Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46caf7259e53977abd1c588f6f4216cf337df76b1b24bb8d3f43664ca6be7453
+oid sha256:3d446a3d88288e1c16467b330855e717cd42bac4d9a6f11761c69284cbc3c7bc
 size 1204200

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b989e222b77abf8aeea2ee6e4a083a1e61f0ca0a3cd7a6a610a265e24affd2b2
+oid sha256:54f8f0a9cad779525b6e21d54c95d31b3e47f3f7cf233ceb4d36203597cca505
 size 2558458

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44c4df4d79f928f8e28b8f5033445329240b13f7d3b90e65ed9afe9b63ae3e56
+oid sha256:a6444f0ab7d4268cef97dbb5605fd06fef24388c09f7a3bd4493c7fdcd3041e3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3282917c39ecf688c5b8137f72408f05f4ffd8cf9e451a66895eb3f4bdfd29f4
+oid sha256:93e1573aee1aedb01b1b4f1724c17a23af3812b67c6bd8b99b1721fdf8be74a4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af81538315897c59ae40f6ebd0607b74dcf71f489a0c782c979faee5b2317ae1
+oid sha256:dd5dba02eb8a86bba7b61b49fd64ec2e4232b3bd17e924fbb97d0849e7d4f913
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfab3f5e270ec4a164cccb7d18177932ea5d5b51ad35f5715e0c48ea2a03b1c2
+oid sha256:639f3f15745cb679e89ca580cb0b6076b50c9396e80422bab61b3c47abb1498e
 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": 11.84626579284668,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.015285261186900531,
+  "best_metric": 11.78856086730957,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.030570522373801062,
   "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": 121.824,
       "eval_steps_per_second": 31.674,
       "step": 25
+    },
+    {
+      "epoch": 0.015896671634376552,
+      "grad_norm": 1.0381468534469604,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.8257,
+      "step": 26
+    },
+    {
+      "epoch": 0.016508082081852574,
+      "grad_norm": 1.0195188522338867,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.83,
+      "step": 27
+    },
+    {
+      "epoch": 0.017119492529328595,
+      "grad_norm": 0.9643056988716125,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.8431,
+      "step": 28
+    },
+    {
+      "epoch": 0.017730902976804616,
+      "grad_norm": 1.0708613395690918,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.825,
+      "step": 29
+    },
+    {
+      "epoch": 0.018342313424280637,
+      "grad_norm": 1.0276070833206177,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.8184,
+      "step": 30
+    },
+    {
+      "epoch": 0.01895372387175666,
+      "grad_norm": 1.0994272232055664,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.8147,
+      "step": 31
+    },
+    {
+      "epoch": 0.01956513431923268,
+      "grad_norm": 0.9396828413009644,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.826,
+      "step": 32
+    },
+    {
+      "epoch": 0.0201765447667087,
+      "grad_norm": 0.9694439172744751,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.8297,
+      "step": 33
+    },
+    {
+      "epoch": 0.020787955214184722,
+      "grad_norm": 0.9245437383651733,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.8114,
+      "step": 34
+    },
+    {
+      "epoch": 0.021399365661660744,
+      "grad_norm": 0.9220021963119507,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.8323,
+      "step": 35
+    },
+    {
+      "epoch": 0.022010776109136765,
+      "grad_norm": 0.8308857083320618,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.8241,
+      "step": 36
+    },
+    {
+      "epoch": 0.022622186556612786,
+      "grad_norm": 0.7949393391609192,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.8212,
+      "step": 37
+    },
+    {
+      "epoch": 0.023233597004088807,
+      "grad_norm": 0.9715374708175659,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.8181,
+      "step": 38
+    },
+    {
+      "epoch": 0.02384500745156483,
+      "grad_norm": 1.1757375001907349,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.7921,
+      "step": 39
+    },
+    {
+      "epoch": 0.02445641789904085,
+      "grad_norm": 1.150641918182373,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.7825,
+      "step": 40
+    },
+    {
+      "epoch": 0.02506782834651687,
+      "grad_norm": 1.1286689043045044,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.7744,
+      "step": 41
+    },
+    {
+      "epoch": 0.025679238793992892,
+      "grad_norm": 1.1655857563018799,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.7883,
+      "step": 42
+    },
+    {
+      "epoch": 0.026290649241468914,
+      "grad_norm": 1.061267375946045,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.7839,
+      "step": 43
+    },
+    {
+      "epoch": 0.026902059688944935,
+      "grad_norm": 1.07465398311615,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.7809,
+      "step": 44
+    },
+    {
+      "epoch": 0.027513470136420956,
+      "grad_norm": 0.8791579604148865,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.7932,
+      "step": 45
+    },
+    {
+      "epoch": 0.028124880583896977,
+      "grad_norm": 0.9649653434753418,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.7967,
+      "step": 46
+    },
+    {
+      "epoch": 0.028736291031373,
+      "grad_norm": 0.9733188152313232,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.8088,
+      "step": 47
+    },
+    {
+      "epoch": 0.02934770147884902,
+      "grad_norm": 0.9870716333389282,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.7881,
+      "step": 48
+    },
+    {
+      "epoch": 0.02995911192632504,
+      "grad_norm": 0.9717673063278198,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.7964,
+      "step": 49
+    },
+    {
+      "epoch": 0.030570522373801062,
+      "grad_norm": 0.969845175743103,
+      "learning_rate": 1e-05,
+      "loss": 11.8003,
+      "step": 50
+    },
+    {
+      "epoch": 0.030570522373801062,
+      "eval_loss": 11.78856086730957,
+      "eval_runtime": 0.4053,
+      "eval_samples_per_second": 123.369,
+      "eval_steps_per_second": 32.076,
+      "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": 208867531161600.0,
+  "total_flos": 417735062323200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null