Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fd6bd14a4bd9aeb65b8c0cfc08a0bc062e480a7319bbbb02bff3df224c7b796
+oid sha256:3ea9bbaa9f836e88548307399cd646ed9a9e416b5de868e1aa57e4c6da5e3452
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55335180b41dba9386f509f6a6652bdfb710eb655457d6f1587f51f075477022
+oid sha256:9247931af67bd9a86e518ee6d4ef73669be7902d5224f399ccb69ba606d7bc86
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fba41c83797779d13308b6490e3948112be5cc81ad2e4ad3102f676415c8ac22
+oid sha256:599ddcee07d5a861ece0f4de1903724e4aca1c3286a9c2cbd77dcae86ba5fdf1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6f284accce65d2ede65b0bb66f4935f6d266e142f2dbafafdf8e291dc52e6ef
+oid sha256:56e481d3f13ff36459d8279663c80a3f95d42710e9f0e63fccf59b1bd807e90b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04073f63101cc92cdf747d9546f6ab9d7e9f2de0add0393843e4344e2287bc45
+oid sha256:1a6844d3eabdd14fe6c38335fcbc9f23cfe6cfecd9d4e6657f75d84170558131
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d5cbe6c848f023bf0a2ea634e1f40a56528e5919d5e670c1c186358d693d28e
+oid sha256:b7454acfb1745ea0de3b382e69cb8a8d7b6de3387a7648d0332213c440912038
 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": 2.51250958442688,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.7020623080298376,
+  "best_metric": 2.4749317169189453,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 1.0530934620447565,
   "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": 98.857,
       "eval_steps_per_second": 25.703,
       "step": 50
+    },
+    {
+      "epoch": 0.7161035541904344,
+      "grad_norm": 0.2579071819782257,
+      "learning_rate": 5.7231268960295e-05,
+      "loss": 1.8802,
+      "step": 51
+    },
+    {
+      "epoch": 0.7301448003510311,
+      "grad_norm": 0.4030728042125702,
+      "learning_rate": 5.574402751448614e-05,
+      "loss": 1.6649,
+      "step": 52
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "grad_norm": 0.5643269419670105,
+      "learning_rate": 5.425597248551387e-05,
+      "loss": 2.049,
+      "step": 53
+    },
+    {
+      "epoch": 0.7582272926722247,
+      "grad_norm": 0.7029362916946411,
+      "learning_rate": 5.2768731039705e-05,
+      "loss": 2.2015,
+      "step": 54
+    },
+    {
+      "epoch": 0.7722685388328214,
+      "grad_norm": 0.9349853992462158,
+      "learning_rate": 5.128392945374505e-05,
+      "loss": 2.4515,
+      "step": 55
+    },
+    {
+      "epoch": 0.7863097849934182,
+      "grad_norm": 0.9511843323707581,
+      "learning_rate": 4.980319133636863e-05,
+      "loss": 2.6827,
+      "step": 56
+    },
+    {
+      "epoch": 0.800351031154015,
+      "grad_norm": 1.3044384717941284,
+      "learning_rate": 4.83281358529671e-05,
+      "loss": 2.8935,
+      "step": 57
+    },
+    {
+      "epoch": 0.8143922773146117,
+      "grad_norm": 1.4280407428741455,
+      "learning_rate": 4.686037595505507e-05,
+      "loss": 2.9421,
+      "step": 58
+    },
+    {
+      "epoch": 0.8284335234752084,
+      "grad_norm": 1.7793262004852295,
+      "learning_rate": 4.54015166165314e-05,
+      "loss": 3.0256,
+      "step": 59
+    },
+    {
+      "epoch": 0.8424747696358051,
+      "grad_norm": 2.2841506004333496,
+      "learning_rate": 4.395315307866405e-05,
+      "loss": 3.1879,
+      "step": 60
+    },
+    {
+      "epoch": 0.8565160157964019,
+      "grad_norm": 3.2203478813171387,
+      "learning_rate": 4.2516869105717004e-05,
+      "loss": 3.5137,
+      "step": 61
+    },
+    {
+      "epoch": 0.8705572619569987,
+      "grad_norm": 4.7022576332092285,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 3.5993,
+      "step": 62
+    },
+    {
+      "epoch": 0.8845985081175954,
+      "grad_norm": 0.3040692210197449,
+      "learning_rate": 3.968680715012606e-05,
+      "loss": 2.1119,
+      "step": 63
+    },
+    {
+      "epoch": 0.8986397542781922,
+      "grad_norm": 0.37016022205352783,
+      "learning_rate": 3.829612379868006e-05,
+      "loss": 1.8168,
+      "step": 64
+    },
+    {
+      "epoch": 0.912681000438789,
+      "grad_norm": 0.7952561378479004,
+      "learning_rate": 3.692370589061639e-05,
+      "loss": 2.1704,
+      "step": 65
+    },
+    {
+      "epoch": 0.9267222465993857,
+      "grad_norm": 1.0236883163452148,
+      "learning_rate": 3.557105414476782e-05,
+      "loss": 2.3811,
+      "step": 66
+    },
+    {
+      "epoch": 0.9407634927599825,
+      "grad_norm": 1.1880155801773071,
+      "learning_rate": 3.423964766595906e-05,
+      "loss": 2.6713,
+      "step": 67
+    },
+    {
+      "epoch": 0.9548047389205792,
+      "grad_norm": 1.3189986944198608,
+      "learning_rate": 3.293094232762715e-05,
+      "loss": 2.7698,
+      "step": 68
+    },
+    {
+      "epoch": 0.9688459850811759,
+      "grad_norm": 1.691144347190857,
+      "learning_rate": 3.164636917984534e-05,
+      "loss": 3.0012,
+      "step": 69
+    },
+    {
+      "epoch": 0.9828872312417727,
+      "grad_norm": 2.0627942085266113,
+      "learning_rate": 3.0387332884490805e-05,
+      "loss": 3.2204,
+      "step": 70
+    },
+    {
+      "epoch": 0.9969284774023695,
+      "grad_norm": 4.911252498626709,
+      "learning_rate": 2.9155210179267546e-05,
+      "loss": 3.705,
+      "step": 71
+    },
+    {
+      "epoch": 1.0109697235629662,
+      "grad_norm": 11.608001708984375,
+      "learning_rate": 2.7951348372263875e-05,
+      "loss": 4.9898,
+      "step": 72
+    },
+    {
+      "epoch": 1.025010969723563,
+      "grad_norm": 0.3285130262374878,
+      "learning_rate": 2.677706386869083e-05,
+      "loss": 1.4574,
+      "step": 73
+    },
+    {
+      "epoch": 1.0390522158841597,
+      "grad_norm": 0.49857988953590393,
+      "learning_rate": 2.5633640731412412e-05,
+      "loss": 1.9682,
+      "step": 74
+    },
+    {
+      "epoch": 1.0530934620447565,
+      "grad_norm": 0.6986849308013916,
+      "learning_rate": 2.4522329276841663e-05,
+      "loss": 1.9892,
+      "step": 75
+    },
+    {
+      "epoch": 1.0530934620447565,
+      "eval_loss": 2.4749317169189453,
+      "eval_runtime": 0.5047,
+      "eval_samples_per_second": 99.064,
+      "eval_steps_per_second": 25.757,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.95300912644096e+16,
+  "total_flos": 4.42951368966144e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null