Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:760077755139239c03913416f7e3b757dda4b38a2a199ee35416878f4aef561a
+oid sha256:0ab7081f376f148c5c5a9c005a1a91f0f2b4e77d5db6376e75201262253a9192
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ced5f1798bb3b8beed28df58af9fec24bddd2e77f6dd5493b8496b02d39f5cf
+oid sha256:64c68e185e9e4ca8f9c568696fd2d7961c9ddfbbb3ffdd0ba318926eaf09eacd
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16145b3d9607570d2ddddad88fdb9ac43e6ff9d447b04491b068684acac507d1
+oid sha256:bf5fffecca7fcccab0b60cc43af34c66f9333571dc3869681cc6356b25fca258
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8506a5b0bf561556b22c3b7594c54bf226a24c5c74783b93b90c04debc5c1751
+oid sha256:10f6b651f65046d4613f599f621bd483376dfdf0ff6fc5cca1475d3d9778b2b9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beefe0986ee57a48f1514e3be111b4583f6ac926a6c88e9983bb5dfb66f20e7a
+oid sha256:14c9aa955f03803b7a78e9b6d5f34ced2f9a3ffed0bcc967d28632899afc9a24
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55c537feef5d75160fe7d97262dee63b7bf09dccd8beb18d68be4a807088c0f1
+oid sha256:a69b6999c4ef0e349c002e6836d15b5c9a6936b61e1d4147156c1f6714dbb5b1
 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": 1.0805189609527588,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.028665615594094883,
+  "best_metric": 1.0622352361679077,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.057331231188189766,
   "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": 39.275,
       "eval_steps_per_second": 10.211,
       "step": 25
+    },
+    {
+      "epoch": 0.02981224021785868,
+      "grad_norm": 0.28330737352371216,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7118,
+      "step": 26
+    },
+    {
+      "epoch": 0.030958864841622472,
+      "grad_norm": 0.2869955897331238,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.911,
+      "step": 27
+    },
+    {
+      "epoch": 0.03210548946538627,
+      "grad_norm": 0.24439777433872223,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.0206,
+      "step": 28
+    },
+    {
+      "epoch": 0.03325211408915006,
+      "grad_norm": 0.20379236340522766,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.9864,
+      "step": 29
+    },
+    {
+      "epoch": 0.03439873871291386,
+      "grad_norm": 0.20275278389453888,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.0327,
+      "step": 30
+    },
+    {
+      "epoch": 0.035545363336677654,
+      "grad_norm": 0.20571181178092957,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.0511,
+      "step": 31
+    },
+    {
+      "epoch": 0.03669198796044145,
+      "grad_norm": 0.2231748253107071,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.1337,
+      "step": 32
+    },
+    {
+      "epoch": 0.03783861258420525,
+      "grad_norm": 0.2300759255886078,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.0262,
+      "step": 33
+    },
+    {
+      "epoch": 0.038985237207969044,
+      "grad_norm": 0.2718110680580139,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.0895,
+      "step": 34
+    },
+    {
+      "epoch": 0.04013186183173283,
+      "grad_norm": 0.33653226494789124,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.0861,
+      "step": 35
+    },
+    {
+      "epoch": 0.04127848645549663,
+      "grad_norm": 0.31303671002388,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.0592,
+      "step": 36
+    },
+    {
+      "epoch": 0.042425111079260426,
+      "grad_norm": 0.3611839711666107,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.1172,
+      "step": 37
+    },
+    {
+      "epoch": 0.04357173570302422,
+      "grad_norm": 0.13642393052577972,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.6939,
+      "step": 38
+    },
+    {
+      "epoch": 0.04471836032678802,
+      "grad_norm": 0.17616373300552368,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.8905,
+      "step": 39
+    },
+    {
+      "epoch": 0.045864984950551815,
+      "grad_norm": 0.2033797800540924,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.0261,
+      "step": 40
+    },
+    {
+      "epoch": 0.04701160957431561,
+      "grad_norm": 0.21175238490104675,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.0022,
+      "step": 41
+    },
+    {
+      "epoch": 0.0481582341980794,
+      "grad_norm": 0.208563432097435,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.0877,
+      "step": 42
+    },
+    {
+      "epoch": 0.0493048588218432,
+      "grad_norm": 0.21357567608356476,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.008,
+      "step": 43
+    },
+    {
+      "epoch": 0.050451483445606994,
+      "grad_norm": 0.2108396291732788,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.0799,
+      "step": 44
+    },
+    {
+      "epoch": 0.05159810806937079,
+      "grad_norm": 0.22082534432411194,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.061,
+      "step": 45
+    },
+    {
+      "epoch": 0.05274473269313459,
+      "grad_norm": 0.23444215953350067,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.0487,
+      "step": 46
+    },
+    {
+      "epoch": 0.05389135731689838,
+      "grad_norm": 0.2532033324241638,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.0605,
+      "step": 47
+    },
+    {
+      "epoch": 0.05503798194066217,
+      "grad_norm": 0.2836669087409973,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.1105,
+      "step": 48
+    },
+    {
+      "epoch": 0.05618460656442597,
+      "grad_norm": 0.2834874391555786,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.0619,
+      "step": 49
+    },
+    {
+      "epoch": 0.057331231188189766,
+      "grad_norm": 0.3379897475242615,
+      "learning_rate": 1e-05,
+      "loss": 1.1187,
+      "step": 50
+    },
+    {
+      "epoch": 0.057331231188189766,
+      "eval_loss": 1.0622352361679077,
+      "eval_runtime": 0.8794,
+      "eval_samples_per_second": 56.854,
+      "eval_steps_per_second": 14.782,
+      "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": 8.193189081828557e+16,
+  "total_flos": 1.6371476935684915e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null