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:c25c6ea3666ced915d59476e74a618ef5522069151bf2173348717db6c54ce65
+oid sha256:14ed8a74034ad6689e66af5cbf66eb850bbe18af8f8bdf51ed726c4027c92a45
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8dfcd5d2dcc8144b7dddcfd1b7e03ed44870908a2e8e3c944de2e7db1db1889
+oid sha256:2b23f04aa9c85f0a14eeb738a47524c80a306cc62bef77a458ca21c9353711f7
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27190d622c9fe852b3e0e7f7f84f2df04ce3b240eeb5e57a0e188c5333677cde
+oid sha256:e9e2b415b7cb5cdf6f33bbbdd93faddc002cc10f928489ce5899b33c7e6196e9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81c1a4908e71477ea7ee7b1df4c2d43489337cf160f827169aeb769f9f550f98
+oid sha256:5ac7496cc7a4e059a8df2de6ba3a72c7b46b1b88c55027e2e2923f4f1279c89d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94dda9d6458b34ad0de4791bd25f8edc87c535bc3db41b1e25c554badb29628a
+oid sha256:aa1b7c85f2e458eddf363733b7e98c73083ec0e079087730181c3f43f7e0e66a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e1b2cec8c36c468f760a9e7cf40c72962a51ea2d2a7935d648e49dd90b370f6
+oid sha256:230866a23bdbc1942a6629a4b94ae8d98960a8cfad9f7a0f1fa59713abf456b9
 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": 4.371005957182206e-08,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.084010840108401,
+  "best_metric": 1.2715656083628346e-08,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.168021680216802,
   "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": 16.476,
       "eval_steps_per_second": 4.284,
       "step": 25
+    },
+    {
+      "epoch": 1.127371273712737,
+      "grad_norm": 0.00014739223115611821,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.170731707317073,
+      "grad_norm": 0.00013095480971969664,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.2140921409214092,
+      "grad_norm": 8.817133493721485e-05,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.2574525745257452,
+      "grad_norm": 0.0008000514935702085,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.3008130081300813,
+      "grad_norm": 0.0004873626457992941,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.3441734417344173,
+      "grad_norm": 7.253765943460166e-05,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 1.3875338753387534,
+      "grad_norm": 5.642367614200339e-05,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 1.4308943089430894,
+      "grad_norm": 0.00024370582832489163,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 1.4742547425474255,
+      "grad_norm": 0.0003627138212323189,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 1.5176151761517616,
+      "grad_norm": 0.0016840276075527072,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 1.5609756097560976,
+      "grad_norm": 0.00012992291885893792,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 1.6043360433604335,
+      "grad_norm": 3.316146103315987e-05,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 1.6476964769647697,
+      "grad_norm": 0.000102144134871196,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 1.6910569105691056,
+      "grad_norm": 0.00013834628043696284,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 1.7344173441734418,
+      "grad_norm": 0.0001972516329260543,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.0009772982448339462,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 1.821138211382114,
+      "grad_norm": 0.00010596256470307708,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 1.8644986449864498,
+      "grad_norm": 3.764119173865765e-05,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 1.907859078590786,
+      "grad_norm": 9.031497029354796e-05,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 1.951219512195122,
+      "grad_norm": 0.00020561007841024548,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 1.994579945799458,
+      "grad_norm": 0.0001520053920103237,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 2.037940379403794,
+      "grad_norm": 0.00019084154337178916,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 2.08130081300813,
+      "grad_norm": 5.529891495825723e-05,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 2.124661246612466,
+      "grad_norm": 2.304013651155401e-05,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 2.168021680216802,
+      "grad_norm": 7.780615851515904e-05,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 2.168021680216802,
+      "eval_loss": 1.2715656083628346e-08,
+      "eval_runtime": 3.0875,
+      "eval_samples_per_second": 16.194,
+      "eval_steps_per_second": 4.211,
+      "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": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null