Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e2526945acc4c40850c3635254c61b75f6d4eae960a0e9e1be4e28f1491c861
+oid sha256:4a0e3e6423021244f025e8a2756138044eaff61a4705331ffbb1494814f5398c
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a2930f632916e59d110946ed72357c49b1fad9ba50098f5f5b031dc99415db8
+oid sha256:330e5ce04c97ff952f87859cd9f1e5459326489e400928028bc5f602c01d72f5
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5505b57b024b012f553f05f90052ede7a30d6c6a94e99c4cf3e92f4bbb8c35b
+oid sha256:3bfe710c13f053a31a062cb49cc8977f07aa304e727842ae94378d16f9c2eb54
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a139d2518a3ad0afb4b693960d9078858d6ba42250df8cc06e21f6337bf0068d
+oid sha256:89d78a1aebf19597cd8ff98f7926ac4269f296aa1d1624299a9f32e8caf8a078
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbe255832337a2756a877deff31268d8c5d6cfe9301dd0a63e0e929a940d6ef2
+oid sha256:609cfa78dc97089f7bb964cf3c72d10ea4ffd6fc0c0a90e1ad086cd3d80896f6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0180cf08d91a13a5d49b8a9e3ad6b37672b39409c7c2490c6df31da684cab372
+oid sha256:b71beadd62f059b758ab2b40331d8b84f794290e592baa996f44a3414cd82f51
 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": 10.22501277923584,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.020649957409462842,
+  "best_metric": 10.138866424560547,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.041299914818925684,
   "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": 616.479,
       "eval_steps_per_second": 160.285,
       "step": 25
+    },
+    {
+      "epoch": 0.021475955705841356,
+      "grad_norm": 2.095871925354004,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 10.2329,
+      "step": 26
+    },
+    {
+      "epoch": 0.02230195400221987,
+      "grad_norm": 2.1666860580444336,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 10.23,
+      "step": 27
+    },
+    {
+      "epoch": 0.023127952298598386,
+      "grad_norm": 2.0563714504241943,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 10.2225,
+      "step": 28
+    },
+    {
+      "epoch": 0.0239539505949769,
+      "grad_norm": 1.9848387241363525,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 10.2097,
+      "step": 29
+    },
+    {
+      "epoch": 0.024779948891355413,
+      "grad_norm": 1.9532544612884521,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 10.2035,
+      "step": 30
+    },
+    {
+      "epoch": 0.025605947187733926,
+      "grad_norm": 1.8774293661117554,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 10.2052,
+      "step": 31
+    },
+    {
+      "epoch": 0.02643194548411244,
+      "grad_norm": 1.7850217819213867,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 10.1989,
+      "step": 32
+    },
+    {
+      "epoch": 0.027257943780490953,
+      "grad_norm": 1.806624174118042,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 10.2075,
+      "step": 33
+    },
+    {
+      "epoch": 0.028083942076869466,
+      "grad_norm": 1.6620304584503174,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 10.1921,
+      "step": 34
+    },
+    {
+      "epoch": 0.02890994037324798,
+      "grad_norm": 1.6251369714736938,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 10.1959,
+      "step": 35
+    },
+    {
+      "epoch": 0.029735938669626493,
+      "grad_norm": 1.5146149396896362,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 10.1807,
+      "step": 36
+    },
+    {
+      "epoch": 0.030561936966005007,
+      "grad_norm": 1.4646108150482178,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 10.1794,
+      "step": 37
+    },
+    {
+      "epoch": 0.03138793526238352,
+      "grad_norm": 1.3250266313552856,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 10.1936,
+      "step": 38
+    },
+    {
+      "epoch": 0.03221393355876204,
+      "grad_norm": 1.303118109703064,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 10.1736,
+      "step": 39
+    },
+    {
+      "epoch": 0.03303993185514055,
+      "grad_norm": 1.2237043380737305,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 10.1605,
+      "step": 40
+    },
+    {
+      "epoch": 0.033865930151519064,
+      "grad_norm": 1.1835358142852783,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 10.166,
+      "step": 41
+    },
+    {
+      "epoch": 0.03469192844789758,
+      "grad_norm": 1.0976448059082031,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 10.1594,
+      "step": 42
+    },
+    {
+      "epoch": 0.03551792674427609,
+      "grad_norm": 1.0374468564987183,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 10.1597,
+      "step": 43
+    },
+    {
+      "epoch": 0.036343925040654604,
+      "grad_norm": 0.9736471176147461,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 10.1546,
+      "step": 44
+    },
+    {
+      "epoch": 0.03716992333703312,
+      "grad_norm": 0.9557368755340576,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 10.1595,
+      "step": 45
+    },
+    {
+      "epoch": 0.03799592163341163,
+      "grad_norm": 0.9107280969619751,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 10.1645,
+      "step": 46
+    },
+    {
+      "epoch": 0.038821919929790144,
+      "grad_norm": 0.8153705596923828,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 10.1512,
+      "step": 47
+    },
+    {
+      "epoch": 0.03964791822616866,
+      "grad_norm": 0.7683850526809692,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 10.1547,
+      "step": 48
+    },
+    {
+      "epoch": 0.04047391652254717,
+      "grad_norm": 0.7185543179512024,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.144,
+      "step": 49
+    },
+    {
+      "epoch": 0.041299914818925684,
+      "grad_norm": 0.671612024307251,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 10.1444,
+      "step": 50
+    },
+    {
+      "epoch": 0.041299914818925684,
+      "eval_loss": 10.138866424560547,
+      "eval_runtime": 0.0814,
+      "eval_samples_per_second": 614.338,
+      "eval_steps_per_second": 159.728,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null