Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58f043d1d7c45d4998eb91f08257052e5f0ef7d7a68c6ba7b591118376b353e0
+oid sha256:fcabd03397c86b422738b48be801ea9567f97c71099fa9afb7b249089799727d
 size 692136856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:305e3d9c54ff17326a5acd6a21ec96ec7c0389ad967c9680a6a1fac54728ba61
+oid sha256:e54bddd565c4985b0159cff3987541401438b541b2a15708f3294cd9fa39cde7
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:091bd03f0fbd4042c10a2daf04c6462f87580fc725558ca1d722a0dd9f77ad17
+oid sha256:18be8932135be8603d5287903e16ad2007de95b8eb49607aad6e547732362c1c
 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": 0.7381670475006104,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.004064049418840933,
+  "best_metric": 0.6914295554161072,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.008128098837681867,
   "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": 3.565,
       "eval_steps_per_second": 1.783,
       "step": 25
+    },
+    {
+      "epoch": 0.00422661139559457,
+      "grad_norm": 1.0687131881713867,
+      "learning_rate": 0.0001,
+      "loss": 0.6585,
+      "step": 26
+    },
+    {
+      "epoch": 0.0043891733723482075,
+      "grad_norm": 1.1945370435714722,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.6396,
+      "step": 27
+    },
+    {
+      "epoch": 0.004551735349101845,
+      "grad_norm": 1.2164644002914429,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.6072,
+      "step": 28
+    },
+    {
+      "epoch": 0.0047142973258554825,
+      "grad_norm": 1.1531621217727661,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.6276,
+      "step": 29
+    },
+    {
+      "epoch": 0.00487685930260912,
+      "grad_norm": 1.1373238563537598,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.6343,
+      "step": 30
+    },
+    {
+      "epoch": 0.005039421279362757,
+      "grad_norm": 1.547668218612671,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.6406,
+      "step": 31
+    },
+    {
+      "epoch": 0.005201983256116394,
+      "grad_norm": 1.48245108127594,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.6305,
+      "step": 32
+    },
+    {
+      "epoch": 0.0053645452328700315,
+      "grad_norm": 1.767665147781372,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.621,
+      "step": 33
+    },
+    {
+      "epoch": 0.005527107209623669,
+      "grad_norm": 1.596113681793213,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.6159,
+      "step": 34
+    },
+    {
+      "epoch": 0.0056896691863773064,
+      "grad_norm": 1.8545340299606323,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.7291,
+      "step": 35
+    },
+    {
+      "epoch": 0.005852231163130944,
+      "grad_norm": 1.7232612371444702,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.577,
+      "step": 36
+    },
+    {
+      "epoch": 0.006014793139884581,
+      "grad_norm": 1.8988685607910156,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.6809,
+      "step": 37
+    },
+    {
+      "epoch": 0.006177355116638218,
+      "grad_norm": 1.8034489154815674,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.5321,
+      "step": 38
+    },
+    {
+      "epoch": 0.0063399170933918555,
+      "grad_norm": 1.6797901391983032,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.4751,
+      "step": 39
+    },
+    {
+      "epoch": 0.006502479070145493,
+      "grad_norm": 2.041771173477173,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.616,
+      "step": 40
+    },
+    {
+      "epoch": 0.00666504104689913,
+      "grad_norm": 1.8300652503967285,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.5089,
+      "step": 41
+    },
+    {
+      "epoch": 0.006827603023652768,
+      "grad_norm": 3.0001614093780518,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.6661,
+      "step": 42
+    },
+    {
+      "epoch": 0.0069901650004064045,
+      "grad_norm": 2.6504576206207275,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.5584,
+      "step": 43
+    },
+    {
+      "epoch": 0.007152726977160042,
+      "grad_norm": 4.451040744781494,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.7299,
+      "step": 44
+    },
+    {
+      "epoch": 0.0073152889539136795,
+      "grad_norm": 3.389237880706787,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.7446,
+      "step": 45
+    },
+    {
+      "epoch": 0.007477850930667317,
+      "grad_norm": 4.1181840896606445,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.6918,
+      "step": 46
+    },
+    {
+      "epoch": 0.007640412907420954,
+      "grad_norm": 6.220348358154297,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.6454,
+      "step": 47
+    },
+    {
+      "epoch": 0.007802974884174592,
+      "grad_norm": 7.369223117828369,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.8291,
+      "step": 48
+    },
+    {
+      "epoch": 0.007965536860928229,
+      "grad_norm": 8.513662338256836,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.7855,
+      "step": 49
+    },
+    {
+      "epoch": 0.008128098837681867,
+      "grad_norm": 14.290572166442871,
+      "learning_rate": 0.0,
+      "loss": 1.6268,
+      "step": 50
+    },
+    {
+      "epoch": 0.008128098837681867,
+      "eval_loss": 0.6914295554161072,
+      "eval_runtime": 726.8542,
+      "eval_samples_per_second": 3.565,
+      "eval_steps_per_second": 1.783,
+      "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": 3.51564950667264e+16,
+  "total_flos": 7.03129901334528e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null