Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0181a939a4ad472164909c5823f18b62da6c81719a036dc0bf9d0987a1427edd
+oid sha256:9b78ae3457b650789ddedd394dfb2de0dc7e5c440520d947dd225e5c75281a2f
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d6f54f8eef1db2a485767802be8c1511559a4923132f2d261168a3d2b7871e9
+oid sha256:b52e524a4163ae1c4aef7a71283364e792005a3cd11eb304a31a97625cc4e009
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d4aac8c8190b2ac9da0e258565b28d2af1952ef10b068bad3fc8b4c9f512517
+oid sha256:a3ab56d40839a7984e3bab7dddf4ea8f2f871714cc53424cf594a53b7b2b819b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa1dfb409e317cd58596eb708a87c41f08e7213f3eac84274a5c1c4a53a9e621
+oid sha256:951a434e9da56110589d5fe6d45c272d5394fec4c00d6799cee065d8595c8ecd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e60569d140c747a727d1b21abc1aa38371a1fd4af343c4cff1fa383aa9770610
+oid sha256:c2ede6c9c8c5ef62527255641ecb09a009ad013c21cc51a548ea8f09d22f5537
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b128b955a14e3a2eddedcfc1113d73460cdb5c8864d2cc1d6cc2f5bd338e16ed
+oid sha256:6156731b7962ca2f3883f5dd93a65cc1726b92b5fdcbd7c5c08b442d1f271743
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
+oid sha256:0b823f3900a3c8aa20bff7ce05b4e552f6bc019793f00b0bb20027204b5c704a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.930290222167969,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.42780748663101603,
+  "best_metric": 11.929637908935547,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.6417112299465241,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 166.609,
       "eval_steps_per_second": 43.318,
       "step": 50
+    },
+    {
+      "epoch": 0.43636363636363634,
+      "grad_norm": 0.030816154554486275,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.9314,
+      "step": 51
+    },
+    {
+      "epoch": 0.4449197860962567,
+      "grad_norm": 0.029961062595248222,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 11.9309,
+      "step": 52
+    },
+    {
+      "epoch": 0.453475935828877,
+      "grad_norm": 0.03276418522000313,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 11.931,
+      "step": 53
+    },
+    {
+      "epoch": 0.46203208556149733,
+      "grad_norm": 0.03670096769928932,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.9305,
+      "step": 54
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.03524468466639519,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 11.9306,
+      "step": 55
+    },
+    {
+      "epoch": 0.47914438502673795,
+      "grad_norm": 0.03465661406517029,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 11.9299,
+      "step": 56
+    },
+    {
+      "epoch": 0.48770053475935826,
+      "grad_norm": 0.03583734482526779,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.93,
+      "step": 57
+    },
+    {
+      "epoch": 0.49625668449197863,
+      "grad_norm": 0.04339265450835228,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 11.9287,
+      "step": 58
+    },
+    {
+      "epoch": 0.5048128342245989,
+      "grad_norm": 0.05683796480298042,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 11.9283,
+      "step": 59
+    },
+    {
+      "epoch": 0.5133689839572193,
+      "grad_norm": 0.05965341255068779,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.9289,
+      "step": 60
+    },
+    {
+      "epoch": 0.5219251336898396,
+      "grad_norm": 0.07276409864425659,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 11.9283,
+      "step": 61
+    },
+    {
+      "epoch": 0.5304812834224599,
+      "grad_norm": 0.08142941445112228,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 11.9266,
+      "step": 62
+    },
+    {
+      "epoch": 0.5390374331550802,
+      "grad_norm": 0.03713444247841835,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.9308,
+      "step": 63
+    },
+    {
+      "epoch": 0.5475935828877005,
+      "grad_norm": 0.03590025380253792,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 11.9305,
+      "step": 64
+    },
+    {
+      "epoch": 0.5561497326203209,
+      "grad_norm": 0.03694842755794525,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 11.9306,
+      "step": 65
+    },
+    {
+      "epoch": 0.5647058823529412,
+      "grad_norm": 0.03804150968790054,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.9306,
+      "step": 66
+    },
+    {
+      "epoch": 0.5732620320855615,
+      "grad_norm": 0.03732200339436531,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 11.9306,
+      "step": 67
+    },
+    {
+      "epoch": 0.5818181818181818,
+      "grad_norm": 0.03894832730293274,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 11.9305,
+      "step": 68
+    },
+    {
+      "epoch": 0.5903743315508021,
+      "grad_norm": 0.046566810458898544,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.9297,
+      "step": 69
+    },
+    {
+      "epoch": 0.5989304812834224,
+      "grad_norm": 0.05046457797288895,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 11.9285,
+      "step": 70
+    },
+    {
+      "epoch": 0.6074866310160428,
+      "grad_norm": 0.053379662334918976,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 11.9297,
+      "step": 71
+    },
+    {
+      "epoch": 0.6160427807486631,
+      "grad_norm": 0.0545305497944355,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9284,
+      "step": 72
+    },
+    {
+      "epoch": 0.6245989304812835,
+      "grad_norm": 0.05352730304002762,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 11.9282,
+      "step": 73
+    },
+    {
+      "epoch": 0.6331550802139038,
+      "grad_norm": 0.06697743386030197,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 11.9294,
+      "step": 74
+    },
+    {
+      "epoch": 0.6417112299465241,
+      "grad_norm": 0.09596454352140427,
+      "learning_rate": 1e-05,
+      "loss": 11.9246,
+      "step": 75
+    },
+    {
+      "epoch": 0.6417112299465241,
+      "eval_loss": 11.929637908935547,
+      "eval_runtime": 0.2899,
+      "eval_samples_per_second": 172.451,
+      "eval_steps_per_second": 44.837,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -404,12 +587,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1042494259200.0,
+  "total_flos": 1563741388800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null