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:b6f39cd59350d7a9a86b1f1588dfe579fe887f22e1da368714d0844270247d1c
+oid sha256:e813b0e6f9e944c29938a9fdba0117850c22d0e8485453022f07ac64b3a1174c
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae54f5254b9b72a049bbbfe644e688bfd7e196079d0263c65b874a3bce38bc10
+oid sha256:7354029c94df401b91ff7b030f2034027ad4c604823b10b47a02edc50596aefb
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a304605d52e214834dfb2c6de8fc86f9ae7fd552f5bf86dd1b50d10b7d4cef7b
+oid sha256:ec39d47edf3e95d505c11a6fb56cf7358f261c33d316c25b718f0b51e89f0a5c
 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": 3.0578625202178955,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.000207671380807011,
+  "best_metric": 2.9130699634552,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.000415342761614022,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 7.155,
       "eval_steps_per_second": 3.578,
       "step": 10
+    },
+    {
+      "epoch": 0.00024920565696841317,
+      "grad_norm": 1.4713549613952637,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 3.5078,
+      "step": 12
+    },
+    {
+      "epoch": 0.00031150707121051647,
+      "grad_norm": 2.724468231201172,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.0636,
+      "step": 15
+    },
+    {
+      "epoch": 0.00031150707121051647,
+      "eval_loss": 2.953822612762451,
+      "eval_runtime": 411.4626,
+      "eval_samples_per_second": 12.319,
+      "eval_steps_per_second": 6.161,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003738084854526198,
+      "grad_norm": 2.139493703842163,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 3.1654,
+      "step": 18
+    },
+    {
+      "epoch": 0.000415342761614022,
+      "eval_loss": 2.9130699634552,
+      "eval_runtime": 411.5201,
+      "eval_samples_per_second": 12.318,
+      "eval_steps_per_second": 6.16,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 41713510907904.0,
+  "total_flos": 83427021815808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null