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:a621083d2305d5a50122ab94d4432150e689dcc7b7077b4dd400afc98b006b4c
+oid sha256:e6f052eaa458ef8853fd6dc572afefb79ac3784f65e156b62a175d89212fd783
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47e97950cdee79cc5e19dcbae9544e9167ccbb25f4f9ff212601871f83bbf225
+oid sha256:b7242068213fba83372fd1c0ed3929282b6582e9fa0f1b2ed5ef4a3d2b8ea325
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dfc09b7d9f84302332ea5fbe1e5e524045dc5e91e4ca17ea5f41576bab092f4
+oid sha256:2526a33b5aa3dfa5541d142cb63a8151e13d58e1df26cab3f8b79c8167e4777b
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e37a281396d2197f56f2c8e1339f30ea771f45d61d83c4fac1aa7c89da8bcb
+oid sha256:680cca85cc95461ba66950ce313f8e2d03d7dcbf224d1da346ea4c3bdb9c945e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06096cbd51ad96418afc18c6f213e64017e61d0c5ce5b8ed4e630a1c7777d251
+oid sha256:79e6573a35289547eab7cad9855a490ff45b7c1564fb8a7379a83d159f4c78e7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65d45ec20ac491ce0f57373ce0601ce906f26977b9248bcad1930b607356f419
+oid sha256:26128f080f7ae685764b6bd7634de87d43595b2cf6f4accc999bb65bd4d23a54
 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": 0.7882411479949951,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.12600409513309183,
+  "best_metric": 0.7074993848800659,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.25200819026618365,
   "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": 16.429,
       "eval_steps_per_second": 4.271,
       "step": 25
+    },
+    {
+      "epoch": 0.1310442589384155,
+      "grad_norm": 12.02678108215332,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 30.3272,
+      "step": 26
+    },
+    {
+      "epoch": 0.13608442274373916,
+      "grad_norm": 12.788291931152344,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 28.0485,
+      "step": 27
+    },
+    {
+      "epoch": 0.14112458654906285,
+      "grad_norm": 11.346626281738281,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 26.7076,
+      "step": 28
+    },
+    {
+      "epoch": 0.14616475035438653,
+      "grad_norm": 9.494963645935059,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 25.2395,
+      "step": 29
+    },
+    {
+      "epoch": 0.15120491415971019,
+      "grad_norm": 7.810816287994385,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 23.878,
+      "step": 30
+    },
+    {
+      "epoch": 0.15624507796503387,
+      "grad_norm": 6.291456699371338,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 23.3567,
+      "step": 31
+    },
+    {
+      "epoch": 0.16128524177035752,
+      "grad_norm": 5.79580545425415,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 21.7162,
+      "step": 32
+    },
+    {
+      "epoch": 0.1663254055756812,
+      "grad_norm": 6.2812371253967285,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 20.6359,
+      "step": 33
+    },
+    {
+      "epoch": 0.1713655693810049,
+      "grad_norm": 6.805625915527344,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 19.7178,
+      "step": 34
+    },
+    {
+      "epoch": 0.17640573318632854,
+      "grad_norm": 7.821481227874756,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 19.1906,
+      "step": 35
+    },
+    {
+      "epoch": 0.18144589699165223,
+      "grad_norm": 8.715185165405273,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 19.334,
+      "step": 36
+    },
+    {
+      "epoch": 0.1864860607969759,
+      "grad_norm": 12.532947540283203,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 28.4381,
+      "step": 37
+    },
+    {
+      "epoch": 0.19152622460229957,
+      "grad_norm": 12.48162841796875,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 27.6077,
+      "step": 38
+    },
+    {
+      "epoch": 0.19656638840762325,
+      "grad_norm": 5.827184200286865,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 27.5133,
+      "step": 39
+    },
+    {
+      "epoch": 0.20160655221294693,
+      "grad_norm": 6.280447006225586,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 25.9376,
+      "step": 40
+    },
+    {
+      "epoch": 0.2066467160182706,
+      "grad_norm": 5.339621543884277,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 24.1776,
+      "step": 41
+    },
+    {
+      "epoch": 0.21168687982359427,
+      "grad_norm": 5.377862930297852,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 22.0573,
+      "step": 42
+    },
+    {
+      "epoch": 0.21672704362891795,
+      "grad_norm": 5.197916030883789,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 22.8626,
+      "step": 43
+    },
+    {
+      "epoch": 0.2217672074342416,
+      "grad_norm": 4.99856424331665,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 20.4139,
+      "step": 44
+    },
+    {
+      "epoch": 0.2268073712395653,
+      "grad_norm": 5.102665424346924,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 20.2285,
+      "step": 45
+    },
+    {
+      "epoch": 0.23184753504488895,
+      "grad_norm": 5.269073963165283,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 19.3747,
+      "step": 46
+    },
+    {
+      "epoch": 0.23688769885021263,
+      "grad_norm": 5.775519371032715,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 19.242,
+      "step": 47
+    },
+    {
+      "epoch": 0.2419278626555363,
+      "grad_norm": 6.65461540222168,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 18.3409,
+      "step": 48
+    },
+    {
+      "epoch": 0.24696802646085997,
+      "grad_norm": 7.8584394454956055,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 23.812,
+      "step": 49
+    },
+    {
+      "epoch": 0.25200819026618365,
+      "grad_norm": 14.629874229431152,
+      "learning_rate": 1e-05,
+      "loss": 25.9946,
+      "step": 50
+    },
+    {
+      "epoch": 0.25200819026618365,
+      "eval_loss": 0.7074993848800659,
+      "eval_runtime": 3.0573,
+      "eval_samples_per_second": 16.354,
+      "eval_steps_per_second": 4.252,
+      "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": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null