Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f08458b3952ea47655a03a32f220981b68d84c014f836b9202812a07e888fd0
+oid sha256:d6c675c0a35bcf24246374da598cc43fa39426e6ae134024ba7e764c46523fbb
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ca9d164733f781f0b4e897a449b0b8a6d7036eb097bacf52dcb0e66818cf152
+oid sha256:e72eaa6731edbc1b9598635bcd456ad47e6b7cdf6658f1e3dabc6f6a1fd168b9
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:608f22a3109f0d9120815028c383d8691b2e223af74f65f7307ec067904d61a3
+oid sha256:ce1dbf419c301211e91f3eb2fb6773b4ab538df7595074af1ea15a16b70a0e0f
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c14edca02cc7a8977c9e6ed927851bffbf9041b9404323de7ab535ba62523dde
+oid sha256:f51262f6dc51dba6769754e16a461cee054b6de5278a4fc8726bfed6940c17ab
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67c1e433ae302f5635efec9d7e3a23bbfccedbeef23469f0534c18d5d99bdd74
+oid sha256:a8dc4dd6987be5f87d753eeefc0faafc2bb436f86a2dc737d76cf98ab08bca0d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:383ecb2eeda4a3904b1730e773c97679cfb8b072362f98d45962d1cb877c7211
+oid sha256:8abe9ed03d233345576bef19d727cc18a936666f3a8cfc108994b64d8a016345
 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": 10.371474266052246,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03281378178835111,
+  "best_metric": 10.368376731872559,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06562756357670221,
   "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": 502.961,
       "eval_steps_per_second": 130.77,
       "step": 25
+    },
+    {
+      "epoch": 0.034126333059885154,
+      "grad_norm": 0.053233131766319275,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3718,
+      "step": 26
+    },
+    {
+      "epoch": 0.035438884331419195,
+      "grad_norm": 0.05241366848349571,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.3713,
+      "step": 27
+    },
+    {
+      "epoch": 0.03675143560295324,
+      "grad_norm": 0.045514870434999466,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.376,
+      "step": 28
+    },
+    {
+      "epoch": 0.03806398687448728,
+      "grad_norm": 0.059033963829278946,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3716,
+      "step": 29
+    },
+    {
+      "epoch": 0.03937653814602133,
+      "grad_norm": 0.052445072680711746,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.3717,
+      "step": 30
+    },
+    {
+      "epoch": 0.04068908941755537,
+      "grad_norm": 0.05115202069282532,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.372,
+      "step": 31
+    },
+    {
+      "epoch": 0.04200164068908942,
+      "grad_norm": 0.05915110930800438,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3724,
+      "step": 32
+    },
+    {
+      "epoch": 0.043314191960623465,
+      "grad_norm": 0.05899716541171074,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3754,
+      "step": 33
+    },
+    {
+      "epoch": 0.044626743232157505,
+      "grad_norm": 0.06602742522954941,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.3774,
+      "step": 34
+    },
+    {
+      "epoch": 0.04593929450369155,
+      "grad_norm": 0.08038340508937836,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.3759,
+      "step": 35
+    },
+    {
+      "epoch": 0.04725184577522559,
+      "grad_norm": 0.08238374441862106,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.378,
+      "step": 36
+    },
+    {
+      "epoch": 0.04856439704675964,
+      "grad_norm": 0.0753418356180191,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3736,
+      "step": 37
+    },
+    {
+      "epoch": 0.04987694831829368,
+      "grad_norm": 0.07205703109502792,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3737,
+      "step": 38
+    },
+    {
+      "epoch": 0.05118949958982773,
+      "grad_norm": 0.05470695346593857,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.3718,
+      "step": 39
+    },
+    {
+      "epoch": 0.052502050861361775,
+      "grad_norm": 0.06746212393045425,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.3725,
+      "step": 40
+    },
+    {
+      "epoch": 0.053814602132895815,
+      "grad_norm": 0.06536153703927994,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.373,
+      "step": 41
+    },
+    {
+      "epoch": 0.05512715340442986,
+      "grad_norm": 0.07258470356464386,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.3715,
+      "step": 42
+    },
+    {
+      "epoch": 0.0564397046759639,
+      "grad_norm": 0.06972433626651764,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.3695,
+      "step": 43
+    },
+    {
+      "epoch": 0.05775225594749795,
+      "grad_norm": 0.06809047609567642,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.3692,
+      "step": 44
+    },
+    {
+      "epoch": 0.05906480721903199,
+      "grad_norm": 0.0657813623547554,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.3746,
+      "step": 45
+    },
+    {
+      "epoch": 0.06037735849056604,
+      "grad_norm": 0.06854860484600067,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3757,
+      "step": 46
+    },
+    {
+      "epoch": 0.06168990976210008,
+      "grad_norm": 0.06397425383329391,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.371,
+      "step": 47
+    },
+    {
+      "epoch": 0.06300246103363413,
+      "grad_norm": 0.07391654700040817,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.3725,
+      "step": 48
+    },
+    {
+      "epoch": 0.06431501230516817,
+      "grad_norm": 0.08552011102437973,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.3695,
+      "step": 49
+    },
+    {
+      "epoch": 0.06562756357670221,
+      "grad_norm": 0.09103067964315414,
+      "learning_rate": 1e-05,
+      "loss": 10.372,
+      "step": 50
+    },
+    {
+      "epoch": 0.06562756357670221,
+      "eval_loss": 10.368376731872559,
+      "eval_runtime": 0.1011,
+      "eval_samples_per_second": 494.675,
+      "eval_steps_per_second": 128.616,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null