Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30833580ffca2948fd5625a1038d5f6a04273da8ff0c4b4d329caff7447a4f52
+oid sha256:dea312c683c66be75416de58d1702bcaee368716233a88b4b1ae682ce0fa2f38
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a09b937eb1ecd0fac4870542b9dfe8ccfe3e712557869be65f11e9df397d79a
+oid sha256:51124d0fdb3009fe2f8ac57c9e0159aefdb7b8d2fe75e57acc767200bdaa56f6
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6442aa28f7a8b4f52877687ecef65055148d8e2fe25535f8866b93b5414671c6
+oid sha256:ff21e0751b3a5cea005fdd4e373110f88946aad70f157d90ebe5ea2842c00ef6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5034407377243042,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.04678362573099415,
+  "best_metric": 1.019839882850647,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0935672514619883,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 4.094,
       "eval_steps_per_second": 2.047,
       "step": 10
+    },
+    {
+      "epoch": 0.05146198830409357,
+      "grad_norm": 0.668283998966217,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.5648,
+      "step": 11
+    },
+    {
+      "epoch": 0.056140350877192984,
+      "grad_norm": 0.5301951169967651,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.6077,
+      "step": 12
+    },
+    {
+      "epoch": 0.0608187134502924,
+      "grad_norm": 0.44159942865371704,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.3352,
+      "step": 13
+    },
+    {
+      "epoch": 0.06549707602339182,
+      "grad_norm": 0.4739885628223419,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.3697,
+      "step": 14
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 0.8631594181060791,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.2833,
+      "step": 15
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "eval_loss": 1.2018710374832153,
+      "eval_runtime": 21.9973,
+      "eval_samples_per_second": 4.091,
+      "eval_steps_per_second": 2.046,
+      "step": 15
+    },
+    {
+      "epoch": 0.07485380116959064,
+      "grad_norm": 0.7966984510421753,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.4431,
+      "step": 16
+    },
+    {
+      "epoch": 0.07953216374269007,
+      "grad_norm": 0.5668115019798279,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.1548,
+      "step": 17
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 0.5761730670928955,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.1111,
+      "step": 18
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.5519751906394958,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.063,
+      "step": 19
+    },
+    {
+      "epoch": 0.0935672514619883,
+      "grad_norm": 0.5273241400718689,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.903,
+      "step": 20
+    },
+    {
+      "epoch": 0.0935672514619883,
+      "eval_loss": 1.019839882850647,
+      "eval_runtime": 22.0266,
+      "eval_samples_per_second": 4.086,
+      "eval_steps_per_second": 2.043,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5303394096906240.0,
+  "total_flos": 1.060678819381248e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null