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:e84b0b715f0dea2f382f077a7f8c4bb7591e386c2385179f0e62f04a2001eef2
+oid sha256:d13d6c17d9f622328a6a548ff31a5de607a5894c20a54c2aceb5b272431d5643
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76a22c3315d7a67dd86140ae43761b3783595c851421d97039662bf78cfc54a8
+oid sha256:42b1a6ae65c96857fdf9649caa39d5620f8d837e63d9c3924522d8013ae3aff4
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5215857db83a850b51602b1b526f39867a486ea94a3191e5d31b95c7d819b67a
+oid sha256:1f1e133b1358043f0aade0ea43a41d3bcf2402211513104fa460a01635e89b57
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aca74ec263d567501e25901dacc15f1ca05abfc483f73c9f6eb0c48579623146
+oid sha256:087a7138fdfa89723d3acbe4ef5e27ca3914ff0b42cb17f88ede2b407e29bb67
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baff787f9895233e5a7cd9a07296156e38cf9b60ac1489bbcd44148752bff9d7
+oid sha256:bf8872e7166d5d4b1fc9bb95efd55c3f4d81aea57f896f1851042c1cb281daff
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c187582dfe3935f286bd56aaf3a01859db7190270642d2a614fcd6c9b6eb5afe
+oid sha256:0fc286d66d8b339ae44ff2f1ad9ceb94094784cfc73b43fc297d0eda3c1abfdb
 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": 1.2222079038619995,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.20110608345902464,
+  "best_metric": 1.1147706508636475,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4022121669180493,
   "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": 10.574,
       "eval_steps_per_second": 2.749,
       "step": 25
+    },
+    {
+      "epoch": 0.20915032679738563,
+      "grad_norm": 59.51567459106445,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 20.4203,
+      "step": 26
+    },
+    {
+      "epoch": 0.2171945701357466,
+      "grad_norm": 94.031005859375,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 20.0566,
+      "step": 27
+    },
+    {
+      "epoch": 0.2252388134741076,
+      "grad_norm": 63.98728942871094,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 18.5908,
+      "step": 28
+    },
+    {
+      "epoch": 0.23328305681246858,
+      "grad_norm": 70.50849151611328,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 18.3789,
+      "step": 29
+    },
+    {
+      "epoch": 0.24132730015082957,
+      "grad_norm": 94.6316909790039,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 20.5791,
+      "step": 30
+    },
+    {
+      "epoch": 0.24937154348919055,
+      "grad_norm": 49.107112884521484,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 20.0751,
+      "step": 31
+    },
+    {
+      "epoch": 0.2574157868275515,
+      "grad_norm": 59.386619567871094,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 19.4646,
+      "step": 32
+    },
+    {
+      "epoch": 0.2654600301659125,
+      "grad_norm": 54.569854736328125,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 18.6054,
+      "step": 33
+    },
+    {
+      "epoch": 0.27350427350427353,
+      "grad_norm": 58.54420471191406,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 19.026,
+      "step": 34
+    },
+    {
+      "epoch": 0.2815485168426345,
+      "grad_norm": 44.54639434814453,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 17.7273,
+      "step": 35
+    },
+    {
+      "epoch": 0.2895927601809955,
+      "grad_norm": 59.34305191040039,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 19.4993,
+      "step": 36
+    },
+    {
+      "epoch": 0.29763700351935646,
+      "grad_norm": 43.02519989013672,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 18.8984,
+      "step": 37
+    },
+    {
+      "epoch": 0.30568124685771747,
+      "grad_norm": 51.63078689575195,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 18.2151,
+      "step": 38
+    },
+    {
+      "epoch": 0.3137254901960784,
+      "grad_norm": 126.79589080810547,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 19.9692,
+      "step": 39
+    },
+    {
+      "epoch": 0.32176973353443944,
+      "grad_norm": 82.25690460205078,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 18.3356,
+      "step": 40
+    },
+    {
+      "epoch": 0.3298139768728004,
+      "grad_norm": 67.15270233154297,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 18.1798,
+      "step": 41
+    },
+    {
+      "epoch": 0.3378582202111614,
+      "grad_norm": 52.148597717285156,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 19.694,
+      "step": 42
+    },
+    {
+      "epoch": 0.34590246354952237,
+      "grad_norm": 52.65068054199219,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 18.6712,
+      "step": 43
+    },
+    {
+      "epoch": 0.3539467068878834,
+      "grad_norm": 63.50575637817383,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 19.3908,
+      "step": 44
+    },
+    {
+      "epoch": 0.36199095022624433,
+      "grad_norm": 45.28229522705078,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 18.7951,
+      "step": 45
+    },
+    {
+      "epoch": 0.37003519356460535,
+      "grad_norm": 43.16271209716797,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 19.3532,
+      "step": 46
+    },
+    {
+      "epoch": 0.3780794369029663,
+      "grad_norm": 57.86573028564453,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 17.9573,
+      "step": 47
+    },
+    {
+      "epoch": 0.3861236802413273,
+      "grad_norm": 32.22254180908203,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 17.9235,
+      "step": 48
+    },
+    {
+      "epoch": 0.3941679235796883,
+      "grad_norm": 36.30216598510742,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 18.8893,
+      "step": 49
+    },
+    {
+      "epoch": 0.4022121669180493,
+      "grad_norm": 45.27206802368164,
+      "learning_rate": 1e-05,
+      "loss": 17.6392,
+      "step": 50
+    },
+    {
+      "epoch": 0.4022121669180493,
+      "eval_loss": 1.1147706508636475,
+      "eval_runtime": 4.7535,
+      "eval_samples_per_second": 10.519,
+      "eval_steps_per_second": 2.735,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null