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:aa26d9690acae831c95e9d0aaa0418c78a2b7b792257f90ac99b1f6bd88dfbe8
+oid sha256:00796d671e095cdcd5068102d83d9a90e9ab911adb2b49fcdc8d0e702feb7539
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2885f8ffca668ca9e216c1bb7af1cee03638a395a27721d9c05bf0a06af845db
+oid sha256:20b5d32f5d35266cc16dbf237c776438e7c641d09f7b4f40df280091916190af
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dceab4046c227d3598b46370e242ac139e7f40b3e24487dd364077928d320ae3
+oid sha256:3182c8132b6e6ce0774d67a7a136b7a5beae5150f5fbedf343c062a8feaaebf0
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa2df0a512ea1dc37c55c4e72f7f701cac86fa563ada24e91c4921738c3802d0
+oid sha256:0e04681ad75d8f09a37315720f4a259e9575409faafbb1d24d2260407f9ebca3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46b8a69a87da9436e2e1130e5c8e11a68e2389d2e599bc3fc2178df956c544d9
+oid sha256:ace17a3cf9c784cd29727f12ffa26ecb7310a7ab0861b4286162e10b05ca0465
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74c10c597b76b3a9e50c72912b3285d5fbd773c5306014380e7c8f07ee17db03
+oid sha256:3a81f58b465f877ad987844f301fa1f4c3669ddef23df741a39c152b8e218e37
 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": 0.3033914864063263,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.6533278889342589,
+  "best_metric": 0.22316619753837585,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.9799918334013883,
   "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": 32.532,
       "eval_steps_per_second": 8.458,
       "step": 50
+    },
+    {
+      "epoch": 0.666394446712944,
+      "grad_norm": 0.9900059103965759,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.3231,
+      "step": 51
+    },
+    {
+      "epoch": 0.6794610044916293,
+      "grad_norm": 0.8345087766647339,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 0.3644,
+      "step": 52
+    },
+    {
+      "epoch": 0.6925275622703144,
+      "grad_norm": 0.8801731467247009,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 0.2791,
+      "step": 53
+    },
+    {
+      "epoch": 0.7055941200489996,
+      "grad_norm": 1.1393957138061523,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.2965,
+      "step": 54
+    },
+    {
+      "epoch": 0.7186606778276847,
+      "grad_norm": 0.9782978892326355,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 0.2393,
+      "step": 55
+    },
+    {
+      "epoch": 0.73172723560637,
+      "grad_norm": 0.8556644916534424,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 0.2027,
+      "step": 56
+    },
+    {
+      "epoch": 0.7447937933850551,
+      "grad_norm": 1.0292524099349976,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.275,
+      "step": 57
+    },
+    {
+      "epoch": 0.7578603511637403,
+      "grad_norm": 1.2255464792251587,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 0.6167,
+      "step": 58
+    },
+    {
+      "epoch": 0.7709269089424254,
+      "grad_norm": 1.345024824142456,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 0.51,
+      "step": 59
+    },
+    {
+      "epoch": 0.7839934667211107,
+      "grad_norm": 2.0753092765808105,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.3936,
+      "step": 60
+    },
+    {
+      "epoch": 0.7970600244997958,
+      "grad_norm": 1.9613157510757446,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 0.4177,
+      "step": 61
+    },
+    {
+      "epoch": 0.810126582278481,
+      "grad_norm": 1.782265543937683,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 0.5354,
+      "step": 62
+    },
+    {
+      "epoch": 0.8231931400571662,
+      "grad_norm": 0.880858302116394,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.227,
+      "step": 63
+    },
+    {
+      "epoch": 0.8362596978358514,
+      "grad_norm": 0.643760621547699,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 0.339,
+      "step": 64
+    },
+    {
+      "epoch": 0.8493262556145366,
+      "grad_norm": 0.610495924949646,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 0.2043,
+      "step": 65
+    },
+    {
+      "epoch": 0.8623928133932217,
+      "grad_norm": 0.7079125642776489,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.2392,
+      "step": 66
+    },
+    {
+      "epoch": 0.8754593711719069,
+      "grad_norm": 0.6936648488044739,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 0.2807,
+      "step": 67
+    },
+    {
+      "epoch": 0.8885259289505921,
+      "grad_norm": 0.7526812553405762,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 0.2831,
+      "step": 68
+    },
+    {
+      "epoch": 0.9015924867292773,
+      "grad_norm": 1.716686725616455,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.117,
+      "step": 69
+    },
+    {
+      "epoch": 0.9146590445079624,
+      "grad_norm": 0.9851632714271545,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 0.4664,
+      "step": 70
+    },
+    {
+      "epoch": 0.9277256022866476,
+      "grad_norm": 1.2416988611221313,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 0.6231,
+      "step": 71
+    },
+    {
+      "epoch": 0.9407921600653328,
+      "grad_norm": 0.8936472535133362,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.3633,
+      "step": 72
+    },
+    {
+      "epoch": 0.953858717844018,
+      "grad_norm": 1.051101803779602,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 0.4201,
+      "step": 73
+    },
+    {
+      "epoch": 0.9669252756227031,
+      "grad_norm": 1.0521873235702515,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 0.395,
+      "step": 74
+    },
+    {
+      "epoch": 0.9799918334013883,
+      "grad_norm": 2.4216976165771484,
+      "learning_rate": 1e-05,
+      "loss": 0.6176,
+      "step": 75
+    },
+    {
+      "epoch": 0.9799918334013883,
+      "eval_loss": 0.22316619753837585,
+      "eval_runtime": 1.5353,
+      "eval_samples_per_second": 32.566,
+      "eval_steps_per_second": 8.467,
+      "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