Training in progress, step 49, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f4dca11228311ff546fd97b45d943f6b45472298304f1e915ff3c0b8352b1f
+oid sha256:d69fcabbb03d42c8a619f19a1af1ac921812da6fd7e08b4a3fca39e483879b9b
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c167e8aee120b520c29ac56b73df402dc68b49e476f22466ccb760c3201115
+oid sha256:c159fea28847411139477d8d88848438c4989c42f80813547a65ab99e2d5304a
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:425b60b4b812e48aaa2ce703677ac1fc4489f1f95b308ea80c64262fc7209a78
+oid sha256:dcf66194043f3ccc1cd7a76e7946395043844ac0ad98f446555c0eefe0fc9f71
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c23a050099b2dbcef730b4c769c461f201b45f8618bc8ca842b3393bc698eb43
+oid sha256:100939b4fec87c65bfb2709010f1618d6ed5d5f111ca7042c53c77e64eb9aa0e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3be7599d6f3fd14e3169bcb6cdeb3f52a5226660bc407ba54b5cc296d027d59d
+oid sha256:14e6669a20dd1d5b3a567ae35214d4bf51cef73a1a60f74e895e951237fa40d8
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:840657c72d1644d32902ed3baed4169f8fa8749780cabcde307874a07544bcbd
+oid sha256:25704ee5478cd4521ee5db3e9e14050e9c72edebe1088acf05e49ba2bb8ed7fb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.550387596899225,
+  "epoch": 3.0387596899224807,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 49,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,174 @@
       "eval_samples_per_second": 78.461,
       "eval_steps_per_second": 10.078,
       "step": 25
+    },
+    {
+      "epoch": 1.6124031007751938,
+      "grad_norm": NaN,
+      "learning_rate": 4.832925114961629e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.6744186046511627,
+      "grad_norm": NaN,
+      "learning_rate": 4.4995215418795085e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.7364341085271318,
+      "grad_norm": NaN,
+      "learning_rate": 4.1683532270843504e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.7984496124031009,
+      "grad_norm": NaN,
+      "learning_rate": 3.840899248662358e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.8604651162790697,
+      "grad_norm": NaN,
+      "learning_rate": 3.5186220955718306e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.9224806201550386,
+      "grad_norm": NaN,
+      "learning_rate": 3.202961135812437e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 1.9844961240310077,
+      "grad_norm": NaN,
+      "learning_rate": 2.895326187858326e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.046511627906977,
+      "grad_norm": NaN,
+      "learning_rate": 2.5970912240665813e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.108527131782946,
+      "grad_norm": NaN,
+      "learning_rate": 2.3095882341831372e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.1705426356589146,
+      "grad_norm": NaN,
+      "learning_rate": 2.0341012763532243e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.2325581395348837,
+      "grad_norm": NaN,
+      "learning_rate": 1.771860742205988e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.294573643410853,
+      "grad_norm": NaN,
+      "learning_rate": 1.5240378616267886e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.356589147286822,
+      "grad_norm": NaN,
+      "learning_rate": 1.2917394717602121e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.4186046511627906,
+      "grad_norm": NaN,
+      "learning_rate": 1.0760030736066951e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.4806201550387597,
+      "grad_norm": NaN,
+      "learning_rate": 8.777921982911996e-06,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.5426356589147288,
+      "grad_norm": NaN,
+      "learning_rate": 6.979921036993042e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.604651162790698,
+      "grad_norm": NaN,
+      "learning_rate": 5.374058207005944e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": NaN,
+      "learning_rate": 3.967505666178556e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 2.7286821705426356,
+      "grad_norm": NaN,
+      "learning_rate": 2.7665454196040664e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 2.7906976744186047,
+      "grad_norm": NaN,
+      "learning_rate": 1.7765412472811771e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 2.8527131782945734,
+      "grad_norm": NaN,
+      "learning_rate": 1.0019147481706625e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 2.9147286821705425,
+      "grad_norm": NaN,
+      "learning_rate": 4.461255922609986e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 2.9767441860465116,
+      "grad_norm": NaN,
+      "learning_rate": 1.1165606884234181e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 3.0387596899224807,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 49
     }
   ],
   "logging_steps": 1,
@@ -221,12 +389,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.47650456322048e+16,
+  "total_flos": 2.893948943912141e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null