Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1451a702699db0b162280617f8d020063fb3bcbd5a2a2a21818960587e1c983e
+oid sha256:f7daceaf2dcbe6256b4ae8c6a63a21ac3c18573e454c59d1a2176432d2a57818
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e2cc4569576a6a5c19a849731d774de646ff7feb129b9d68a2a889eef397e1a
+oid sha256:456ad96068cbf3d113327f5d90e5514b474994209c0def9c858bdb3519a2e4c1
 size 71077780

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f68da0255841021d9166b7bc111c4ce967822f514670ce270007fb6c9af3efb
+oid sha256:e098d21f402c01f47452f94c679d0b9cb9c748cbe1ac6784d8bda38660959ccb
 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": 1.4338550567626953,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.009140767824497258,
+  "best_metric": 1.400192141532898,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.018281535648994516,
   "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": 67.134,
       "eval_steps_per_second": 8.394,
       "step": 25
+    },
+    {
+      "epoch": 0.009506398537477149,
+      "grad_norm": 0.15829448401927948,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.4437,
+      "step": 26
+    },
+    {
+      "epoch": 0.009872029250457038,
+      "grad_norm": 0.14465104043483734,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.4092,
+      "step": 27
+    },
+    {
+      "epoch": 0.010237659963436929,
+      "grad_norm": 0.1586385816335678,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.4306,
+      "step": 28
+    },
+    {
+      "epoch": 0.01060329067641682,
+      "grad_norm": 0.16052576899528503,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.4512,
+      "step": 29
+    },
+    {
+      "epoch": 0.010968921389396709,
+      "grad_norm": 0.15008322894573212,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.4282,
+      "step": 30
+    },
+    {
+      "epoch": 0.0113345521023766,
+      "grad_norm": 0.1620539277791977,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.489,
+      "step": 31
+    },
+    {
+      "epoch": 0.01170018281535649,
+      "grad_norm": 0.16483284533023834,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.4853,
+      "step": 32
+    },
+    {
+      "epoch": 0.01206581352833638,
+      "grad_norm": 0.15536175668239594,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.4549,
+      "step": 33
+    },
+    {
+      "epoch": 0.01243144424131627,
+      "grad_norm": 0.14910203218460083,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.3926,
+      "step": 34
+    },
+    {
+      "epoch": 0.012797074954296161,
+      "grad_norm": 0.14977602660655975,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.3395,
+      "step": 35
+    },
+    {
+      "epoch": 0.01316270566727605,
+      "grad_norm": 0.15815122425556183,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.4415,
+      "step": 36
+    },
+    {
+      "epoch": 0.013528336380255941,
+      "grad_norm": 0.15232770144939423,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.431,
+      "step": 37
+    },
+    {
+      "epoch": 0.013893967093235832,
+      "grad_norm": 0.16287685930728912,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.4705,
+      "step": 38
+    },
+    {
+      "epoch": 0.014259597806215722,
+      "grad_norm": 0.16413241624832153,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.4865,
+      "step": 39
+    },
+    {
+      "epoch": 0.014625228519195612,
+      "grad_norm": 0.146493062376976,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.4395,
+      "step": 40
+    },
+    {
+      "epoch": 0.014990859232175503,
+      "grad_norm": 0.1493939459323883,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.4134,
+      "step": 41
+    },
+    {
+      "epoch": 0.015356489945155392,
+      "grad_norm": 0.16362649202346802,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.4669,
+      "step": 42
+    },
+    {
+      "epoch": 0.015722120658135285,
+      "grad_norm": 0.17766478657722473,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.4814,
+      "step": 43
+    },
+    {
+      "epoch": 0.016087751371115174,
+      "grad_norm": 0.14952148497104645,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.4376,
+      "step": 44
+    },
+    {
+      "epoch": 0.016453382084095063,
+      "grad_norm": 0.16464552283287048,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.5386,
+      "step": 45
+    },
+    {
+      "epoch": 0.016819012797074956,
+      "grad_norm": 0.1606977880001068,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.4878,
+      "step": 46
+    },
+    {
+      "epoch": 0.017184643510054845,
+      "grad_norm": 0.16758908331394196,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.4678,
+      "step": 47
+    },
+    {
+      "epoch": 0.017550274223034734,
+      "grad_norm": 0.16065165400505066,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.4645,
+      "step": 48
+    },
+    {
+      "epoch": 0.017915904936014627,
+      "grad_norm": 0.17361202836036682,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.5199,
+      "step": 49
+    },
+    {
+      "epoch": 0.018281535648994516,
+      "grad_norm": 0.19459863007068634,
+      "learning_rate": 0.0,
+      "loss": 1.4341,
+      "step": 50
+    },
+    {
+      "epoch": 0.018281535648994516,
+      "eval_loss": 1.400192141532898,
+      "eval_runtime": 68.6675,
+      "eval_samples_per_second": 67.091,
+      "eval_steps_per_second": 8.388,
+      "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": 1717219885056000.0,
+  "total_flos": 3434439770112000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null