Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60a6bf4ca8d3f3bf7c5c78a406b9f984c060ff17dd9e38ce06ee5bde504a11c9
+oid sha256:f76a057e5a97e2eb36e17e549765ef124130801d4a781ac8057ea1e3f7f2df29
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30380e24582f82f3da32d8c2929b3986b5ada1428d9cae763aeb2cabba2a35d5
+oid sha256:a4d5fbfe04a981f6aad1a7481b53d961f176fd5c9b0846e6a74070b1a50e05b2
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f78b8755b5c5bafbd19ccb7cea9e07277bc4171d6c0e7ac43fe9702ff6f6be7f
+oid sha256:e0b8d089f1fa90908f28435fe1afff72926ef30f8e348882e2219304e3c29ed6
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3643be8e9a34a717c316787d78305fc730266e9276926a53b69185270d62f530
+oid sha256:c772ed06d30e532ee6ebc02c9eb64796bea49196d8226b0dab4922f0ce4d1ce8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f56eebe1a7bac08b64e18704fba61afa0bb463da66fad0650a876c9c8ccc4162
+oid sha256:87c7809d35748d65d3bba65a2d3ac79f6098171040ee41dbe308d04124638ece
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2180a47ae3f710db94f8743cd4d2e0621b5f34847b9bb9730497e06e18adb483
+oid sha256:453a1aa9709b63a98e89131a3a7fac795a9ebd2e417d1209b18ea8a9d7e95bed
 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": 0.9043247699737549,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.022093344380005524,
+  "best_metric": 0.2489974945783615,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04418668876001105,
   "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": 14.345,
       "eval_steps_per_second": 3.73,
       "step": 25
+    },
+    {
+      "epoch": 0.022977078155205746,
+      "grad_norm": 53.11459732055664,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3292,
+      "step": 26
+    },
+    {
+      "epoch": 0.023860811930405967,
+      "grad_norm": 59.67228317260742,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 14.2238,
+      "step": 27
+    },
+    {
+      "epoch": 0.024744545705606188,
+      "grad_norm": 76.35183715820312,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.0212,
+      "step": 28
+    },
+    {
+      "epoch": 0.025628279480806405,
+      "grad_norm": 81.94586944580078,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 14.2928,
+      "step": 29
+    },
+    {
+      "epoch": 0.026512013256006627,
+      "grad_norm": 57.83568572998047,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 4.3004,
+      "step": 30
+    },
+    {
+      "epoch": 0.027395747031206848,
+      "grad_norm": 37.16580581665039,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 4.3446,
+      "step": 31
+    },
+    {
+      "epoch": 0.02827948080640707,
+      "grad_norm": 43.2403450012207,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 7.3295,
+      "step": 32
+    },
+    {
+      "epoch": 0.02916321458160729,
+      "grad_norm": 92.82877349853516,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 9.9978,
+      "step": 33
+    },
+    {
+      "epoch": 0.03004694835680751,
+      "grad_norm": 47.803977966308594,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 5.1052,
+      "step": 34
+    },
+    {
+      "epoch": 0.030930682132007732,
+      "grad_norm": 71.9683609008789,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 9.7027,
+      "step": 35
+    },
+    {
+      "epoch": 0.03181441590720795,
+      "grad_norm": 50.05008316040039,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 8.7477,
+      "step": 36
+    },
+    {
+      "epoch": 0.032698149682408174,
+      "grad_norm": 52.16643524169922,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 7.9946,
+      "step": 37
+    },
+    {
+      "epoch": 0.033581883457608395,
+      "grad_norm": 44.67985916137695,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 7.7456,
+      "step": 38
+    },
+    {
+      "epoch": 0.03446561723280862,
+      "grad_norm": 26.479564666748047,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 4.5466,
+      "step": 39
+    },
+    {
+      "epoch": 0.03534935100800884,
+      "grad_norm": 38.651485443115234,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 5.1983,
+      "step": 40
+    },
+    {
+      "epoch": 0.03623308478320906,
+      "grad_norm": 33.117156982421875,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.2513,
+      "step": 41
+    },
+    {
+      "epoch": 0.03711681855840928,
+      "grad_norm": 60.45636749267578,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.6929,
+      "step": 42
+    },
+    {
+      "epoch": 0.0380005523336095,
+      "grad_norm": 18.882118225097656,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.9959,
+      "step": 43
+    },
+    {
+      "epoch": 0.03888428610880972,
+      "grad_norm": 17.66207504272461,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.375,
+      "step": 44
+    },
+    {
+      "epoch": 0.03976801988400994,
+      "grad_norm": 43.678035736083984,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.586,
+      "step": 45
+    },
+    {
+      "epoch": 0.040651753659210164,
+      "grad_norm": 40.00962448120117,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.0767,
+      "step": 46
+    },
+    {
+      "epoch": 0.041535487434410386,
+      "grad_norm": 27.8352108001709,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.1636,
+      "step": 47
+    },
+    {
+      "epoch": 0.04241922120961061,
+      "grad_norm": 79.74462127685547,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 5.0177,
+      "step": 48
+    },
+    {
+      "epoch": 0.04330295498481083,
+      "grad_norm": 39.04483413696289,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 4.5345,
+      "step": 49
+    },
+    {
+      "epoch": 0.04418668876001105,
+      "grad_norm": 36.16383743286133,
+      "learning_rate": 1e-05,
+      "loss": 4.9568,
+      "step": 50
+    },
+    {
+      "epoch": 0.04418668876001105,
+      "eval_loss": 0.2489974945783615,
+      "eval_runtime": 3.468,
+      "eval_samples_per_second": 14.418,
+      "eval_steps_per_second": 3.749,
+      "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": 1.483568811343872e+17,
+  "total_flos": 2.967137622687744e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null