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:e09843e511157a23e837214f33c0a201122a3a43b20853e8220b34cabed42c00
+oid sha256:31523872e165a61bd875d588bea6bd15db21bad48e5fce41b30385bba35de27c
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:759a90d31708007fb32cce87243a832c4ff7009536e3a697927ec239c7b7525e
+oid sha256:fbde5e298775de02d3246efe8a287bdaf76890cff6ff1fed04eadcb1be23d661
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca7d403f3113b680a55e7ebd20d179c199fea5e08658be28ee328c905464010c
+oid sha256:9a5f1d0b2268a4c6afdae4fdfe10dd0e68f2df1c03910205545a58a581b05be2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20b7c6e99e4a978f04b66857889c2492983ad9f4a74070634ab2abdd5f8a5271
+oid sha256:d40929fe7bfcc00fd6706ef92377406a2256102c11fb68078a527c2518eac166
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b887b96dbb7181e7e39e114a153da289fdaaf0e6ebfdebe2d1dfaaf3697dd5ca
+oid sha256:374f13639ec865df682a15d11856c9f472a635b9c7b4f3e06d3402d1de119812
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11a72566f0919f18e9c852918d99dab8401f901289d70b0afb6a208c211ef029
+oid sha256:08963af70c8031b0ed8daa50f74e56d6f5dfea34856cce91661bc4d0fecb964f
 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": 0.11587636917829514,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3225806451612903,
+  "best_metric": 0.05516192317008972,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6451612903225806,
   "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": 11.89,
       "eval_steps_per_second": 3.091,
       "step": 25
+    },
+    {
+      "epoch": 0.33548387096774196,
+      "grad_norm": 0.6196833252906799,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0815,
+      "step": 26
+    },
+    {
+      "epoch": 0.34838709677419355,
+      "grad_norm": 1.389115333557129,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.1802,
+      "step": 27
+    },
+    {
+      "epoch": 0.36129032258064514,
+      "grad_norm": 0.7861359119415283,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0859,
+      "step": 28
+    },
+    {
+      "epoch": 0.3741935483870968,
+      "grad_norm": 0.6421568393707275,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.1309,
+      "step": 29
+    },
+    {
+      "epoch": 0.3870967741935484,
+      "grad_norm": 0.9904139637947083,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.2293,
+      "step": 30
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.9061548709869385,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.1937,
+      "step": 31
+    },
+    {
+      "epoch": 0.4129032258064516,
+      "grad_norm": 1.0943150520324707,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.1755,
+      "step": 32
+    },
+    {
+      "epoch": 0.4258064516129032,
+      "grad_norm": 0.8827422857284546,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.2004,
+      "step": 33
+    },
+    {
+      "epoch": 0.43870967741935485,
+      "grad_norm": 1.2713053226470947,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.1994,
+      "step": 34
+    },
+    {
+      "epoch": 0.45161290322580644,
+      "grad_norm": 1.8664768934249878,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.2095,
+      "step": 35
+    },
+    {
+      "epoch": 0.4645161290322581,
+      "grad_norm": 1.5270920991897583,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.19,
+      "step": 36
+    },
+    {
+      "epoch": 0.4774193548387097,
+      "grad_norm": 2.041300058364868,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.1653,
+      "step": 37
+    },
+    {
+      "epoch": 0.49032258064516127,
+      "grad_norm": 0.4778480529785156,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.1365,
+      "step": 38
+    },
+    {
+      "epoch": 0.5032258064516129,
+      "grad_norm": 0.8028175234794617,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0985,
+      "step": 39
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 0.9442226886749268,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.1129,
+      "step": 40
+    },
+    {
+      "epoch": 0.5290322580645161,
+      "grad_norm": 1.3180819749832153,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.1321,
+      "step": 41
+    },
+    {
+      "epoch": 0.5419354838709678,
+      "grad_norm": 0.7343201041221619,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.1373,
+      "step": 42
+    },
+    {
+      "epoch": 0.5548387096774193,
+      "grad_norm": 1.6494495868682861,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.2925,
+      "step": 43
+    },
+    {
+      "epoch": 0.567741935483871,
+      "grad_norm": 1.4144569635391235,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.2289,
+      "step": 44
+    },
+    {
+      "epoch": 0.5806451612903226,
+      "grad_norm": 0.785733163356781,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.1329,
+      "step": 45
+    },
+    {
+      "epoch": 0.5935483870967742,
+      "grad_norm": 1.2976585626602173,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.2443,
+      "step": 46
+    },
+    {
+      "epoch": 0.6064516129032258,
+      "grad_norm": 1.1602989435195923,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.1924,
+      "step": 47
+    },
+    {
+      "epoch": 0.6193548387096774,
+      "grad_norm": 0.6371066570281982,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.1168,
+      "step": 48
+    },
+    {
+      "epoch": 0.632258064516129,
+      "grad_norm": 0.46553662419319153,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0942,
+      "step": 49
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.7974909543991089,
+      "learning_rate": 1e-05,
+      "loss": 0.1389,
+      "step": 50
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "eval_loss": 0.05516192317008972,
+      "eval_runtime": 4.1583,
+      "eval_samples_per_second": 12.024,
+      "eval_steps_per_second": 3.126,
+      "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": 2.66009604784128e+17,
+  "total_flos": 5.32019209568256e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null