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:ae7c763fa6efec0369438287f8c98705649d9e9446d3584a373e3531a13c0f61
+oid sha256:7b8cac80befa11132ca608765f3b1154978c775459afe4fd7090fef4a1f0c7f0
 size 261131840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3d2df9a28f9effdf500c65cf6a9fdd148b605e6d1b757b48e784a3153969cf3
+oid sha256:188468f70400def1e1e0f92a73cc8470aea6c85ff1b2524ebfd0ee2347274555
 size 522406650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d7fb7fb6a8c1ab41cb7d6c1bd8d62a9d23e8478edbaf6d8d34353c3ce53c33
+oid sha256:647a861fcbe8884a48e9597072461f45ba21ebbed6b8e2094ea18c8859788bce
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f991a1fd33b7824a44665c35e3a0084e2c90c7cdf8ab3187049cc8bb96b4bb0
+oid sha256:cab17844897211306b7adcabdc074d7639470eb71ae02e57a3cf84f8db6b7cdd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:943b793c0f1949c002e0d85bf97e32d4b17764446071a804d21610cd8f01f162
+oid sha256:98655b5729b0388a7c7df5e1ff8891ab12d0bbfab553e5fce468c3d05351927a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ff2e346d4c655649c911d6630521c82a519c35bba558d5bd41edee94d703ae8
+oid sha256:6406f3b9154253227ffcd344cf14cee6a841b6f0c54636e76077fb5f245e9e61
 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": 0.9916588664054871,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22675736961451248,
+  "best_metric": 0.9367274641990662,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.45351473922902497,
   "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": 15.969,
       "eval_steps_per_second": 4.152,
       "step": 25
+    },
+    {
+      "epoch": 0.23582766439909297,
+      "grad_norm": 34.72603988647461,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 41.4229,
+      "step": 26
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": 29.00994873046875,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 37.8385,
+      "step": 27
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 29.791704177856445,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 37.1688,
+      "step": 28
+    },
+    {
+      "epoch": 0.26303854875283444,
+      "grad_norm": 21.486818313598633,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 33.5763,
+      "step": 29
+    },
+    {
+      "epoch": 0.272108843537415,
+      "grad_norm": 17.391510009765625,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 31.8093,
+      "step": 30
+    },
+    {
+      "epoch": 0.2811791383219955,
+      "grad_norm": 14.429960250854492,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 29.819,
+      "step": 31
+    },
+    {
+      "epoch": 0.29024943310657597,
+      "grad_norm": 13.572725296020508,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 29.4895,
+      "step": 32
+    },
+    {
+      "epoch": 0.29931972789115646,
+      "grad_norm": 16.76784896850586,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 29.3145,
+      "step": 33
+    },
+    {
+      "epoch": 0.30839002267573695,
+      "grad_norm": 18.062070846557617,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 26.8548,
+      "step": 34
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 20.56993293762207,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 27.9149,
+      "step": 35
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 23.277589797973633,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 28.7237,
+      "step": 36
+    },
+    {
+      "epoch": 0.3356009070294785,
+      "grad_norm": 22.635587692260742,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 22.4117,
+      "step": 37
+    },
+    {
+      "epoch": 0.34467120181405897,
+      "grad_norm": 18.91414451599121,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 32.7469,
+      "step": 38
+    },
+    {
+      "epoch": 0.35374149659863946,
+      "grad_norm": 13.754558563232422,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 35.7876,
+      "step": 39
+    },
+    {
+      "epoch": 0.36281179138321995,
+      "grad_norm": 15.152359962463379,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 34.6626,
+      "step": 40
+    },
+    {
+      "epoch": 0.37188208616780044,
+      "grad_norm": 13.985898971557617,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 32.2783,
+      "step": 41
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 13.5012845993042,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 32.2167,
+      "step": 42
+    },
+    {
+      "epoch": 0.3900226757369615,
+      "grad_norm": 13.727423667907715,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 31.4028,
+      "step": 43
+    },
+    {
+      "epoch": 0.39909297052154197,
+      "grad_norm": 13.151164054870605,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 28.9454,
+      "step": 44
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 12.17611026763916,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 28.3156,
+      "step": 45
+    },
+    {
+      "epoch": 0.41723356009070295,
+      "grad_norm": 13.333844184875488,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 26.8998,
+      "step": 46
+    },
+    {
+      "epoch": 0.42630385487528344,
+      "grad_norm": 13.045530319213867,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 27.8567,
+      "step": 47
+    },
+    {
+      "epoch": 0.43537414965986393,
+      "grad_norm": 14.13997745513916,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 27.0215,
+      "step": 48
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 15.954257011413574,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 24.4307,
+      "step": 49
+    },
+    {
+      "epoch": 0.45351473922902497,
+      "grad_norm": 22.00568389892578,
+      "learning_rate": 1e-05,
+      "loss": 22.3285,
+      "step": 50
+    },
+    {
+      "epoch": 0.45351473922902497,
+      "eval_loss": 0.9367274641990662,
+      "eval_runtime": 3.102,
+      "eval_samples_per_second": 16.119,
+      "eval_steps_per_second": 4.191,
+      "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": 2.631214808694784e+17,
+  "total_flos": 5.262429617389568e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null