Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2235868cbfe64bc7ed91819cd4d77d27d896f4c5e0b481e15e0db441753a070f
+oid sha256:9c115f04807581b2770985a6f855078ef8e5257ca7ca6ae919b65b4f0860a255
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb388f0a2b09c45095974c8650a49b19e40ff4d992582bc74e56b37832d2127
+oid sha256:ba886592b2a6672cf210e75f2ac748e2e4732e8e927c9e23b652f0b4518cfea8
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:198880355d69836e8d969ba56f910a3906fe2fdf3a4222d72971f6a2c7b9deb3
+oid sha256:7c1cedd422f95c616c9921d9c2b0b7f450edc09f9f58e59c7cfe33bf86353ccf
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:872f608404dcb445df442829c1378677d23455a96e5bda1b70e12ce4ccd70951
+oid sha256:1664f76e4f4a0eb0086113d4f38f040f4f17780acd2ffa2a8e61d2fa9947dede
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9786223e5c6333bbd673a87ec449175d93624cf2ed38966e8dab7782e48bc9d
+oid sha256:82c5005b061155693e44ef1703233f9ad82f2db8a33d842cbc3269ac2f7b1fc1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb08ef9da12f851416d6f45dc900bf8d229bcd39bb866ef944b302cb374fd696
+oid sha256:e90433fee02cc00f1834d9a6d7419bbbe6ced9e1ddd9aa53ca1fdc96c4b7f604
 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": 0.10174055397510529,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.04113322021697774,
+  "best_metric": 0.08922764658927917,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08226644043395548,
   "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": 6.054,
       "eval_steps_per_second": 1.574,
       "step": 25
+    },
+    {
+      "epoch": 0.042778549025656844,
+      "grad_norm": 0.891169011592865,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.5517,
+      "step": 26
+    },
+    {
+      "epoch": 0.044423877834335955,
+      "grad_norm": 0.7230943441390991,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.6284,
+      "step": 27
+    },
+    {
+      "epoch": 0.046069206643015066,
+      "grad_norm": 0.6296717524528503,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.6151,
+      "step": 28
+    },
+    {
+      "epoch": 0.04771453545169418,
+      "grad_norm": 0.5857284665107727,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.6614,
+      "step": 29
+    },
+    {
+      "epoch": 0.04935986426037328,
+      "grad_norm": 0.654015064239502,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.809,
+      "step": 30
+    },
+    {
+      "epoch": 0.05100519306905239,
+      "grad_norm": 0.729507565498352,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.9166,
+      "step": 31
+    },
+    {
+      "epoch": 0.052650521877731504,
+      "grad_norm": 0.8457760214805603,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.1044,
+      "step": 32
+    },
+    {
+      "epoch": 0.054295850686410616,
+      "grad_norm": 1.332365870475769,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.5837,
+      "step": 33
+    },
+    {
+      "epoch": 0.05594117949508972,
+      "grad_norm": 2.186558961868286,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.5722,
+      "step": 34
+    },
+    {
+      "epoch": 0.05758650830376883,
+      "grad_norm": 8.118924140930176,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 6.0169,
+      "step": 35
+    },
+    {
+      "epoch": 0.05923183711244794,
+      "grad_norm": 10.122238159179688,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.1049,
+      "step": 36
+    },
+    {
+      "epoch": 0.060877165921127054,
+      "grad_norm": 11.095065116882324,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.9234,
+      "step": 37
+    },
+    {
+      "epoch": 0.06252249472980616,
+      "grad_norm": 15.164539337158203,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 8.3837,
+      "step": 38
+    },
+    {
+      "epoch": 0.06416782353848527,
+      "grad_norm": 0.9335575103759766,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4713,
+      "step": 39
+    },
+    {
+      "epoch": 0.06581315234716438,
+      "grad_norm": 0.951163649559021,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.5083,
+      "step": 40
+    },
+    {
+      "epoch": 0.06745848115584349,
+      "grad_norm": 1.1648244857788086,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.5451,
+      "step": 41
+    },
+    {
+      "epoch": 0.0691038099645226,
+      "grad_norm": 0.5956860780715942,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.6876,
+      "step": 42
+    },
+    {
+      "epoch": 0.0707491387732017,
+      "grad_norm": 1.2150315046310425,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.8026,
+      "step": 43
+    },
+    {
+      "epoch": 0.07239446758188081,
+      "grad_norm": 1.453965663909912,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.9668,
+      "step": 44
+    },
+    {
+      "epoch": 0.07403979639055992,
+      "grad_norm": 2.6636314392089844,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.3575,
+      "step": 45
+    },
+    {
+      "epoch": 0.07568512519923903,
+      "grad_norm": 3.017009735107422,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.7308,
+      "step": 46
+    },
+    {
+      "epoch": 0.07733045400791815,
+      "grad_norm": 4.661072254180908,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.6012,
+      "step": 47
+    },
+    {
+      "epoch": 0.07897578281659726,
+      "grad_norm": 8.242691040039062,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 8.213,
+      "step": 48
+    },
+    {
+      "epoch": 0.08062111162527637,
+      "grad_norm": 11.560867309570312,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.5814,
+      "step": 49
+    },
+    {
+      "epoch": 0.08226644043395548,
+      "grad_norm": 18.662717819213867,
+      "learning_rate": 1e-05,
+      "loss": 13.808,
+      "step": 50
+    },
+    {
+      "epoch": 0.08226644043395548,
+      "eval_loss": 0.08922764658927917,
+      "eval_runtime": 8.2665,
+      "eval_samples_per_second": 6.048,
+      "eval_steps_per_second": 1.573,
+      "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": 3.2845074557147546e+17,
+  "total_flos": 6.570658412877578e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null