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:c8272a38f3d535f54d6d85c84a949f07374e3a91c84ffaafcc64931c94a4a6ff
+oid sha256:1a012c2820ba0237cc64680cf69e9d38ebfbed5a291b322a883ca90225048e22
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:748fc115ffd337d3af3cf97001d7f98b863df002d47e2c4c8f815fe8934f6cef
+oid sha256:22bcc63d0ef26744cc14aa28d5fb394da8e5ae65fcbcb85b1dc16cb403704391
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65248751b9d1f4974ce7e76e6708a0d1fc2e1229a1cb7754e108886031b99470
+oid sha256:5742dd433ee3ae60e4b3a90fdad43ff46cc6ea4b4f2744fa31781352ce7ddb2b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8690e916f94ab2f0cde1f3a30b694f44f07173f24b1c4640a41cc1561b73d277
+oid sha256:dc1c972811a5b35b45ca0f9da96ca5d4ccad8141bb4c6eedf8ef5c25d450faff
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35a1d80028cd2421d5e6589956e5e261338acce94b00a3982a1856b50ab8c8dd
+oid sha256:adb9c6b9c0c2d5452cfb6e67cd9803d35665084bb5eaec4c9434f39252459f5a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b3ebe4c276db977fd509c8039e5b36d1c72fe7ee7627ec25f09160fb45458b2
+oid sha256:99006e2dcbe2a806a4e5201319fb8556cfc5e36b099db46ef1a3899ca6ff4a37
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd8b969ce6a3f06e5c06504065f43d471f4f8e360f2eb91a5068e5fed0b0d9dc
+oid sha256:344fc18df9c84f214bc47e69d1bbde70d66cf3ec6caeac9cd529dfb5814c4b9a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0427753925323486,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.626713670191931,
+  "best_metric": 1.0223414897918701,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.9400705052878966,
   "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": 99.253,
       "eval_steps_per_second": 25.806,
       "step": 50
+    },
+    {
+      "epoch": 0.6392479435957696,
+      "grad_norm": 0.6127623915672302,
+      "learning_rate": 5.7231268960295e-05,
+      "loss": 1.5449,
+      "step": 51
+    },
+    {
+      "epoch": 0.6517822169996083,
+      "grad_norm": 0.15788757801055908,
+      "learning_rate": 5.574402751448614e-05,
+      "loss": 1.1523,
+      "step": 52
+    },
+    {
+      "epoch": 0.664316490403447,
+      "grad_norm": 0.19719970226287842,
+      "learning_rate": 5.425597248551387e-05,
+      "loss": 1.0965,
+      "step": 53
+    },
+    {
+      "epoch": 0.6768507638072856,
+      "grad_norm": 0.20220746099948883,
+      "learning_rate": 5.2768731039705e-05,
+      "loss": 1.0729,
+      "step": 54
+    },
+    {
+      "epoch": 0.6893850372111242,
+      "grad_norm": 0.21883238852024078,
+      "learning_rate": 5.128392945374505e-05,
+      "loss": 1.0133,
+      "step": 55
+    },
+    {
+      "epoch": 0.7019193106149628,
+      "grad_norm": 0.20048078894615173,
+      "learning_rate": 4.980319133636863e-05,
+      "loss": 0.9661,
+      "step": 56
+    },
+    {
+      "epoch": 0.7144535840188014,
+      "grad_norm": 0.23357737064361572,
+      "learning_rate": 4.83281358529671e-05,
+      "loss": 0.983,
+      "step": 57
+    },
+    {
+      "epoch": 0.72698785742264,
+      "grad_norm": 0.24839633703231812,
+      "learning_rate": 4.686037595505507e-05,
+      "loss": 1.0299,
+      "step": 58
+    },
+    {
+      "epoch": 0.7395221308264787,
+      "grad_norm": 0.2856897711753845,
+      "learning_rate": 4.54015166165314e-05,
+      "loss": 1.083,
+      "step": 59
+    },
+    {
+      "epoch": 0.7520564042303173,
+      "grad_norm": 0.3443909287452698,
+      "learning_rate": 4.395315307866405e-05,
+      "loss": 1.0942,
+      "step": 60
+    },
+    {
+      "epoch": 0.7645906776341559,
+      "grad_norm": 0.3818349242210388,
+      "learning_rate": 4.2516869105717004e-05,
+      "loss": 1.1876,
+      "step": 61
+    },
+    {
+      "epoch": 0.7771249510379945,
+      "grad_norm": 0.5584022998809814,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 1.2389,
+      "step": 62
+    },
+    {
+      "epoch": 0.7896592244418331,
+      "grad_norm": 1.83659029006958,
+      "learning_rate": 3.968680715012606e-05,
+      "loss": 1.8469,
+      "step": 63
+    },
+    {
+      "epoch": 0.8021934978456717,
+      "grad_norm": 0.15524441003799438,
+      "learning_rate": 3.829612379868006e-05,
+      "loss": 1.1955,
+      "step": 64
+    },
+    {
+      "epoch": 0.8147277712495103,
+      "grad_norm": 0.15641632676124573,
+      "learning_rate": 3.692370589061639e-05,
+      "loss": 1.1487,
+      "step": 65
+    },
+    {
+      "epoch": 0.827262044653349,
+      "grad_norm": 0.1683935523033142,
+      "learning_rate": 3.557105414476782e-05,
+      "loss": 1.0506,
+      "step": 66
+    },
+    {
+      "epoch": 0.8397963180571876,
+      "grad_norm": 0.17298902571201324,
+      "learning_rate": 3.423964766595906e-05,
+      "loss": 1.0407,
+      "step": 67
+    },
+    {
+      "epoch": 0.8523305914610263,
+      "grad_norm": 0.19782142341136932,
+      "learning_rate": 3.293094232762715e-05,
+      "loss": 0.9614,
+      "step": 68
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 0.2152557373046875,
+      "learning_rate": 3.164636917984534e-05,
+      "loss": 0.9624,
+      "step": 69
+    },
+    {
+      "epoch": 0.8773991382687035,
+      "grad_norm": 0.2377156764268875,
+      "learning_rate": 3.0387332884490805e-05,
+      "loss": 0.9853,
+      "step": 70
+    },
+    {
+      "epoch": 0.8899334116725421,
+      "grad_norm": 0.24591700732707977,
+      "learning_rate": 2.9155210179267546e-05,
+      "loss": 1.0166,
+      "step": 71
+    },
+    {
+      "epoch": 0.9024676850763808,
+      "grad_norm": 0.32400262355804443,
+      "learning_rate": 2.7951348372263875e-05,
+      "loss": 1.0993,
+      "step": 72
+    },
+    {
+      "epoch": 0.9150019584802194,
+      "grad_norm": 0.3385933041572571,
+      "learning_rate": 2.677706386869083e-05,
+      "loss": 1.0851,
+      "step": 73
+    },
+    {
+      "epoch": 0.927536231884058,
+      "grad_norm": 0.4308682382106781,
+      "learning_rate": 2.5633640731412412e-05,
+      "loss": 1.1932,
+      "step": 74
+    },
+    {
+      "epoch": 0.9400705052878966,
+      "grad_norm": 0.8425101041793823,
+      "learning_rate": 2.4522329276841663e-05,
+      "loss": 1.2269,
+      "step": 75
+    },
+    {
+      "epoch": 0.9400705052878966,
+      "eval_loss": 1.0223414897918701,
+      "eval_runtime": 0.5047,
+      "eval_samples_per_second": 99.066,
+      "eval_steps_per_second": 25.757,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.437038735740109e+16,
+  "total_flos": 1.26601158625067e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null