Training in progress, step 46, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb06df3d95b800f68a465865ef4f078f1e1ce23c3d8001649483bc618a5f69d5
+oid sha256:e12a67170ef13e90e823a6354f90534476a59727d9ed1fa4e0e8fb75deec8f66
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd788af798bcfde5b83ec792290fc53379f08181deba923314f13982ea5cd958
+oid sha256:111d920b0b86f29ea6be0447e1933170796dcccd9918f4a0ec6aade6c0879dae
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7ba268176f43cb7de85f55ca81a70c997b63ecb4ecc2db55b52a28fa5bba135
+oid sha256:86f0f647b6ca4f40a450aa32d954fc27a11f78fc7d6221686e861feccdcc0c0a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c12e32429c7e843ac4c23747e4b77e50887228b666df813c28748e82f10cf488
+oid sha256:aea995ae1a0cd1ad7f0a9845700a932d6c27e421a82faf75304ac0602cc43d5e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b968db47d858641847b141654bf57c5d146d15382c57c44dc1395ab92ba4e8b
+oid sha256:d45b25fd7097089349c79757288fee5897d69fc35dbe10f389165ccfd0a69425
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43c559cbde9153c17d7a372e6ef412013941e6297ae86a5518b43caf90efbb1f
+oid sha256:b7f1ee7e5310274a73405630534a716def8b331763fa23521c74926adf94696e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.6528925619834711,
+  "epoch": 3.041322314049587,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 46,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,153 @@
       "eval_samples_per_second": 37.717,
       "eval_steps_per_second": 4.807,
       "step": 25
+    },
+    {
+      "epoch": 1.71900826446281,
+      "grad_norm": NaN,
+      "learning_rate": 4.288425808633575e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.7851239669421488,
+      "grad_norm": NaN,
+      "learning_rate": 3.937173552235117e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.8512396694214877,
+      "grad_norm": NaN,
+      "learning_rate": 3.591337215792852e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.9173553719008265,
+      "grad_norm": NaN,
+      "learning_rate": 3.2526791020045086e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.9834710743801653,
+      "grad_norm": NaN,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.049586776859504,
+      "grad_norm": NaN,
+      "learning_rate": 2.603755066399718e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.115702479338843,
+      "grad_norm": NaN,
+      "learning_rate": 2.296795912722014e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": NaN,
+      "learning_rate": 2.0036116674432654e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.2479338842975207,
+      "grad_norm": NaN,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.3140495867768593,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.3801652892561984,
+      "grad_norm": NaN,
+      "learning_rate": 1.2212521282287092e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.446280991735537,
+      "grad_norm": NaN,
+      "learning_rate": 9.972937953781986e-06,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.512396694214876,
+      "grad_norm": NaN,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.5785123966942147,
+      "grad_norm": NaN,
+      "learning_rate": 6.116050521637218e-06,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.644628099173554,
+      "grad_norm": NaN,
+      "learning_rate": 4.5184002322740785e-06,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.7107438016528924,
+      "grad_norm": NaN,
+      "learning_rate": 3.1525137500119207e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.7768595041322315,
+      "grad_norm": NaN,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 2.84297520661157,
+      "grad_norm": NaN,
+      "learning_rate": 1.1426567014420297e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": NaN,
+      "learning_rate": 5.089279059533658e-07,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 2.975206611570248,
+      "grad_norm": NaN,
+      "learning_rate": 1.2739426948732424e-07,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 3.041322314049587,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 46
     }
   ],
   "logging_steps": 1,
@@ -221,12 +368,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.629578157719552e+17,
+  "total_flos": 4.838423810203976e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null