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:f4db3be2c65761ca5a8e83c63a3d496cd59c044a0cbc39f809ab318466798821
+oid sha256:d4f4678ce90a16fee21c53238e7ac3b0b15b7542ed74672437e0981e8518141e
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87cfc20d5bf4b5c402b68a12aa5b44c8402622d92540853b865b7879c1ed0d73
+oid sha256:fd83b7ccef1cc5f5adc8b362f52d654d94604a28e54b40f467edb86f588073a9
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:870f715c4414d531d9788311f7243348b53522547a089faa8a32367237cea8f6
+oid sha256:9cc3692150dd634bd6d30911e2c881f26a128819de61c5d49e0b4889840a7894
 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": 2.0449941158294678,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.028851702250432775,
+  "epoch": 0.05770340450086555,
   "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": 26.302,
       "eval_steps_per_second": 3.297,
       "step": 25
+    },
+    {
+      "epoch": 0.030005770340450086,
+      "grad_norm": 8.109495162963867,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 7.9473,
+      "step": 26
+    },
+    {
+      "epoch": 0.031159838430467397,
+      "grad_norm": 8.148787498474121,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 7.2724,
+      "step": 27
+    },
+    {
+      "epoch": 0.03231390652048471,
+      "grad_norm": 8.987346649169922,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 7.6946,
+      "step": 28
+    },
+    {
+      "epoch": 0.03346797461050202,
+      "grad_norm": 8.511104583740234,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 7.9146,
+      "step": 29
+    },
+    {
+      "epoch": 0.03462204270051933,
+      "grad_norm": 9.82064151763916,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 8.1611,
+      "step": 30
+    },
+    {
+      "epoch": 0.03577611079053664,
+      "grad_norm": 10.174384117126465,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 8.4572,
+      "step": 31
+    },
+    {
+      "epoch": 0.03693017888055395,
+      "grad_norm": 9.278128623962402,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 7.8648,
+      "step": 32
+    },
+    {
+      "epoch": 0.038084246970571264,
+      "grad_norm": 9.342947959899902,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 8.363,
+      "step": 33
+    },
+    {
+      "epoch": 0.03923831506058857,
+      "grad_norm": 9.482563972473145,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 8.0515,
+      "step": 34
+    },
+    {
+      "epoch": 0.040392383150605886,
+      "grad_norm": 11.584480285644531,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 8.4733,
+      "step": 35
+    },
+    {
+      "epoch": 0.0415464512406232,
+      "grad_norm": 9.485844612121582,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 7.3311,
+      "step": 36
+    },
+    {
+      "epoch": 0.04270051933064051,
+      "grad_norm": 9.728912353515625,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 7.9032,
+      "step": 37
+    },
+    {
+      "epoch": 0.04385458742065782,
+      "grad_norm": 9.852460861206055,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 8.1847,
+      "step": 38
+    },
+    {
+      "epoch": 0.04500865551067513,
+      "grad_norm": 10.66511344909668,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 8.5239,
+      "step": 39
+    },
+    {
+      "epoch": 0.04616272360069244,
+      "grad_norm": 11.959909439086914,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 8.5198,
+      "step": 40
+    },
+    {
+      "epoch": 0.04731679169070975,
+      "grad_norm": 11.096136093139648,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 8.3557,
+      "step": 41
+    },
+    {
+      "epoch": 0.048470859780727064,
+      "grad_norm": 10.416865348815918,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 7.6118,
+      "step": 42
+    },
+    {
+      "epoch": 0.04962492787074437,
+      "grad_norm": 12.099180221557617,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 8.1399,
+      "step": 43
+    },
+    {
+      "epoch": 0.050778995960761686,
+      "grad_norm": 11.580448150634766,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 8.2984,
+      "step": 44
+    },
+    {
+      "epoch": 0.05193306405077899,
+      "grad_norm": 12.245722770690918,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 8.5435,
+      "step": 45
+    },
+    {
+      "epoch": 0.05308713214079631,
+      "grad_norm": 13.376921653747559,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 8.0788,
+      "step": 46
+    },
+    {
+      "epoch": 0.054241200230813615,
+      "grad_norm": 17.974956512451172,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 8.3619,
+      "step": 47
+    },
+    {
+      "epoch": 0.05539526832083093,
+      "grad_norm": 18.45572280883789,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 8.801,
+      "step": 48
+    },
+    {
+      "epoch": 0.05654933641084824,
+      "grad_norm": 28.996519088745117,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 8.9224,
+      "step": 49
+    },
+    {
+      "epoch": 0.05770340450086555,
+      "grad_norm": 45.305240631103516,
+      "learning_rate": 0.0,
+      "loss": 9.7115,
+      "step": 50
+    },
+    {
+      "epoch": 0.05770340450086555,
+      "eval_loss": 2.064781904220581,
+      "eval_runtime": 55.3206,
+      "eval_samples_per_second": 26.392,
+      "eval_steps_per_second": 3.308,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.806637019745485e+16,
+  "total_flos": 3.595386544245965e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null