Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:206ae7aa1944eac3d1139767e599b4586026e557d25e380af21cda528433504e
+oid sha256:69df28d7033764aa8a84563a1295a629e7b9a1a2d585ae91570bc78a4baaebaf
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4009f62a458542d62e7a21b288a263ec36999a7ea90d17fef312a578d2306e13
+oid sha256:978e0514252b0bf1233485840aa22015cbaa3f2c68ec1f8fd9ee328e6cde8329
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c97e09e1198b162eb64dadf6a581f9a49db431c5d06412664e916362c070ce74
+oid sha256:5591a2650b4e39dbb8ff89b3c3fddade668f950f5846193602edc1614f293e18
 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": 0.003693485399708152,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.02818687900782186,
+  "epoch": 0.042280318511732785,
   "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": 6.144,
       "eval_steps_per_second": 1.536,
       "step": 50
+    },
+    {
+      "epoch": 0.028750616587978298,
+      "grad_norm": 0.1225830614566803,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 0.0021,
+      "step": 51
+    },
+    {
+      "epoch": 0.029314354168134733,
+      "grad_norm": 0.2588897943496704,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 0.0056,
+      "step": 52
+    },
+    {
+      "epoch": 0.02987809174829117,
+      "grad_norm": 0.032464101910591125,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0014,
+      "step": 53
+    },
+    {
+      "epoch": 0.030441829328447606,
+      "grad_norm": 0.06320462375879288,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 0.0015,
+      "step": 54
+    },
+    {
+      "epoch": 0.031005566908604044,
+      "grad_norm": 0.09139032661914825,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.0038,
+      "step": 55
+    },
+    {
+      "epoch": 0.03156930448876048,
+      "grad_norm": 0.21807141602039337,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 0.0058,
+      "step": 56
+    },
+    {
+      "epoch": 0.03213304206891692,
+      "grad_norm": 0.044844482094049454,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 0.0015,
+      "step": 57
+    },
+    {
+      "epoch": 0.03269677964907336,
+      "grad_norm": 0.411823034286499,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 0.0509,
+      "step": 58
+    },
+    {
+      "epoch": 0.03326051722922979,
+      "grad_norm": 0.08910378813743591,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 0.0028,
+      "step": 59
+    },
+    {
+      "epoch": 0.03382425480938623,
+      "grad_norm": 0.02365848794579506,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.0012,
+      "step": 60
+    },
+    {
+      "epoch": 0.03438799238954267,
+      "grad_norm": 0.07241960614919662,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 0.002,
+      "step": 61
+    },
+    {
+      "epoch": 0.03495172996969911,
+      "grad_norm": 0.12868086993694305,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 0.0068,
+      "step": 62
+    },
+    {
+      "epoch": 0.035515467549855545,
+      "grad_norm": 0.2509536147117615,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 0.0093,
+      "step": 63
+    },
+    {
+      "epoch": 0.036079205130011976,
+      "grad_norm": 0.16926199197769165,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0135,
+      "step": 64
+    },
+    {
+      "epoch": 0.036642942710168415,
+      "grad_norm": 0.06538938730955124,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.0022,
+      "step": 65
+    },
+    {
+      "epoch": 0.03720668029032485,
+      "grad_norm": 0.03876176103949547,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 0.0015,
+      "step": 66
+    },
+    {
+      "epoch": 0.03777041787048129,
+      "grad_norm": 0.05735520273447037,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 0.0021,
+      "step": 67
+    },
+    {
+      "epoch": 0.03833415545063773,
+      "grad_norm": 0.04489413648843765,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 0.0018,
+      "step": 68
+    },
+    {
+      "epoch": 0.03889789303079417,
+      "grad_norm": 0.05411110073328018,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 0.0019,
+      "step": 69
+    },
+    {
+      "epoch": 0.0394616306109506,
+      "grad_norm": 0.13937705755233765,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.0019,
+      "step": 70
+    },
+    {
+      "epoch": 0.04002536819110704,
+      "grad_norm": 0.11924191564321518,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 0.0035,
+      "step": 71
+    },
+    {
+      "epoch": 0.04058910577126348,
+      "grad_norm": 0.08436208218336105,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 0.003,
+      "step": 72
+    },
+    {
+      "epoch": 0.041152843351419915,
+      "grad_norm": 0.36739325523376465,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 0.0077,
+      "step": 73
+    },
+    {
+      "epoch": 0.041716580931576354,
+      "grad_norm": 0.10039687901735306,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 0.0047,
+      "step": 74
+    },
+    {
+      "epoch": 0.042280318511732785,
+      "grad_norm": 0.1667713224887848,
+      "learning_rate": 0.0,
+      "loss": 0.006,
+      "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": 1.5122848626927206e+17,
+  "total_flos": 2.2703129360125133e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null