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:b9c4b10b7fea599f0e3aa477a25b219093c9bb1a4518135942bca1c47f928952
+oid sha256:6116ba9bdb32e058073d5d71820ab2748bd229f6356c13e7695d45e0e58c4a33
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:957b50790e5e630ece6f3edd9ff56281259ff7b9eeb0c3c49d7d6b5c83cff43f
+oid sha256:c9965a7197909b86f7c7ae1dcfd465d917f68014f2c106b271dd4f6cfaebf260
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8117bc33c2211d288a3b4648678473459aa0cac526a935f55ca077fdd884a167
+oid sha256:f99d89928cb6b064d06aab3037606d4c8f62a0c3ea9b4c2f01092be14ae6b56a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d10bad395edcdef67ca97761afa569e85563ec196e651042e8e1f30bf77acf31
+oid sha256:a874492c67d487c51ed17d584d1b6dc07b70a151ea0a5f76ae84796a21604b94
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16bc4225fbbb2a6399238b188c84cb6610b59e3342454d3672dd3db0b9c6b692
+oid sha256:05f89fb41cb495727feaede94276307a5219438e86f5fdf6207cfba00e400d6a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f28c5d2b33d70f7970ce8984bb29fa21089185659740efe8cf9f6e6fd04e780e
+oid sha256:d3536ce552e10d9d1c9b4928d6955c8094145e2581bce3d55a8e53a23e6a6dbf
 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": 0.4710754156112671,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.13788348845225784,
+  "best_metric": 0.31743958592414856,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2757669769045157,
   "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": 24.009,
       "eval_steps_per_second": 6.242,
       "step": 25
+    },
+    {
+      "epoch": 0.14339882799034814,
+      "grad_norm": 15.763641357421875,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 1.0617,
+      "step": 26
+    },
+    {
+      "epoch": 0.14891416752843847,
+      "grad_norm": 15.280720710754395,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 1.3544,
+      "step": 27
+    },
+    {
+      "epoch": 0.15442950706652878,
+      "grad_norm": 14.879006385803223,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 1.4492,
+      "step": 28
+    },
+    {
+      "epoch": 0.1599448466046191,
+      "grad_norm": 14.426602363586426,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 1.3997,
+      "step": 29
+    },
+    {
+      "epoch": 0.1654601861427094,
+      "grad_norm": 14.272067070007324,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 1.2409,
+      "step": 30
+    },
+    {
+      "epoch": 0.1709755256807997,
+      "grad_norm": 9.54008960723877,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 0.7096,
+      "step": 31
+    },
+    {
+      "epoch": 0.17649086521889004,
+      "grad_norm": 0.5781741738319397,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 0.0109,
+      "step": 32
+    },
+    {
+      "epoch": 0.18200620475698034,
+      "grad_norm": 1.3752659559249878,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 0.0241,
+      "step": 33
+    },
+    {
+      "epoch": 0.18752154429507067,
+      "grad_norm": 1.6789705753326416,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 0.0301,
+      "step": 34
+    },
+    {
+      "epoch": 0.19303688383316098,
+      "grad_norm": 1.4155908823013306,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 0.0255,
+      "step": 35
+    },
+    {
+      "epoch": 0.19855222337125128,
+      "grad_norm": 0.8778910040855408,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 0.0164,
+      "step": 36
+    },
+    {
+      "epoch": 0.2040675629093416,
+      "grad_norm": 0.4698180556297302,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 0.0094,
+      "step": 37
+    },
+    {
+      "epoch": 0.2095829024474319,
+      "grad_norm": 7.407131671905518,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 0.5839,
+      "step": 38
+    },
+    {
+      "epoch": 0.21509824198552224,
+      "grad_norm": 11.81148624420166,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 0.9861,
+      "step": 39
+    },
+    {
+      "epoch": 0.22061358152361255,
+      "grad_norm": 11.63061237335205,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 0.9721,
+      "step": 40
+    },
+    {
+      "epoch": 0.22612892106170285,
+      "grad_norm": 11.430267333984375,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 0.9024,
+      "step": 41
+    },
+    {
+      "epoch": 0.23164426059979318,
+      "grad_norm": 11.040278434753418,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 0.7755,
+      "step": 42
+    },
+    {
+      "epoch": 0.23715960013788348,
+      "grad_norm": 9.684221267700195,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 0.5668,
+      "step": 43
+    },
+    {
+      "epoch": 0.2426749396759738,
+      "grad_norm": 2.087521553039551,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 0.0431,
+      "step": 44
+    },
+    {
+      "epoch": 0.2481902792140641,
+      "grad_norm": 3.5265278816223145,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 0.0777,
+      "step": 45
+    },
+    {
+      "epoch": 0.2537056187521544,
+      "grad_norm": 4.007287502288818,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 0.0911,
+      "step": 46
+    },
+    {
+      "epoch": 0.2592209582902447,
+      "grad_norm": 3.595430612564087,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 0.0834,
+      "step": 47
+    },
+    {
+      "epoch": 0.2647362978283351,
+      "grad_norm": 2.904953956604004,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 0.0653,
+      "step": 48
+    },
+    {
+      "epoch": 0.2702516373664254,
+      "grad_norm": 1.9227010011672974,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0425,
+      "step": 49
+    },
+    {
+      "epoch": 0.2757669769045157,
+      "grad_norm": 1.1187314987182617,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 0.0248,
+      "step": 50
+    },
+    {
+      "epoch": 0.2757669769045157,
+      "eval_loss": 0.31743958592414856,
+      "eval_runtime": 2.0803,
+      "eval_samples_per_second": 24.035,
+      "eval_steps_per_second": 6.249,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null