Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2557b4f31a9e29833005dea024cf2bb289f5fc165e47c3b6925531e9d8d74095
+oid sha256:9343ffea7796edd567a2d6dd3d2d4659795d533896415fc1233e1b780aa4a333
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec9b3ca41a4e10f513bca0d4f5a9868b63ffefd6adfea7c6ab5591d1cda49dcd
+oid sha256:9c9038448a8de65723ca2fd76ecba869487ecb75e6ffed6a5624f6952a371c00
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acface3b356b6123803b625683b949ebf3136bcb061efb62ce4a55de239257da
+oid sha256:d970c68451f64a6ce313fcfd035ff050f0dbf87372ec80c53952c4f78f7dca3e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:914411fc1f0f063e58321b70b1f58f250d24a803cd0b2476d39cae458ae32b3a
+oid sha256:84d967f4d23410519f291a56d7c38d32e14126ce4870f0afe880e8f9126f5cb4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca49173a34cb0be5d522b72ecc8e69fa143d329c0f5e28bd1f370ddf021016a1
+oid sha256:ec351ac1c3e86117ca673cdc9fbce73ca7644a8b528230690821fe3b9b239c08
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c64a93432a75920dc39205e75fa2f5b42aa71df68b815ad65cd044fd3cf78c6d
+oid sha256:d28c6878676e547478a6612ee4885d72d6711cc54c2ff946f1567869597bac04
 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": 0.528091311454773,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.31007751937984496,
+  "best_metric": 0.46879658102989197,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6201550387596899,
   "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": 24.035,
       "eval_steps_per_second": 6.249,
       "step": 25
+    },
+    {
+      "epoch": 0.32248062015503876,
+      "grad_norm": 6.642690181732178,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.8365,
+      "step": 26
+    },
+    {
+      "epoch": 0.33488372093023255,
+      "grad_norm": 3.7332913875579834,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.6802,
+      "step": 27
+    },
+    {
+      "epoch": 0.34728682170542635,
+      "grad_norm": 1.695497751235962,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.5761,
+      "step": 28
+    },
+    {
+      "epoch": 0.35968992248062015,
+      "grad_norm": 1.8069305419921875,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.6018,
+      "step": 29
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 1.9271109104156494,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.5892,
+      "step": 30
+    },
+    {
+      "epoch": 0.38449612403100775,
+      "grad_norm": 2.6150898933410645,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.5628,
+      "step": 31
+    },
+    {
+      "epoch": 0.39689922480620154,
+      "grad_norm": 2.0166444778442383,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.544,
+      "step": 32
+    },
+    {
+      "epoch": 0.40930232558139534,
+      "grad_norm": 2.3682992458343506,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.4747,
+      "step": 33
+    },
+    {
+      "epoch": 0.42170542635658914,
+      "grad_norm": 1.7106528282165527,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.4567,
+      "step": 34
+    },
+    {
+      "epoch": 0.43410852713178294,
+      "grad_norm": 1.7924227714538574,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.4622,
+      "step": 35
+    },
+    {
+      "epoch": 0.44651162790697674,
+      "grad_norm": 1.8440314531326294,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.3794,
+      "step": 36
+    },
+    {
+      "epoch": 0.45891472868217054,
+      "grad_norm": 2.1702985763549805,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.3674,
+      "step": 37
+    },
+    {
+      "epoch": 0.47131782945736433,
+      "grad_norm": 3.5106520652770996,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.4877,
+      "step": 38
+    },
+    {
+      "epoch": 0.48372093023255813,
+      "grad_norm": 3.0614447593688965,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.6244,
+      "step": 39
+    },
+    {
+      "epoch": 0.49612403100775193,
+      "grad_norm": 2.051356792449951,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.5893,
+      "step": 40
+    },
+    {
+      "epoch": 0.5085271317829457,
+      "grad_norm": 1.6510694026947021,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.5597,
+      "step": 41
+    },
+    {
+      "epoch": 0.5209302325581395,
+      "grad_norm": 0.8817880749702454,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.5195,
+      "step": 42
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.1567829847335815,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.5009,
+      "step": 43
+    },
+    {
+      "epoch": 0.5457364341085271,
+      "grad_norm": 1.164838433265686,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.5142,
+      "step": 44
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "grad_norm": 2.1000521183013916,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.4716,
+      "step": 45
+    },
+    {
+      "epoch": 0.5705426356589147,
+      "grad_norm": 2.214428424835205,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.4248,
+      "step": 46
+    },
+    {
+      "epoch": 0.5829457364341085,
+      "grad_norm": 1.865970253944397,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.4353,
+      "step": 47
+    },
+    {
+      "epoch": 0.5953488372093023,
+      "grad_norm": 1.5044881105422974,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.4025,
+      "step": 48
+    },
+    {
+      "epoch": 0.6077519379844961,
+      "grad_norm": 1.0346555709838867,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.3396,
+      "step": 49
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "grad_norm": 0.7697737812995911,
+      "learning_rate": 1e-05,
+      "loss": 0.3228,
+      "step": 50
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "eval_loss": 0.46879658102989197,
+      "eval_runtime": 2.075,
+      "eval_samples_per_second": 24.097,
+      "eval_steps_per_second": 6.265,
+      "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