Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:562b0f0b08222af3617d64071a46643cfc0ee70d10630411f23d692034178ceb
+oid sha256:b3da767c772cb318f860aa62abd397ab3221f62138c85bc6bff679210c42dadb
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8870f0de72c6621a13a2a299340a721dfe3e5392915d5f067c6c2018c59253be
+oid sha256:3035ed6db07f0e9dd2b4d38f62a055da88a99d6866a935339430d41e928e1d44
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e6930a84686b1d21bc31dd143e064588d64582b3e90e4709c76dd69e84fb87f
+oid sha256:d72d9cffd43832779c372bbf535fbe48051733d9b45dacf964446717074e5979
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7d9864da0e4f8a88388271a5a89431df919be54c815c73543a37b3d2ecf235
+oid sha256:0e9f837e6ed437302117e9da4f8bdbc62049f3d364a6a1a658ee0334904562d4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5227563abf0c7ac82b11e18abe2e428fb95dea49eb80ccb7acc378fdbe96d0cc
+oid sha256:1abbba2693efb35991196888f0ee19407976c33a61507b0cfb2f7471156ad1fe
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7477b1b300da279e4f411c7e6b62eadfc55426bdb9058197125c74ac88d0516
+oid sha256:6dc5df588cb9b1057b59db490d9eaa2ddc5b3027060ed5b3223f73059c5477cd
 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": 0.5152958035469055,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.09530617107457708,
+  "best_metric": 0.5070711374282837,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.19061234214915415,
   "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": 18.138,
       "eval_steps_per_second": 2.267,
       "step": 25
+    },
+    {
+      "epoch": 0.09911841791756017,
+      "grad_norm": 0.10792405158281326,
+      "learning_rate": 5e-05,
+      "loss": 0.5462,
+      "step": 26
+    },
+    {
+      "epoch": 0.10293066476054324,
+      "grad_norm": 0.11865006387233734,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5619,
+      "step": 27
+    },
+    {
+      "epoch": 0.10674291160352632,
+      "grad_norm": 0.11148977279663086,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5233,
+      "step": 28
+    },
+    {
+      "epoch": 0.11055515844650941,
+      "grad_norm": 0.12350525707006454,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.5382,
+      "step": 29
+    },
+    {
+      "epoch": 0.11436740528949249,
+      "grad_norm": 0.11989864706993103,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5144,
+      "step": 30
+    },
+    {
+      "epoch": 0.11817965213247558,
+      "grad_norm": 0.12140996754169464,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.544,
+      "step": 31
+    },
+    {
+      "epoch": 0.12199189897545866,
+      "grad_norm": 0.12538982927799225,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5021,
+      "step": 32
+    },
+    {
+      "epoch": 0.12580414581844174,
+      "grad_norm": 0.13155509531497955,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5056,
+      "step": 33
+    },
+    {
+      "epoch": 0.12961639266142483,
+      "grad_norm": 0.13385814428329468,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.533,
+      "step": 34
+    },
+    {
+      "epoch": 0.13342863950440792,
+      "grad_norm": 0.13156044483184814,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.512,
+      "step": 35
+    },
+    {
+      "epoch": 0.13724088634739098,
+      "grad_norm": 0.14174248278141022,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4998,
+      "step": 36
+    },
+    {
+      "epoch": 0.14105313319037407,
+      "grad_norm": 0.15541359782218933,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4809,
+      "step": 37
+    },
+    {
+      "epoch": 0.14486538003335717,
+      "grad_norm": 0.11500518769025803,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5598,
+      "step": 38
+    },
+    {
+      "epoch": 0.14867762687634023,
+      "grad_norm": 0.09926284849643707,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.497,
+      "step": 39
+    },
+    {
+      "epoch": 0.15248987371932332,
+      "grad_norm": 0.11181768029928207,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5104,
+      "step": 40
+    },
+    {
+      "epoch": 0.1563021205623064,
+      "grad_norm": 0.10740184783935547,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5102,
+      "step": 41
+    },
+    {
+      "epoch": 0.1601143674052895,
+      "grad_norm": 0.115020751953125,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5418,
+      "step": 42
+    },
+    {
+      "epoch": 0.16392661424827257,
+      "grad_norm": 0.11854977160692215,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4986,
+      "step": 43
+    },
+    {
+      "epoch": 0.16773886109125566,
+      "grad_norm": 0.11391133815050125,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4962,
+      "step": 44
+    },
+    {
+      "epoch": 0.17155110793423875,
+      "grad_norm": 0.12022404372692108,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.5195,
+      "step": 45
+    },
+    {
+      "epoch": 0.1753633547772218,
+      "grad_norm": 0.1278664618730545,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5102,
+      "step": 46
+    },
+    {
+      "epoch": 0.1791756016202049,
+      "grad_norm": 0.1261085867881775,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.5061,
+      "step": 47
+    },
+    {
+      "epoch": 0.182987848463188,
+      "grad_norm": 0.13194888830184937,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4893,
+      "step": 48
+    },
+    {
+      "epoch": 0.1868000953061711,
+      "grad_norm": 0.1402422934770584,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.5238,
+      "step": 49
+    },
+    {
+      "epoch": 0.19061234214915415,
+      "grad_norm": 0.1567613035440445,
+      "learning_rate": 0.0,
+      "loss": 0.4982,
+      "step": 50
+    },
+    {
+      "epoch": 0.19061234214915415,
+      "eval_loss": 0.5070711374282837,
+      "eval_runtime": 97.9047,
+      "eval_samples_per_second": 18.058,
+      "eval_steps_per_second": 2.257,
+      "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": 2.987771858905989e+17,
+  "total_flos": 5.979273768059535e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null