Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200ef5d323e59135bbf832076d8c7508b0af76aa78e38a5c2b5079e42eff36c2
+oid sha256:1f3a4831bfcfcbfc0cce15ba02e6f32520dfbd34e929c62c67aba86e10e2bd08
 size 100690288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9270b2bcfce8043f1f5d22a53f303afa6b207f874299f10e0ecd2c2b4dbce4ac
+oid sha256:166c9202a4064b80029c6b151d68f66ff9f86d9decc779f783ca8fdcd5536f27
 size 201488570

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80466024ada000ef6a0dfea079e9f08fa5da78f23ff291e3483c580dcb5dd1e8
+oid sha256:1a56b241f3b8fc13feed6af9e00d13b2196416be637b8638b59def607b488f43
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6466e3f3a56124cb9b946832131a16522d0d8f7879ac7bd474320c462ff766dc
+oid sha256:88379e490d72a4f7aa7c2db51865fe027a8641f8f4c3f2fcb3030d1bacbc1789
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53b55ed0a640eead5a9dabc92fa4b6fde43c10ab948aaa36087ff5cc10cb347b
+oid sha256:23826a14db2c82499d87267b22cd460c0673813dfaa5219cf6405064acbac8f8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cb9f778935ab33c0e1ad69872f41fd7a6719dfeae70dd45a3ea25a89ccbc6bf
+oid sha256:4e500e27c3906b27948a9536b1effa7ee899755ba0d849a3b021db9f8664c8cb
 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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05395926075812761,
+  "epoch": 0.10791852151625522,
   "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": 31.9,
       "eval_steps_per_second": 8.294,
       "step": 25
+    },
+    {
+      "epoch": 0.05611763118845272,
+      "grad_norm": 0.0,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.05827600161877782,
+      "grad_norm": 0.0,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.06043437204910293,
+      "grad_norm": 0.0,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.06259274247942803,
+      "grad_norm": 0.00033452859497629106,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0455,
+      "step": 29
+    },
+    {
+      "epoch": 0.06475111290975313,
+      "grad_norm": 0.0,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.06690948334007824,
+      "grad_norm": 0.3195914924144745,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0495,
+      "step": 31
+    },
+    {
+      "epoch": 0.06906785377040335,
+      "grad_norm": 18.950136184692383,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.3005,
+      "step": 32
+    },
+    {
+      "epoch": 0.07122622420072845,
+      "grad_norm": 18.768531799316406,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 51.4499,
+      "step": 33
+    },
+    {
+      "epoch": 0.07338459463105355,
+      "grad_norm": 5.757758617401123,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.353,
+      "step": 34
+    },
+    {
+      "epoch": 0.07554296506137866,
+      "grad_norm": 3.475687026977539,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.1307,
+      "step": 35
+    },
+    {
+      "epoch": 0.07770133549170376,
+      "grad_norm": 4.415914535522461,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.2457,
+      "step": 36
+    },
+    {
+      "epoch": 0.07985970592202887,
+      "grad_norm": 3.654486656188965,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.1651,
+      "step": 37
+    },
+    {
+      "epoch": 0.08201807635235397,
+      "grad_norm": 2.106903553009033,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 16.0562,
+      "step": 38
+    },
+    {
+      "epoch": 0.08417644678267908,
+      "grad_norm": 0.0,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.08633481721300418,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.08849318764332928,
+      "grad_norm": 0.0,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.0906515580736544,
+      "grad_norm": 0.7044157385826111,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 44.9168,
+      "step": 42
+    },
+    {
+      "epoch": 0.0928099285039795,
+      "grad_norm": 0.026013152673840523,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0082,
+      "step": 43
+    },
+    {
+      "epoch": 0.0949682989343046,
+      "grad_norm": 0.19379185140132904,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0175,
+      "step": 44
+    },
+    {
+      "epoch": 0.0971266693646297,
+      "grad_norm": 1.7980287075042725,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 5.6403,
+      "step": 45
+    },
+    {
+      "epoch": 0.09928503979495482,
+      "grad_norm": 4.9771246910095215,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 23.1134,
+      "step": 46
+    },
+    {
+      "epoch": 0.10144341022527992,
+      "grad_norm": 2.0049068927764893,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.1428,
+      "step": 47
+    },
+    {
+      "epoch": 0.10360178065560502,
+      "grad_norm": 4.939352512359619,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.139,
+      "step": 48
+    },
+    {
+      "epoch": 0.10576015108593012,
+      "grad_norm": 0.6309598088264465,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0207,
+      "step": 49
+    },
+    {
+      "epoch": 0.10791852151625522,
+      "grad_norm": 2.4616317749023438,
+      "learning_rate": 1e-05,
+      "loss": 0.1247,
+      "step": 50
+    },
+    {
+      "epoch": 0.10791852151625522,
+      "eval_loss": NaN,
+      "eval_runtime": 1.5575,
+      "eval_samples_per_second": 32.103,
+      "eval_steps_per_second": 8.347,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.857439165874176e+16,
+  "total_flos": 9.708814106361856e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null