Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:534bfcbb9586e2fc3aff83bbd869edff29d4eb07756f4fb366bad7d347ceb035
+oid sha256:b895212e30f58c97fd52e1956d5bf95fce54552d582b6c81e0cc96ccf4097beb
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4328996e9e73e5575d8d8dd24725b638a8cce58494701192edef403e0efecf14
+oid sha256:fb87f2733240f25aa961cb0da6c413b722ed18e53a7f84711a6b9e42fe899b68
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b541cdedf7e47820fbe2d84316ff8e8d29eea8cfb264ebb20752bebfc72be6d7
+oid sha256:82cd8ad120eae16d9150b1f1c55d2d5b99f81b260a43a0436ed7d86faddef17d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51ae823878f2bbd8ccfaaa461503c625837d21057b060964b08a6afb5745ece2
+oid sha256:1f71e04bdf2b35f37e2e8e80b6440f8a1035cc1206cfd722b07cda54528fc090
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75d8aa4c456a06896a215d0111ae66e8260def24f9b7a23e3238ab3e5a2b1936
+oid sha256:24ec41aa1157c766667eb8776a62c4e3ef45a3b6f6d7ac81c3a6c4e02416875a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7b3004f77c933ba647ba8cb83d695552b8818f41fdf9b461099f3e9e507304b
+oid sha256:3ef6dc2b147ade5cdeef14a2509b0bc55c66e226769881b172ef443e302720d4
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.927361488342285,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05864242779651078,
+  "best_metric": 11.926499366760254,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11728485559302156,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 236.464,
       "eval_steps_per_second": 29.558,
       "step": 25
+    },
+    {
+      "epoch": 0.06098812490837121,
+      "grad_norm": 0.046790074557065964,
+      "learning_rate": 5e-05,
+      "loss": 11.9202,
+      "step": 26
+    },
+    {
+      "epoch": 0.06333382202023163,
+      "grad_norm": 0.045101504772901535,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.9141,
+      "step": 27
+    },
+    {
+      "epoch": 0.06567951913209207,
+      "grad_norm": 0.0466698482632637,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.9107,
+      "step": 28
+    },
+    {
+      "epoch": 0.0680252162439525,
+      "grad_norm": 0.05154228210449219,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.9064,
+      "step": 29
+    },
+    {
+      "epoch": 0.07037091335581293,
+      "grad_norm": 0.05609067901968956,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.9028,
+      "step": 30
+    },
+    {
+      "epoch": 0.07271661046767336,
+      "grad_norm": 0.054825764149427414,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.8996,
+      "step": 31
+    },
+    {
+      "epoch": 0.07506230757953379,
+      "grad_norm": 0.05315624177455902,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.8977,
+      "step": 32
+    },
+    {
+      "epoch": 0.07740800469139422,
+      "grad_norm": 0.05658416450023651,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.8949,
+      "step": 33
+    },
+    {
+      "epoch": 0.07975370180325465,
+      "grad_norm": 0.05000322312116623,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.8919,
+      "step": 34
+    },
+    {
+      "epoch": 0.08209939891511508,
+      "grad_norm": 0.06540560722351074,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.8874,
+      "step": 35
+    },
+    {
+      "epoch": 0.08444509602697552,
+      "grad_norm": 0.051300302147865295,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.8832,
+      "step": 36
+    },
+    {
+      "epoch": 0.08679079313883595,
+      "grad_norm": 0.05268245190382004,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.8738,
+      "step": 37
+    },
+    {
+      "epoch": 0.08913649025069638,
+      "grad_norm": 0.05355386808514595,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9155,
+      "step": 38
+    },
+    {
+      "epoch": 0.09148218736255681,
+      "grad_norm": 0.05276748165488243,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.916,
+      "step": 39
+    },
+    {
+      "epoch": 0.09382788447441724,
+      "grad_norm": 0.05582776665687561,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.9113,
+      "step": 40
+    },
+    {
+      "epoch": 0.09617358158627767,
+      "grad_norm": 0.06121082231402397,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.9071,
+      "step": 41
+    },
+    {
+      "epoch": 0.0985192786981381,
+      "grad_norm": 0.054675329476594925,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.904,
+      "step": 42
+    },
+    {
+      "epoch": 0.10086497580999854,
+      "grad_norm": 0.06488271802663803,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.9007,
+      "step": 43
+    },
+    {
+      "epoch": 0.10321067292185897,
+      "grad_norm": 0.0639345645904541,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.8972,
+      "step": 44
+    },
+    {
+      "epoch": 0.1055563700337194,
+      "grad_norm": 0.06195634603500366,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.8954,
+      "step": 45
+    },
+    {
+      "epoch": 0.10790206714557983,
+      "grad_norm": 0.06594201922416687,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.8923,
+      "step": 46
+    },
+    {
+      "epoch": 0.11024776425744026,
+      "grad_norm": 0.0577872097492218,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.8897,
+      "step": 47
+    },
+    {
+      "epoch": 0.11259346136930069,
+      "grad_norm": 0.057595305144786835,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.8845,
+      "step": 48
+    },
+    {
+      "epoch": 0.11493915848116112,
+      "grad_norm": 0.057064544409513474,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.8792,
+      "step": 49
+    },
+    {
+      "epoch": 0.11728485559302156,
+      "grad_norm": 0.05568932741880417,
+      "learning_rate": 0.0,
+      "loss": 11.8627,
+      "step": 50
+    },
+    {
+      "epoch": 0.11728485559302156,
+      "eval_loss": 11.926499366760254,
+      "eval_runtime": 12.1765,
+      "eval_samples_per_second": 235.864,
+      "eval_steps_per_second": 29.483,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null