Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39d511e4697e1a7223df36cd8043426f7ec6ca2b5bf3d59cb030714866a1a7b5
+oid sha256:e98748644bb15f1f2b50c80173c56d3dbcd00b93d5e0195edf3c3d63d254bb34
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1a1458adf9ffc601b1478680bb625fd2d975f070efc400aa7953d58bca32881
+oid sha256:9e8e2731255737933680766b1ee8fe9710ba23b9314541de17eb3ef453c46c21
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:065fd2d62ca710b7ecd71d75b6b23123cf766b72177184f937e06bfa3e5b5cda
+oid sha256:4b812d15282e69d4cfb78bd44c6f39179d78386ea530025964382b221173cee6
 size 14244

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": 10.354788780212402,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0011751433674908338,
+  "best_metric": 10.350831031799316,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0023502867349816676,
   "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": 99.752,
       "eval_steps_per_second": 49.876,
       "step": 25
+    },
+    {
+      "epoch": 0.0012221491021904673,
+      "grad_norm": 0.11649630963802338,
+      "learning_rate": 0.0001,
+      "loss": 10.3567,
+      "step": 26
+    },
+    {
+      "epoch": 0.0012691548368901006,
+      "grad_norm": 0.12191897630691528,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 10.3572,
+      "step": 27
+    },
+    {
+      "epoch": 0.001316160571589734,
+      "grad_norm": 0.09873288124799728,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 10.3488,
+      "step": 28
+    },
+    {
+      "epoch": 0.0013631663062893672,
+      "grad_norm": 0.12206266075372696,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 10.3544,
+      "step": 29
+    },
+    {
+      "epoch": 0.0014101720409890007,
+      "grad_norm": 0.10885295271873474,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 10.3586,
+      "step": 30
+    },
+    {
+      "epoch": 0.001457177775688634,
+      "grad_norm": 0.11052808910608292,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 10.3566,
+      "step": 31
+    },
+    {
+      "epoch": 0.0015041835103882673,
+      "grad_norm": 0.11033797264099121,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 10.3518,
+      "step": 32
+    },
+    {
+      "epoch": 0.0015511892450879006,
+      "grad_norm": 0.14301928877830505,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 10.3582,
+      "step": 33
+    },
+    {
+      "epoch": 0.0015981949797875341,
+      "grad_norm": 0.1133815199136734,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 10.366,
+      "step": 34
+    },
+    {
+      "epoch": 0.0016452007144871674,
+      "grad_norm": 0.13060739636421204,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 10.3568,
+      "step": 35
+    },
+    {
+      "epoch": 0.0016922064491868007,
+      "grad_norm": 0.11268500238656998,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 10.3563,
+      "step": 36
+    },
+    {
+      "epoch": 0.001739212183886434,
+      "grad_norm": 0.11154811084270477,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 10.3537,
+      "step": 37
+    },
+    {
+      "epoch": 0.0017862179185860676,
+      "grad_norm": 0.1264294683933258,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 10.3504,
+      "step": 38
+    },
+    {
+      "epoch": 0.0018332236532857009,
+      "grad_norm": 0.13054020702838898,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 10.3461,
+      "step": 39
+    },
+    {
+      "epoch": 0.0018802293879853342,
+      "grad_norm": 0.1202877089381218,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 10.3538,
+      "step": 40
+    },
+    {
+      "epoch": 0.0019272351226849677,
+      "grad_norm": 0.12251313030719757,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 10.3526,
+      "step": 41
+    },
+    {
+      "epoch": 0.0019742408573846008,
+      "grad_norm": 0.14759667217731476,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 10.3545,
+      "step": 42
+    },
+    {
+      "epoch": 0.0020212465920842345,
+      "grad_norm": 0.12316801398992538,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 10.3516,
+      "step": 43
+    },
+    {
+      "epoch": 0.002068252326783868,
+      "grad_norm": 0.14139099419116974,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 10.3559,
+      "step": 44
+    },
+    {
+      "epoch": 0.002115258061483501,
+      "grad_norm": 0.1286371797323227,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 10.3545,
+      "step": 45
+    },
+    {
+      "epoch": 0.0021622637961831344,
+      "grad_norm": 0.12192552536725998,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 10.3513,
+      "step": 46
+    },
+    {
+      "epoch": 0.0022092695308827677,
+      "grad_norm": 0.14616093039512634,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 10.3587,
+      "step": 47
+    },
+    {
+      "epoch": 0.002256275265582401,
+      "grad_norm": 0.14441625773906708,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 10.3626,
+      "step": 48
+    },
+    {
+      "epoch": 0.0023032810002820343,
+      "grad_norm": 0.15917129814624786,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 10.3599,
+      "step": 49
+    },
+    {
+      "epoch": 0.0023502867349816676,
+      "grad_norm": 0.2211294025182724,
+      "learning_rate": 0.0,
+      "loss": 10.3714,
+      "step": 50
+    },
+    {
+      "epoch": 0.0023502867349816676,
+      "eval_loss": 10.350831031799316,
+      "eval_runtime": 89.671,
+      "eval_samples_per_second": 99.899,
+      "eval_steps_per_second": 49.949,
+      "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": 2615122329600.0,
+  "total_flos": 5230244659200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null