Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06ddf823e440b64c972491e6fdb7a9eba2293cb2c72f405795fe44e30f378123
+oid sha256:62f7135065459649015159caa52e6bbc789be5a904c10e6e418de69bd97a3989
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3198141c663a6d84ec949f35858642e5095b1dad8011997f51aa061910ea5184
+oid sha256:ad7bdaa28bc4769272ca23b2b1538f5a0486a2df2d7b9955149fa554f95a13e4
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9731387f2014e0931504a5dc91dc766fe00f33e8e2cc1f01a6aaa5e270ca470
+oid sha256:4ad99526e02b587115fd7b5bc7c291e898627845e9dd34009d5dcad640b70185
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a562df190435a61a34a464c81cfb9b380b85731b6925f7f71c1f07e5281dab
+oid sha256:75407a046483ddd8adfd5a339765908144faef5e3f7cb529fb26827531ff7848
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3cfb1efd949f5ad95fd95aa153521f380f50b732595393fbbcaae4e567ec90e
+oid sha256:01deeec2dc84dfbc2573839cbdf3d01556ee9b190c471236e4e144c31b5eba9d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73b2b3ba129c170c6222539537df46fff585eb1ea0bb0bbe6d891fdee755aa95
+oid sha256:0404cd7df249584dc1f9cf6e9aee3b5b026bc9a6556f5bd5300b18c9cd431460
 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": 1.3723218441009521,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.033425252778474135,
+  "best_metric": 1.338729977607727,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06685050555694827,
   "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": 22.274,
       "eval_steps_per_second": 2.785,
       "step": 25
+    },
+    {
+      "epoch": 0.0347622628896131,
+      "grad_norm": 27.988006591796875,
+      "learning_rate": 5e-05,
+      "loss": 1.5653,
+      "step": 26
+    },
+    {
+      "epoch": 0.036099273000752066,
+      "grad_norm": 23.9869384765625,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.5689,
+      "step": 27
+    },
+    {
+      "epoch": 0.03743628311189103,
+      "grad_norm": 23.481412887573242,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.428,
+      "step": 28
+    },
+    {
+      "epoch": 0.03877329322303,
+      "grad_norm": 23.574743270874023,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.4138,
+      "step": 29
+    },
+    {
+      "epoch": 0.04011030333416896,
+      "grad_norm": 24.408958435058594,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.3259,
+      "step": 30
+    },
+    {
+      "epoch": 0.04144731344530793,
+      "grad_norm": 25.739273071289062,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.3485,
+      "step": 31
+    },
+    {
+      "epoch": 0.042784323556446895,
+      "grad_norm": 26.332134246826172,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.3323,
+      "step": 32
+    },
+    {
+      "epoch": 0.04412133366758586,
+      "grad_norm": 27.37655258178711,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.3009,
+      "step": 33
+    },
+    {
+      "epoch": 0.045458343778724826,
+      "grad_norm": 29.02335548400879,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.4547,
+      "step": 34
+    },
+    {
+      "epoch": 0.04679535388986379,
+      "grad_norm": 30.307477951049805,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.32,
+      "step": 35
+    },
+    {
+      "epoch": 0.04813236400100276,
+      "grad_norm": 29.861248016357422,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1157,
+      "step": 36
+    },
+    {
+      "epoch": 0.04946937411214172,
+      "grad_norm": 37.60776138305664,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.2336,
+      "step": 37
+    },
+    {
+      "epoch": 0.05080638422328069,
+      "grad_norm": 31.587434768676758,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3959,
+      "step": 38
+    },
+    {
+      "epoch": 0.052143394334419654,
+      "grad_norm": 19.443872451782227,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.5545,
+      "step": 39
+    },
+    {
+      "epoch": 0.05348040444555862,
+      "grad_norm": 20.82927894592285,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.5071,
+      "step": 40
+    },
+    {
+      "epoch": 0.054817414556697586,
+      "grad_norm": 21.544597625732422,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.4133,
+      "step": 41
+    },
+    {
+      "epoch": 0.05615442466783655,
+      "grad_norm": 22.356794357299805,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3494,
+      "step": 42
+    },
+    {
+      "epoch": 0.05749143477897552,
+      "grad_norm": 22.970012664794922,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2914,
+      "step": 43
+    },
+    {
+      "epoch": 0.05882844489011448,
+      "grad_norm": 25.380735397338867,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2244,
+      "step": 44
+    },
+    {
+      "epoch": 0.06016545500125345,
+      "grad_norm": 25.606966018676758,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.2434,
+      "step": 45
+    },
+    {
+      "epoch": 0.061502465112392414,
+      "grad_norm": 26.491294860839844,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2931,
+      "step": 46
+    },
+    {
+      "epoch": 0.06283947522353138,
+      "grad_norm": 29.655942916870117,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.3152,
+      "step": 47
+    },
+    {
+      "epoch": 0.06417648533467034,
+      "grad_norm": 29.71782875061035,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.1351,
+      "step": 48
+    },
+    {
+      "epoch": 0.06551349544580931,
+      "grad_norm": 34.75334548950195,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.2264,
+      "step": 49
+    },
+    {
+      "epoch": 0.06685050555694827,
+      "grad_norm": 47.528446197509766,
+      "learning_rate": 0.0,
+      "loss": 1.2762,
+      "step": 50
+    },
+    {
+      "epoch": 0.06685050555694827,
+      "eval_loss": 1.338729977607727,
+      "eval_runtime": 145.7924,
+      "eval_samples_per_second": 34.563,
+      "eval_steps_per_second": 4.321,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null