:60151f2f898b5c28a69a1486d70c2478073c19bb7160e889251c25cec702d390
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d79c73246b07e024b254fcc3cd20c900e0be21114f977bbc4165720c9ed2069f
+oid sha256:976621e5db52719b3f4fb1fd4f928e0d70aa02e6f82174f610b6399fce408c70
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c409614fe7c4294c30c517ac4a1097721f51ec5d3456b5de1ee4e4e2aed9ba
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.055474655016989116,
+  "epoch": 0.08321198252548367,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,181 @@
       "eval_samples_per_second": 7.203,
       "eval_steps_per_second": 1.801,
       "step": 50
+    },
+    {
+      "epoch": 0.0565841481173289,
+      "grad_norm": NaN,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.05769364121766868,
+      "grad_norm": NaN,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.05880313431800846,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.05991262741834824,
+      "grad_norm": NaN,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.06102212051868802,
+      "grad_norm": NaN,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.0621316136190278,
+      "grad_norm": NaN,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.06324110671936758,
+      "grad_norm": NaN,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.06435059981970737,
+      "grad_norm": NaN,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.06546009292004715,
+      "grad_norm": NaN,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.06656958602038694,
+      "grad_norm": NaN,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.06767907912072672,
+      "grad_norm": NaN,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.0687885722210665,
+      "grad_norm": NaN,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.06989806532140629,
+      "grad_norm": NaN,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.07100755842174607,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.07211705152208585,
+      "grad_norm": NaN,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.07322654462242563,
+      "grad_norm": NaN,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.07433603772276541,
+      "grad_norm": NaN,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.07544553082310519,
+      "grad_norm": NaN,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.07655502392344497,
+      "grad_norm": NaN,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.07766451702378475,
+      "grad_norm": NaN,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.07877401012412454,
+      "grad_norm": NaN,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.07988350322446432,
+      "grad_norm": NaN,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.08099299632480411,
+      "grad_norm": NaN,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.08210248942514389,
+      "grad_norm": NaN,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.08321198252548367,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -396,12 +571,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.8508868141121536e+17,
+  "total_flos": 4.279884942881587e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null