Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55b070d210390a8ae76458ea286cfe213b1ba11fe0337d032166a6c3d1169fab
+oid sha256:fb493449776f4920b39e459651b9cfdf7b9b1f3273c2be8b3766285765cc326a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b016ed818dc8400add81fcb4330d4914c0061240103a078253a6094d6ff612a5
+oid sha256:03eb175a4462a4f411efbe39f12dead7eaa62b7667f3a8ba80e737962123a1c4
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28fcf214e3e11de11cd222567678a81649203a9e6134f76716452512220dc3c6
+oid sha256:019afd73d20e710290867bf97afc45f090b8fbd74e026f2741f89192c1d962d0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c409614fe7c4294c30c517ac4a1097721f51ec5d3456b5de1ee4e4e2aed9ba
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6350438594818115,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.32441200324412,
+  "epoch": 0.48661800486618007,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,181 @@
       "eval_samples_per_second": 6.286,
       "eval_steps_per_second": 0.787,
       "step": 50
+    },
+    {
+      "epoch": 0.3309002433090024,
+      "grad_norm": 1.1093209981918335,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 0.4294,
+      "step": 51
+    },
+    {
+      "epoch": 0.33738848337388483,
+      "grad_norm": 1.7794939279556274,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 0.5775,
+      "step": 52
+    },
+    {
+      "epoch": 0.34387672343876724,
+      "grad_norm": 1.381375789642334,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.6621,
+      "step": 53
+    },
+    {
+      "epoch": 0.35036496350364965,
+      "grad_norm": 1.4836828708648682,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 0.7448,
+      "step": 54
+    },
+    {
+      "epoch": 0.35685320356853206,
+      "grad_norm": 1.253775954246521,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.5938,
+      "step": 55
+    },
+    {
+      "epoch": 0.3633414436334144,
+      "grad_norm": 1.5513309240341187,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 0.6217,
+      "step": 56
+    },
+    {
+      "epoch": 0.36982968369829683,
+      "grad_norm": 1.777928352355957,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 0.5749,
+      "step": 57
+    },
+    {
+      "epoch": 0.37631792376317924,
+      "grad_norm": 1.605820655822754,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 0.6827,
+      "step": 58
+    },
+    {
+      "epoch": 0.38280616382806165,
+      "grad_norm": 1.2288376092910767,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 0.5258,
+      "step": 59
+    },
+    {
+      "epoch": 0.38929440389294406,
+      "grad_norm": 1.3616653680801392,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.5963,
+      "step": 60
+    },
+    {
+      "epoch": 0.3957826439578264,
+      "grad_norm": 1.4875752925872803,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 0.6351,
+      "step": 61
+    },
+    {
+      "epoch": 0.40227088402270883,
+      "grad_norm": 1.4477332830429077,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 0.5471,
+      "step": 62
+    },
+    {
+      "epoch": 0.40875912408759124,
+      "grad_norm": 1.8846336603164673,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 0.7482,
+      "step": 63
+    },
+    {
+      "epoch": 0.41524736415247365,
+      "grad_norm": 1.851898431777954,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.6356,
+      "step": 64
+    },
+    {
+      "epoch": 0.42173560421735606,
+      "grad_norm": 1.6405341625213623,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.7012,
+      "step": 65
+    },
+    {
+      "epoch": 0.4282238442822384,
+      "grad_norm": 1.5401231050491333,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 0.5817,
+      "step": 66
+    },
+    {
+      "epoch": 0.43471208434712083,
+      "grad_norm": 1.2834601402282715,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 0.6662,
+      "step": 67
+    },
+    {
+      "epoch": 0.44120032441200324,
+      "grad_norm": 1.7023755311965942,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 0.7074,
+      "step": 68
+    },
+    {
+      "epoch": 0.44768856447688565,
+      "grad_norm": 1.2349250316619873,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 0.5058,
+      "step": 69
+    },
+    {
+      "epoch": 0.45417680454176806,
+      "grad_norm": 1.5026576519012451,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.7246,
+      "step": 70
+    },
+    {
+      "epoch": 0.4606650446066504,
+      "grad_norm": 1.2308121919631958,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 0.7091,
+      "step": 71
+    },
+    {
+      "epoch": 0.46715328467153283,
+      "grad_norm": 1.6818972826004028,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 0.6945,
+      "step": 72
+    },
+    {
+      "epoch": 0.47364152473641524,
+      "grad_norm": 1.253867268562317,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 0.5318,
+      "step": 73
+    },
+    {
+      "epoch": 0.48012976480129765,
+      "grad_norm": 1.5630402565002441,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 0.7055,
+      "step": 74
+    },
+    {
+      "epoch": 0.48661800486618007,
+      "grad_norm": 1.377374291419983,
+      "learning_rate": 0.0,
+      "loss": 0.5693,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -396,12 +571,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.967549134241792e+17,
+  "total_flos": 4.451323701362688e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null