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:f98370bcd5eab9f1395e704256243456f6d5f2a1ff36a715e97f793860b0bbce
+oid sha256:cf4ad140565134e4e563fd7e44b04711a1c4cefe87fb59cbc9549f4fe88d7f5f
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bfdb2b4db98714e03b6503430db58001e954d9709417c000c4a9dfa993eafd2
+oid sha256:079029058fe63945acccc9bcefd8f8efca6fe1c3559b6263aac0fc0dced81009
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea8b79c45fb7883a851b5838a0f04ce7fbcff2c78bdc16a0bce1e7c4cb639f90
+oid sha256:11ef54b7e04f168c0afe2a9182e88913d27b42f486cc2379e229b8b7532bcb3a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78f02e572e62ff82d2e77bb8b64166d9d04c41e77db5252dbba50922732f3a07
+oid sha256:8002e033338bbc183fc6aad867132bf156c6ae99da5b217049a1e4f550151e41
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af9ed11ac4a268a6e3fc5762ffbbd6d62720b2dd78f513da70a2511f36992d8
+oid sha256:66324232f636557fb60ab70078deade123d7761590bc877b482a585dc03ac326
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d044734d709d42a9a0b5937ff958a322e5058740c05d22914053908f0fe787f6
+oid sha256:7b19a2344f7dc2c1fe50d792ebd96a396b6841ddca1c0215068983430ed8e919
 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": 0.2061881422996521,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2597402597402597,
+  "best_metric": 0.11191346496343613,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5194805194805194,
   "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": 23.905,
       "eval_steps_per_second": 6.215,
       "step": 25
+    },
+    {
+      "epoch": 0.2701298701298701,
+      "grad_norm": 1.8239445686340332,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.1851,
+      "step": 26
+    },
+    {
+      "epoch": 0.2805194805194805,
+      "grad_norm": 1.5958229303359985,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.181,
+      "step": 27
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 1.5911153554916382,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.2248,
+      "step": 28
+    },
+    {
+      "epoch": 0.3012987012987013,
+      "grad_norm": 1.8410097360610962,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.2173,
+      "step": 29
+    },
+    {
+      "epoch": 0.3116883116883117,
+      "grad_norm": 1.519921064376831,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.2138,
+      "step": 30
+    },
+    {
+      "epoch": 0.3220779220779221,
+      "grad_norm": 1.644580364227295,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.2149,
+      "step": 31
+    },
+    {
+      "epoch": 0.33246753246753247,
+      "grad_norm": 1.4669926166534424,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.1716,
+      "step": 32
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 1.3145791292190552,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.1769,
+      "step": 33
+    },
+    {
+      "epoch": 0.35324675324675325,
+      "grad_norm": 1.5595966577529907,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.1775,
+      "step": 34
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 1.5390815734863281,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.1712,
+      "step": 35
+    },
+    {
+      "epoch": 0.37402597402597404,
+      "grad_norm": 1.0273857116699219,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.195,
+      "step": 36
+    },
+    {
+      "epoch": 0.38441558441558443,
+      "grad_norm": 0.9481903314590454,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.1387,
+      "step": 37
+    },
+    {
+      "epoch": 0.3948051948051948,
+      "grad_norm": 1.0735758543014526,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.1442,
+      "step": 38
+    },
+    {
+      "epoch": 0.4051948051948052,
+      "grad_norm": 1.3054051399230957,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.1906,
+      "step": 39
+    },
+    {
+      "epoch": 0.4155844155844156,
+      "grad_norm": 1.3446217775344849,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.1826,
+      "step": 40
+    },
+    {
+      "epoch": 0.42597402597402595,
+      "grad_norm": 1.1781445741653442,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.1747,
+      "step": 41
+    },
+    {
+      "epoch": 0.43636363636363634,
+      "grad_norm": 1.1007606983184814,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.187,
+      "step": 42
+    },
+    {
+      "epoch": 0.44675324675324674,
+      "grad_norm": 1.232513666152954,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.1438,
+      "step": 43
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 1.1253693103790283,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.1622,
+      "step": 44
+    },
+    {
+      "epoch": 0.4675324675324675,
+      "grad_norm": 0.9642559885978699,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.1817,
+      "step": 45
+    },
+    {
+      "epoch": 0.4779220779220779,
+      "grad_norm": 0.9171271324157715,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.1687,
+      "step": 46
+    },
+    {
+      "epoch": 0.4883116883116883,
+      "grad_norm": 1.2926783561706543,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.1738,
+      "step": 47
+    },
+    {
+      "epoch": 0.4987012987012987,
+      "grad_norm": 1.2792022228240967,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.2063,
+      "step": 48
+    },
+    {
+      "epoch": 0.509090909090909,
+      "grad_norm": 0.9798829555511475,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.1324,
+      "step": 49
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "grad_norm": 1.1944818496704102,
+      "learning_rate": 1e-05,
+      "loss": 0.1829,
+      "step": 50
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "eval_loss": 0.11191346496343613,
+      "eval_runtime": 2.1059,
+      "eval_samples_per_second": 23.743,
+      "eval_steps_per_second": 6.173,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null