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:bc597375ff00e980e81ca0892e27ef43450281c7e4832960abd99bdb6875931c
+oid sha256:4dc8be1b905ef63172e837a930b766557dc7b84367d04608d2507ae5a1cca9e2
 size 113284112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:636824613ae05339ac7f3e2c2df074a455b15d3483eec6e9713eaf4fea826dc6
+oid sha256:17d19a14d7c855cad19426fe2e52ad73a5b94f8e4768b9b7333a70c5ed3448ba
 size 226735226

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac5c3bfd9985611381bbe6ba01a0b46977dad618187bfcd474bf67df4d0f3b0f
+oid sha256:338d8f7dc047d16fa409a96749d608609fcff70feb0d5c8c5bccd065e98bbe58
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1115f6c2bc5f2af2cb65461102616cca54c61679a2d44d1ccc6eb5bc3b44b57b
+oid sha256:39f866eeafffc8f37488684641ca8953510246648804364c9feee6ae3d0e1baa
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b130b05431e7bb4766db3b4ee8fa6d97f0de9b838e2298481e5bcf1e0f6b5254
+oid sha256:27ff81d32916f9fb502645f94eeacdf4aa4efb4a9eb67aea0c6024fafa9f4d81
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:404eafd552760cf476196a4eeb52bcbfd6530f24a1974055a4641dfaf18c3251
+oid sha256:d43744f7180341b88af99cf6a23dba680363e796f51bf35b0102fe6429093457
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5180265307426453,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006616272722761632,
+  "best_metric": 0.47327739000320435,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.013232545445523264,
   "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": 78.016,
       "eval_steps_per_second": 9.752,
       "step": 25
+    },
+    {
+      "epoch": 0.006880923631672097,
+      "grad_norm": 0.420188307762146,
+      "learning_rate": 5e-05,
+      "loss": 0.937,
+      "step": 26
+    },
+    {
+      "epoch": 0.007145574540582563,
+      "grad_norm": 0.5700767636299133,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.695,
+      "step": 27
+    },
+    {
+      "epoch": 0.007410225449493028,
+      "grad_norm": 0.5167895555496216,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.6035,
+      "step": 28
+    },
+    {
+      "epoch": 0.007674876358403493,
+      "grad_norm": 0.6467077732086182,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4506,
+      "step": 29
+    },
+    {
+      "epoch": 0.00793952726731396,
+      "grad_norm": 0.45690345764160156,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5379,
+      "step": 30
+    },
+    {
+      "epoch": 0.008204178176224423,
+      "grad_norm": 0.4311066269874573,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4912,
+      "step": 31
+    },
+    {
+      "epoch": 0.00846882908513489,
+      "grad_norm": 0.39850619435310364,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.46,
+      "step": 32
+    },
+    {
+      "epoch": 0.008733479994045355,
+      "grad_norm": 0.3314412534236908,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4209,
+      "step": 33
+    },
+    {
+      "epoch": 0.00899813090295582,
+      "grad_norm": 0.4438161849975586,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3976,
+      "step": 34
+    },
+    {
+      "epoch": 0.009262781811866285,
+      "grad_norm": 0.36361584067344666,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3816,
+      "step": 35
+    },
+    {
+      "epoch": 0.00952743272077675,
+      "grad_norm": 0.3931230902671814,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3412,
+      "step": 36
+    },
+    {
+      "epoch": 0.009792083629687216,
+      "grad_norm": 0.4425284266471863,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3258,
+      "step": 37
+    },
+    {
+      "epoch": 0.010056734538597682,
+      "grad_norm": 0.32975614070892334,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9773,
+      "step": 38
+    },
+    {
+      "epoch": 0.010321385447508146,
+      "grad_norm": 0.3308790326118469,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6732,
+      "step": 39
+    },
+    {
+      "epoch": 0.010586036356418612,
+      "grad_norm": 0.4055446982383728,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6384,
+      "step": 40
+    },
+    {
+      "epoch": 0.010850687265329078,
+      "grad_norm": 0.4504941999912262,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.4432,
+      "step": 41
+    },
+    {
+      "epoch": 0.011115338174239542,
+      "grad_norm": 0.3198263347148895,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.543,
+      "step": 42
+    },
+    {
+      "epoch": 0.011379989083150008,
+      "grad_norm": 0.34442195296287537,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.5181,
+      "step": 43
+    },
+    {
+      "epoch": 0.011644639992060472,
+      "grad_norm": 0.3284602463245392,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4109,
+      "step": 44
+    },
+    {
+      "epoch": 0.011909290900970938,
+      "grad_norm": 0.33481574058532715,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3932,
+      "step": 45
+    },
+    {
+      "epoch": 0.012173941809881404,
+      "grad_norm": 0.3298023045063019,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.3983,
+      "step": 46
+    },
+    {
+      "epoch": 0.012438592718791868,
+      "grad_norm": 0.28835529088974,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3985,
+      "step": 47
+    },
+    {
+      "epoch": 0.012703243627702334,
+      "grad_norm": 0.343580037355423,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3632,
+      "step": 48
+    },
+    {
+      "epoch": 0.0129678945366128,
+      "grad_norm": 0.3463713228702545,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2849,
+      "step": 49
+    },
+    {
+      "epoch": 0.013232545445523264,
+      "grad_norm": 0.4292154908180237,
+      "learning_rate": 0.0,
+      "loss": 0.3038,
+      "step": 50
+    },
+    {
+      "epoch": 0.013232545445523264,
+      "eval_loss": 0.47327739000320435,
+      "eval_runtime": 328.3977,
+      "eval_samples_per_second": 77.516,
+      "eval_steps_per_second": 9.689,
+      "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": 5.351716806669107e+16,
+  "total_flos": 1.0683649061237555e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null