Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2e95b68a1d31a07def21df4ae5db81f1b6f8786516869b2ffdf66b97d1884de
+oid sha256:dd75e79e15a21c061c36831653d5e4f242039ccce5088f3444ac4db972a25ac6
 size 19552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a65909892099873524456fe212b9a75a9a0839f0c3d13e0228f573d9f701081c
+oid sha256:4abde123bec65d70d2a491fb2e2bc2bb56413a0b6d15f803ffdf4b208e304840
 size 47860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f947e080e78415fc2cd068ade128168b4b0e33eb9d6d1f6f3c55b42d202ca7b2
+oid sha256:6ab8ac4d78789b28929bf0bca6c975098bedef6ad81c07465d482ebfc87ce0ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9567f2f3182e832808fd621212e0dd5e8f1a88bd24ddda3ea0d289496073738c
+oid sha256:67bdc1680e75e7cf9661cc84482edc217f841c56aca5f9a3979c1c72a436f392
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 12.454829216003418,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.25906735751295334,
+  "best_metric": 12.451294898986816,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.38860103626943004,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 30.184,
       "eval_steps_per_second": 15.092,
       "step": 50
+    },
+    {
+      "epoch": 0.26424870466321243,
+      "grad_norm": 0.05474114790558815,
+      "learning_rate": 0.00010495837546732224,
+      "loss": 12.4555,
+      "step": 51
+    },
+    {
+      "epoch": 0.2694300518134715,
+      "grad_norm": 0.06194544583559036,
+      "learning_rate": 0.00010165339447663587,
+      "loss": 12.4549,
+      "step": 52
+    },
+    {
+      "epoch": 0.27461139896373055,
+      "grad_norm": 0.07049047946929932,
+      "learning_rate": 9.834660552336415e-05,
+      "loss": 12.4587,
+      "step": 53
+    },
+    {
+      "epoch": 0.27979274611398963,
+      "grad_norm": 0.06702786684036255,
+      "learning_rate": 9.504162453267777e-05,
+      "loss": 12.4568,
+      "step": 54
+    },
+    {
+      "epoch": 0.2849740932642487,
+      "grad_norm": 0.06343399733304977,
+      "learning_rate": 9.174206545276677e-05,
+      "loss": 12.4554,
+      "step": 55
+    },
+    {
+      "epoch": 0.29015544041450775,
+      "grad_norm": 0.06678463518619537,
+      "learning_rate": 8.845153630304139e-05,
+      "loss": 12.4561,
+      "step": 56
+    },
+    {
+      "epoch": 0.29533678756476683,
+      "grad_norm": 0.07747721672058105,
+      "learning_rate": 8.517363522881579e-05,
+      "loss": 12.4523,
+      "step": 57
+    },
+    {
+      "epoch": 0.3005181347150259,
+      "grad_norm": 0.07417742162942886,
+      "learning_rate": 8.191194656678904e-05,
+      "loss": 12.4628,
+      "step": 58
+    },
+    {
+      "epoch": 0.30569948186528495,
+      "grad_norm": 0.07810303568840027,
+      "learning_rate": 7.867003692562534e-05,
+      "loss": 12.4572,
+      "step": 59
+    },
+    {
+      "epoch": 0.31088082901554404,
+      "grad_norm": 0.08061844110488892,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 12.4548,
+      "step": 60
+    },
+    {
+      "epoch": 0.3160621761658031,
+      "grad_norm": 0.0870494544506073,
+      "learning_rate": 7.225970912381556e-05,
+      "loss": 12.4503,
+      "step": 61
+    },
+    {
+      "epoch": 0.32124352331606215,
+      "grad_norm": 0.08460117876529694,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 12.4587,
+      "step": 62
+    },
+    {
+      "epoch": 0.32642487046632124,
+      "grad_norm": 0.08417250216007233,
+      "learning_rate": 6.59706825558357e-05,
+      "loss": 12.4613,
+      "step": 63
+    },
+    {
+      "epoch": 0.3316062176165803,
+      "grad_norm": 0.09139107912778854,
+      "learning_rate": 6.28802751081779e-05,
+      "loss": 12.453,
+      "step": 64
+    },
+    {
+      "epoch": 0.33678756476683935,
+      "grad_norm": 0.0929340347647667,
+      "learning_rate": 5.983045753470308e-05,
+      "loss": 12.4633,
+      "step": 65
+    },
+    {
+      "epoch": 0.34196891191709844,
+      "grad_norm": 0.09280311316251755,
+      "learning_rate": 5.6824564766150726e-05,
+      "loss": 12.4553,
+      "step": 66
+    },
+    {
+      "epoch": 0.3471502590673575,
+      "grad_norm": 0.08577651530504227,
+      "learning_rate": 5.386588370213124e-05,
+      "loss": 12.4622,
+      "step": 67
+    },
+    {
+      "epoch": 0.35233160621761656,
+      "grad_norm": 0.10077881813049316,
+      "learning_rate": 5.095764961694922e-05,
+      "loss": 12.4606,
+      "step": 68
+    },
+    {
+      "epoch": 0.35751295336787564,
+      "grad_norm": 0.09882701188325882,
+      "learning_rate": 4.810304262187852e-05,
+      "loss": 12.4532,
+      "step": 69
+    },
+    {
+      "epoch": 0.3626943005181347,
+      "grad_norm": 0.10326765477657318,
+      "learning_rate": 4.530518418775733e-05,
+      "loss": 12.4606,
+      "step": 70
+    },
+    {
+      "epoch": 0.36787564766839376,
+      "grad_norm": 0.101172536611557,
+      "learning_rate": 4.256713373170564e-05,
+      "loss": 12.4627,
+      "step": 71
+    },
+    {
+      "epoch": 0.37305699481865284,
+      "grad_norm": 0.09795894473791122,
+      "learning_rate": 3.9891885271697496e-05,
+      "loss": 12.4615,
+      "step": 72
+    },
+    {
+      "epoch": 0.37823834196891193,
+      "grad_norm": 0.10780131071805954,
+      "learning_rate": 3.7282364152646297e-05,
+      "loss": 12.4575,
+      "step": 73
+    },
+    {
+      "epoch": 0.38341968911917096,
+      "grad_norm": 0.11272040009498596,
+      "learning_rate": 3.4741423847583134e-05,
+      "loss": 12.4538,
+      "step": 74
+    },
+    {
+      "epoch": 0.38860103626943004,
+      "grad_norm": 0.10471823811531067,
+      "learning_rate": 3.227184283742591e-05,
+      "loss": 12.4525,
+      "step": 75
+    },
+    {
+      "epoch": 0.38860103626943004,
+      "eval_loss": 12.451294898986816,
+      "eval_runtime": 2.7116,
+      "eval_samples_per_second": 30.241,
+      "eval_steps_per_second": 15.12,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 61656268800.0,
+  "total_flos": 92484403200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null