Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d380bb1859eeaa0281a616287c07d0f0b6ad033e27d0512caf188d366f89105
+oid sha256:00e8a613ce2d5e43e3332fb567a47c7fd12657fff016ac254d3a4f496313ed51
 size 493712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f2b895a0ee9cfc4c150497a2275227a59f4ef2c7e42bf70ebb2e9dc0f702a51
+oid sha256:3ecb5d6f55b609ce0ef973f0fb116cb525b0c80d33b8f87ac0e485cb90bd426f
 size 997038

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:392f7fa81698d91aeb6202f072a9eda76e19496d93d2c64d5d9af3b692c2ef87
+oid sha256:3f5e4868dd3c43f74b652ef946b98ef8c0e250a78364ca63b25903baed937c73
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a407dab23a4f9b2e5a8e366387ff4af2dd71fd296d39888f7268b1f5027e1dd
+oid sha256:df7f1dd29468ce751e44ac705f002a3528a3a223782c7356b2c8b3c0c6a7db5c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc7127525b85321116f51840a4986a498761d381fe972cdd6c20808b9471a371
+oid sha256:1247609c6d6e84447c3cc92d6f7f3bb0ccdbc7ad795faf501aaaf49e4c2caad2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50c78d82180a8cb9fe313aea96246a3267ed6dc33e868e7bdce05e3a5f33628f
+oid sha256:44b0a399cfda9ecbecbb601b682b8186c934134ec0c0ece83606e883632e5503
 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": 10.896605491638184,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.030417094407056765,
+  "best_metric": 10.817767143249512,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06083418881411353,
   "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": 390.544,
       "eval_steps_per_second": 101.541,
       "step": 25
+    },
+    {
+      "epoch": 0.03163377818333904,
+      "grad_norm": 18.040603637695312,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 349.5131,
+      "step": 26
+    },
+    {
+      "epoch": 0.03285046195962131,
+      "grad_norm": 18.675752639770508,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 349.1621,
+      "step": 27
+    },
+    {
+      "epoch": 0.03406714573590358,
+      "grad_norm": 18.330108642578125,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 348.9829,
+      "step": 28
+    },
+    {
+      "epoch": 0.035283829512185845,
+      "grad_norm": 18.89789581298828,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 348.2867,
+      "step": 29
+    },
+    {
+      "epoch": 0.036500513288468116,
+      "grad_norm": 19.309520721435547,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 347.864,
+      "step": 30
+    },
+    {
+      "epoch": 0.037717197064750387,
+      "grad_norm": 19.69744110107422,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 347.5605,
+      "step": 31
+    },
+    {
+      "epoch": 0.03893388084103266,
+      "grad_norm": 19.83424186706543,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 347.3673,
+      "step": 32
+    },
+    {
+      "epoch": 0.04015056461731493,
+      "grad_norm": 20.2271728515625,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 347.0189,
+      "step": 33
+    },
+    {
+      "epoch": 0.0413672483935972,
+      "grad_norm": 20.975255966186523,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 346.4841,
+      "step": 34
+    },
+    {
+      "epoch": 0.04258393216987947,
+      "grad_norm": 19.940893173217773,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 346.9113,
+      "step": 35
+    },
+    {
+      "epoch": 0.04380061594616174,
+      "grad_norm": 19.74258804321289,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 347.1817,
+      "step": 36
+    },
+    {
+      "epoch": 0.04501729972244401,
+      "grad_norm": 20.28154945373535,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 346.913,
+      "step": 37
+    },
+    {
+      "epoch": 0.04623398349872628,
+      "grad_norm": 18.254350662231445,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 347.7138,
+      "step": 38
+    },
+    {
+      "epoch": 0.04745066727500855,
+      "grad_norm": 17.178295135498047,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 348.0967,
+      "step": 39
+    },
+    {
+      "epoch": 0.04866735105129082,
+      "grad_norm": 17.47958755493164,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 347.5675,
+      "step": 40
+    },
+    {
+      "epoch": 0.049884034827573094,
+      "grad_norm": 18.04706573486328,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 346.9237,
+      "step": 41
+    },
+    {
+      "epoch": 0.051100718603855365,
+      "grad_norm": 18.062149047851562,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 346.8773,
+      "step": 42
+    },
+    {
+      "epoch": 0.052317402380137636,
+      "grad_norm": 18.64065933227539,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 346.389,
+      "step": 43
+    },
+    {
+      "epoch": 0.053534086156419906,
+      "grad_norm": 19.041563034057617,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 346.3907,
+      "step": 44
+    },
+    {
+      "epoch": 0.05475076993270218,
+      "grad_norm": 19.454313278198242,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 346.0135,
+      "step": 45
+    },
+    {
+      "epoch": 0.05596745370898445,
+      "grad_norm": 19.951858520507812,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 345.8296,
+      "step": 46
+    },
+    {
+      "epoch": 0.05718413748526672,
+      "grad_norm": 20.76808738708496,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 345.2634,
+      "step": 47
+    },
+    {
+      "epoch": 0.05840082126154899,
+      "grad_norm": 19.44123649597168,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 346.0006,
+      "step": 48
+    },
+    {
+      "epoch": 0.05961750503783126,
+      "grad_norm": 19.380727767944336,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 346.2804,
+      "step": 49
+    },
+    {
+      "epoch": 0.06083418881411353,
+      "grad_norm": 20.843095779418945,
+      "learning_rate": 1e-05,
+      "loss": 346.0149,
+      "step": 50
+    },
+    {
+      "epoch": 0.06083418881411353,
+      "eval_loss": 10.817767143249512,
+      "eval_runtime": 0.1347,
+      "eval_samples_per_second": 371.185,
+      "eval_steps_per_second": 96.508,
+      "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": 19055561932800.0,
+  "total_flos": 38111123865600.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null