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:be997b47917b14c40139e581ae358cd9bf6d4996282a89ded8c6d24c29c5e36a
+oid sha256:b020cc74206bf6abec80a5826589b13d13400b5b46c0cb113af0db29f869e155
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:269b9c5cb23a86da6e27220196a82c631d8af5b0871c794426d84ca2feecd230
+oid sha256:3f93a1c6a494fa9fbed62e2c9297899c0fce6a7b2fbffdc933b843c6df872c24
 size 60837186

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf03b812cd611b2c4a6d61ada30b06d0cb846c1ab95bb1f1008815dad23b71b6
+oid sha256:12694005df4414ab429027bdeb4e1ca13d7a801ede4e461291de6d7314a05fcb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.1716570109128952,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01638001638001638,
+  "best_metric": 0.03165920078754425,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03276003276003276,
   "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": 13.545,
       "eval_steps_per_second": 6.783,
       "step": 25
+    },
+    {
+      "epoch": 0.017035217035217036,
+      "grad_norm": 0.06484061479568481,
+      "learning_rate": 0.0001,
+      "loss": 0.0006,
+      "step": 26
+    },
+    {
+      "epoch": 0.01769041769041769,
+      "grad_norm": 0.9557607769966125,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.0036,
+      "step": 27
+    },
+    {
+      "epoch": 0.018345618345618344,
+      "grad_norm": 0.2809895873069763,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.0008,
+      "step": 28
+    },
+    {
+      "epoch": 0.019000819000819,
+      "grad_norm": 0.05950084701180458,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.0004,
+      "step": 29
+    },
+    {
+      "epoch": 0.019656019656019656,
+      "grad_norm": 8.605826377868652,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.1053,
+      "step": 30
+    },
+    {
+      "epoch": 0.02031122031122031,
+      "grad_norm": 4.249216556549072,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.0207,
+      "step": 31
+    },
+    {
+      "epoch": 0.020966420966420967,
+      "grad_norm": 0.7386406064033508,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0041,
+      "step": 32
+    },
+    {
+      "epoch": 0.021621621621621623,
+      "grad_norm": 0.3371402621269226,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.0048,
+      "step": 33
+    },
+    {
+      "epoch": 0.022276822276822275,
+      "grad_norm": 10.98389720916748,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0363,
+      "step": 34
+    },
+    {
+      "epoch": 0.02293202293202293,
+      "grad_norm": 15.460600852966309,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.2665,
+      "step": 35
+    },
+    {
+      "epoch": 0.023587223587223587,
+      "grad_norm": 0.05989992246031761,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.0004,
+      "step": 36
+    },
+    {
+      "epoch": 0.024242424242424242,
+      "grad_norm": 0.5496867299079895,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.0037,
+      "step": 37
+    },
+    {
+      "epoch": 0.024897624897624898,
+      "grad_norm": 23.222116470336914,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.2077,
+      "step": 38
+    },
+    {
+      "epoch": 0.025552825552825554,
+      "grad_norm": 4.982071876525879,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.0356,
+      "step": 39
+    },
+    {
+      "epoch": 0.02620802620802621,
+      "grad_norm": 2.1850380897521973,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.007,
+      "step": 40
+    },
+    {
+      "epoch": 0.026863226863226862,
+      "grad_norm": 0.0053272852674126625,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.027518427518427518,
+      "grad_norm": 32.137962341308594,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.2831,
+      "step": 42
+    },
+    {
+      "epoch": 0.028173628173628174,
+      "grad_norm": 0.3219406306743622,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.002,
+      "step": 43
+    },
+    {
+      "epoch": 0.02882882882882883,
+      "grad_norm": 0.6160392761230469,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0045,
+      "step": 44
+    },
+    {
+      "epoch": 0.029484029484029485,
+      "grad_norm": 0.635273814201355,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0045,
+      "step": 45
+    },
+    {
+      "epoch": 0.03013923013923014,
+      "grad_norm": 1.5323097705841064,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0096,
+      "step": 46
+    },
+    {
+      "epoch": 0.030794430794430793,
+      "grad_norm": 1.9046576023101807,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.0121,
+      "step": 47
+    },
+    {
+      "epoch": 0.03144963144963145,
+      "grad_norm": 0.9863927364349365,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.0071,
+      "step": 48
+    },
+    {
+      "epoch": 0.03210483210483211,
+      "grad_norm": 1.4912574291229248,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.01,
+      "step": 49
+    },
+    {
+      "epoch": 0.03276003276003276,
+      "grad_norm": 0.752311646938324,
+      "learning_rate": 0.0,
+      "loss": 0.0066,
+      "step": 50
+    },
+    {
+      "epoch": 0.03276003276003276,
+      "eval_loss": 0.03165920078754425,
+      "eval_runtime": 47.498,
+      "eval_samples_per_second": 13.537,
+      "eval_steps_per_second": 6.779,
+      "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": 1553078629171200.0,
+  "total_flos": 3106157258342400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null