Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18301c74ba4a8ed1e44389447f1ec27dce784e9f124f8c94158688961f54cf0e
+oid sha256:25e7e9399880afb6c91b6b1bf05bd30ab018bf1beacbc9a284cf4f01eb5a1a5c
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ea8de46df7e110598d0c0ae77239a2fead513d05a185d2f4f21b402963b69bc
+oid sha256:2c66115ded7e22e2c7846360be02f824c807af9c79141211c73c602f72c3b6c0
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f259c521ac09e9089b430c37d5d4e7e22ce75b61f7a7cc925fd4e287165fcfe9
+oid sha256:9d9995b4f14e20f17b93642ca7897465fc555d2a0c2c1cd9d40e2737c70f1e04
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f21d579073e2c98789a432bfaf7f542ef538c02fe240bb780ef40cb6e0a94502
+oid sha256:1feb5934b28264a04faa8f87ec55b7ab2e90346a9db95efa06bf03aca87a8dcc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2111404e74abd4d0fc87200c15ce42898f6c59d6ba1d06ad4a293c7765d4c1ee
+oid sha256:2031f15284dd1163ef22c39a2cb0a08fd6e6a519c6dc8c5b68224ab5282bba5a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f76c7b3dc7686a495a85172690887a99a28beb6f824671d12f577cffd80703f
+oid sha256:b028c64004f09b2073fffe1f806560ea6824ffcb6957d23f47ba0f2b34e70727
 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": 11.914083480834961,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.10902153175252112,
+  "best_metric": 11.910526275634766,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.21804306350504224,
   "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": 189.049,
       "eval_steps_per_second": 49.153,
       "step": 25
+    },
+    {
+      "epoch": 0.11338239302262197,
+      "grad_norm": 0.1174607127904892,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9126,
+      "step": 26
+    },
+    {
+      "epoch": 0.11774325429272281,
+      "grad_norm": 0.11482725292444229,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.9119,
+      "step": 27
+    },
+    {
+      "epoch": 0.12210411556282366,
+      "grad_norm": 0.11343596875667572,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9197,
+      "step": 28
+    },
+    {
+      "epoch": 0.1264649768329245,
+      "grad_norm": 0.11668799072504044,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.9139,
+      "step": 29
+    },
+    {
+      "epoch": 0.13082583810302534,
+      "grad_norm": 0.12418890744447708,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.915,
+      "step": 30
+    },
+    {
+      "epoch": 0.1351866993731262,
+      "grad_norm": 0.1196955218911171,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.9202,
+      "step": 31
+    },
+    {
+      "epoch": 0.13954756064322704,
+      "grad_norm": 0.12244880199432373,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.9153,
+      "step": 32
+    },
+    {
+      "epoch": 0.1439084219133279,
+      "grad_norm": 0.12886793911457062,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.9183,
+      "step": 33
+    },
+    {
+      "epoch": 0.14826928318342872,
+      "grad_norm": 0.13539661467075348,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.9169,
+      "step": 34
+    },
+    {
+      "epoch": 0.15263014445352957,
+      "grad_norm": 0.12643979489803314,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.9173,
+      "step": 35
+    },
+    {
+      "epoch": 0.15699100572363042,
+      "grad_norm": 0.15959049761295319,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.915,
+      "step": 36
+    },
+    {
+      "epoch": 0.16135186699373127,
+      "grad_norm": 0.16403581202030182,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.9144,
+      "step": 37
+    },
+    {
+      "epoch": 0.1657127282638321,
+      "grad_norm": 0.17608655989170074,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.909,
+      "step": 38
+    },
+    {
+      "epoch": 0.17007358953393295,
+      "grad_norm": 0.13675826787948608,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.9135,
+      "step": 39
+    },
+    {
+      "epoch": 0.1744344508040338,
+      "grad_norm": 0.13929931819438934,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.9144,
+      "step": 40
+    },
+    {
+      "epoch": 0.17879531207413465,
+      "grad_norm": 0.13613401353359222,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.9147,
+      "step": 41
+    },
+    {
+      "epoch": 0.18315617334423548,
+      "grad_norm": 0.13010174036026,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.9169,
+      "step": 42
+    },
+    {
+      "epoch": 0.18751703461433633,
+      "grad_norm": 0.12880177795886993,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.9154,
+      "step": 43
+    },
+    {
+      "epoch": 0.19187789588443718,
+      "grad_norm": 0.14026358723640442,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.9142,
+      "step": 44
+    },
+    {
+      "epoch": 0.19623875715453803,
+      "grad_norm": 0.14814183115959167,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.9181,
+      "step": 45
+    },
+    {
+      "epoch": 0.20059961842463886,
+      "grad_norm": 0.13746632635593414,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.9112,
+      "step": 46
+    },
+    {
+      "epoch": 0.2049604796947397,
+      "grad_norm": 0.13578639924526215,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.9114,
+      "step": 47
+    },
+    {
+      "epoch": 0.20932134096484056,
+      "grad_norm": 0.157059907913208,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9092,
+      "step": 48
+    },
+    {
+      "epoch": 0.2136822022349414,
+      "grad_norm": 0.14988134801387787,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.9142,
+      "step": 49
+    },
+    {
+      "epoch": 0.21804306350504224,
+      "grad_norm": 0.24737708270549774,
+      "learning_rate": 1e-05,
+      "loss": 11.9087,
+      "step": 50
+    },
+    {
+      "epoch": 0.21804306350504224,
+      "eval_loss": 11.910526275634766,
+      "eval_runtime": 0.2494,
+      "eval_samples_per_second": 200.488,
+      "eval_steps_per_second": 52.127,
+      "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": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null