Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c8a12a9510aa3fa3ba9ab5d69aff64c8b0fa203db684334c9cd3877144c497e
+oid sha256:2e56526d9f700b56d287f2e3b9e8cea988392eff424da54d386fc9101c223ef5
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c00dddf8bc382f6dddd3ed7503a4972cf11f6218f1ed0aad29dfda98fc0a20f5
+oid sha256:38c179504fb23c1d51ee529f8d4bfe3aa233396dd4659a2e192feeb60ac82b3c
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83032b7e527379eb761fc6e9c1048ed3b1ffcb41d7718197a0536046332c8f54
+oid sha256:746135bb8d8199902e8027bd9a9232a6791b4089583bba4b904d4d2ab09a6178
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c28b09c060943e1d9762363b71fc9de14a99c2ce4bdbabefb556109216731d59
+oid sha256:b4c11bc3371e460b4c703f8d4264f27ba30af394195a8495817f9d8ac4077d4e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51cf789c86cbe7c5679cb9dd105fba8c9b468d196548e3dc423a9ad175c8c23e
+oid sha256:b93e2ef28ee00a87403770941b584694d87063f3c48df3ab6e4a7639482f489f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424d81d0e56aff4f4d12a005c8d41e93e1e60f46479eb8c1f600627f8dfbf148
+oid sha256:2467b9b8c5a910c51ac8759abf4b6022047d25bc0275cee8adcae4b9519e3157
 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": 10.369140625,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.7094017094017095,
+  "best_metric": 10.366877555847168,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 2.564102564102564,
   "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": 515.162,
       "eval_steps_per_second": 133.942,
       "step": 50
+    },
+    {
+      "epoch": 1.7435897435897436,
+      "grad_norm": 0.04459521546959877,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.0781,
+      "step": 51
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.09696029871702194,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 16.5477,
+      "step": 52
+    },
+    {
+      "epoch": 1.811965811965812,
+      "grad_norm": 0.07526196539402008,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 10.3167,
+      "step": 53
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 0.07211493700742722,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.3497,
+      "step": 54
+    },
+    {
+      "epoch": 1.8803418803418803,
+      "grad_norm": 0.0758114755153656,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 10.5534,
+      "step": 55
+    },
+    {
+      "epoch": 1.9145299145299144,
+      "grad_norm": 0.08330105990171432,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 10.3561,
+      "step": 56
+    },
+    {
+      "epoch": 1.9487179487179487,
+      "grad_norm": 0.1038593128323555,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.4654,
+      "step": 57
+    },
+    {
+      "epoch": 1.982905982905983,
+      "grad_norm": 0.10510390996932983,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 10.8554,
+      "step": 58
+    },
+    {
+      "epoch": 2.017094017094017,
+      "grad_norm": 0.12666811048984528,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 17.6932,
+      "step": 59
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 0.07206396758556366,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.1238,
+      "step": 60
+    },
+    {
+      "epoch": 2.0854700854700856,
+      "grad_norm": 0.08021845668554306,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 10.3257,
+      "step": 61
+    },
+    {
+      "epoch": 2.1196581196581197,
+      "grad_norm": 0.0848311111330986,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 10.6517,
+      "step": 62
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 0.08744092285633087,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.3375,
+      "step": 63
+    },
+    {
+      "epoch": 2.1880341880341883,
+      "grad_norm": 0.09486929327249527,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 10.7017,
+      "step": 64
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.11365848779678345,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 10.3117,
+      "step": 65
+    },
+    {
+      "epoch": 2.2564102564102564,
+      "grad_norm": 0.0729779526591301,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 8.8041,
+      "step": 66
+    },
+    {
+      "epoch": 2.2905982905982905,
+      "grad_norm": 0.08433752506971359,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 11.3562,
+      "step": 67
+    },
+    {
+      "epoch": 2.324786324786325,
+      "grad_norm": 0.09108246862888336,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 10.4199,
+      "step": 68
+    },
+    {
+      "epoch": 2.358974358974359,
+      "grad_norm": 0.0905907079577446,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.6594,
+      "step": 69
+    },
+    {
+      "epoch": 2.393162393162393,
+      "grad_norm": 0.09025926142930984,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 10.3229,
+      "step": 70
+    },
+    {
+      "epoch": 2.427350427350427,
+      "grad_norm": 0.09516981989145279,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 10.6938,
+      "step": 71
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.11765694618225098,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.066,
+      "step": 72
+    },
+    {
+      "epoch": 2.4957264957264957,
+      "grad_norm": 0.058387916535139084,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 5.3975,
+      "step": 73
+    },
+    {
+      "epoch": 2.52991452991453,
+      "grad_norm": 0.10583050549030304,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 15.0466,
+      "step": 74
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 0.0866541638970375,
+      "learning_rate": 1e-05,
+      "loss": 10.3698,
+      "step": 75
+    },
+    {
+      "epoch": 2.564102564102564,
+      "eval_loss": 10.366877555847168,
+      "eval_runtime": 0.101,
+      "eval_samples_per_second": 495.053,
+      "eval_steps_per_second": 128.714,
+      "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": 42848249708544.0,
+  "total_flos": 64285739581440.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null