Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e500e69f995fc4835f4ecf2b88c0770bc67c91668de517cdbc5f5b921ba1a90c
+oid sha256:3954302d71cc6841f4e5736afc7d51353c28a34669497917ee1e87d09eb32ce2
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e55f8205588f7d4276c3ed3cc9806b673847681f311c7013b2f6c4abcecb83e0
+oid sha256:1cf0a11051f197e1667878863a87a76a611d1a598e2752f25388677c6f88c65a
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f177e070b88d704cde1c3bd06a55c03b3a8f5a9e026196e0eec53e68adef3ba
+oid sha256:3cc671f8aadc248569e12466d17067320428e39a0f471de63e31a3dfc9ac9ba6
 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": 1.1159125566482544,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.02353979696925114,
+  "epoch": 0.03530969545387671,
   "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": 6.704,
       "eval_steps_per_second": 1.676,
       "step": 50
+    },
+    {
+      "epoch": 0.024010592908636164,
+      "grad_norm": 0.6711025834083557,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 1.0878,
+      "step": 51
+    },
+    {
+      "epoch": 0.024481388848021184,
+      "grad_norm": 0.6568624973297119,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 1.0447,
+      "step": 52
+    },
+    {
+      "epoch": 0.02495218478740621,
+      "grad_norm": 0.6191370487213135,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.1122,
+      "step": 53
+    },
+    {
+      "epoch": 0.025422980726791233,
+      "grad_norm": 0.6773213744163513,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 1.1193,
+      "step": 54
+    },
+    {
+      "epoch": 0.025893776666176253,
+      "grad_norm": 0.6792715191841125,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 1.1247,
+      "step": 55
+    },
+    {
+      "epoch": 0.026364572605561278,
+      "grad_norm": 0.6690425872802734,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 1.1017,
+      "step": 56
+    },
+    {
+      "epoch": 0.026835368544946298,
+      "grad_norm": 0.6485929489135742,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 1.0747,
+      "step": 57
+    },
+    {
+      "epoch": 0.027306164484331322,
+      "grad_norm": 0.675126314163208,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 1.07,
+      "step": 58
+    },
+    {
+      "epoch": 0.027776960423716347,
+      "grad_norm": 0.6962899565696716,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 1.0591,
+      "step": 59
+    },
+    {
+      "epoch": 0.028247756363101367,
+      "grad_norm": 0.662079393863678,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 1.1415,
+      "step": 60
+    },
+    {
+      "epoch": 0.02871855230248639,
+      "grad_norm": 0.6812634468078613,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 1.0937,
+      "step": 61
+    },
+    {
+      "epoch": 0.029189348241871412,
+      "grad_norm": 0.7200164198875427,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 1.2216,
+      "step": 62
+    },
+    {
+      "epoch": 0.029660144181256436,
+      "grad_norm": 0.6734728813171387,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 1.1649,
+      "step": 63
+    },
+    {
+      "epoch": 0.03013094012064146,
+      "grad_norm": 0.650775671005249,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.1018,
+      "step": 64
+    },
+    {
+      "epoch": 0.03060173606002648,
+      "grad_norm": 0.6936342716217041,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 1.16,
+      "step": 65
+    },
+    {
+      "epoch": 0.031072531999411505,
+      "grad_norm": 0.6400872468948364,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 1.083,
+      "step": 66
+    },
+    {
+      "epoch": 0.03154332793879653,
+      "grad_norm": 0.6761430501937866,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 1.0366,
+      "step": 67
+    },
+    {
+      "epoch": 0.032014123878181554,
+      "grad_norm": 0.6780744194984436,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 1.1405,
+      "step": 68
+    },
+    {
+      "epoch": 0.03248491981756657,
+      "grad_norm": 0.6598646640777588,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 1.084,
+      "step": 69
+    },
+    {
+      "epoch": 0.032955715756951595,
+      "grad_norm": 0.6628397107124329,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 1.061,
+      "step": 70
+    },
+    {
+      "epoch": 0.03342651169633662,
+      "grad_norm": 0.6676144599914551,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 1.1337,
+      "step": 71
+    },
+    {
+      "epoch": 0.033897307635721644,
+      "grad_norm": 0.6578212976455688,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 1.1128,
+      "step": 72
+    },
+    {
+      "epoch": 0.03436810357510667,
+      "grad_norm": 0.6542023420333862,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 1.0441,
+      "step": 73
+    },
+    {
+      "epoch": 0.034838899514491685,
+      "grad_norm": 0.6668130159378052,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 1.0559,
+      "step": 74
+    },
+    {
+      "epoch": 0.03530969545387671,
+      "grad_norm": 0.6653211712837219,
+      "learning_rate": 0.0,
+      "loss": 1.1329,
+      "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": 2.84377737068544e+17,
+  "total_flos": 4.26566605602816e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null