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:b873acfd92a3fef25680c8ede20170f83823d033143e0de5d36af28a50d70370
+oid sha256:811fdb1de4cfd2ece9587443a7c26978289e481c061c3c234c81b257c4cf0b10
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f257641cef92f104a3e2a41c2301a3947c764c2a5b206e8e2444f7577896e88d
+oid sha256:167b236b8db10a3bf7a3fcde2b541a6a43e2cdb3d1b6f22c33a66eec3c2a8caf
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3475773cf4d30f125e4160547f4d708deb3df6ade1f517cc08677c6d0b448fd8
+oid sha256:1b29fbc834ecaaec50b32fe597457ad1808ff99ce77d5cbb4a0487c15843b733
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fca47bef9198f409ae8d1e3a1616a83cf767278655070510a5750417d6b7f20a
+oid sha256:ab25b6f4b9e4b762da699e838105b33a4da45ed401a5c31e2e05d72a4e88b330
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4322a6d2ed13a9eac8a490e4cbf506dfbe1a34619b4f9e4fa8f51148a50a705
+oid sha256:09d2af3ef4241c66e5c20a68ae47dfff8b0281ca01b5ae193c5bdb8f40ba7672
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db02f7ca0a45eddca4c80ba26c66527a87464cadf7a5308db4771287ac1533ab
+oid sha256:095d23084f0a1b3820cb1b998d49e8fb9e9c269c227bf49bcdb0c0ac94dfee90
 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": 1.805835247039795,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.025839793281653745,
+  "best_metric": 1.739266037940979,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05167958656330749,
   "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": 64.225,
       "eval_steps_per_second": 16.698,
       "step": 25
+    },
+    {
+      "epoch": 0.026873385012919897,
+      "grad_norm": 0.563585102558136,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.602,
+      "step": 26
+    },
+    {
+      "epoch": 0.027906976744186046,
+      "grad_norm": 0.5569491386413574,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.4559,
+      "step": 27
+    },
+    {
+      "epoch": 0.028940568475452195,
+      "grad_norm": 0.5632328391075134,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.5699,
+      "step": 28
+    },
+    {
+      "epoch": 0.029974160206718347,
+      "grad_norm": 0.5582482218742371,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.5948,
+      "step": 29
+    },
+    {
+      "epoch": 0.031007751937984496,
+      "grad_norm": 0.5458480715751648,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.5245,
+      "step": 30
+    },
+    {
+      "epoch": 0.03204134366925065,
+      "grad_norm": 0.5486528277397156,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.6522,
+      "step": 31
+    },
+    {
+      "epoch": 0.03307493540051679,
+      "grad_norm": 0.4946439862251282,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.677,
+      "step": 32
+    },
+    {
+      "epoch": 0.034108527131782945,
+      "grad_norm": 0.5885268449783325,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.6474,
+      "step": 33
+    },
+    {
+      "epoch": 0.0351421188630491,
+      "grad_norm": 0.5598137378692627,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.6737,
+      "step": 34
+    },
+    {
+      "epoch": 0.03617571059431524,
+      "grad_norm": 0.5388458967208862,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.6732,
+      "step": 35
+    },
+    {
+      "epoch": 0.037209302325581395,
+      "grad_norm": 0.6448724269866943,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.7968,
+      "step": 36
+    },
+    {
+      "epoch": 0.03824289405684755,
+      "grad_norm": 1.0652443170547485,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.8869,
+      "step": 37
+    },
+    {
+      "epoch": 0.03927648578811369,
+      "grad_norm": 0.5180839896202087,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.5899,
+      "step": 38
+    },
+    {
+      "epoch": 0.040310077519379844,
+      "grad_norm": 0.4015357494354248,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.4246,
+      "step": 39
+    },
+    {
+      "epoch": 0.041343669250646,
+      "grad_norm": 0.36983615159988403,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.4877,
+      "step": 40
+    },
+    {
+      "epoch": 0.04237726098191214,
+      "grad_norm": 0.3772043287754059,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.489,
+      "step": 41
+    },
+    {
+      "epoch": 0.043410852713178294,
+      "grad_norm": 0.3773873448371887,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.48,
+      "step": 42
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 0.35318583250045776,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.5648,
+      "step": 43
+    },
+    {
+      "epoch": 0.04547803617571059,
+      "grad_norm": 0.38485991954803467,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.5377,
+      "step": 44
+    },
+    {
+      "epoch": 0.046511627906976744,
+      "grad_norm": 0.3673318326473236,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.6161,
+      "step": 45
+    },
+    {
+      "epoch": 0.047545219638242896,
+      "grad_norm": 0.3764628469944,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.6054,
+      "step": 46
+    },
+    {
+      "epoch": 0.04857881136950904,
+      "grad_norm": 0.5201135873794556,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.7079,
+      "step": 47
+    },
+    {
+      "epoch": 0.04961240310077519,
+      "grad_norm": 0.5968867540359497,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.7181,
+      "step": 48
+    },
+    {
+      "epoch": 0.050645994832041345,
+      "grad_norm": 0.8235591650009155,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.7999,
+      "step": 49
+    },
+    {
+      "epoch": 0.05167958656330749,
+      "grad_norm": 1.5277827978134155,
+      "learning_rate": 1e-05,
+      "loss": 1.89,
+      "step": 50
+    },
+    {
+      "epoch": 0.05167958656330749,
+      "eval_loss": 1.739266037940979,
+      "eval_runtime": 0.7761,
+      "eval_samples_per_second": 64.421,
+      "eval_steps_per_second": 16.749,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null