Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ed9554c2937f51a4b5d0b83c40d075655345afe20ad24bd196c0d354b7ee6d1
+oid sha256:121dc6327b5af86a847f01632d0e06385eb711c31e565456f5c6062f0cb1879f
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1365dae1b689bb4e2634db551077043caf2ad8fe42eccd1cf8743986544e61de
+oid sha256:e512cc25240e50625a18a266122f40a09cb785b35b3c6f0fb2afd353cf2d837b
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc1ac17452726e5cedfbf9cc2e40377e5a6129f49113fea151b529c4b6d68216
+oid sha256:3ec7fddaa93b8a5104562fd596c16565abf5deb95425dbc4839aa86c8fa34863
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:321b462a2538632d6d720f0cf198c8f471dee11f51db9b50cc50d1fa7f132bbe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.38599851727485657,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.018484288354898338,
+  "best_metric": 0.3295012414455414,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.036968576709796676,
   "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": 1.31,
       "eval_steps_per_second": 0.655,
       "step": 10
+    },
+    {
+      "epoch": 0.02033271719038817,
+      "grad_norm": 3.8678717613220215,
+      "learning_rate": 0.0001999979446958366,
+      "loss": 1.6367,
+      "step": 11
+    },
+    {
+      "epoch": 0.022181146025878003,
+      "grad_norm": 3.9537124633789062,
+      "learning_rate": 0.00019999177886783194,
+      "loss": 1.5529,
+      "step": 12
+    },
+    {
+      "epoch": 0.024029574861367836,
+      "grad_norm": 5.052474498748779,
+      "learning_rate": 0.00019998150276943902,
+      "loss": 2.002,
+      "step": 13
+    },
+    {
+      "epoch": 0.025878003696857672,
+      "grad_norm": 3.856994152069092,
+      "learning_rate": 0.000199967116823068,
+      "loss": 1.3814,
+      "step": 14
+    },
+    {
+      "epoch": 0.027726432532347505,
+      "grad_norm": 4.525390625,
+      "learning_rate": 0.0001999486216200688,
+      "loss": 2.113,
+      "step": 15
+    },
+    {
+      "epoch": 0.027726432532347505,
+      "eval_loss": 0.34281158447265625,
+      "eval_runtime": 172.8847,
+      "eval_samples_per_second": 1.319,
+      "eval_steps_per_second": 0.659,
+      "step": 15
+    },
+    {
+      "epoch": 0.029574861367837338,
+      "grad_norm": 2.5049190521240234,
+      "learning_rate": 0.00019992601792070679,
+      "loss": 1.1666,
+      "step": 16
+    },
+    {
+      "epoch": 0.031423290203327174,
+      "grad_norm": 5.2193169593811035,
+      "learning_rate": 0.00019989930665413147,
+      "loss": 1.5721,
+      "step": 17
+    },
+    {
+      "epoch": 0.033271719038817,
+      "grad_norm": 3.3948168754577637,
+      "learning_rate": 0.00019986848891833845,
+      "loss": 0.8586,
+      "step": 18
+    },
+    {
+      "epoch": 0.03512014787430684,
+      "grad_norm": 3.3094377517700195,
+      "learning_rate": 0.0001998335659801241,
+      "loss": 0.989,
+      "step": 19
+    },
+    {
+      "epoch": 0.036968576709796676,
+      "grad_norm": 3.9788992404937744,
+      "learning_rate": 0.00019979453927503364,
+      "loss": 1.4677,
+      "step": 20
+    },
+    {
+      "epoch": 0.036968576709796676,
+      "eval_loss": 0.3295012414455414,
+      "eval_runtime": 174.1601,
+      "eval_samples_per_second": 1.309,
+      "eval_steps_per_second": 0.655,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.414506945183744e+16,
+  "total_flos": 2.829013890367488e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null