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:c6f4146fbbfb52b8f96c566775a4645c66521d1dee86583e76129376a7e4ccbe
+oid sha256:b492ffecf9df6d573e310606af89b71b162f18cc0c44a0527e7697c05e4acaaa
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8045eeec8dd00c26eefde1db6f4be582b57a4f9ac4453a201de241a3bdf2fc5c
+oid sha256:99b9ec93f92123e36fd3bedd607546889cdcdeede7531307392cab39cfcfefaa
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f05977fbd8be67895f5c29ba8404504f004f539b203fd8b81b83e6c979fdbf8
+oid sha256:60512a8eb35aaf8b1b99bd5f45869c7c0531e4f2ff8f3fd5be6fb4a47a5ffeed
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:081c54c9c01ce1ea54955a3a5abd58d677667e3864cfd2a12481ed1a90f7f944
+oid sha256:a54e70d28e2dee153c533fb3414b93d0313810d2dcbf9128250b2f5b17077e8e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fabdf0974dd98454821e402f14f532a39394fe70fe2c259efbcb85a054eb358b
+oid sha256:4153e828abda57ae44a2e610ba94cd505d8fbef677e0f5fc71f5ad22a1397cc0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2ead22fa6945d10eafb4b72edf5c6ea6b589a3cc11a5254282ef81982aed17c
+oid sha256:353193f2cd30013120e2f69858acf81b43b94ce0456908954e908a217fbb2ab4
 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": 11.933380126953125,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.4333694474539545,
+  "best_metric": 11.930976867675781,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.6500541711809318,
   "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": 192.978,
       "eval_steps_per_second": 50.174,
       "step": 50
+    },
+    {
+      "epoch": 0.4420368364030336,
+      "grad_norm": 0.04358985275030136,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.931,
+      "step": 51
+    },
+    {
+      "epoch": 0.4507042253521127,
+      "grad_norm": 0.06944932788610458,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 11.931,
+      "step": 52
+    },
+    {
+      "epoch": 0.4593716143011918,
+      "grad_norm": 0.07410332560539246,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 11.9319,
+      "step": 53
+    },
+    {
+      "epoch": 0.46803900325027087,
+      "grad_norm": 0.08937946707010269,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.9307,
+      "step": 54
+    },
+    {
+      "epoch": 0.47670639219934996,
+      "grad_norm": 0.09634770452976227,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 11.9313,
+      "step": 55
+    },
+    {
+      "epoch": 0.48537378114842905,
+      "grad_norm": 0.09646016359329224,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 11.9307,
+      "step": 56
+    },
+    {
+      "epoch": 0.49404117009750814,
+      "grad_norm": 0.11758565157651901,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.9291,
+      "step": 57
+    },
+    {
+      "epoch": 0.5027085590465872,
+      "grad_norm": 0.12455835193395615,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 11.9313,
+      "step": 58
+    },
+    {
+      "epoch": 0.5113759479956663,
+      "grad_norm": 0.1459084004163742,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 11.9316,
+      "step": 59
+    },
+    {
+      "epoch": 0.5200433369447454,
+      "grad_norm": 0.1777600347995758,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.93,
+      "step": 60
+    },
+    {
+      "epoch": 0.5287107258938245,
+      "grad_norm": 0.2380158007144928,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 11.931,
+      "step": 61
+    },
+    {
+      "epoch": 0.5373781148429035,
+      "grad_norm": 0.30322137475013733,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 11.9312,
+      "step": 62
+    },
+    {
+      "epoch": 0.5460455037919827,
+      "grad_norm": 0.0573463998734951,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.9318,
+      "step": 63
+    },
+    {
+      "epoch": 0.5547128927410617,
+      "grad_norm": 0.06148889288306236,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 11.9306,
+      "step": 64
+    },
+    {
+      "epoch": 0.5633802816901409,
+      "grad_norm": 0.07989097386598587,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 11.9313,
+      "step": 65
+    },
+    {
+      "epoch": 0.5720476706392199,
+      "grad_norm": 0.0917278379201889,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.9306,
+      "step": 66
+    },
+    {
+      "epoch": 0.580715059588299,
+      "grad_norm": 0.09770037978887558,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 11.9305,
+      "step": 67
+    },
+    {
+      "epoch": 0.5893824485373781,
+      "grad_norm": 0.1190197691321373,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 11.9297,
+      "step": 68
+    },
+    {
+      "epoch": 0.5980498374864572,
+      "grad_norm": 0.12440388649702072,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.9297,
+      "step": 69
+    },
+    {
+      "epoch": 0.6067172264355363,
+      "grad_norm": 0.1328328549861908,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 11.9293,
+      "step": 70
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.1649710088968277,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 11.9295,
+      "step": 71
+    },
+    {
+      "epoch": 0.6240520043336945,
+      "grad_norm": 0.16425499320030212,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9306,
+      "step": 72
+    },
+    {
+      "epoch": 0.6327193932827736,
+      "grad_norm": 0.1935925930738449,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 11.9294,
+      "step": 73
+    },
+    {
+      "epoch": 0.6413867822318526,
+      "grad_norm": 0.2569132447242737,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 11.9302,
+      "step": 74
+    },
+    {
+      "epoch": 0.6500541711809318,
+      "grad_norm": 0.3602008521556854,
+      "learning_rate": 1e-05,
+      "loss": 11.9282,
+      "step": 75
+    },
+    {
+      "epoch": 0.6500541711809318,
+      "eval_loss": 11.930976867675781,
+      "eval_runtime": 0.2483,
+      "eval_samples_per_second": 201.391,
+      "eval_steps_per_second": 52.362,
+      "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": 1045263384576.0,
+  "total_flos": 1567487852544.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null