Training in progress, step 330, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e47c5e37aeb9ba7c9d351cd6d3f2d34e7a16fbc5e8e214fa50df6016a912f81e
+oid sha256:4bd871ffaaf005b4ae82e3fe0574e188d290bd56611e88b2ee15dcc1170f10b7
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c8676f7ad327b1a667c04cbff92a64401964795cdbde06f9afb0439e5da7b66
+oid sha256:b3f145bed0430746d11b64162710df80efd4565776390d51f03bf26c95c602c2
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6d096910032d49eddb6029582f1caa936c833fef6de52cfa0342e08b8dcfcd2
+oid sha256:26b546f9e36af2b502a1f657b47e744aea84f04f078ad1d8590bd9010e8547d4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c4b5b0b5a3cd85dde69bc18b7d6ada534f4917a21cce1323408aed5ed9b4ef
+oid sha256:319ff6bc537233144a9a1321d603147241bbe6a5f63a69d9ed8b2711e764b26e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.018913269042969,
-  "best_model_checkpoint": "miner_id_24/checkpoint-320",
-  "epoch": 0.014462949989830737,
+  "best_metric": 11.018866539001465,
+  "best_model_checkpoint": "miner_id_24/checkpoint-330",
+  "epoch": 0.01491491717701295,
   "eval_steps": 5,
-  "global_step": 320,
+  "global_step": 330,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2767,6 +2767,92 @@
       "eval_samples_per_second": 52.829,
       "eval_steps_per_second": 26.417,
       "step": 320
+    },
+    {
+      "epoch": 0.014508146708548959,
+      "grad_norm": 0.47462332248687744,
+      "learning_rate": 5.893623390640621e-05,
+      "loss": 44.0712,
+      "step": 321
+    },
+    {
+      "epoch": 0.01455334342726718,
+      "grad_norm": 0.3999902307987213,
+      "learning_rate": 5.835249009564012e-05,
+      "loss": 44.0985,
+      "step": 322
+    },
+    {
+      "epoch": 0.014598540145985401,
+      "grad_norm": 0.5390244126319885,
+      "learning_rate": 5.777045825088404e-05,
+      "loss": 44.0947,
+      "step": 323
+    },
+    {
+      "epoch": 0.014643736864703622,
+      "grad_norm": 0.5316472053527832,
+      "learning_rate": 5.7190162297187475e-05,
+      "loss": 44.0887,
+      "step": 324
+    },
+    {
+      "epoch": 0.014688933583421843,
+      "grad_norm": 0.43537721037864685,
+      "learning_rate": 5.6611626088244194e-05,
+      "loss": 44.1142,
+      "step": 325
+    },
+    {
+      "epoch": 0.014688933583421843,
+      "eval_loss": 11.018884658813477,
+      "eval_runtime": 176.0785,
+      "eval_samples_per_second": 52.914,
+      "eval_steps_per_second": 26.46,
+      "step": 325
+    },
+    {
+      "epoch": 0.014734130302140065,
+      "grad_norm": 0.42780250310897827,
+      "learning_rate": 5.60348734054118e-05,
+      "loss": 44.0567,
+      "step": 326
+    },
+    {
+      "epoch": 0.014779327020858286,
+      "grad_norm": 0.418026864528656,
+      "learning_rate": 5.545992795673408e-05,
+      "loss": 44.0578,
+      "step": 327
+    },
+    {
+      "epoch": 0.014824523739576507,
+      "grad_norm": 0.507036030292511,
+      "learning_rate": 5.488681337596653e-05,
+      "loss": 44.0708,
+      "step": 328
+    },
+    {
+      "epoch": 0.014869720458294728,
+      "grad_norm": 0.4779205322265625,
+      "learning_rate": 5.431555322160483e-05,
+      "loss": 44.0879,
+      "step": 329
+    },
+    {
+      "epoch": 0.01491491717701295,
+      "grad_norm": 0.48253196477890015,
+      "learning_rate": 5.37461709759165e-05,
+      "loss": 44.005,
+      "step": 330
+    },
+    {
+      "epoch": 0.01491491717701295,
+      "eval_loss": 11.018866539001465,
+      "eval_runtime": 176.4141,
+      "eval_samples_per_second": 52.813,
+      "eval_steps_per_second": 26.409,
+      "step": 330
     }
   ],
   "logging_steps": 1,
@@ -2795,7 +2881,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3362154086400.0,
+  "total_flos": 3467221401600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null