Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e9b98b4d99c3f1be9928ee61005f19c7dc7ecb5756d9ec788e6286d8575399d
+oid sha256:c9ea0f7e639ed419acad8a70c7fd1d334865e8b1b23fabe75b636dd546b6b4fe
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1031149535b5f577d65db45130dd61d9b5c5af2253135ba216a0b40c1594f2e4
+oid sha256:cfcb5b7d33cf500e24aad580d0cec6eb3ef1d76bfa02a0dcfb1a1c3a459898c6
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:650eb51a3a3c34eca0a5d672228c41080481f9f379d19d971aa128f5a96629a7
+oid sha256:75c38b3a69274a6c4f8e6cafbb8cf7d118170f65773be5d69d13572646c29cd3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a528a30c2cafa90036c14c114f18bc4d24ec3d75409e48f1d26a9014e6445d7f
+oid sha256:f6f67716407b0e17a16a75d68ada7d88c6816238b0c32e7609b4edfe410d713c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:627b063c6be9328188b95d87d1582e55762f2d1255928e1b87694d21f2bac586
+oid sha256:b0c6ce806e48ad49aae708cd20ac28bf1f15fd08d0ea7fede1d18dd9ffaa9b3b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3bb65f6664fb56047c6a097e3146e78dd773519ab9f1310c514b5fa285cf183
+oid sha256:ea2ba508aa26dad5938b0d7d9640539fac36d32ad47294243b707cc21d6dc2da
 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": 1.2017804384231567,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5818181818181818,
+  "best_metric": 1.1560208797454834,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.1658181818181819,
   "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": 12.351,
       "eval_steps_per_second": 3.211,
       "step": 25
+    },
+    {
+      "epoch": 0.6050909090909091,
+      "grad_norm": 0.36338701844215393,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.1141,
+      "step": 26
+    },
+    {
+      "epoch": 0.6283636363636363,
+      "grad_norm": 0.367141991853714,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.1142,
+      "step": 27
+    },
+    {
+      "epoch": 0.6516363636363637,
+      "grad_norm": 0.3999696373939514,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.1136,
+      "step": 28
+    },
+    {
+      "epoch": 0.6749090909090909,
+      "grad_norm": 0.39164677262306213,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.1816,
+      "step": 29
+    },
+    {
+      "epoch": 0.6981818181818182,
+      "grad_norm": 0.45403310656547546,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.2989,
+      "step": 30
+    },
+    {
+      "epoch": 0.7214545454545455,
+      "grad_norm": 0.5455201864242554,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.3082,
+      "step": 31
+    },
+    {
+      "epoch": 0.7447272727272727,
+      "grad_norm": 0.3580777645111084,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.2199,
+      "step": 32
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.38596412539482117,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.2403,
+      "step": 33
+    },
+    {
+      "epoch": 0.7912727272727272,
+      "grad_norm": 0.3120631277561188,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.1839,
+      "step": 34
+    },
+    {
+      "epoch": 0.8145454545454546,
+      "grad_norm": 0.3093988001346588,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.1151,
+      "step": 35
+    },
+    {
+      "epoch": 0.8378181818181818,
+      "grad_norm": 0.2600014805793762,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.1773,
+      "step": 36
+    },
+    {
+      "epoch": 0.8610909090909091,
+      "grad_norm": 0.27386701107025146,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.0633,
+      "step": 37
+    },
+    {
+      "epoch": 0.8843636363636364,
+      "grad_norm": 0.2746947407722473,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.0732,
+      "step": 38
+    },
+    {
+      "epoch": 0.9076363636363637,
+      "grad_norm": 0.28902333974838257,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.117,
+      "step": 39
+    },
+    {
+      "epoch": 0.9309090909090909,
+      "grad_norm": 0.3158881962299347,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.2144,
+      "step": 40
+    },
+    {
+      "epoch": 0.9541818181818181,
+      "grad_norm": 0.3764362931251526,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.3209,
+      "step": 41
+    },
+    {
+      "epoch": 0.9774545454545455,
+      "grad_norm": 0.5556831359863281,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.3623,
+      "step": 42
+    },
+    {
+      "epoch": 1.002909090909091,
+      "grad_norm": 0.31221914291381836,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.2963,
+      "step": 43
+    },
+    {
+      "epoch": 1.026181818181818,
+      "grad_norm": 0.35975971817970276,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.1284,
+      "step": 44
+    },
+    {
+      "epoch": 1.0494545454545454,
+      "grad_norm": 0.28899094462394714,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.1973,
+      "step": 45
+    },
+    {
+      "epoch": 1.0727272727272728,
+      "grad_norm": 0.25856634974479675,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.1399,
+      "step": 46
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.248923197388649,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.0896,
+      "step": 47
+    },
+    {
+      "epoch": 1.1192727272727272,
+      "grad_norm": 0.25821453332901,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.0757,
+      "step": 48
+    },
+    {
+      "epoch": 1.1425454545454545,
+      "grad_norm": 0.26640933752059937,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.0786,
+      "step": 49
+    },
+    {
+      "epoch": 1.1658181818181819,
+      "grad_norm": 0.30744296312332153,
+      "learning_rate": 1e-05,
+      "loss": 1.1057,
+      "step": 50
+    },
+    {
+      "epoch": 1.1658181818181819,
+      "eval_loss": 1.1560208797454834,
+      "eval_runtime": 3.9511,
+      "eval_samples_per_second": 12.655,
+      "eval_steps_per_second": 3.29,
+      "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": 1.62480894509056e+17,
+  "total_flos": 3.24961789018112e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null