Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66c785c945e3cd813f321dfc33de5d9d3868a736101b55c7b496179dad8b2acc
+oid sha256:09296fda61d55631a96c5a4386ea81b10824729b1ade2356089a7c364a6ce98d
 size 186962

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c8d0bb05a167681f65137954b879e4bf181d5fb125ce6cbda084eafbe860aa2
+oid sha256:02dbc1ddfca1272332d9ce802725cace46dacbb7af78affe26ac97754fb4eb80
 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": 6.729074954986572,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08733624454148471,
+  "best_metric": 6.661139965057373,
+  "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": 867.649,
       "eval_steps_per_second": 109.806,
       "step": 25
+    },
+    {
+      "epoch": 0.09082969432314411,
+      "grad_norm": 1.7198904752731323,
+      "learning_rate": 0.0001,
+      "loss": 6.721,
+      "step": 26
+    },
+    {
+      "epoch": 0.0943231441048035,
+      "grad_norm": 1.4587581157684326,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 6.7278,
+      "step": 27
+    },
+    {
+      "epoch": 0.09781659388646288,
+      "grad_norm": 1.5983480215072632,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 6.7303,
+      "step": 28
+    },
+    {
+      "epoch": 0.10131004366812227,
+      "grad_norm": 1.626555323600769,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 6.7129,
+      "step": 29
+    },
+    {
+      "epoch": 0.10480349344978165,
+      "grad_norm": 1.3530901670455933,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 6.7166,
+      "step": 30
+    },
+    {
+      "epoch": 0.10829694323144105,
+      "grad_norm": 1.6371723413467407,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 6.7081,
+      "step": 31
+    },
+    {
+      "epoch": 0.11179039301310044,
+      "grad_norm": 1.4091604948043823,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 6.6933,
+      "step": 32
+    },
+    {
+      "epoch": 0.11528384279475982,
+      "grad_norm": 1.3315062522888184,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 6.7152,
+      "step": 33
+    },
+    {
+      "epoch": 0.11877729257641921,
+      "grad_norm": 1.406883716583252,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 6.6903,
+      "step": 34
+    },
+    {
+      "epoch": 0.1222707423580786,
+      "grad_norm": 1.270359992980957,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 6.6839,
+      "step": 35
+    },
+    {
+      "epoch": 0.125764192139738,
+      "grad_norm": 1.3271560668945312,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 6.6798,
+      "step": 36
+    },
+    {
+      "epoch": 0.12925764192139738,
+      "grad_norm": 1.5681676864624023,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 6.6776,
+      "step": 37
+    },
+    {
+      "epoch": 0.13275109170305677,
+      "grad_norm": 1.1914104223251343,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 6.6897,
+      "step": 38
+    },
+    {
+      "epoch": 0.13624454148471615,
+      "grad_norm": 1.5367497205734253,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 6.658,
+      "step": 39
+    },
+    {
+      "epoch": 0.13973799126637554,
+      "grad_norm": 1.427626132965088,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 6.6709,
+      "step": 40
+    },
+    {
+      "epoch": 0.14323144104803492,
+      "grad_norm": 1.4009745121002197,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 6.6851,
+      "step": 41
+    },
+    {
+      "epoch": 0.1467248908296943,
+      "grad_norm": 1.2408397197723389,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 6.6675,
+      "step": 42
+    },
+    {
+      "epoch": 0.15021834061135372,
+      "grad_norm": 1.4328770637512207,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 6.6639,
+      "step": 43
+    },
+    {
+      "epoch": 0.1537117903930131,
+      "grad_norm": 1.4258441925048828,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 6.6586,
+      "step": 44
+    },
+    {
+      "epoch": 0.1572052401746725,
+      "grad_norm": 1.161400556564331,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 6.6903,
+      "step": 45
+    },
+    {
+      "epoch": 0.16069868995633188,
+      "grad_norm": 1.23970365524292,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 6.6612,
+      "step": 46
+    },
+    {
+      "epoch": 0.16419213973799127,
+      "grad_norm": 1.5629112720489502,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 6.6537,
+      "step": 47
+    },
+    {
+      "epoch": 0.16768558951965065,
+      "grad_norm": 1.22788405418396,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 6.6729,
+      "step": 48
+    },
+    {
+      "epoch": 0.17117903930131004,
+      "grad_norm": 1.2596584558486938,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 6.6638,
+      "step": 49
+    },
+    {
+      "epoch": 0.17467248908296942,
+      "grad_norm": 1.359727382659912,
+      "learning_rate": 0.0,
+      "loss": 6.659,
+      "step": 50
+    },
+    {
+      "epoch": 0.17467248908296942,
+      "eval_loss": 6.661139965057373,
+      "eval_runtime": 0.5655,
+      "eval_samples_per_second": 852.39,
+      "eval_steps_per_second": 107.875,
+      "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