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:e1b8b8ef43bf4f675d592e402697f3673b82772a6eb253d32dc27e148ee48b57
+oid sha256:17f17dbd10baeb951791278b0717ea24f9618864384a6216d4f33925fce22f57
 size 100690288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4995cfea8b1559ab7c3b0b63772f878c18208b905a3a816574b8447f4ff8a43d
+oid sha256:c0ed8848f86fa1508c21e7b4f92f8a6bce9e0b8de5b2f3276a8c20233f4afbc3
 size 201488570

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e7e8c65cb0d28f9883b5cd77a66c1c8771950f93c2e3ebaf375e38381e22beb
+oid sha256:d77c756c08c99b642474269395a33a1b71b445de4d889da41682529298a31265
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e7a6ee10c4f4085be4e969a0a85cf5e18512bf874eeb351de059068da7ca5cf
+oid sha256:2efc19d60950ee137d2e00603ebf1f4576e440185198e67fef46735bd9f065a0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:474360a4e0f48f218d086b48422126d05da499608b545cb8e6ad19e2a1b25c1e
+oid sha256:3587d3902d4e4bdc57a52767b102a7d1faa7d889c03f17ea0f0e9b8b611ab2a6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c2d946f36f0d67f325843e30b945cf3237bda99fd1dedc11cc0a8d70e18e9a0
+oid sha256:9f03fb68b88b6a72f21a54569061d42496975f4ddec5394a31e1e8f8ebc5cffd
 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": 1.3633499145507812,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03281378178835111,
+  "best_metric": 1.0918526649475098,
+  "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": 19.802,
       "eval_steps_per_second": 5.149,
       "step": 25
+    },
+    {
+      "epoch": 0.034126333059885154,
+      "grad_norm": 27.724285125732422,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 18.6064,
+      "step": 26
+    },
+    {
+      "epoch": 0.035438884331419195,
+      "grad_norm": 30.41544532775879,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 18.2207,
+      "step": 27
+    },
+    {
+      "epoch": 0.03675143560295324,
+      "grad_norm": 21.56080436706543,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 15.5897,
+      "step": 28
+    },
+    {
+      "epoch": 0.03806398687448728,
+      "grad_norm": 25.616636276245117,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 16.9239,
+      "step": 29
+    },
+    {
+      "epoch": 0.03937653814602133,
+      "grad_norm": 24.559080123901367,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 16.3541,
+      "step": 30
+    },
+    {
+      "epoch": 0.04068908941755537,
+      "grad_norm": 24.85494041442871,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 16.8927,
+      "step": 31
+    },
+    {
+      "epoch": 0.04200164068908942,
+      "grad_norm": 19.774295806884766,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 14.4716,
+      "step": 32
+    },
+    {
+      "epoch": 0.043314191960623465,
+      "grad_norm": 24.674156188964844,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 16.114,
+      "step": 33
+    },
+    {
+      "epoch": 0.044626743232157505,
+      "grad_norm": 25.642627716064453,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 15.6742,
+      "step": 34
+    },
+    {
+      "epoch": 0.04593929450369155,
+      "grad_norm": 29.65949058532715,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 18.0492,
+      "step": 35
+    },
+    {
+      "epoch": 0.04725184577522559,
+      "grad_norm": 27.748992919921875,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 16.1016,
+      "step": 36
+    },
+    {
+      "epoch": 0.04856439704675964,
+      "grad_norm": 38.540897369384766,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 20.7696,
+      "step": 37
+    },
+    {
+      "epoch": 0.04987694831829368,
+      "grad_norm": 31.065410614013672,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 18.9581,
+      "step": 38
+    },
+    {
+      "epoch": 0.05118949958982773,
+      "grad_norm": 27.85570526123047,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 16.0154,
+      "step": 39
+    },
+    {
+      "epoch": 0.052502050861361775,
+      "grad_norm": 26.385791778564453,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 14.5608,
+      "step": 40
+    },
+    {
+      "epoch": 0.053814602132895815,
+      "grad_norm": 22.490495681762695,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 13.9427,
+      "step": 41
+    },
+    {
+      "epoch": 0.05512715340442986,
+      "grad_norm": 27.185117721557617,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 15.745,
+      "step": 42
+    },
+    {
+      "epoch": 0.0564397046759639,
+      "grad_norm": 24.99716567993164,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 13.7456,
+      "step": 43
+    },
+    {
+      "epoch": 0.05775225594749795,
+      "grad_norm": 22.399248123168945,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 12.8401,
+      "step": 44
+    },
+    {
+      "epoch": 0.05906480721903199,
+      "grad_norm": 23.183446884155273,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 15.7644,
+      "step": 45
+    },
+    {
+      "epoch": 0.06037735849056604,
+      "grad_norm": 29.278457641601562,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 16.1645,
+      "step": 46
+    },
+    {
+      "epoch": 0.06168990976210008,
+      "grad_norm": 26.757448196411133,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 13.7631,
+      "step": 47
+    },
+    {
+      "epoch": 0.06300246103363413,
+      "grad_norm": 27.09531593322754,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 15.2399,
+      "step": 48
+    },
+    {
+      "epoch": 0.06431501230516817,
+      "grad_norm": 27.507986068725586,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 16.0252,
+      "step": 49
+    },
+    {
+      "epoch": 0.06562756357670221,
+      "grad_norm": 31.12259292602539,
+      "learning_rate": 1e-05,
+      "loss": 17.0739,
+      "step": 50
+    },
+    {
+      "epoch": 0.06562756357670221,
+      "eval_loss": 1.0918526649475098,
+      "eval_runtime": 2.5035,
+      "eval_samples_per_second": 19.972,
+      "eval_steps_per_second": 5.193,
+      "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": 4.85137494048768e+16,
+  "total_flos": 9.70274988097536e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null