Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f473ef6734a38314b81e5592263fe0a0af4c7a79549a1a0390c6b369b7f6fe4
+oid sha256:9f2748fa899242a40131ec0e7097f32b1e3413ab551a296cd1cc1be6fba2b075
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06793fadc758d8db962737be2de7de862bd72120ab3feca924dfb8dbb0aa20db
+oid sha256:f716e662cbb3dc7ecc25b3bb824888e2789b9b9c28e05e3053e5036c89ab6066
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:362168cfbfb5995c026c378295358eb33d43e912aea86c60390765419b6ab4b2
+oid sha256:0ed7805ad8c402a11622c3526fac59da57d8830b31b1ff7bd7646002cd099481
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d767c525b8032e2e40e4af8757e52c33f8b34e5ea6340bbdd052a4aec2790e0
+oid sha256:0e427f63e93180be13fac369dae2eb46b81dc6ab64b4a588b091a06f480c4f57
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1708dc82a0e99b103dc3872f8e6611db476b86d45570eead1d14efcf46f3b862
+oid sha256:e5b601fbc99ba67955295dc13446f3b94a79638687335afe1d0f550b4a4b3cd7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d824f6963245724777c16f2d6d707b7dfc3d184321ff3429193ffd02d3a324e7
+oid sha256:0b315deac2a4155a6829da73746db49c735976799f638701ffe6b268cf56d001
 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": 6.8990583419799805,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11253340835560557,
+  "best_metric": 6.884387969970703,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.22506681671121115,
   "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": 305.639,
       "eval_steps_per_second": 79.466,
       "step": 25
+    },
+    {
+      "epoch": 0.11703474468982979,
+      "grad_norm": 0.3027767539024353,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 6.9021,
+      "step": 26
+    },
+    {
+      "epoch": 0.12153608102405401,
+      "grad_norm": 0.2898428738117218,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 6.8995,
+      "step": 27
+    },
+    {
+      "epoch": 0.12603741735827823,
+      "grad_norm": 0.27990737557411194,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 6.9008,
+      "step": 28
+    },
+    {
+      "epoch": 0.13053875369250245,
+      "grad_norm": 0.29302507638931274,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 6.8963,
+      "step": 29
+    },
+    {
+      "epoch": 0.13504009002672668,
+      "grad_norm": 0.2960253655910492,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 6.8934,
+      "step": 30
+    },
+    {
+      "epoch": 0.1395414263609509,
+      "grad_norm": 0.2894373834133148,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 6.8945,
+      "step": 31
+    },
+    {
+      "epoch": 0.14404276269517513,
+      "grad_norm": 0.29182955622673035,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 6.8926,
+      "step": 32
+    },
+    {
+      "epoch": 0.14854409902939936,
+      "grad_norm": 0.29192373156547546,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 6.8918,
+      "step": 33
+    },
+    {
+      "epoch": 0.15304543536362358,
+      "grad_norm": 0.2958221733570099,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 6.89,
+      "step": 34
+    },
+    {
+      "epoch": 0.1575467716978478,
+      "grad_norm": 0.29976916313171387,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 6.8893,
+      "step": 35
+    },
+    {
+      "epoch": 0.162048108032072,
+      "grad_norm": 0.28821298480033875,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 6.8906,
+      "step": 36
+    },
+    {
+      "epoch": 0.16654944436629623,
+      "grad_norm": 0.32392418384552,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 6.885,
+      "step": 37
+    },
+    {
+      "epoch": 0.17105078070052046,
+      "grad_norm": 0.31561553478240967,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 6.89,
+      "step": 38
+    },
+    {
+      "epoch": 0.1755521170347447,
+      "grad_norm": 0.2910025417804718,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 6.8909,
+      "step": 39
+    },
+    {
+      "epoch": 0.1800534533689689,
+      "grad_norm": 0.28736042976379395,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 6.8916,
+      "step": 40
+    },
+    {
+      "epoch": 0.18455478970319314,
+      "grad_norm": 0.29170575737953186,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 6.8888,
+      "step": 41
+    },
+    {
+      "epoch": 0.18905612603741737,
+      "grad_norm": 0.2956409752368927,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 6.8871,
+      "step": 42
+    },
+    {
+      "epoch": 0.1935574623716416,
+      "grad_norm": 0.3005565106868744,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 6.8849,
+      "step": 43
+    },
+    {
+      "epoch": 0.1980587987058658,
+      "grad_norm": 0.29543253779411316,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 6.8857,
+      "step": 44
+    },
+    {
+      "epoch": 0.20256013504009002,
+      "grad_norm": 0.288479208946228,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 6.8869,
+      "step": 45
+    },
+    {
+      "epoch": 0.20706147137431424,
+      "grad_norm": 0.2988308072090149,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 6.8835,
+      "step": 46
+    },
+    {
+      "epoch": 0.21156280770853847,
+      "grad_norm": 0.29880666732788086,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 6.883,
+      "step": 47
+    },
+    {
+      "epoch": 0.2160641440427627,
+      "grad_norm": 0.29033946990966797,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 6.8861,
+      "step": 48
+    },
+    {
+      "epoch": 0.22056548037698692,
+      "grad_norm": 0.2861062288284302,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 6.8875,
+      "step": 49
+    },
+    {
+      "epoch": 0.22506681671121115,
+      "grad_norm": 0.3452097773551941,
+      "learning_rate": 1e-05,
+      "loss": 6.8749,
+      "step": 50
+    },
+    {
+      "epoch": 0.22506681671121115,
+      "eval_loss": 6.884387969970703,
+      "eval_runtime": 0.1671,
+      "eval_samples_per_second": 299.175,
+      "eval_steps_per_second": 77.785,
+      "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": 5705957376000.0,
+  "total_flos": 11411914752000.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null