Training in progress, step 42, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b358ad0253115bd5d5130d1f49d30e4bf07c5d68ef60223c32bcd803ddffe8c4
+oid sha256:42ec93f5f3ae839a92cf6b9cf18ed064f7beca49b6d9b38904eda1c92f6219ca
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33eaa656ac85ff67b5162b97358fcfa02013418493422bd8344673215fa431ae
+oid sha256:a15138386766749b7c60b05cc1e321eb4346f007a788c67461d5eda2b6ceb3e6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e7fa24dd339f02eaf48c538fb4068b5df21da0e6ac754d8f37bcee599eae6d5
+oid sha256:7b3d7a0ea8c700a3e0eb05433c4b1d6f8c9b26bba96ce3f1295a324f3b933686
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e35481f632a8fde4f21e2b928a87e59f63ee97da06c7ff9ddf4309a57a6ff938
+oid sha256:22cbf8c170dc06a9e158d227ed11c961d89f4fa8b745d27479a7b995b7a7cdee
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76a40cbf2d19b21a23676917dbe8144796f8784860cbdb93b0c2d0080098b0dc
+oid sha256:b731be823c28d4317d9bc7652ddac48c775f35e1274b2fe13448699a5f9815b8
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8f5af44da266da277e7531f687942d737458dea336c0a84bf03af6d775c87ac
+oid sha256:dde78f0152770b6d9ff9d100a4e49fd7ae2ec975980251062a46af49a9f251c7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.810810810810811,
+  "epoch": 3.054054054054054,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 42,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,125 @@
       "eval_samples_per_second": 45.948,
       "eval_steps_per_second": 11.947,
       "step": 25
+    },
+    {
+      "epoch": 1.8828828828828827,
+      "grad_norm": NaN,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.954954954954955,
+      "grad_norm": NaN,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.036036036036036,
+      "grad_norm": NaN,
+      "learning_rate": 3.45704275117204e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.108108108108108,
+      "grad_norm": NaN,
+      "learning_rate": 3.1487564587782306e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.18018018018018,
+      "grad_norm": NaN,
+      "learning_rate": 2.854966364683872e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.2522522522522523,
+      "grad_norm": NaN,
+      "learning_rate": 2.577483782514174e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.3243243243243246,
+      "grad_norm": NaN,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.3963963963963963,
+      "grad_norm": NaN,
+      "learning_rate": 2.0781731547998614e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.4684684684684686,
+      "grad_norm": NaN,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.5405405405405403,
+      "grad_norm": NaN,
+      "learning_rate": 1.6631192604065855e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.6126126126126126,
+      "grad_norm": NaN,
+      "learning_rate": 1.490470641152345e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.684684684684685,
+      "grad_norm": NaN,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.756756756756757,
+      "grad_norm": NaN,
+      "learning_rate": 1.2202456766718093e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.828828828828829,
+      "grad_norm": NaN,
+      "learning_rate": 1.1243353582104556e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.900900900900901,
+      "grad_norm": NaN,
+      "learning_rate": 1.0554024673218807e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.972972972972973,
+      "grad_norm": NaN,
+      "learning_rate": 1.0138719982009242e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 3.054054054054054,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 42
     }
   ],
   "logging_steps": 1,
@@ -221,12 +340,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.114626154561536e+17,
+  "total_flos": 1.8725719396633805e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null