Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ece18d2ea3767c3742e7c5fb1e83ccfa9f0338d446caa0d54cfb48b727940b4
+oid sha256:a500d527bd665725a1706ba7a7fc43db79258b29bc46f45d0cf79eef010e151e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf9dff93c69427479201a64ce8130aec5d049d467f059a78333ae7082a196874
+oid sha256:a020065d8f53f65f9efff87aaedab0de195e0e4dd8a46c32eacde22095b4f244
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06d6d402d5f02f7929aff34f81a458e60d606f41e55e492b3b6ee35543dfac4a
+oid sha256:068cd73488d298d5312ba06672f2d4ed7bffa4308e7ed39defd45b58f277adb5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35c1840371e97b29e3a6f2a2b59d96a04efbf18baa2f6c3a2f3fe58262899ae7
+oid sha256:0ab718f900c5e126aaca7ed56b111145e77344cf7539462e1d5b52dfe4c03e9d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c8faa4ed3f925a524736f63fcba07a55acf0f1ec7606dc88f0184ebfa92ec74
+oid sha256:a362519ca699f3973750c15737f0e223613f413ba5592fd658aa217d4cc3e5a6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76ce4183648af9aba07b0e64408eaa9fe8b34e2b9611294f9772de6f905268ae
+oid sha256:f037cd444f7b3a679de6e695f2d105259b0751c1c7a954eb2b30c4f262d1b1af
 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": 0.9329157471656799,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22358859698155395,
+  "best_metric": 0.8612193465232849,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4471771939631079,
   "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": 16.317,
       "eval_steps_per_second": 4.242,
       "step": 25
+    },
+    {
+      "epoch": 0.2325321408608161,
+      "grad_norm": 1.5254967212677002,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.1298,
+      "step": 26
+    },
+    {
+      "epoch": 0.24147568474007824,
+      "grad_norm": 1.5145419836044312,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.1004,
+      "step": 27
+    },
+    {
+      "epoch": 0.2504192286193404,
+      "grad_norm": 1.1959255933761597,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.0102,
+      "step": 28
+    },
+    {
+      "epoch": 0.25936277249860257,
+      "grad_norm": 0.8409033417701721,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.9419,
+      "step": 29
+    },
+    {
+      "epoch": 0.26830631637786473,
+      "grad_norm": 0.5640770196914673,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.9541,
+      "step": 30
+    },
+    {
+      "epoch": 0.2772498602571269,
+      "grad_norm": 0.5304577946662903,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.8527,
+      "step": 31
+    },
+    {
+      "epoch": 0.28619340413638905,
+      "grad_norm": 0.7212780714035034,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.8461,
+      "step": 32
+    },
+    {
+      "epoch": 0.2951369480156512,
+      "grad_norm": 0.9113336801528931,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.8521,
+      "step": 33
+    },
+    {
+      "epoch": 0.3040804918949134,
+      "grad_norm": 0.9317920804023743,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.8544,
+      "step": 34
+    },
+    {
+      "epoch": 0.31302403577417554,
+      "grad_norm": 0.8762340545654297,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.813,
+      "step": 35
+    },
+    {
+      "epoch": 0.3219675796534377,
+      "grad_norm": 0.7749875783920288,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.7464,
+      "step": 36
+    },
+    {
+      "epoch": 0.33091112353269986,
+      "grad_norm": 0.6698021292686462,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.6547,
+      "step": 37
+    },
+    {
+      "epoch": 0.33985466741196196,
+      "grad_norm": 0.6533907651901245,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.0302,
+      "step": 38
+    },
+    {
+      "epoch": 0.3487982112912241,
+      "grad_norm": 0.8068573474884033,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.9967,
+      "step": 39
+    },
+    {
+      "epoch": 0.3577417551704863,
+      "grad_norm": 0.816889226436615,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.9799,
+      "step": 40
+    },
+    {
+      "epoch": 0.36668529904974845,
+      "grad_norm": 0.8150957226753235,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.9593,
+      "step": 41
+    },
+    {
+      "epoch": 0.3756288429290106,
+      "grad_norm": 0.7163166999816895,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.9513,
+      "step": 42
+    },
+    {
+      "epoch": 0.38457238680827277,
+      "grad_norm": 0.5624445080757141,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.8999,
+      "step": 43
+    },
+    {
+      "epoch": 0.39351593068753493,
+      "grad_norm": 0.5166836977005005,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.8222,
+      "step": 44
+    },
+    {
+      "epoch": 0.4024594745667971,
+      "grad_norm": 0.42919614911079407,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.7809,
+      "step": 45
+    },
+    {
+      "epoch": 0.41140301844605925,
+      "grad_norm": 0.43555784225463867,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.81,
+      "step": 46
+    },
+    {
+      "epoch": 0.4203465623253214,
+      "grad_norm": 0.50513756275177,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.8089,
+      "step": 47
+    },
+    {
+      "epoch": 0.4292901062045836,
+      "grad_norm": 0.6194409728050232,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.8606,
+      "step": 48
+    },
+    {
+      "epoch": 0.43823365008384574,
+      "grad_norm": 0.7608831524848938,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.768,
+      "step": 49
+    },
+    {
+      "epoch": 0.4471771939631079,
+      "grad_norm": 0.9651173949241638,
+      "learning_rate": 1e-05,
+      "loss": 0.6667,
+      "step": 50
+    },
+    {
+      "epoch": 0.4471771939631079,
+      "eval_loss": 0.8612193465232849,
+      "eval_runtime": 3.0064,
+      "eval_samples_per_second": 16.631,
+      "eval_steps_per_second": 4.324,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null