Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1882108af6d608e2676ecaa6664223ceb00dc7174189258500bfc93339e2e029
+oid sha256:793dfc603f2c7a7c15dcdf4bb51da84a72125a8219b19ce1cbd254729d64737e
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46030a6e9332c869aa2458095b8e3dd9ba63a49424c9fd44d7b74b1609df6982
+oid sha256:856e7d4eb9bd346bf124dff87a8946f1671a604bfd7531d553ff39abb77add29
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91636dec793429ee602fdaf9b9faa0afdc47095f72ae969f5c58810a97da0987
+oid sha256:1c54bf62083df637d1530b0f4e42da7a5383f1440dcf59914ac070a0cc961306
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e50f70672872f3b8010a720ca817361faa4c57b49eed6c138b47d944908fb4fb
+oid sha256:45b3ae6d3c75fc9a883598570634d2d02e94adb288116ee96016d8e66593f33c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f07cf1bebaf9d9405dc7edc08f6baf744cadc9272e707450483ddf1b8d071a67
+oid sha256:ca4e985a3b2ce7e77c43587f7b4ad3d34862356bce8859e611d669cac953ad1a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a4d2fc00d7f1440110e76ad6cee684c0489b4e4ff90c7bcb515e8b99f55976
+oid sha256:2338ab34fe89067e42575e3154cbe5a7bc3334783ac35e5c51d9e7df9a240fec
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
+oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.91409969329834,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.012340346763744061,
+  "best_metric": 6.8887457847595215,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.024680693527488123,
   "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": 593.267,
       "eval_steps_per_second": 154.249,
       "step": 25
+    },
+    {
+      "epoch": 0.012833960634293824,
+      "grad_norm": 0.15400898456573486,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 6.92,
+      "step": 26
+    },
+    {
+      "epoch": 0.013327574504843585,
+      "grad_norm": 0.16461063921451569,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 6.9187,
+      "step": 27
+    },
+    {
+      "epoch": 0.013821188375393348,
+      "grad_norm": 0.15997587144374847,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 6.9185,
+      "step": 28
+    },
+    {
+      "epoch": 0.014314802245943111,
+      "grad_norm": 0.17501673102378845,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 6.915,
+      "step": 29
+    },
+    {
+      "epoch": 0.014808416116492874,
+      "grad_norm": 0.16417518258094788,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 6.9176,
+      "step": 30
+    },
+    {
+      "epoch": 0.015302029987042635,
+      "grad_norm": 0.17748786509037018,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 6.9119,
+      "step": 31
+    },
+    {
+      "epoch": 0.015795643857592398,
+      "grad_norm": 0.17625170946121216,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 6.9124,
+      "step": 32
+    },
+    {
+      "epoch": 0.01628925772814216,
+      "grad_norm": 0.16539260745048523,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 6.914,
+      "step": 33
+    },
+    {
+      "epoch": 0.016782871598691924,
+      "grad_norm": 0.18232646584510803,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 6.9073,
+      "step": 34
+    },
+    {
+      "epoch": 0.017276485469241685,
+      "grad_norm": 0.17349576950073242,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 6.9101,
+      "step": 35
+    },
+    {
+      "epoch": 0.01777009933979145,
+      "grad_norm": 0.1874023824930191,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 6.9062,
+      "step": 36
+    },
+    {
+      "epoch": 0.01826371321034121,
+      "grad_norm": 0.17965620756149292,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 6.905,
+      "step": 37
+    },
+    {
+      "epoch": 0.01875732708089097,
+      "grad_norm": 0.17918899655342102,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 6.9092,
+      "step": 38
+    },
+    {
+      "epoch": 0.019250940951440736,
+      "grad_norm": 0.18893581628799438,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 6.9072,
+      "step": 39
+    },
+    {
+      "epoch": 0.019744554821990497,
+      "grad_norm": 0.189700648188591,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 6.9048,
+      "step": 40
+    },
+    {
+      "epoch": 0.020238168692540262,
+      "grad_norm": 0.19713561236858368,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 6.9022,
+      "step": 41
+    },
+    {
+      "epoch": 0.020731782563090023,
+      "grad_norm": 0.18430104851722717,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 6.9024,
+      "step": 42
+    },
+    {
+      "epoch": 0.021225396433639784,
+      "grad_norm": 0.18701981008052826,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 6.903,
+      "step": 43
+    },
+    {
+      "epoch": 0.02171901030418955,
+      "grad_norm": 0.18464837968349457,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 6.902,
+      "step": 44
+    },
+    {
+      "epoch": 0.02221262417473931,
+      "grad_norm": 0.18956860899925232,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 6.8958,
+      "step": 45
+    },
+    {
+      "epoch": 0.02270623804528907,
+      "grad_norm": 0.18333902955055237,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 6.9006,
+      "step": 46
+    },
+    {
+      "epoch": 0.023199851915838836,
+      "grad_norm": 0.17345166206359863,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 6.8991,
+      "step": 47
+    },
+    {
+      "epoch": 0.023693465786388597,
+      "grad_norm": 0.17997267842292786,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 6.9001,
+      "step": 48
+    },
+    {
+      "epoch": 0.02418707965693836,
+      "grad_norm": 0.18579334020614624,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 6.8974,
+      "step": 49
+    },
+    {
+      "epoch": 0.024680693527488123,
+      "grad_norm": 0.1840241253376007,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 6.8931,
+      "step": 50
+    },
+    {
+      "epoch": 0.024680693527488123,
+      "eval_loss": 6.8887457847595215,
+      "eval_runtime": 0.0853,
+      "eval_samples_per_second": 586.013,
+      "eval_steps_per_second": 152.363,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2852978688000.0,
+  "total_flos": 5705957376000.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null