Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52c8bbc42feb4563f312568413f6303ec690e185e2796fadf747c2e541268ac9
+oid sha256:54cba7d4dcf6f8a2d0a77dfa26886585ac6e1adcb74343c827ffcf5b0beb997a
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1b057d5f259f04ce97469bea831c47d83e7891a2190a53b8a22965a1ae5786d
+oid sha256:843bc4e3bf2c2f53382ab655c79062e25f936d8bdbe17845b4c87e30d1ced136
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac7e4378c49f67e2485a178fd5fa2846235b7e174b4f87a7ccc1257239a660de
+oid sha256:bd6981ac5fbd6e8a6689fc60b6b9306d4ef9d58cbe68dd437ee41e4684379316
 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": 1.4536380767822266,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.023323615160349854,
+  "best_metric": 1.4150354862213135,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.04664723032069971,
   "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": 4.923,
       "eval_steps_per_second": 2.475,
       "step": 10
+    },
+    {
+      "epoch": 0.02565597667638484,
+      "grad_norm": 0.7684414982795715,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.7667,
+      "step": 11
+    },
+    {
+      "epoch": 0.027988338192419825,
+      "grad_norm": 0.6388105154037476,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.0316,
+      "step": 12
+    },
+    {
+      "epoch": 0.030320699708454812,
+      "grad_norm": 0.6296985149383545,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.4975,
+      "step": 13
+    },
+    {
+      "epoch": 0.0326530612244898,
+      "grad_norm": 0.39826327562332153,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.9386,
+      "step": 14
+    },
+    {
+      "epoch": 0.03498542274052478,
+      "grad_norm": 0.5714980363845825,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.6855,
+      "step": 15
+    },
+    {
+      "epoch": 0.03498542274052478,
+      "eval_loss": 1.4195315837860107,
+      "eval_runtime": 36.5975,
+      "eval_samples_per_second": 4.946,
+      "eval_steps_per_second": 2.487,
+      "step": 15
+    },
+    {
+      "epoch": 0.037317784256559766,
+      "grad_norm": 0.6020028591156006,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.8779,
+      "step": 16
+    },
+    {
+      "epoch": 0.03965014577259475,
+      "grad_norm": 0.49338093400001526,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.465,
+      "step": 17
+    },
+    {
+      "epoch": 0.04198250728862974,
+      "grad_norm": 0.7286747694015503,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.2786,
+      "step": 18
+    },
+    {
+      "epoch": 0.044314868804664724,
+      "grad_norm": 0.5588726997375488,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.398,
+      "step": 19
+    },
+    {
+      "epoch": 0.04664723032069971,
+      "grad_norm": 0.5118404626846313,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.3029,
+      "step": 20
+    },
+    {
+      "epoch": 0.04664723032069971,
+      "eval_loss": 1.4150354862213135,
+      "eval_runtime": 36.6336,
+      "eval_samples_per_second": 4.941,
+      "eval_steps_per_second": 2.484,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 987692228149248.0,
+  "total_flos": 1987886889566208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null