Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1474f6f9d559e6e70ac14131c8f03d67e08b5ba6a023518ffad4ca8a1f360a66
+oid sha256:a5aab16f15ec8a83420cc943a20846458effd2b909d82edcde6ee2615c6dda5c
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:207bda815f0767c76c372a677b159fb23ecdbe7425891ff96bfb281d3b104dd3
+oid sha256:9bf2acd04f7fe13bc98cb90dcea4f4eb9f7abfcf3802b2bc2da860b5b334c07c
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1592db3805eafdb4c9e2185d509843b01eaeb816ba62b62a9261d879c42f516b
+oid sha256:1def2a2e0e66bd9d4738a2b4648f9a5c75dda3f112fc6ca0bf401feb8d76d3e6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92d704ee7df4a32889ee4b90a815ed0c14f401071f202ac1517cb34d5b8a0519
+oid sha256:cbbacfb1f03d25afb804ad39adce7fa800dd6f1f61173f16e63eaee0264c10fd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d038fcac5afb060789f8b4a33b3ca597bb8f8a020746a381a96d4ba711cb13
+oid sha256:6cd951268cef34079a73c96f1351567ffdf70b8644509d91580e413429d04ec9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f8da15467b78dc159b5a583fd59db3b47807d6596bc3ae1e3a24737491e62de
+oid sha256:a18a7c489f033d7f604b3b4c8f755d4117e9494cff251b467685befce239745f
 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": 0.032049428671598434,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.6496142915144133,
+  "best_metric": 0.021049948409199715,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.97442143727162,
   "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": 32.348,
       "eval_steps_per_second": 8.411,
       "step": 50
+    },
+    {
+      "epoch": 0.6626065773447016,
+      "grad_norm": 3.8544723987579346,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.1116,
+      "step": 51
+    },
+    {
+      "epoch": 0.6755988631749898,
+      "grad_norm": 1.4536547660827637,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 0.0447,
+      "step": 52
+    },
+    {
+      "epoch": 0.6885911490052781,
+      "grad_norm": 1.1871592998504639,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 0.0683,
+      "step": 53
+    },
+    {
+      "epoch": 0.7015834348355664,
+      "grad_norm": 0.5502886772155762,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0404,
+      "step": 54
+    },
+    {
+      "epoch": 0.7145757206658546,
+      "grad_norm": 0.49863505363464355,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 0.0324,
+      "step": 55
+    },
+    {
+      "epoch": 0.727568006496143,
+      "grad_norm": 0.8850557208061218,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 0.0645,
+      "step": 56
+    },
+    {
+      "epoch": 0.7405602923264312,
+      "grad_norm": 0.7965983748435974,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0548,
+      "step": 57
+    },
+    {
+      "epoch": 0.7535525781567195,
+      "grad_norm": 0.6387767791748047,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 0.0658,
+      "step": 58
+    },
+    {
+      "epoch": 0.7665448639870077,
+      "grad_norm": 0.8699201345443726,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 0.0624,
+      "step": 59
+    },
+    {
+      "epoch": 0.7795371498172959,
+      "grad_norm": 1.0982764959335327,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0866,
+      "step": 60
+    },
+    {
+      "epoch": 0.7925294356475843,
+      "grad_norm": 1.1414963006973267,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 0.075,
+      "step": 61
+    },
+    {
+      "epoch": 0.8055217214778725,
+      "grad_norm": 0.8054099082946777,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 0.0604,
+      "step": 62
+    },
+    {
+      "epoch": 0.8185140073081608,
+      "grad_norm": 1.1966440677642822,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0677,
+      "step": 63
+    },
+    {
+      "epoch": 0.831506293138449,
+      "grad_norm": 0.9174244403839111,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 0.0516,
+      "step": 64
+    },
+    {
+      "epoch": 0.8444985789687373,
+      "grad_norm": 0.6317915916442871,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 0.0512,
+      "step": 65
+    },
+    {
+      "epoch": 0.8574908647990256,
+      "grad_norm": 1.381137490272522,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0516,
+      "step": 66
+    },
+    {
+      "epoch": 0.8704831506293138,
+      "grad_norm": 0.45590871572494507,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 0.0427,
+      "step": 67
+    },
+    {
+      "epoch": 0.8834754364596021,
+      "grad_norm": 1.784468650817871,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 0.059,
+      "step": 68
+    },
+    {
+      "epoch": 0.8964677222898904,
+      "grad_norm": 1.0624321699142456,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0443,
+      "step": 69
+    },
+    {
+      "epoch": 0.9094600081201787,
+      "grad_norm": 1.522290587425232,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 0.0563,
+      "step": 70
+    },
+    {
+      "epoch": 0.9224522939504669,
+      "grad_norm": 0.38779476284980774,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 0.0314,
+      "step": 71
+    },
+    {
+      "epoch": 0.9354445797807551,
+      "grad_norm": 1.1681578159332275,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0623,
+      "step": 72
+    },
+    {
+      "epoch": 0.9484368656110435,
+      "grad_norm": 0.5920040011405945,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 0.0566,
+      "step": 73
+    },
+    {
+      "epoch": 0.9614291514413317,
+      "grad_norm": 0.5902805328369141,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 0.0524,
+      "step": 74
+    },
+    {
+      "epoch": 0.97442143727162,
+      "grad_norm": 0.6527218222618103,
+      "learning_rate": 1e-05,
+      "loss": 0.0566,
+      "step": 75
+    },
+    {
+      "epoch": 0.97442143727162,
+      "eval_loss": 0.021049948409199715,
+      "eval_runtime": 1.5036,
+      "eval_samples_per_second": 33.255,
+      "eval_steps_per_second": 8.646,
+      "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": 2.95300912644096e+16,
+  "total_flos": 4.42951368966144e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null