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:ea2dbf3f4b251f51f913be0e4bd70106e172c22c9c69c43f372351cba77c1ff0
+oid sha256:f5d34fa3fb7c89fe8af1e14f3994ad1abf221bff1d28ee5f0f861ac5ef8111bd
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8efdb8a9d7f8011cc9309dd5aa5d8bb1f799196504a3ef73c95a8b3a69465fd
+oid sha256:ee6bd336ae99a7d5a955fbfb800bcab3692e16d441b13d9e81198a89ef726638
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25277a114387dd269017e1f5513ed0418a360468713c07c39c92f2e9b805e2d0
+oid sha256:a4c01cfdd06da3ca6b6c60392fafe567713c84c36d4644a5b3a39c77f0b1b651
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91076d3b338c3c65cf021f671dea04e162261cb54121c5e16dcda8dd631a6f0e
+oid sha256:6c58283ffe99f8f3bd9e9c7beac2c5bd0793e642197bb66ca256d3ce4bf349ae
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8bbbfc6eeb2a79fb25b83a1bed99e22ae8a2360356abaebb7d82d5fabcb1017
+oid sha256:cdc3e212eadbba9cd084fe18b4dce010bb191a0a91a1140136759f3508d9d237
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5172ebdfcec88f3e5d76271c56e0256fd2964a247ceb7c5fb4f21d69a6e82be6
+oid sha256:2c227b8a58a76c0541d9fb4d91c93cfa88ff395a344229b957281067faaf7b37
 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": 0.0024434493388980627,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5979073243647235,
+  "best_metric": 0.0014751702547073364,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.2062780269058295,
   "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": 17.154,
       "eval_steps_per_second": 4.46,
       "step": 25
+    },
+    {
+      "epoch": 0.6218236173393124,
+      "grad_norm": 0.06525561958551407,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0014,
+      "step": 26
+    },
+    {
+      "epoch": 0.6457399103139013,
+      "grad_norm": 0.056695058941841125,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0013,
+      "step": 27
+    },
+    {
+      "epoch": 0.6696562032884903,
+      "grad_norm": 0.08220528066158295,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0016,
+      "step": 28
+    },
+    {
+      "epoch": 0.6935724962630793,
+      "grad_norm": 0.02752971462905407,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0003,
+      "step": 29
+    },
+    {
+      "epoch": 0.7174887892376681,
+      "grad_norm": 0.04567359760403633,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0006,
+      "step": 30
+    },
+    {
+      "epoch": 0.7414050822122571,
+      "grad_norm": 0.06756115704774857,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0099,
+      "step": 31
+    },
+    {
+      "epoch": 0.7653213751868461,
+      "grad_norm": 0.040632255375385284,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0023,
+      "step": 32
+    },
+    {
+      "epoch": 0.7892376681614349,
+      "grad_norm": 0.03136821463704109,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.002,
+      "step": 33
+    },
+    {
+      "epoch": 0.8131539611360239,
+      "grad_norm": 0.03969261422753334,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0016,
+      "step": 34
+    },
+    {
+      "epoch": 0.8370702541106129,
+      "grad_norm": 0.0348944216966629,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0012,
+      "step": 35
+    },
+    {
+      "epoch": 0.8609865470852018,
+      "grad_norm": 0.05596629157662392,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0017,
+      "step": 36
+    },
+    {
+      "epoch": 0.8849028400597907,
+      "grad_norm": 0.05693504586815834,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0019,
+      "step": 37
+    },
+    {
+      "epoch": 0.9088191330343797,
+      "grad_norm": 0.028402505442500114,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0002,
+      "step": 38
+    },
+    {
+      "epoch": 0.9327354260089686,
+      "grad_norm": 0.10989071428775787,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0024,
+      "step": 39
+    },
+    {
+      "epoch": 0.9566517189835575,
+      "grad_norm": 0.02785768359899521,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0002,
+      "step": 40
+    },
+    {
+      "epoch": 0.9805680119581465,
+      "grad_norm": 0.04585525766015053,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0008,
+      "step": 41
+    },
+    {
+      "epoch": 1.014947683109118,
+      "grad_norm": 0.05161361023783684,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0135,
+      "step": 42
+    },
+    {
+      "epoch": 1.038863976083707,
+      "grad_norm": 0.02895764261484146,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0011,
+      "step": 43
+    },
+    {
+      "epoch": 1.062780269058296,
+      "grad_norm": 0.027964701876044273,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0013,
+      "step": 44
+    },
+    {
+      "epoch": 1.086696562032885,
+      "grad_norm": 0.03263154253363609,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0012,
+      "step": 45
+    },
+    {
+      "epoch": 1.1106128550074739,
+      "grad_norm": 0.02236635610461235,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0007,
+      "step": 46
+    },
+    {
+      "epoch": 1.1345291479820627,
+      "grad_norm": 0.021304232999682426,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0004,
+      "step": 47
+    },
+    {
+      "epoch": 1.1584454409566518,
+      "grad_norm": 0.04713241755962372,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0011,
+      "step": 48
+    },
+    {
+      "epoch": 1.1823617339312407,
+      "grad_norm": 0.031454771757125854,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0003,
+      "step": 49
+    },
+    {
+      "epoch": 1.2062780269058295,
+      "grad_norm": 0.019992325454950333,
+      "learning_rate": 1e-05,
+      "loss": 0.0002,
+      "step": 50
+    },
+    {
+      "epoch": 1.2062780269058295,
+      "eval_loss": 0.0014751702547073364,
+      "eval_runtime": 2.7042,
+      "eval_samples_per_second": 18.49,
+      "eval_steps_per_second": 4.807,
+      "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": 3.1567025970715034e+17,
+  "total_flos": 6.29218041065898e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null