Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e223154b1b610767e8527e149a88df2e9fd439a20681a9e4e5d2ff70a49530c
+oid sha256:2a14f2760a3512182c1828fa75ee71697ca20820831249fce96902ac69120944
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ae4dbaf7edfbc2f3a77babb44920c55ae9a7be81dcad33f3f254285cb1c2710
+oid sha256:3b123dbfebdead18f52a7f268801ee7e571870fda421c450d0464c81037967ef
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f975fb365bc383aec4428f9823ea6d996494fba5328979149706efa6858fd177
+oid sha256:4b0528d228e243b2e2228467264f59ee9e4ac9a965250e37509a5319515f25dc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d37f90ae6a26b97f051b6ae9d782d8de35f4ac8089398a5ca38f836cfa94daa
+oid sha256:dcf10f4a123e449e3ac4cd32b5adb66a0caac215fd281cca44aac5ba14634aed
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c73a70ac25c65ae0b1e8ae04666f455989c44dea275b6967aba952a32c5c7274
+oid sha256:d7c04060ec6c602808edf021203e9d31eb772bca5773e69a55c864ae205a0375
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ec6cbb23f360179c10d0632d0ac74faf597686416991c94c243da1edd4e0fd7
+oid sha256:f3511144d0b915cfbc1fa3a3bfc9fbb85e1fbf7a689c2cdc093f3a15da26d008
 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": 0.8458815813064575,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0648403306856865,
+  "best_metric": 0.8230445981025696,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.129680661371373,
   "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": 16.254,
       "eval_steps_per_second": 4.226,
       "step": 25
+    },
+    {
+      "epoch": 0.06743394391311396,
+      "grad_norm": 0.23086683452129364,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7114,
+      "step": 26
+    },
+    {
+      "epoch": 0.07002755714054142,
+      "grad_norm": 0.25243982672691345,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.7805,
+      "step": 27
+    },
+    {
+      "epoch": 0.07262117036796888,
+      "grad_norm": 0.23748691380023956,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.8093,
+      "step": 28
+    },
+    {
+      "epoch": 0.07521478359539634,
+      "grad_norm": 0.2173396199941635,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.8479,
+      "step": 29
+    },
+    {
+      "epoch": 0.0778083968228238,
+      "grad_norm": 0.21329988539218903,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.8344,
+      "step": 30
+    },
+    {
+      "epoch": 0.08040201005025126,
+      "grad_norm": 0.19844605028629303,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.8939,
+      "step": 31
+    },
+    {
+      "epoch": 0.08299562327767872,
+      "grad_norm": 0.19081762433052063,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.8595,
+      "step": 32
+    },
+    {
+      "epoch": 0.08558923650510618,
+      "grad_norm": 0.20479382574558258,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.869,
+      "step": 33
+    },
+    {
+      "epoch": 0.08818284973253364,
+      "grad_norm": 0.24034421145915985,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.8896,
+      "step": 34
+    },
+    {
+      "epoch": 0.0907764629599611,
+      "grad_norm": 0.25905755162239075,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.9076,
+      "step": 35
+    },
+    {
+      "epoch": 0.09337007618738856,
+      "grad_norm": 0.2752353549003601,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.9571,
+      "step": 36
+    },
+    {
+      "epoch": 0.09596368941481602,
+      "grad_norm": 0.3349551558494568,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.0071,
+      "step": 37
+    },
+    {
+      "epoch": 0.09855730264224348,
+      "grad_norm": 0.1601610630750656,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.723,
+      "step": 38
+    },
+    {
+      "epoch": 0.10115091586967094,
+      "grad_norm": 0.14773516356945038,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.7755,
+      "step": 39
+    },
+    {
+      "epoch": 0.1037445290970984,
+      "grad_norm": 0.16305404901504517,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.798,
+      "step": 40
+    },
+    {
+      "epoch": 0.10633814232452586,
+      "grad_norm": 0.17203955352306366,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.7997,
+      "step": 41
+    },
+    {
+      "epoch": 0.10893175555195332,
+      "grad_norm": 0.16851209104061127,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.8467,
+      "step": 42
+    },
+    {
+      "epoch": 0.11152536877938077,
+      "grad_norm": 0.1819651573896408,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.8372,
+      "step": 43
+    },
+    {
+      "epoch": 0.11411898200680823,
+      "grad_norm": 0.18483349680900574,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.874,
+      "step": 44
+    },
+    {
+      "epoch": 0.11671259523423569,
+      "grad_norm": 0.19454142451286316,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.8774,
+      "step": 45
+    },
+    {
+      "epoch": 0.11930620846166315,
+      "grad_norm": 0.19523195922374725,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.8659,
+      "step": 46
+    },
+    {
+      "epoch": 0.12189982168909061,
+      "grad_norm": 0.19370612502098083,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.9048,
+      "step": 47
+    },
+    {
+      "epoch": 0.12449343491651807,
+      "grad_norm": 0.21113789081573486,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.925,
+      "step": 48
+    },
+    {
+      "epoch": 0.12708704814394553,
+      "grad_norm": 0.2328350991010666,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.9406,
+      "step": 49
+    },
+    {
+      "epoch": 0.129680661371373,
+      "grad_norm": 0.3309152126312256,
+      "learning_rate": 1e-05,
+      "loss": 1.0261,
+      "step": 50
+    },
+    {
+      "epoch": 0.129680661371373,
+      "eval_loss": 0.8230445981025696,
+      "eval_runtime": 3.0208,
+      "eval_samples_per_second": 16.552,
+      "eval_steps_per_second": 4.304,
+      "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": 2.8237595991762534e+17,
+  "total_flos": 5.6466370550195814e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null