Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6882cc21367041594176f3159a00cf356c729a2d261cc37717102d1ef68dbecc
+oid sha256:45274f7293e56f712e5c83f2d5336059031522a323184c65655abccbebdb72a6
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8001dff90cbe4fa842f75afb3950ef87726d509592a4c9d4335665d0800f2eda
+oid sha256:bbb3f5b5e86ada762c99de862bca7efae27ab69e63b015a8b80b404c6f5b0806
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53a9f6728c7f104d24b3c21fab5949b43aa629ee5a14a361aedd15cbbf24b740
+oid sha256:24c86d1c2608543c74007ec479148bef9e8cea70a0aca77051f156c5f0ff9be9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2164a3173697805cad422149872e7bb175a4de9d6b9ffaa3191f744b3f403ecc
+oid sha256:861cc34889ca906d7bd151bcc1126d77383ac6d989a0470e92dd44246b42d710
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee0a13f7af8b74aaea2f17f0ac1a9b4c7b1c73c0a8e86a42ca3e1e060a427e54
+oid sha256:b13c997b583237a72a77c86d1c3421b40caf6f2df0606010f2d9c1be13839988
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:415f6018e7a29dceaf2cfbf7c260c72033ea0a387ed308a18b9c94cfc920e21d
+oid sha256:511bed456c1eb7df2e2581daae4fd114052d6953b8eacd6f189a2dcb2b588985
 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": 0.7062661051750183,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.017404925593943087,
+  "best_metric": 0.5986165404319763,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.034809851187886175,
   "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": 14.746,
       "eval_steps_per_second": 3.834,
       "step": 25
+    },
+    {
+      "epoch": 0.018101122617700808,
+      "grad_norm": 1.3576762676239014,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7465,
+      "step": 26
+    },
+    {
+      "epoch": 0.018797319641458532,
+      "grad_norm": 1.313129186630249,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.6395,
+      "step": 27
+    },
+    {
+      "epoch": 0.019493516665216256,
+      "grad_norm": 1.188519835472107,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.7079,
+      "step": 28
+    },
+    {
+      "epoch": 0.02018971368897398,
+      "grad_norm": 1.1454977989196777,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.6928,
+      "step": 29
+    },
+    {
+      "epoch": 0.020885910712731704,
+      "grad_norm": 1.0681382417678833,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.6142,
+      "step": 30
+    },
+    {
+      "epoch": 0.021582107736489428,
+      "grad_norm": 1.1505845785140991,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.5769,
+      "step": 31
+    },
+    {
+      "epoch": 0.02227830476024715,
+      "grad_norm": 1.2340224981307983,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5512,
+      "step": 32
+    },
+    {
+      "epoch": 0.022974501784004873,
+      "grad_norm": 1.0733771324157715,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.5667,
+      "step": 33
+    },
+    {
+      "epoch": 0.023670698807762597,
+      "grad_norm": 1.0927112102508545,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.5102,
+      "step": 34
+    },
+    {
+      "epoch": 0.02436689583152032,
+      "grad_norm": 1.3149555921554565,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.5898,
+      "step": 35
+    },
+    {
+      "epoch": 0.025063092855278045,
+      "grad_norm": 1.3991199731826782,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.6337,
+      "step": 36
+    },
+    {
+      "epoch": 0.025759289879035766,
+      "grad_norm": 1.4893077611923218,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.6278,
+      "step": 37
+    },
+    {
+      "epoch": 0.02645548690279349,
+      "grad_norm": 1.150443434715271,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.8092,
+      "step": 38
+    },
+    {
+      "epoch": 0.027151683926551214,
+      "grad_norm": 0.8582993745803833,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.6176,
+      "step": 39
+    },
+    {
+      "epoch": 0.027847880950308938,
+      "grad_norm": 1.009572148323059,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.5971,
+      "step": 40
+    },
+    {
+      "epoch": 0.02854407797406666,
+      "grad_norm": 1.0766137838363647,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.5786,
+      "step": 41
+    },
+    {
+      "epoch": 0.029240274997824386,
+      "grad_norm": 0.9323824644088745,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.555,
+      "step": 42
+    },
+    {
+      "epoch": 0.029936472021582106,
+      "grad_norm": 1.1088814735412598,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.5825,
+      "step": 43
+    },
+    {
+      "epoch": 0.03063266904533983,
+      "grad_norm": 0.9386204481124878,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.5434,
+      "step": 44
+    },
+    {
+      "epoch": 0.03132886606909756,
+      "grad_norm": 0.8790339827537537,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.4153,
+      "step": 45
+    },
+    {
+      "epoch": 0.03202506309285528,
+      "grad_norm": 1.0394346714019775,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.4865,
+      "step": 46
+    },
+    {
+      "epoch": 0.032721260116613,
+      "grad_norm": 1.093427062034607,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.5469,
+      "step": 47
+    },
+    {
+      "epoch": 0.03341745714037073,
+      "grad_norm": 1.174867033958435,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.5534,
+      "step": 48
+    },
+    {
+      "epoch": 0.03411365416412845,
+      "grad_norm": 1.370957851409912,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.5735,
+      "step": 49
+    },
+    {
+      "epoch": 0.034809851187886175,
+      "grad_norm": 1.5540739297866821,
+      "learning_rate": 1e-05,
+      "loss": 0.6185,
+      "step": 50
+    },
+    {
+      "epoch": 0.034809851187886175,
+      "eval_loss": 0.5986165404319763,
+      "eval_runtime": 3.3935,
+      "eval_samples_per_second": 14.734,
+      "eval_steps_per_second": 3.831,
+      "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": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null