Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86481326777d88b56e266110078b616898134239eaf3ad8c12dee3d93debee55
+oid sha256:ae5ed928a43303348bb3702371bc2941af1a00baf1bb1467a7e617aa3ce11193
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8175883dcc03839d3cb6e67e71dbd9ad28359818a1f4e95cceb5416f95cac14
+oid sha256:fe0050bf591756cc97a97f6209235a6c5f4b2718af63c4a914c86062c2ba4d32
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed24157843733a720e9b3d1b006fa11ac517dab21a9d332b9aa678dbbf520076
+oid sha256:53857b31065290226097899a29c43817f42b59cc1033072766ec46b6e8e362ce
 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": 1.2248835563659668,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.001884570082449941,
+  "best_metric": 1.0215682983398438,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.003769140164899882,
   "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": 7.359,
       "eval_steps_per_second": 3.681,
       "step": 10
+    },
+    {
+      "epoch": 0.0020730270906949354,
+      "grad_norm": 1.9571467638015747,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 5.2611,
+      "step": 11
+    },
+    {
+      "epoch": 0.0022614840989399294,
+      "grad_norm": 2.674177885055542,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 5.136,
+      "step": 12
+    },
+    {
+      "epoch": 0.0024499411071849234,
+      "grad_norm": 3.918393850326538,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 4.7382,
+      "step": 13
+    },
+    {
+      "epoch": 0.0026383981154299175,
+      "grad_norm": 3.2529351711273193,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 4.2274,
+      "step": 14
+    },
+    {
+      "epoch": 0.0028268551236749115,
+      "grad_norm": 3.0015501976013184,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 4.9855,
+      "step": 15
+    },
+    {
+      "epoch": 0.0028268551236749115,
+      "eval_loss": 1.0979372262954712,
+      "eval_runtime": 303.6779,
+      "eval_samples_per_second": 7.36,
+      "eval_steps_per_second": 3.682,
+      "step": 15
+    },
+    {
+      "epoch": 0.0030153121319199056,
+      "grad_norm": 2.5914523601531982,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.8228,
+      "step": 16
+    },
+    {
+      "epoch": 0.0032037691401649,
+      "grad_norm": 2.8210129737854004,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 4.5255,
+      "step": 17
+    },
+    {
+      "epoch": 0.003392226148409894,
+      "grad_norm": 2.186068534851074,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 4.4055,
+      "step": 18
+    },
+    {
+      "epoch": 0.003580683156654888,
+      "grad_norm": 2.8630177974700928,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 4.3739,
+      "step": 19
+    },
+    {
+      "epoch": 0.003769140164899882,
+      "grad_norm": 2.374098539352417,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 4.2284,
+      "step": 20
+    },
+    {
+      "epoch": 0.003769140164899882,
+      "eval_loss": 1.0215682983398438,
+      "eval_runtime": 304.7006,
+      "eval_samples_per_second": 7.335,
+      "eval_steps_per_second": 3.669,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2852805358387200.0,
+  "total_flos": 5705610716774400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null