Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04882c37b01bb0f2478c2dd60300a1d782100d478e661823c186337a3fb21aed
+oid sha256:bad0c83672491c1116b2c2ce941560ea9196dc9eec58909516990f8200f670e1
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c36490c2a77e4c9ccd4baad4ecad16880b4c7989216d775122ee0a2dbb88a58
+oid sha256:aca561dc5f4d1af6716d7c52e7e3c5aa0ec2ffe48a3f43a2bdf7942b37aab7fc
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd113f0a0c0c153fa9c0fe49e00c6111c11aae924cd771c6e400db104a6e8cda
+oid sha256:1fae6a3b2715a58a61faf71a658bfc22f669a739f57e8018eb393f8f0d07c1c1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7dab2412792b6bc803bee85217b8b4d59214af59f25275189d15f67131b2008
+oid sha256:f60f7c1ea2c45c22bc4de04fc8728788f0630683e14b15371bf6a317be79c691
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c0056b46795fb8cfe0b4626f5030006e06610e2d647de1908c08ae556f3c19
+oid sha256:8304126766991fc6c7590091fdda7232e3593bdf1f8e99b7fd4cf8165b84d4b8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33327d05dcecd159cd27fda02bd5d5a8eeb9b4fc5f9fdb99ac0b592064ab3c48
+oid sha256:726ddff706efad189ed657fd070737d7617d145efa167d943d528604b06ab825
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.926277160644531,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.00928203462198914,
+  "best_metric": 11.925542831420898,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.01856406924397828,
   "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": 183.973,
       "eval_steps_per_second": 23.006,
       "step": 25
+    },
+    {
+      "epoch": 0.009653316006868706,
+      "grad_norm": 0.01857578009366989,
+      "learning_rate": 5e-05,
+      "loss": 11.9292,
+      "step": 26
+    },
+    {
+      "epoch": 0.01002459739174827,
+      "grad_norm": 0.021577468141913414,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.9293,
+      "step": 27
+    },
+    {
+      "epoch": 0.010395878776627837,
+      "grad_norm": 0.022688543424010277,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.9284,
+      "step": 28
+    },
+    {
+      "epoch": 0.010767160161507403,
+      "grad_norm": 0.029039891436696053,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.928,
+      "step": 29
+    },
+    {
+      "epoch": 0.011138441546386968,
+      "grad_norm": 0.027141861617565155,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.9282,
+      "step": 30
+    },
+    {
+      "epoch": 0.011509722931266534,
+      "grad_norm": 0.031942471861839294,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.9279,
+      "step": 31
+    },
+    {
+      "epoch": 0.0118810043161461,
+      "grad_norm": 0.03531135991215706,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9274,
+      "step": 32
+    },
+    {
+      "epoch": 0.012252285701025665,
+      "grad_norm": 0.031263090670108795,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.9269,
+      "step": 33
+    },
+    {
+      "epoch": 0.01262356708590523,
+      "grad_norm": 0.03525080159306526,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.9252,
+      "step": 34
+    },
+    {
+      "epoch": 0.012994848470784796,
+      "grad_norm": 0.04339566454291344,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.9251,
+      "step": 35
+    },
+    {
+      "epoch": 0.013366129855664361,
+      "grad_norm": 0.043329868465662,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.9248,
+      "step": 36
+    },
+    {
+      "epoch": 0.013737411240543927,
+      "grad_norm": 0.05429895594716072,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.9228,
+      "step": 37
+    },
+    {
+      "epoch": 0.014108692625423493,
+      "grad_norm": 0.02292412705719471,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9292,
+      "step": 38
+    },
+    {
+      "epoch": 0.014479974010303058,
+      "grad_norm": 0.026886217296123505,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.9286,
+      "step": 39
+    },
+    {
+      "epoch": 0.014851255395182623,
+      "grad_norm": 0.026999138295650482,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.928,
+      "step": 40
+    },
+    {
+      "epoch": 0.01522253678006219,
+      "grad_norm": 0.027867605909705162,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.9281,
+      "step": 41
+    },
+    {
+      "epoch": 0.015593818164941755,
+      "grad_norm": 0.028749389573931694,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.9278,
+      "step": 42
+    },
+    {
+      "epoch": 0.01596509954982132,
+      "grad_norm": 0.0331251323223114,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.927,
+      "step": 43
+    },
+    {
+      "epoch": 0.016336380934700887,
+      "grad_norm": 0.034101732075214386,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9271,
+      "step": 44
+    },
+    {
+      "epoch": 0.01670766231958045,
+      "grad_norm": 0.03889305517077446,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.9268,
+      "step": 45
+    },
+    {
+      "epoch": 0.017078943704460017,
+      "grad_norm": 0.0389268584549427,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.9257,
+      "step": 46
+    },
+    {
+      "epoch": 0.017450225089339584,
+      "grad_norm": 0.0436691977083683,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.9256,
+      "step": 47
+    },
+    {
+      "epoch": 0.017821506474219147,
+      "grad_norm": 0.04428064823150635,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.9243,
+      "step": 48
+    },
+    {
+      "epoch": 0.018192787859098714,
+      "grad_norm": 0.05177050083875656,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.9234,
+      "step": 49
+    },
+    {
+      "epoch": 0.01856406924397828,
+      "grad_norm": 0.07301251590251923,
+      "learning_rate": 0.0,
+      "loss": 11.9203,
+      "step": 50
+    },
+    {
+      "epoch": 0.01856406924397828,
+      "eval_loss": 11.925542831420898,
+      "eval_runtime": 108.4513,
+      "eval_samples_per_second": 167.31,
+      "eval_steps_per_second": 20.922,
+      "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": 559037546496.0,
+  "total_flos": 1120029769728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null