Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a1ad25736adf0e4fe0fda2850edf1ab10d5b91f6af07ef28a373eaa4633e23e
+oid sha256:1d1514a5633cbab65bd766609bb86882622c2e5990264a385fc8b7121d419df2
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d202c18564f922557e65329e1f72d8c1fde4996d2706ca1a8d427f2b34c9dd
+oid sha256:48df706cd0b0653477678cd138fc22eb402614ae1faf5fb51ffedfc128437d57
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:231906c72178ff7131f455b3c3dbb653e8bf996ad8b86170c27e610a941778d5
+oid sha256:acff88f2b05aa7a4a548f97ca12aadff1ec12a19d47830a0275d7d60dcc582f1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd4cdcec2e891aaeae0844296e260cbffdc630961a6327342cbdcfa1e14df4da
+oid sha256:65b37d6d9185895e78984157966eec72fdbe6831fd0ec7d01e510bc0a72e4fc2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ec915fc62cdc13e3c0697007e8b41417c8ac62e4dfa0280a359baae9ad9de1f
+oid sha256:31635963de81dc58e63cdeb5bb6c6faa03bc233fe652fc150a4ac7d78b171f94
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ca71c4796f165b972a83eebfe5abfea914f6a16978e42bd9a2e4032cb146c58
+oid sha256:d985e6fe47d3b7e320661113c78b3d43196df06cab0ffeb0b90fd2ed509f81ac
 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": 1.2116010189056396,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05385754678874377,
+  "best_metric": 1.1570563316345215,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.10771509357748754,
   "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": 17.545,
       "eval_steps_per_second": 4.562,
       "step": 25
+    },
+    {
+      "epoch": 0.056011848660293524,
+      "grad_norm": 16.40360450744629,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 14.7959,
+      "step": 26
+    },
+    {
+      "epoch": 0.05816615053184328,
+      "grad_norm": 10.675568580627441,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 16.9706,
+      "step": 27
+    },
+    {
+      "epoch": 0.060320452403393024,
+      "grad_norm": 11.316140174865723,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 17.8713,
+      "step": 28
+    },
+    {
+      "epoch": 0.06247475427494278,
+      "grad_norm": 15.755949974060059,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 17.6029,
+      "step": 29
+    },
+    {
+      "epoch": 0.06462905614649253,
+      "grad_norm": 12.196805953979492,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 19.5617,
+      "step": 30
+    },
+    {
+      "epoch": 0.06678335801804228,
+      "grad_norm": 12.657279968261719,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 19.5314,
+      "step": 31
+    },
+    {
+      "epoch": 0.06893765988959202,
+      "grad_norm": 13.666502952575684,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 19.9685,
+      "step": 32
+    },
+    {
+      "epoch": 0.07109196176114178,
+      "grad_norm": 15.66434097290039,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 19.0098,
+      "step": 33
+    },
+    {
+      "epoch": 0.07324626363269153,
+      "grad_norm": 19.04754066467285,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 18.1732,
+      "step": 34
+    },
+    {
+      "epoch": 0.07540056550424128,
+      "grad_norm": 21.20579719543457,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 18.7094,
+      "step": 35
+    },
+    {
+      "epoch": 0.07755486737579104,
+      "grad_norm": 26.361967086791992,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 16.9715,
+      "step": 36
+    },
+    {
+      "epoch": 0.07970916924734078,
+      "grad_norm": 47.8284797668457,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 19.8467,
+      "step": 37
+    },
+    {
+      "epoch": 0.08186347111889053,
+      "grad_norm": 87.42459869384766,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 19.9201,
+      "step": 38
+    },
+    {
+      "epoch": 0.08401777299044029,
+      "grad_norm": 9.333584785461426,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 16.6894,
+      "step": 39
+    },
+    {
+      "epoch": 0.08617207486199004,
+      "grad_norm": 9.861259460449219,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 16.4402,
+      "step": 40
+    },
+    {
+      "epoch": 0.08832637673353978,
+      "grad_norm": 11.06502628326416,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 18.4886,
+      "step": 41
+    },
+    {
+      "epoch": 0.09048067860508954,
+      "grad_norm": 27.977924346923828,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 17.8642,
+      "step": 42
+    },
+    {
+      "epoch": 0.09263498047663929,
+      "grad_norm": 13.159262657165527,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 19.8223,
+      "step": 43
+    },
+    {
+      "epoch": 0.09478928234818904,
+      "grad_norm": 11.276972770690918,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 19.9521,
+      "step": 44
+    },
+    {
+      "epoch": 0.0969435842197388,
+      "grad_norm": 12.780776977539062,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 18.9005,
+      "step": 45
+    },
+    {
+      "epoch": 0.09909788609128854,
+      "grad_norm": 14.059585571289062,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 18.8465,
+      "step": 46
+    },
+    {
+      "epoch": 0.10125218796283829,
+      "grad_norm": 16.014514923095703,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 19.1576,
+      "step": 47
+    },
+    {
+      "epoch": 0.10340648983438805,
+      "grad_norm": 23.282018661499023,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 19.4527,
+      "step": 48
+    },
+    {
+      "epoch": 0.1055607917059378,
+      "grad_norm": 34.15425491333008,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 18.9092,
+      "step": 49
+    },
+    {
+      "epoch": 0.10771509357748754,
+      "grad_norm": 82.45684814453125,
+      "learning_rate": 1e-05,
+      "loss": 19.8975,
+      "step": 50
+    },
+    {
+      "epoch": 0.10771509357748754,
+      "eval_loss": 1.1570563316345215,
+      "eval_runtime": 2.8352,
+      "eval_samples_per_second": 17.635,
+      "eval_steps_per_second": 4.585,
+      "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": 2.8484601064194048e+17,
+  "total_flos": 5.703992746222551e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null