Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e038ba28927bf03124d83f6b474b6d362d5d786286a27f811769fda0ba80db2
+oid sha256:384fa86200ed657f1f85071ed9279f7be8c7e0ae1c81095fcb29a55a8fcaf3e1
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0cab0d3356a4f59499096a4c6c2c30223b0c26b7d00ecdb54c79e869c1ad16a
+oid sha256:41ef2dba38118a906731d0a020c8c7af33534b45a49ee294baed543e84b9a95e
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5624d58037519df2ed5d1c02bc49581f7b9a384f99fcaa0c5ec71a96541beca6
+oid sha256:f74941f75e308f769f1a0d21c685a66a9187a378ed09c69f4d5099efc15b16ff
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:943615e3ceebbfb2fe9e2781d91f243c367509ab756d40310b755f9b1c11138f
+oid sha256:823eab2c5225d683eddaa888b90d7570bff19e2b7da8dcc39354a5271c3e7cfd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e35f570380d4ee1e030a84f8c9ba769977b917a08be3ebeb23fac6acfb966d4
+oid sha256:121063f6ec13b8e25517fdfbc7084dc05997cc90a700bb89fc412be2a7ce451d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd4d625a1dbf9ef17b1dded5809eaf43653428c7a0f98d21dddf154f47f63ca
+oid sha256:969a2dba5823f181d90e29848de9ee5febf8f276b45ab73e4a3a2bfd45c469f8
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.914447784423828,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7421150278293135,
+  "best_metric": 11.910688400268555,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.4916512059369202,
   "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": 343.26,
       "eval_steps_per_second": 89.248,
       "step": 25
+    },
+    {
+      "epoch": 0.7717996289424861,
+      "grad_norm": 0.07111849635839462,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9242,
+      "step": 26
+    },
+    {
+      "epoch": 0.8014842300556586,
+      "grad_norm": 0.07921064645051956,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.923,
+      "step": 27
+    },
+    {
+      "epoch": 0.8311688311688312,
+      "grad_norm": 0.10227816551923752,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9234,
+      "step": 28
+    },
+    {
+      "epoch": 0.8608534322820037,
+      "grad_norm": 0.11948052048683167,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.9263,
+      "step": 29
+    },
+    {
+      "epoch": 0.8905380333951762,
+      "grad_norm": 0.15240927040576935,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.929,
+      "step": 30
+    },
+    {
+      "epoch": 0.9202226345083488,
+      "grad_norm": 0.1400817185640335,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.9298,
+      "step": 31
+    },
+    {
+      "epoch": 0.9499072356215214,
+      "grad_norm": 0.17380662262439728,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.9234,
+      "step": 32
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 0.181602343916893,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.9239,
+      "step": 33
+    },
+    {
+      "epoch": 1.0166975881261595,
+      "grad_norm": 0.1615762561559677,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 17.6084,
+      "step": 34
+    },
+    {
+      "epoch": 1.0463821892393321,
+      "grad_norm": 0.09680893272161484,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 13.2432,
+      "step": 35
+    },
+    {
+      "epoch": 1.0760667903525047,
+      "grad_norm": 0.10842955857515335,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.7133,
+      "step": 36
+    },
+    {
+      "epoch": 1.1057513914656771,
+      "grad_norm": 0.11968661844730377,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 12.1176,
+      "step": 37
+    },
+    {
+      "epoch": 1.1354359925788498,
+      "grad_norm": 0.15758144855499268,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.5781,
+      "step": 38
+    },
+    {
+      "epoch": 1.1651205936920221,
+      "grad_norm": 0.16318297386169434,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.8551,
+      "step": 39
+    },
+    {
+      "epoch": 1.1948051948051948,
+      "grad_norm": 0.1592426300048828,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.8129,
+      "step": 40
+    },
+    {
+      "epoch": 1.2244897959183674,
+      "grad_norm": 0.18521009385585785,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.9893,
+      "step": 41
+    },
+    {
+      "epoch": 1.25417439703154,
+      "grad_norm": 0.1403988003730774,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.9091,
+      "step": 42
+    },
+    {
+      "epoch": 1.2838589981447124,
+      "grad_norm": 0.10750801116228104,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 13.3784,
+      "step": 43
+    },
+    {
+      "epoch": 1.313543599257885,
+      "grad_norm": 0.10899406671524048,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.5317,
+      "step": 44
+    },
+    {
+      "epoch": 1.3432282003710574,
+      "grad_norm": 0.13023824989795685,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.4102,
+      "step": 45
+    },
+    {
+      "epoch": 1.37291280148423,
+      "grad_norm": 0.1307949274778366,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 13.2577,
+      "step": 46
+    },
+    {
+      "epoch": 1.4025974025974026,
+      "grad_norm": 0.1620696485042572,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.2825,
+      "step": 47
+    },
+    {
+      "epoch": 1.4322820037105752,
+      "grad_norm": 0.15053598582744598,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 12.119,
+      "step": 48
+    },
+    {
+      "epoch": 1.4619666048237476,
+      "grad_norm": 0.19470062851905823,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 12.0202,
+      "step": 49
+    },
+    {
+      "epoch": 1.4916512059369202,
+      "grad_norm": 0.15723778307437897,
+      "learning_rate": 1e-05,
+      "loss": 10.541,
+      "step": 50
+    },
+    {
+      "epoch": 1.4916512059369202,
+      "eval_loss": 11.910688400268555,
+      "eval_runtime": 0.1299,
+      "eval_samples_per_second": 385.038,
+      "eval_steps_per_second": 100.11,
+      "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