Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ea8bcdad29eddd8529b4d9001afb1d895989933644e045f441224641562a5b2
+oid sha256:9446b445f9e798cb09f0e181c66fefae8a6f9b3fa6f428f578a8c326f3283978
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba739f1e275689dd7a4f56f3bb74c24005b5edb8cb4544641a55f320975f6c7a
+oid sha256:d834383945e44055953d0c514af3a5ef666c346eae2edff61990450790bee3ce
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92098fa57d5ba3ef3e5c1efc629ec964fe256fb720230fb4415e63febf4e0ac5
+oid sha256:ef0b6d3fca7b5394c20b7f83a12afa6d17ff9e3209cdf47605a45059fc75324d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f0f18a15b74e70821c9ee9817f53386333611a66597434c45ccac1026a6d698
+oid sha256:cc1df8b78f4144bce15f97f6f8cedab506cb287b55b538e6d387683a3e83a5d8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ede70b814d2d82f39b9b843cbb7336f2eaa84f18cd52d0f3de2aa68b1dfa026e
+oid sha256:fb1be75ef788e761f328a192654e43fdf2a0fc4bb1c6f587e5c7ea67709b4651
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d6edcbb10832163ef5f62eac53ec8837b814f980e774e2f564ae30a928e805e
+oid sha256:2102a52bcfb19ae917bd0a6667e38d798608f9f7627eb6baadc2ca054f8b6df2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08785244822502136,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.9768009768009768,
+  "best_metric": 0.06207295507192612,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.9645909645909647,
   "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": 16.906,
       "eval_steps_per_second": 4.396,
       "step": 25
+    },
+    {
+      "epoch": 1.0268620268620268,
+      "grad_norm": 0.5360961556434631,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.1334,
+      "step": 26
+    },
+    {
+      "epoch": 1.065934065934066,
+      "grad_norm": 0.38586679100990295,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0611,
+      "step": 27
+    },
+    {
+      "epoch": 1.105006105006105,
+      "grad_norm": 0.2803765833377838,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.071,
+      "step": 28
+    },
+    {
+      "epoch": 1.144078144078144,
+      "grad_norm": 0.26485010981559753,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0692,
+      "step": 29
+    },
+    {
+      "epoch": 1.1831501831501832,
+      "grad_norm": 0.28996384143829346,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0566,
+      "step": 30
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.47175368666648865,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0565,
+      "step": 31
+    },
+    {
+      "epoch": 1.2612942612942613,
+      "grad_norm": 0.29181963205337524,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0338,
+      "step": 32
+    },
+    {
+      "epoch": 1.3003663003663004,
+      "grad_norm": 0.32808589935302734,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0561,
+      "step": 33
+    },
+    {
+      "epoch": 1.3394383394383396,
+      "grad_norm": 0.2767590582370758,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0465,
+      "step": 34
+    },
+    {
+      "epoch": 1.3785103785103785,
+      "grad_norm": 0.3915354609489441,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.062,
+      "step": 35
+    },
+    {
+      "epoch": 1.4175824175824177,
+      "grad_norm": 0.24747319519519806,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.059,
+      "step": 36
+    },
+    {
+      "epoch": 1.4566544566544566,
+      "grad_norm": 0.1756383627653122,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0318,
+      "step": 37
+    },
+    {
+      "epoch": 1.4957264957264957,
+      "grad_norm": 0.1586117446422577,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.024,
+      "step": 38
+    },
+    {
+      "epoch": 1.5347985347985347,
+      "grad_norm": 0.22885628044605255,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0441,
+      "step": 39
+    },
+    {
+      "epoch": 1.5738705738705738,
+      "grad_norm": 0.18986821174621582,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0354,
+      "step": 40
+    },
+    {
+      "epoch": 1.612942612942613,
+      "grad_norm": 0.30566394329071045,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0535,
+      "step": 41
+    },
+    {
+      "epoch": 1.652014652014652,
+      "grad_norm": 0.23684832453727722,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0529,
+      "step": 42
+    },
+    {
+      "epoch": 1.691086691086691,
+      "grad_norm": 0.23424597084522247,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0356,
+      "step": 43
+    },
+    {
+      "epoch": 1.7301587301587302,
+      "grad_norm": 0.28173795342445374,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0224,
+      "step": 44
+    },
+    {
+      "epoch": 1.7692307692307692,
+      "grad_norm": 0.22328241169452667,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0311,
+      "step": 45
+    },
+    {
+      "epoch": 1.8083028083028083,
+      "grad_norm": 0.2587464451789856,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0451,
+      "step": 46
+    },
+    {
+      "epoch": 1.8473748473748475,
+      "grad_norm": 0.31801164150238037,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0679,
+      "step": 47
+    },
+    {
+      "epoch": 1.8864468864468864,
+      "grad_norm": 0.29504692554473877,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0622,
+      "step": 48
+    },
+    {
+      "epoch": 1.9255189255189256,
+      "grad_norm": 0.18160757422447205,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.047,
+      "step": 49
+    },
+    {
+      "epoch": 1.9645909645909647,
+      "grad_norm": 0.13465796411037445,
+      "learning_rate": 1e-05,
+      "loss": 0.0238,
+      "step": 50
+    },
+    {
+      "epoch": 1.9645909645909647,
+      "eval_loss": 0.06207295507192612,
+      "eval_runtime": 2.9728,
+      "eval_samples_per_second": 16.819,
+      "eval_steps_per_second": 4.373,
+      "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": 2.66009604784128e+17,
+  "total_flos": 5.32019209568256e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null