Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0966db4e9fa8fcbdf7fb75f84432a38fd35c5cd3baafc4aa4f6b3626aa32b61a
+oid sha256:c3d591ffcba46c45d9e1c6d584c7b6fba7f7b9caa5466afea59cc7fe76034c11
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1e09d79ebb07669e316a8417f13c04f0f0b4f32e80dea02bd0b095517d61496
+oid sha256:2568745332de2ff6cf0f55b92287af43cfe514b848767b6839588af3d14647d8
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba3beffa4437d8223b2e93c208c2ad76f10f73b38c3c833d70b4769d4b704cea
+oid sha256:43fa4248efbf4187c69aca8c4b201ed8e982331effd9516dce436056ea355fc9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce1137135dd234a314203f126a1a88dd3fb4b95234c07f06132546cfba359152
+oid sha256:7eb3dfcb592a888cc9f28a12da8133a200d32db2425f2e1e7a779f44320368a0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f235bc45d81dec00bf192398e2ed603b48a939e86970ffa3d307cdadc724edd0
+oid sha256:16b6e0b4728fa6e4e46f11f0e870bbd5f02e8005f0f8828efc1d32df6fdcc0da
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cf121f6b0f6b1f537ae6f0dc3d2bc73af374cfe43b0cd81501b422caf3c3abf
+oid sha256:fcfd6445b05f22536a189aece6d1c5fdace3aaabe41fefb1dcb5eb22f5a4ee6a
 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": 0.8458690047264099,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.008494552867973413,
+  "best_metric": 0.592200517654419,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.016989105735946825,
   "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": 11.623,
       "eval_steps_per_second": 3.022,
       "step": 25
+    },
+    {
+      "epoch": 0.008834334982692349,
+      "grad_norm": 85.23617553710938,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 41.989,
+      "step": 26
+    },
+    {
+      "epoch": 0.009174117097411285,
+      "grad_norm": 141.01113891601562,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 70.3916,
+      "step": 27
+    },
+    {
+      "epoch": 0.00951389921213022,
+      "grad_norm": 87.8305435180664,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 44.4188,
+      "step": 28
+    },
+    {
+      "epoch": 0.009853681326849158,
+      "grad_norm": 103.69757843017578,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 35.7415,
+      "step": 29
+    },
+    {
+      "epoch": 0.010193463441568094,
+      "grad_norm": 70.0342025756836,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 20.2094,
+      "step": 30
+    },
+    {
+      "epoch": 0.01053324555628703,
+      "grad_norm": 60.558433532714844,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 26.0278,
+      "step": 31
+    },
+    {
+      "epoch": 0.010873027671005968,
+      "grad_norm": 90.48796081542969,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 20.534,
+      "step": 32
+    },
+    {
+      "epoch": 0.011212809785724904,
+      "grad_norm": 54.44171142578125,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 22.8126,
+      "step": 33
+    },
+    {
+      "epoch": 0.01155259190044384,
+      "grad_norm": 45.97940444946289,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 17.5795,
+      "step": 34
+    },
+    {
+      "epoch": 0.011892374015162776,
+      "grad_norm": 51.6795654296875,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 21.1725,
+      "step": 35
+    },
+    {
+      "epoch": 0.012232156129881714,
+      "grad_norm": 68.59659576416016,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.7635,
+      "step": 36
+    },
+    {
+      "epoch": 0.01257193824460065,
+      "grad_norm": 75.74279022216797,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 14.5458,
+      "step": 37
+    },
+    {
+      "epoch": 0.012911720359319586,
+      "grad_norm": 47.76968002319336,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 15.4607,
+      "step": 38
+    },
+    {
+      "epoch": 0.013251502474038522,
+      "grad_norm": 99.84883880615234,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 58.2234,
+      "step": 39
+    },
+    {
+      "epoch": 0.01359128458875746,
+      "grad_norm": 116.46077728271484,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 48.2057,
+      "step": 40
+    },
+    {
+      "epoch": 0.013931066703476396,
+      "grad_norm": 66.34112548828125,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 27.3147,
+      "step": 41
+    },
+    {
+      "epoch": 0.014270848818195332,
+      "grad_norm": 62.514739990234375,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 20.174,
+      "step": 42
+    },
+    {
+      "epoch": 0.01461063093291427,
+      "grad_norm": 76.1456298828125,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 17.344,
+      "step": 43
+    },
+    {
+      "epoch": 0.014950413047633206,
+      "grad_norm": 84.74457550048828,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 22.5312,
+      "step": 44
+    },
+    {
+      "epoch": 0.015290195162352142,
+      "grad_norm": 44.78037643432617,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 18.2871,
+      "step": 45
+    },
+    {
+      "epoch": 0.015629977277071078,
+      "grad_norm": 73.1561279296875,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 19.4562,
+      "step": 46
+    },
+    {
+      "epoch": 0.015969759391790014,
+      "grad_norm": 41.429466247558594,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 12.4755,
+      "step": 47
+    },
+    {
+      "epoch": 0.01630954150650895,
+      "grad_norm": 40.766700744628906,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.7315,
+      "step": 48
+    },
+    {
+      "epoch": 0.01664932362122789,
+      "grad_norm": 42.87800598144531,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 13.0668,
+      "step": 49
+    },
+    {
+      "epoch": 0.016989105735946825,
+      "grad_norm": 54.83426284790039,
+      "learning_rate": 1e-05,
+      "loss": 13.1161,
+      "step": 50
+    },
+    {
+      "epoch": 0.016989105735946825,
+      "eval_loss": 0.592200517654419,
+      "eval_runtime": 4.2256,
+      "eval_samples_per_second": 11.833,
+      "eval_steps_per_second": 3.076,
+      "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": 1.483568811343872e+17,
+  "total_flos": 2.967137622687744e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null