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:a4f57888e4f0eac957ad689128710b9eabec9609cc784402830e38aa0f0816e8
+oid sha256:a7296cb060a0f40745d3e5a769f41fb237908d2bfb5181706c03bb72c78e6f51
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa83f49cbdd390ca22dc4fa2ab5c846b8d6f884259a850caa866ee0dba595dbf
+oid sha256:79a21034a18206a574c694f04045c9d005401ca5738946653c05cf3c314631b6
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2c2f432aa105a4cab1c4ed006d417b0183724b8f5b2f80bfb6dec7887d7042f
+oid sha256:338db0114e853931eea223a995c0b1bda81822d868de7d98536b41f13794732e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:170d47c40c77b3075df78576be29f12b7e8d04c9ad47c29c83e603e1176ac227
+oid sha256:bf93f4b481943684580a19e37bd2a6a721e38c8f7a567ca85ac35700c5903ea6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91a8bd8a0ca964a8cd93c8eca82ca797f1b73999fb201755fe942165b387f675
+oid sha256:dd8eb90b473a25dc4c232fdd12ab44805676efa45778a511c1d2681437ce605d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9a4ff4276df93af24ff73b297b09a65e8da3ce6e6afe9347bc6ae6fa4e612af
+oid sha256:4b28a19403985b8563908f0c1509f3b76977928a4e5ecabd88a8db51e860ddc0
 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": 0.001722008571960032,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03211174888612371,
+  "best_metric": 0.0005954264779575169,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06422349777224742,
   "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": 11.513,
       "eval_steps_per_second": 2.993,
       "step": 25
+    },
+    {
+      "epoch": 0.03339621884156866,
+      "grad_norm": 0.10468930006027222,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0027,
+      "step": 26
+    },
+    {
+      "epoch": 0.03468068879701361,
+      "grad_norm": 0.043511610478162766,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0003,
+      "step": 27
+    },
+    {
+      "epoch": 0.03596515875245856,
+      "grad_norm": 0.047194723039865494,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0004,
+      "step": 28
+    },
+    {
+      "epoch": 0.03724962870790351,
+      "grad_norm": 0.010208461433649063,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0002,
+      "step": 29
+    },
+    {
+      "epoch": 0.038534098663348455,
+      "grad_norm": 0.004359261132776737,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0001,
+      "step": 30
+    },
+    {
+      "epoch": 0.039818568618793404,
+      "grad_norm": 0.004191869869828224,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0001,
+      "step": 31
+    },
+    {
+      "epoch": 0.04110303857423835,
+      "grad_norm": 0.00581542169675231,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0002,
+      "step": 32
+    },
+    {
+      "epoch": 0.042387508529683295,
+      "grad_norm": 0.029106365516781807,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0006,
+      "step": 33
+    },
+    {
+      "epoch": 0.04367197848512824,
+      "grad_norm": 0.012221266515552998,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0001,
+      "step": 34
+    },
+    {
+      "epoch": 0.04495644844057319,
+      "grad_norm": 0.024582967162132263,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0003,
+      "step": 35
+    },
+    {
+      "epoch": 0.04624091839601814,
+      "grad_norm": 0.002639414044097066,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0001,
+      "step": 36
+    },
+    {
+      "epoch": 0.04752538835146309,
+      "grad_norm": 0.006335746496915817,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0001,
+      "step": 37
+    },
+    {
+      "epoch": 0.04880985830690804,
+      "grad_norm": 0.05119847506284714,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0009,
+      "step": 38
+    },
+    {
+      "epoch": 0.05009432826235299,
+      "grad_norm": 0.005954067222774029,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0002,
+      "step": 39
+    },
+    {
+      "epoch": 0.051378798217797936,
+      "grad_norm": 0.018545329570770264,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0004,
+      "step": 40
+    },
+    {
+      "epoch": 0.052663268173242885,
+      "grad_norm": 0.04680047929286957,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0005,
+      "step": 41
+    },
+    {
+      "epoch": 0.05394773812868783,
+      "grad_norm": 0.030956776812672615,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0002,
+      "step": 42
+    },
+    {
+      "epoch": 0.05523220808413278,
+      "grad_norm": 0.029979685321450233,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0009,
+      "step": 43
+    },
+    {
+      "epoch": 0.05651667803957773,
+      "grad_norm": 0.05502396449446678,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0004,
+      "step": 44
+    },
+    {
+      "epoch": 0.05780114799502268,
+      "grad_norm": 0.022603997960686684,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0003,
+      "step": 45
+    },
+    {
+      "epoch": 0.05908561795046763,
+      "grad_norm": 0.06383545696735382,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0017,
+      "step": 46
+    },
+    {
+      "epoch": 0.06037008790591258,
+      "grad_norm": 0.004797203931957483,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0001,
+      "step": 47
+    },
+    {
+      "epoch": 0.061654557861357526,
+      "grad_norm": 0.001430455595254898,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0001,
+      "step": 48
+    },
+    {
+      "epoch": 0.06293902781680247,
+      "grad_norm": 0.0032753057312220335,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0001,
+      "step": 49
+    },
+    {
+      "epoch": 0.06422349777224742,
+      "grad_norm": 0.026153214275836945,
+      "learning_rate": 1e-05,
+      "loss": 0.0006,
+      "step": 50
+    },
+    {
+      "epoch": 0.06422349777224742,
+      "eval_loss": 0.0005954264779575169,
+      "eval_runtime": 4.3372,
+      "eval_samples_per_second": 11.528,
+      "eval_steps_per_second": 2.997,
+      "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": 2.984974321220321e+17,
+  "total_flos": 5.969016129878753e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null