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:d71725811e9c5447f63e8d7918f9ff214a0fa85429e90d70291fc72adf64254f
+oid sha256:07d7787f9aec30487046e39e51002a4e91d9ee65e89828ced52fd1910e107915
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:928f7d4f4ae81afbc7438972f08ae9041d29ffe6c7af5891051fd397cdd1454d
+oid sha256:fa8a88a67b5b1c7d58b3ff4ca81322fd49fcef2c3a522ffbf118e7255a9c7bc0
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a65f8c299403a506d06cb719f981fb97e5389fb48ee7b4e62ec5fb723bb812db
+oid sha256:0d55073102a025f77ddb19131e3fb9177ea3f6071cf8e3bd5d6e70ca43c4e3c8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.456721544265747,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0018803000958953048,
+  "best_metric": 2.421727180480957,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0037606001917906097,
   "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": 9.756,
       "eval_steps_per_second": 4.879,
       "step": 25
+    },
+    {
+      "epoch": 0.001955512099731117,
+      "grad_norm": 0.8755390644073486,
+      "learning_rate": 0.0001,
+      "loss": 2.3892,
+      "step": 26
+    },
+    {
+      "epoch": 0.002030724103566929,
+      "grad_norm": 0.9554408192634583,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 2.6242,
+      "step": 27
+    },
+    {
+      "epoch": 0.0021059361074027413,
+      "grad_norm": 0.9592045545578003,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 2.4899,
+      "step": 28
+    },
+    {
+      "epoch": 0.0021811481112385535,
+      "grad_norm": 1.0437732934951782,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 2.5779,
+      "step": 29
+    },
+    {
+      "epoch": 0.002256360115074366,
+      "grad_norm": 0.9619537591934204,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 2.4567,
+      "step": 30
+    },
+    {
+      "epoch": 0.002331572118910178,
+      "grad_norm": 0.9852949380874634,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 2.1505,
+      "step": 31
+    },
+    {
+      "epoch": 0.0024067841227459904,
+      "grad_norm": 0.8928741216659546,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 2.3989,
+      "step": 32
+    },
+    {
+      "epoch": 0.0024819961265818025,
+      "grad_norm": 0.9359666109085083,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 2.1978,
+      "step": 33
+    },
+    {
+      "epoch": 0.0025572081304176147,
+      "grad_norm": 0.9542161226272583,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.4736,
+      "step": 34
+    },
+    {
+      "epoch": 0.002632420134253427,
+      "grad_norm": 0.9373902678489685,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 2.2662,
+      "step": 35
+    },
+    {
+      "epoch": 0.002707632138089239,
+      "grad_norm": 0.9853395819664001,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 2.5583,
+      "step": 36
+    },
+    {
+      "epoch": 0.002782844141925051,
+      "grad_norm": 0.9831791520118713,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 2.4576,
+      "step": 37
+    },
+    {
+      "epoch": 0.0028580561457608633,
+      "grad_norm": 1.011431097984314,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 2.2787,
+      "step": 38
+    },
+    {
+      "epoch": 0.0029332681495966755,
+      "grad_norm": 0.9966049194335938,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 2.3312,
+      "step": 39
+    },
+    {
+      "epoch": 0.0030084801534324876,
+      "grad_norm": 1.0577329397201538,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 2.3972,
+      "step": 40
+    },
+    {
+      "epoch": 0.0030836921572683002,
+      "grad_norm": 1.1195677518844604,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 2.6029,
+      "step": 41
+    },
+    {
+      "epoch": 0.0031589041611041124,
+      "grad_norm": 1.2073577642440796,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 2.5786,
+      "step": 42
+    },
+    {
+      "epoch": 0.0032341161649399246,
+      "grad_norm": 1.2137610912322998,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 2.4174,
+      "step": 43
+    },
+    {
+      "epoch": 0.0033093281687757367,
+      "grad_norm": 1.1731866598129272,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 2.2682,
+      "step": 44
+    },
+    {
+      "epoch": 0.003384540172611549,
+      "grad_norm": 0.9700923562049866,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 2.5303,
+      "step": 45
+    },
+    {
+      "epoch": 0.003459752176447361,
+      "grad_norm": 1.1716365814208984,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 2.4727,
+      "step": 46
+    },
+    {
+      "epoch": 0.003534964180283173,
+      "grad_norm": 1.3430166244506836,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 2.7678,
+      "step": 47
+    },
+    {
+      "epoch": 0.0036101761841189853,
+      "grad_norm": 1.5608717203140259,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 2.7983,
+      "step": 48
+    },
+    {
+      "epoch": 0.0036853881879547975,
+      "grad_norm": 1.3978331089019775,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 2.4935,
+      "step": 49
+    },
+    {
+      "epoch": 0.0037606001917906097,
+      "grad_norm": 3.3572194576263428,
+      "learning_rate": 0.0,
+      "loss": 2.6906,
+      "step": 50
+    },
+    {
+      "epoch": 0.0037606001917906097,
+      "eval_loss": 2.421727180480957,
+      "eval_runtime": 573.259,
+      "eval_samples_per_second": 9.767,
+      "eval_steps_per_second": 4.884,
+      "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": 5146843860172800.0,
+  "total_flos": 1.02936877203456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null