Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:581899f242f604f1c3366551ace3f7d9b40b6f417ca2ce2f939231c18dba699a
+oid sha256:68756d1468f330bf117ccf71660578642f41b024d6d45715d9e923a09ca2b294
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b079b839151ec0ab08318958bafcb6051a94e118b32bc57c8bc316702f697792
+oid sha256:fa0f317d3ea9d3508edd0246e515f2cb8a8d8d0aa2363e96d77cfe0b50179060
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0b3fe63ae2b2fbc32bfd369fe6e7a0e82d11aba44e6a58ab9b7ce60b4b024d
+oid sha256:22ef0b2563c7766bc5aa41721cbcb81a0e86b617c25bf41a226284041e859cbf
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a64f9494bdafb2415524d0ffc768346114ec4b353a09dcf4dfe2f898208da2ac
+oid sha256:ce5a97c445495d0d126187aa87e6953233f8c7bd7e3ddd39dcbe2b61eebfc3f0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fe84818888b345bd9095dc8eaa51715ac135677a2c4edab63184ef2531dd21c
+oid sha256:f3c4cb0cc16e805227e18dc77693e2ffe5950b41f9c14da87429a04abb8a1ff1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a1f496a45edf3e8387fa433ed9c7fca1dd82d37742a033e246f19014cbbec5d
+oid sha256:0d557fb71b09d14815fee2babef2545ceb38573a8f70950db32b1b424b9ab000
 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": 1.844842553138733,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.8869179600886918,
+  "best_metric": 1.8023031949996948,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.7760532150776052,
   "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": 57.26,
       "eval_steps_per_second": 14.888,
       "step": 25
+    },
+    {
+      "epoch": 0.9223946784922394,
+      "grad_norm": 2.189703941345215,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.6794,
+      "step": 26
+    },
+    {
+      "epoch": 0.9578713968957872,
+      "grad_norm": 2.097830295562744,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.7231,
+      "step": 27
+    },
+    {
+      "epoch": 0.9933481152993349,
+      "grad_norm": 2.1691596508026123,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.7862,
+      "step": 28
+    },
+    {
+      "epoch": 1.0310421286031042,
+      "grad_norm": 5.34002685546875,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.0291,
+      "step": 29
+    },
+    {
+      "epoch": 1.0665188470066518,
+      "grad_norm": 1.8050270080566406,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.6163,
+      "step": 30
+    },
+    {
+      "epoch": 1.1019955654101996,
+      "grad_norm": 1.752409815788269,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.5963,
+      "step": 31
+    },
+    {
+      "epoch": 1.1374722838137472,
+      "grad_norm": 1.962044358253479,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.3796,
+      "step": 32
+    },
+    {
+      "epoch": 1.1729490022172948,
+      "grad_norm": 2.2525737285614014,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.5301,
+      "step": 33
+    },
+    {
+      "epoch": 1.2084257206208426,
+      "grad_norm": 1.9950754642486572,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.5008,
+      "step": 34
+    },
+    {
+      "epoch": 1.2439024390243902,
+      "grad_norm": 2.0618607997894287,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.4928,
+      "step": 35
+    },
+    {
+      "epoch": 1.2793791574279378,
+      "grad_norm": 2.0370469093322754,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.4469,
+      "step": 36
+    },
+    {
+      "epoch": 1.3148558758314857,
+      "grad_norm": 2.0353357791900635,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.4729,
+      "step": 37
+    },
+    {
+      "epoch": 1.3503325942350333,
+      "grad_norm": 2.2255871295928955,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.5445,
+      "step": 38
+    },
+    {
+      "epoch": 1.3858093126385809,
+      "grad_norm": 2.0936543941497803,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.5054,
+      "step": 39
+    },
+    {
+      "epoch": 1.4212860310421287,
+      "grad_norm": 2.298006534576416,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.4022,
+      "step": 40
+    },
+    {
+      "epoch": 1.4567627494456763,
+      "grad_norm": 2.1407575607299805,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.426,
+      "step": 41
+    },
+    {
+      "epoch": 1.492239467849224,
+      "grad_norm": 2.340196132659912,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.504,
+      "step": 42
+    },
+    {
+      "epoch": 1.5277161862527717,
+      "grad_norm": 2.015380620956421,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.3684,
+      "step": 43
+    },
+    {
+      "epoch": 1.5631929046563193,
+      "grad_norm": 2.134154796600342,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.5322,
+      "step": 44
+    },
+    {
+      "epoch": 1.598669623059867,
+      "grad_norm": 2.0442440509796143,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.525,
+      "step": 45
+    },
+    {
+      "epoch": 1.6341463414634148,
+      "grad_norm": 1.9398062229156494,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.3588,
+      "step": 46
+    },
+    {
+      "epoch": 1.6696230598669624,
+      "grad_norm": 2.1052966117858887,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.3799,
+      "step": 47
+    },
+    {
+      "epoch": 1.70509977827051,
+      "grad_norm": 2.180793523788452,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.3701,
+      "step": 48
+    },
+    {
+      "epoch": 1.7405764966740578,
+      "grad_norm": 2.127793312072754,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.4814,
+      "step": 49
+    },
+    {
+      "epoch": 1.7760532150776052,
+      "grad_norm": 2.040327548980713,
+      "learning_rate": 1e-05,
+      "loss": 1.3444,
+      "step": 50
+    },
+    {
+      "epoch": 1.7760532150776052,
+      "eval_loss": 1.8023031949996948,
+      "eval_runtime": 0.8606,
+      "eval_samples_per_second": 58.101,
+      "eval_steps_per_second": 15.106,
+      "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": 7.94731890081792e+16,
+  "total_flos": 1.589463780163584e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null