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:bd800217f47882bd751eacc1c2945ab32574faa42e083e0f09b7bf6eacf9773f
+oid sha256:1424822c6a3cf27e781fc23cf797c5f3a1590531efe5a4f2e3dd2b9e0a31aace
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad421139af52064b8e8e2c01fe8c8f9caf847b1233775b7784a2a52629d0f737
+oid sha256:4cf45601d34e45896572d96cdac7a13e7b556825a1f109d7988e5ed6e025ae2b
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29bef9384302b07ef3b332447b3643199b5ede04045a3e6ea01bd4383e87f16a
+oid sha256:641e390aa9ef445d90db715615723d840a0951486f59416c06eb80eadfe26db8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:237d04a13e8c5037ff1c5810840ce870adb36143ac9825927be34e91029b7df0
+oid sha256:e01d609443d425319bfb19018796bf49b3a8a154f472b8dedcf5524c82559c66
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5293544f9f9b9d504a18a4bb27a06ee9166254203add7b0f1b5ac66709845e96
+oid sha256:c0a45ae2c71a8d5fdd725252c6bd48165c0dea3d35c8589e8df3f6c9e01bfe17
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1687cfb0fc1a634c48a0fcdfe304bbff5fea1599c527d2082d975e83fb3817c
+oid sha256:69047b278143c16989c6cb9026b74c8df76a72b422701ffb8316eeecc1fc11f3
 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": 2.924403190612793,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5215123859191656,
+  "best_metric": 2.4227938652038574,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.0534550195567145,
   "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": 24.248,
       "eval_steps_per_second": 6.304,
       "step": 25
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "grad_norm": 4.208644866943359,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.495,
+      "step": 26
+    },
+    {
+      "epoch": 0.5632333767926988,
+      "grad_norm": 3.7513959407806396,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 3.5881,
+      "step": 27
+    },
+    {
+      "epoch": 0.5840938722294654,
+      "grad_norm": 3.0269153118133545,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.5614,
+      "step": 28
+    },
+    {
+      "epoch": 0.6049543676662321,
+      "grad_norm": 3.4557063579559326,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.5098,
+      "step": 29
+    },
+    {
+      "epoch": 0.6258148631029987,
+      "grad_norm": 3.736849308013916,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.4906,
+      "step": 30
+    },
+    {
+      "epoch": 0.6466753585397653,
+      "grad_norm": 4.803586006164551,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.6127,
+      "step": 31
+    },
+    {
+      "epoch": 0.6675358539765319,
+      "grad_norm": 6.40614652633667,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.7518,
+      "step": 32
+    },
+    {
+      "epoch": 0.6883963494132985,
+      "grad_norm": 4.483238220214844,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.7023,
+      "step": 33
+    },
+    {
+      "epoch": 0.7092568448500652,
+      "grad_norm": 1.4310004711151123,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.2358,
+      "step": 34
+    },
+    {
+      "epoch": 0.7301173402868318,
+      "grad_norm": 2.1178836822509766,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.07,
+      "step": 35
+    },
+    {
+      "epoch": 0.7509778357235984,
+      "grad_norm": 3.472343683242798,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.0525,
+      "step": 36
+    },
+    {
+      "epoch": 0.771838331160365,
+      "grad_norm": 3.5565571784973145,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.2537,
+      "step": 37
+    },
+    {
+      "epoch": 0.7926988265971316,
+      "grad_norm": 3.446967601776123,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.1724,
+      "step": 38
+    },
+    {
+      "epoch": 0.8135593220338984,
+      "grad_norm": 3.225677490234375,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.2635,
+      "step": 39
+    },
+    {
+      "epoch": 0.834419817470665,
+      "grad_norm": 3.0172581672668457,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.2634,
+      "step": 40
+    },
+    {
+      "epoch": 0.8552803129074316,
+      "grad_norm": 3.3737077713012695,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.4262,
+      "step": 41
+    },
+    {
+      "epoch": 0.8761408083441982,
+      "grad_norm": 3.4301564693450928,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.4815,
+      "step": 42
+    },
+    {
+      "epoch": 0.8970013037809648,
+      "grad_norm": 3.4359047412872314,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.4434,
+      "step": 43
+    },
+    {
+      "epoch": 0.9178617992177314,
+      "grad_norm": 3.938171148300171,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.3815,
+      "step": 44
+    },
+    {
+      "epoch": 0.9387222946544981,
+      "grad_norm": 1.9196503162384033,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.7353,
+      "step": 45
+    },
+    {
+      "epoch": 0.9595827900912647,
+      "grad_norm": 1.731357455253601,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.3883,
+      "step": 46
+    },
+    {
+      "epoch": 0.9804432855280313,
+      "grad_norm": 1.4864057302474976,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0512,
+      "step": 47
+    },
+    {
+      "epoch": 1.0117340286831813,
+      "grad_norm": 4.474582195281982,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 5.1054,
+      "step": 48
+    },
+    {
+      "epoch": 1.032594524119948,
+      "grad_norm": 2.65756893157959,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.9023,
+      "step": 49
+    },
+    {
+      "epoch": 1.0534550195567145,
+      "grad_norm": 2.487783432006836,
+      "learning_rate": 1e-05,
+      "loss": 2.6625,
+      "step": 50
+    },
+    {
+      "epoch": 1.0534550195567145,
+      "eval_loss": 2.4227938652038574,
+      "eval_runtime": 2.066,
+      "eval_samples_per_second": 24.201,
+      "eval_steps_per_second": 6.292,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null