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:bb6041cb5a0e5116437fd1762a973422248d9e2489e5edfa61613feb549dc3bd
+oid sha256:37de12eb3298ecf33fd7dcdea581c36d5ae18ecec3ddf0adb224312c2f48edb6
 size 2373352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab10b02a5d52cae26d0a89e299940c429c0714a48c8340ff5a3038c029c0f6b
+oid sha256:2260753ac01adfceeddd0d4b50b09150b7460a76e0bd6e1a8317f838bbab1e16
 size 4830714

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:794bf4adaeefa0e631ced24ab3474cee4d08c4e29834296ec2812792dd22e3c7
+oid sha256:76f2908465eaa961816b181a32ba220dee4f2afb834f2d7e28e303e14f57e5d4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.879182815551758,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.002799630448780761,
+  "best_metric": 11.870880126953125,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.005599260897561522,
   "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": 202.792,
       "eval_steps_per_second": 25.349,
       "step": 25
+    },
+    {
+      "epoch": 0.0029116156667319914,
+      "grad_norm": 0.36206889152526855,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 11.8883,
+      "step": 26
+    },
+    {
+      "epoch": 0.0030236008846832216,
+      "grad_norm": 0.35606443881988525,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 11.8859,
+      "step": 27
+    },
+    {
+      "epoch": 0.0031355861026344523,
+      "grad_norm": 0.36061397194862366,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 11.8798,
+      "step": 28
+    },
+    {
+      "epoch": 0.003247571320585683,
+      "grad_norm": 0.32018181681632996,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 11.8738,
+      "step": 29
+    },
+    {
+      "epoch": 0.003359556538536913,
+      "grad_norm": 0.3145982027053833,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 11.8761,
+      "step": 30
+    },
+    {
+      "epoch": 0.0034715417564881437,
+      "grad_norm": 0.32793933153152466,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 11.8738,
+      "step": 31
+    },
+    {
+      "epoch": 0.003583526974439374,
+      "grad_norm": 0.3352945148944855,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 11.8786,
+      "step": 32
+    },
+    {
+      "epoch": 0.0036955121923906045,
+      "grad_norm": 0.3643173277378082,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 11.8678,
+      "step": 33
+    },
+    {
+      "epoch": 0.0038074974103418347,
+      "grad_norm": 0.2782880365848541,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 11.8736,
+      "step": 34
+    },
+    {
+      "epoch": 0.003919482628293065,
+      "grad_norm": 0.29699552059173584,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.8726,
+      "step": 35
+    },
+    {
+      "epoch": 0.0040314678462442955,
+      "grad_norm": 0.32504162192344666,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 11.8758,
+      "step": 36
+    },
+    {
+      "epoch": 0.0041434530641955266,
+      "grad_norm": 0.30580511689186096,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 11.8762,
+      "step": 37
+    },
+    {
+      "epoch": 0.004255438282146757,
+      "grad_norm": 0.29958587884902954,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 11.8768,
+      "step": 38
+    },
+    {
+      "epoch": 0.004367423500097987,
+      "grad_norm": 0.2728487551212311,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 11.8704,
+      "step": 39
+    },
+    {
+      "epoch": 0.004479408718049217,
+      "grad_norm": 0.30847886204719543,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 11.8689,
+      "step": 40
+    },
+    {
+      "epoch": 0.004591393936000448,
+      "grad_norm": 0.26389238238334656,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.8693,
+      "step": 41
+    },
+    {
+      "epoch": 0.004703379153951678,
+      "grad_norm": 0.28372612595558167,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 11.8676,
+      "step": 42
+    },
+    {
+      "epoch": 0.004815364371902909,
+      "grad_norm": 0.2954985797405243,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 11.869,
+      "step": 43
+    },
+    {
+      "epoch": 0.00492734958985414,
+      "grad_norm": 0.33279144763946533,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 11.8715,
+      "step": 44
+    },
+    {
+      "epoch": 0.00503933480780537,
+      "grad_norm": 0.3475021421909332,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 11.8734,
+      "step": 45
+    },
+    {
+      "epoch": 0.0051513200257566,
+      "grad_norm": 0.4072447121143341,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 11.8688,
+      "step": 46
+    },
+    {
+      "epoch": 0.00526330524370783,
+      "grad_norm": 0.3972657322883606,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 11.8737,
+      "step": 47
+    },
+    {
+      "epoch": 0.005375290461659061,
+      "grad_norm": 0.3975347578525543,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 11.8708,
+      "step": 48
+    },
+    {
+      "epoch": 0.0054872756796102914,
+      "grad_norm": 0.39711788296699524,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 11.8774,
+      "step": 49
+    },
+    {
+      "epoch": 0.005599260897561522,
+      "grad_norm": 0.5159602761268616,
+      "learning_rate": 0.0,
+      "loss": 11.877,
+      "step": 50
+    },
+    {
+      "epoch": 0.005599260897561522,
+      "eval_loss": 11.870880126953125,
+      "eval_runtime": 73.79,
+      "eval_samples_per_second": 203.822,
+      "eval_steps_per_second": 25.478,
+      "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": 13910114304000.0,
+  "total_flos": 27682504704000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null