Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33dbd4ffa9d98ebd26381da61dd3ce866edec1a6972b86982de082d78f7b9e10
+oid sha256:2105fc3cf59b772ffa4c08435318a440730655751c3e983fed3664111158a404
 size 60599872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd1880a92706cd833a2aae9f9bdd34118c2296b504d643b85394a8741ceb473c
+oid sha256:e533177ff6ce7e282ac00d673cef060f9ab5c631beaa9d43e3464ce82c5fe617
 size 121392706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a21a0f0434cb5cbedf68f8faef2da1740b04ded2f51ffaf8793c6a9331085b5d
+oid sha256:3a16cdea4ab6cd5189a5eb581a1814fa4f81fe45ad060d5bd31aff2fe3c0a9ff
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6c95cb605a0203cfb312fc76e97a24ce137aceb48d8d9a3c6a0d1a1f69a587a
+oid sha256:461f615bb6d5f10fb39244c5cd08621475b9922ce50eb3dbab195994fc77c354
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:536c52bad12032e48af6f1b8686bbf36a4559fc127d186eaef3dd04e7efd2197
+oid sha256:04fcdb452e42ce667cae2036cf36082b7c488423d72302b63a59effebb867b81
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d47692fb7c509d992a41d911e6acb752bdfb94759bfee05a269fe6101021c776
+oid sha256:37ac76350d28e1e3d492b285e5f6d277edda42f2bad33f9b9a66921808e4d174
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4245748519897461,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1554605518849592,
+  "best_metric": 0.4202527701854706,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3109211037699184,
   "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": 98.859,
       "eval_steps_per_second": 25.703,
       "step": 25
+    },
+    {
+      "epoch": 0.16167897396035755,
+      "grad_norm": 0.20568077266216278,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.4854,
+      "step": 26
+    },
+    {
+      "epoch": 0.16789739603575593,
+      "grad_norm": 0.231986865401268,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.472,
+      "step": 27
+    },
+    {
+      "epoch": 0.17411581811115429,
+      "grad_norm": 0.22924061119556427,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.4573,
+      "step": 28
+    },
+    {
+      "epoch": 0.18033424018655267,
+      "grad_norm": 0.26050734519958496,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.4439,
+      "step": 29
+    },
+    {
+      "epoch": 0.18655266226195102,
+      "grad_norm": 0.2478851079940796,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.464,
+      "step": 30
+    },
+    {
+      "epoch": 0.1927710843373494,
+      "grad_norm": 0.2619074285030365,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.4037,
+      "step": 31
+    },
+    {
+      "epoch": 0.19898950641274776,
+      "grad_norm": 0.2379845380783081,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.3882,
+      "step": 32
+    },
+    {
+      "epoch": 0.20520792848814615,
+      "grad_norm": 0.23740604519844055,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.4082,
+      "step": 33
+    },
+    {
+      "epoch": 0.2114263505635445,
+      "grad_norm": 0.2532176077365875,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.4227,
+      "step": 34
+    },
+    {
+      "epoch": 0.21764477263894286,
+      "grad_norm": 0.2832277715206146,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.4474,
+      "step": 35
+    },
+    {
+      "epoch": 0.22386319471434124,
+      "grad_norm": 0.3031919598579407,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4277,
+      "step": 36
+    },
+    {
+      "epoch": 0.2300816167897396,
+      "grad_norm": 0.35860636830329895,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.4453,
+      "step": 37
+    },
+    {
+      "epoch": 0.23630003886513798,
+      "grad_norm": 0.16608692705631256,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.5265,
+      "step": 38
+    },
+    {
+      "epoch": 0.24251846094053633,
+      "grad_norm": 0.1570015847682953,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4632,
+      "step": 39
+    },
+    {
+      "epoch": 0.24873688301593472,
+      "grad_norm": 0.17254012823104858,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.446,
+      "step": 40
+    },
+    {
+      "epoch": 0.2549553050913331,
+      "grad_norm": 0.1886199414730072,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.4512,
+      "step": 41
+    },
+    {
+      "epoch": 0.26117372716673143,
+      "grad_norm": 0.19815868139266968,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.4144,
+      "step": 42
+    },
+    {
+      "epoch": 0.2673921492421298,
+      "grad_norm": 0.2087705135345459,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.3708,
+      "step": 43
+    },
+    {
+      "epoch": 0.2736105713175282,
+      "grad_norm": 0.22395019233226776,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.4433,
+      "step": 44
+    },
+    {
+      "epoch": 0.27982899339292655,
+      "grad_norm": 0.23942124843597412,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.417,
+      "step": 45
+    },
+    {
+      "epoch": 0.2860474154683249,
+      "grad_norm": 0.23817619681358337,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.4103,
+      "step": 46
+    },
+    {
+      "epoch": 0.29226583754372326,
+      "grad_norm": 0.2759843170642853,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.4418,
+      "step": 47
+    },
+    {
+      "epoch": 0.2984842596191217,
+      "grad_norm": 0.31546300649642944,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.4751,
+      "step": 48
+    },
+    {
+      "epoch": 0.30470268169452003,
+      "grad_norm": 0.34774115681648254,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.4728,
+      "step": 49
+    },
+    {
+      "epoch": 0.3109211037699184,
+      "grad_norm": 0.5190607905387878,
+      "learning_rate": 1e-05,
+      "loss": 0.5034,
+      "step": 50
+    },
+    {
+      "epoch": 0.3109211037699184,
+      "eval_loss": 0.4202527701854706,
+      "eval_runtime": 0.5035,
+      "eval_samples_per_second": 99.296,
+      "eval_steps_per_second": 25.817,
+      "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": 1.2754075942649856e+16,
+  "total_flos": 2.549622476111872e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null