Training in progress, step 74, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1cb137347a523562a0037c78e1939dc7907e137b7e1aaabcdfffab0f1e32420
+oid sha256:454e47b0c1e5f7a3034b14282e64674891078add219f00342a663c15c05432a6
 size 1007201074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e24f81c995427989a9f283466a2a7a9f38494dae3090cabaefe42c3a30ac618
+oid sha256:4a83d91977f44b5b4422b1b21c044376365f42813e9dc0006b7d0a9de686605d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:163434374b9c1378509a87e97d00ede53e7253a4e0d456aae4d9aec3f792d3ac
+oid sha256:0ae7e08fcc06da1703203d5619b800ce4295ba8a44be2b48e9934b3ccdb901c2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.058931860036832415,
+  "epoch": 0.08721915285451197,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 74,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,174 @@
       "eval_samples_per_second": 2.537,
       "eval_steps_per_second": 2.537,
       "step": 50
+    },
+    {
+      "epoch": 0.06011049723756906,
+      "grad_norm": NaN,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.061289134438305706,
+      "grad_norm": NaN,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.06246777163904236,
+      "grad_norm": NaN,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.06364640883977901,
+      "grad_norm": NaN,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.06482504604051566,
+      "grad_norm": NaN,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.0660036832412523,
+      "grad_norm": NaN,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.06718232044198895,
+      "grad_norm": NaN,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.0683609576427256,
+      "grad_norm": NaN,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.06953959484346224,
+      "grad_norm": NaN,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.0707182320441989,
+      "grad_norm": NaN,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.07189686924493555,
+      "grad_norm": NaN,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.07307550644567219,
+      "grad_norm": NaN,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.07425414364640884,
+      "grad_norm": NaN,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.07543278084714548,
+      "grad_norm": NaN,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.07661141804788213,
+      "grad_norm": NaN,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.07779005524861879,
+      "grad_norm": NaN,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.07896869244935543,
+      "grad_norm": NaN,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.08014732965009208,
+      "grad_norm": NaN,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.08132596685082873,
+      "grad_norm": NaN,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.08250460405156537,
+      "grad_norm": NaN,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.08368324125230203,
+      "grad_norm": NaN,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.08486187845303868,
+      "grad_norm": NaN,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.08604051565377532,
+      "grad_norm": NaN,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.08721915285451197,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 74
     }
   ],
   "logging_steps": 1,
@@ -404,12 +572,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.4291577382200934e+17,
+  "total_flos": 3.7300685833764864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null