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:ad634d6cd1db71f4fbefff7ec4b1e87349713c61d99f7f9470c581d9a1d98283
+oid sha256:a5461dc1d3eecf9f4c60d5f55df481765ef2a7e7cb15f560e7c4506b33b4c83a
 size 186962

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc36ac0c806c0204695e99f9a631f059aa7273b80a34f15366799c131357bf7f
+oid sha256:b91f7a26656da7552e7e5dcc2cc3c1fdf13dfa6f1e454b049ac0df4a510219a1
 size 121430

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb8c5ab4ea8a44c42a9277eaceca8d509e8a7e9d16341ba22e5d019a774e17f4
+oid sha256:f94361ebfdaf456f16be06b4021876e5697b15a0c734902d2ffcf217a5c39c2f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e7e7d7ab07a3662ef4f0f05e5c0bd0813078b27bf4438bac147af2489a7c86e
+oid sha256:8c911d9de0ded58d6ff86350dddc481d29aca046b080f7456e1f579787a0cc06
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b26c58582bdf79e9828b07d852591bebdb850950801bcc39432f50b20bfa223
+oid sha256:bbcef5d3e2dcee47b0450effca8e026bb996f920640929b95970789a3e6421df
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca28c64a9e19144de341a1af1cafd2673d7f753ce86b189cb3a5285502b83852
+oid sha256:f66b28efc23eb3ac2be221ca98d264cd23c736e16357161a0217e0383fc4c26d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.726648807525635,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08733624454148471,
+  "best_metric": 6.652959823608398,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.17467248908296942,
   "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": 888.912,
       "eval_steps_per_second": 112.497,
       "step": 25
+    },
+    {
+      "epoch": 0.09082969432314411,
+      "grad_norm": 1.812982201576233,
+      "learning_rate": 0.0001,
+      "loss": 6.7298,
+      "step": 26
+    },
+    {
+      "epoch": 0.0943231441048035,
+      "grad_norm": 1.5379116535186768,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 6.7249,
+      "step": 27
+    },
+    {
+      "epoch": 0.09781659388646288,
+      "grad_norm": 1.741886019706726,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 6.7238,
+      "step": 28
+    },
+    {
+      "epoch": 0.10131004366812227,
+      "grad_norm": 1.7986143827438354,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 6.7093,
+      "step": 29
+    },
+    {
+      "epoch": 0.10480349344978165,
+      "grad_norm": 1.425921082496643,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 6.7057,
+      "step": 30
+    },
+    {
+      "epoch": 0.10829694323144105,
+      "grad_norm": 1.772549033164978,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 6.6974,
+      "step": 31
+    },
+    {
+      "epoch": 0.11179039301310044,
+      "grad_norm": 1.5202797651290894,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 6.6887,
+      "step": 32
+    },
+    {
+      "epoch": 0.11528384279475982,
+      "grad_norm": 1.4495679140090942,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 6.7014,
+      "step": 33
+    },
+    {
+      "epoch": 0.11877729257641921,
+      "grad_norm": 1.540390968322754,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 6.6742,
+      "step": 34
+    },
+    {
+      "epoch": 0.1222707423580786,
+      "grad_norm": 1.3800748586654663,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 6.6797,
+      "step": 35
+    },
+    {
+      "epoch": 0.125764192139738,
+      "grad_norm": 1.4461179971694946,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 6.6783,
+      "step": 36
+    },
+    {
+      "epoch": 0.12925764192139738,
+      "grad_norm": 1.652401089668274,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 6.6752,
+      "step": 37
+    },
+    {
+      "epoch": 0.13275109170305677,
+      "grad_norm": 1.2902202606201172,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 6.6734,
+      "step": 38
+    },
+    {
+      "epoch": 0.13624454148471615,
+      "grad_norm": 1.6424710750579834,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 6.652,
+      "step": 39
+    },
+    {
+      "epoch": 0.13973799126637554,
+      "grad_norm": 1.5350518226623535,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 6.6633,
+      "step": 40
+    },
+    {
+      "epoch": 0.14323144104803492,
+      "grad_norm": 1.5188205242156982,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 6.6782,
+      "step": 41
+    },
+    {
+      "epoch": 0.1467248908296943,
+      "grad_norm": 1.3603993654251099,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 6.658,
+      "step": 42
+    },
+    {
+      "epoch": 0.15021834061135372,
+      "grad_norm": 1.5245517492294312,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 6.6588,
+      "step": 43
+    },
+    {
+      "epoch": 0.1537117903930131,
+      "grad_norm": 1.564213514328003,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 6.6585,
+      "step": 44
+    },
+    {
+      "epoch": 0.1572052401746725,
+      "grad_norm": 1.2466707229614258,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 6.6749,
+      "step": 45
+    },
+    {
+      "epoch": 0.16069868995633188,
+      "grad_norm": 1.3464109897613525,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 6.6599,
+      "step": 46
+    },
+    {
+      "epoch": 0.16419213973799127,
+      "grad_norm": 1.6725873947143555,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 6.647,
+      "step": 47
+    },
+    {
+      "epoch": 0.16768558951965065,
+      "grad_norm": 1.3510116338729858,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 6.6581,
+      "step": 48
+    },
+    {
+      "epoch": 0.17117903930131004,
+      "grad_norm": 1.3306465148925781,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 6.6537,
+      "step": 49
+    },
+    {
+      "epoch": 0.17467248908296942,
+      "grad_norm": 1.4314719438552856,
+      "learning_rate": 0.0,
+      "loss": 6.6494,
+      "step": 50
+    },
+    {
+      "epoch": 0.17467248908296942,
+      "eval_loss": 6.652959823608398,
+      "eval_runtime": 0.5563,
+      "eval_samples_per_second": 866.488,
+      "eval_steps_per_second": 109.659,
+      "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": 1178605977600.0,
+  "total_flos": 2357211955200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null