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:bd756a3d7719aa23fbae9c98eea52e03e94bcfc2658549aa77cc3fcfd61391a6
+oid sha256:3d9dd949176f4c5e47502e388fb867ccab7903fdcafe8be0bc82a23ebb80ebfb
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcc3776697c7bee22b96f5d09297f0f0e5905bc6965e03486e5cff69bd19d308
+oid sha256:6a4a7c1525ad81a6fc0e9347554cd66d5f84d004d611640bcbd86df6f2448de7
 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": 1.3706095218658447,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.033425252778474135,
+  "best_metric": 1.3382925987243652,
+  "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": 34.628,
       "eval_steps_per_second": 4.329,
       "step": 25
+    },
+    {
+      "epoch": 0.0347622628896131,
+      "grad_norm": 25.990808486938477,
+      "learning_rate": 5e-05,
+      "loss": 1.5636,
+      "step": 26
+    },
+    {
+      "epoch": 0.036099273000752066,
+      "grad_norm": 22.69860076904297,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.5672,
+      "step": 27
+    },
+    {
+      "epoch": 0.03743628311189103,
+      "grad_norm": 22.71676254272461,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.43,
+      "step": 28
+    },
+    {
+      "epoch": 0.03877329322303,
+      "grad_norm": 23.096960067749023,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.4142,
+      "step": 29
+    },
+    {
+      "epoch": 0.04011030333416896,
+      "grad_norm": 23.61298942565918,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.326,
+      "step": 30
+    },
+    {
+      "epoch": 0.04144731344530793,
+      "grad_norm": 25.191864013671875,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.3509,
+      "step": 31
+    },
+    {
+      "epoch": 0.042784323556446895,
+      "grad_norm": 25.648237228393555,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.333,
+      "step": 32
+    },
+    {
+      "epoch": 0.04412133366758586,
+      "grad_norm": 27.153898239135742,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.3001,
+      "step": 33
+    },
+    {
+      "epoch": 0.045458343778724826,
+      "grad_norm": 28.19595718383789,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.4561,
+      "step": 34
+    },
+    {
+      "epoch": 0.04679535388986379,
+      "grad_norm": 29.54447364807129,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.3213,
+      "step": 35
+    },
+    {
+      "epoch": 0.04813236400100276,
+      "grad_norm": 31.437786102294922,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1158,
+      "step": 36
+    },
+    {
+      "epoch": 0.04946937411214172,
+      "grad_norm": 37.75790023803711,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.2325,
+      "step": 37
+    },
+    {
+      "epoch": 0.05080638422328069,
+      "grad_norm": 31.451086044311523,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3948,
+      "step": 38
+    },
+    {
+      "epoch": 0.052143394334419654,
+      "grad_norm": 19.551162719726562,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.5541,
+      "step": 39
+    },
+    {
+      "epoch": 0.05348040444555862,
+      "grad_norm": 20.893918991088867,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.5098,
+      "step": 40
+    },
+    {
+      "epoch": 0.054817414556697586,
+      "grad_norm": 21.392484664916992,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.4131,
+      "step": 41
+    },
+    {
+      "epoch": 0.05615442466783655,
+      "grad_norm": 21.886232376098633,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.348,
+      "step": 42
+    },
+    {
+      "epoch": 0.05749143477897552,
+      "grad_norm": 22.548765182495117,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2932,
+      "step": 43
+    },
+    {
+      "epoch": 0.05882844489011448,
+      "grad_norm": 24.45055389404297,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2246,
+      "step": 44
+    },
+    {
+      "epoch": 0.06016545500125345,
+      "grad_norm": 25.212177276611328,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.2447,
+      "step": 45
+    },
+    {
+      "epoch": 0.061502465112392414,
+      "grad_norm": 25.975236892700195,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2924,
+      "step": 46
+    },
+    {
+      "epoch": 0.06283947522353138,
+      "grad_norm": 28.950206756591797,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.317,
+      "step": 47
+    },
+    {
+      "epoch": 0.06417648533467034,
+      "grad_norm": 29.081235885620117,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.136,
+      "step": 48
+    },
+    {
+      "epoch": 0.06551349544580931,
+      "grad_norm": 33.672969818115234,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.2239,
+      "step": 49
+    },
+    {
+      "epoch": 0.06685050555694827,
+      "grad_norm": 46.237857818603516,
+      "learning_rate": 0.0,
+      "loss": 1.2762,
+      "step": 50
+    },
+    {
+      "epoch": 0.06685050555694827,
+      "eval_loss": 1.3382925987243652,
+      "eval_runtime": 292.4772,
+      "eval_samples_per_second": 17.229,
+      "eval_steps_per_second": 2.154,
+      "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