Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79687727f210f8a610d67ee9a33f406313cdf02a95bbcef9f87602ec2252f6b7
+oid sha256:7c525aad721c1eccec80c853c3681677329cad10a47fe0fab0ef42a0bab2f124
 size 1204200

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:987dc0a0adb8583304fabdeba7760a979cc2c44a2504c5424df910f1a54254d3
+oid sha256:e5edbfe1da101b507d7e994cc0fc0462341bf5c92ed2174f558b3568e71726c1
 size 2558458

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dac12d3953c9305d9613aa4182fe0929d74506f733c14700a52e8a88393d578
+oid sha256:de9dc9116c606849b7fd0d22e854f5a1248f4b5f811b12d6f1fc242fff615e64
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c86b50a93038a3fd9f4f8deb0defa5740de1dcdc8af97caac8bde1e1ee51132
+oid sha256:d0a368612a1440ca043022efab7e0a0aa575b55ca579d92c46b392aa00fe44a0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fc1e1f8e4c66d4f778237ed221c2d1469351e605ccbfc5786ba088cba3edea8
+oid sha256:6e787f6b6f9652b2d9b2349d400254f0ba8d2a6d9b88070db04e76e8898b3fd0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42bd2de3e5aafa298b09bd18bd9c5a2b03336628f2eed7570b1542d2063402b6
+oid sha256:c67c0add6670aabf3afdf01e63e1dea50730aa0f8441af1d1b0a35164c3aaeee
 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": 11.922410011291504,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.030804774740084712,
+  "best_metric": 11.915068626403809,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.061609549480169425,
   "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": 111.969,
       "eval_steps_per_second": 29.112,
       "step": 25
+    },
+    {
+      "epoch": 0.0320369657296881,
+      "grad_norm": 0.14079074561595917,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9271,
+      "step": 26
+    },
+    {
+      "epoch": 0.03326915671929149,
+      "grad_norm": 0.1567951738834381,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.9258,
+      "step": 27
+    },
+    {
+      "epoch": 0.03450134770889488,
+      "grad_norm": 0.16366036236286163,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9249,
+      "step": 28
+    },
+    {
+      "epoch": 0.03573353869849827,
+      "grad_norm": 0.1638365387916565,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.926,
+      "step": 29
+    },
+    {
+      "epoch": 0.036965729688101655,
+      "grad_norm": 0.17652325332164764,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.9231,
+      "step": 30
+    },
+    {
+      "epoch": 0.03819792067770504,
+      "grad_norm": 0.15289749205112457,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.9256,
+      "step": 31
+    },
+    {
+      "epoch": 0.039430111667308435,
+      "grad_norm": 0.21502667665481567,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.918,
+      "step": 32
+    },
+    {
+      "epoch": 0.04066230265691182,
+      "grad_norm": 0.16959460079669952,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.9229,
+      "step": 33
+    },
+    {
+      "epoch": 0.04189449364651521,
+      "grad_norm": 0.18960808217525482,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.921,
+      "step": 34
+    },
+    {
+      "epoch": 0.0431266846361186,
+      "grad_norm": 0.20932435989379883,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.9176,
+      "step": 35
+    },
+    {
+      "epoch": 0.04435887562572199,
+      "grad_norm": 0.2247883677482605,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.9166,
+      "step": 36
+    },
+    {
+      "epoch": 0.045591066615325374,
+      "grad_norm": 0.2090682089328766,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.9216,
+      "step": 37
+    },
+    {
+      "epoch": 0.04682325760492877,
+      "grad_norm": 0.19237466156482697,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.9209,
+      "step": 38
+    },
+    {
+      "epoch": 0.04805544859453215,
+      "grad_norm": 0.15888743102550507,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.9218,
+      "step": 39
+    },
+    {
+      "epoch": 0.04928763958413554,
+      "grad_norm": 0.1693039834499359,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.9215,
+      "step": 40
+    },
+    {
+      "epoch": 0.050519830573738926,
+      "grad_norm": 0.18711499869823456,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.9198,
+      "step": 41
+    },
+    {
+      "epoch": 0.05175202156334232,
+      "grad_norm": 0.1777219921350479,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.9196,
+      "step": 42
+    },
+    {
+      "epoch": 0.052984212552945706,
+      "grad_norm": 0.17029505968093872,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.9212,
+      "step": 43
+    },
+    {
+      "epoch": 0.05421640354254909,
+      "grad_norm": 0.1959444284439087,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.92,
+      "step": 44
+    },
+    {
+      "epoch": 0.055448594532152486,
+      "grad_norm": 0.19401198625564575,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.9157,
+      "step": 45
+    },
+    {
+      "epoch": 0.05668078552175587,
+      "grad_norm": 0.18555186688899994,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.9181,
+      "step": 46
+    },
+    {
+      "epoch": 0.05791297651135926,
+      "grad_norm": 0.207061767578125,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.9177,
+      "step": 47
+    },
+    {
+      "epoch": 0.05914516750096265,
+      "grad_norm": 0.19741538166999817,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9168,
+      "step": 48
+    },
+    {
+      "epoch": 0.06037735849056604,
+      "grad_norm": 0.2410183548927307,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.9102,
+      "step": 49
+    },
+    {
+      "epoch": 0.061609549480169425,
+      "grad_norm": 0.27445363998413086,
+      "learning_rate": 1e-05,
+      "loss": 11.9102,
+      "step": 50
+    },
+    {
+      "epoch": 0.061609549480169425,
+      "eval_loss": 11.915068626403809,
+      "eval_runtime": 0.4086,
+      "eval_samples_per_second": 122.365,
+      "eval_steps_per_second": 31.815,
+      "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": 208867531161600.0,
+  "total_flos": 417735062323200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null