Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d919b19c734ab4a0f9f658575a298873d0900894f13a959e6f6d272e1e7b2839
+oid sha256:9adec3c4d4ce7c1a955666abbde366adcc406302669a947745d14914760d8325
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f64eaea8b54e013178061440067044e05a02048220ee2ba751fd6b1a63dc57
+oid sha256:2a4abfc37dfb521100817cffdd7d23ed37eadaaea8e94bafc799d8d68a769f6f
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b45687303c00b13d8e9b52de95720e0ed5dc926fbf68377a741058997b79541f
+oid sha256:d9dece06a2a475795a147ee35c2a3453b2663869fb01988081543a009bb20250
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:690fb5c3b77136eb9ac64ab5fc11d4dbbb9d207d93dada0789c563a004b5c21a
+oid sha256:d3d45c96467833182ded638377a74d35c27bfc6d409c3a75a7ed9d96313f2209
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.364795446395874,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.4132231404958678,
+  "best_metric": 2.21439266204834,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.8264462809917356,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 5.802,
       "eval_steps_per_second": 2.901,
       "step": 25
+    },
+    {
+      "epoch": 0.4297520661157025,
+      "grad_norm": 10.043116569519043,
+      "learning_rate": 6.5965076506799e-05,
+      "loss": 2.9622,
+      "step": 26
+    },
+    {
+      "epoch": 0.4462809917355372,
+      "grad_norm": 16.373950958251953,
+      "learning_rate": 6.337641692646106e-05,
+      "loss": 2.9865,
+      "step": 27
+    },
+    {
+      "epoch": 0.4628099173553719,
+      "grad_norm": 7.408267498016357,
+      "learning_rate": 6.0748522010551215e-05,
+      "loss": 2.1804,
+      "step": 28
+    },
+    {
+      "epoch": 0.4793388429752066,
+      "grad_norm": 9.184383392333984,
+      "learning_rate": 5.808909982763825e-05,
+      "loss": 2.4657,
+      "step": 29
+    },
+    {
+      "epoch": 0.49586776859504134,
+      "grad_norm": 9.664917945861816,
+      "learning_rate": 5.540595092119709e-05,
+      "loss": 2.2407,
+      "step": 30
+    },
+    {
+      "epoch": 0.512396694214876,
+      "grad_norm": 11.779993057250977,
+      "learning_rate": 5.270694542927088e-05,
+      "loss": 3.5904,
+      "step": 31
+    },
+    {
+      "epoch": 0.5289256198347108,
+      "grad_norm": 6.609020233154297,
+      "learning_rate": 5e-05,
+      "loss": 2.1943,
+      "step": 32
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 7.8492889404296875,
+      "learning_rate": 4.729305457072913e-05,
+      "loss": 2.1845,
+      "step": 33
+    },
+    {
+      "epoch": 0.5619834710743802,
+      "grad_norm": 8.724394798278809,
+      "learning_rate": 4.4594049078802925e-05,
+      "loss": 2.3286,
+      "step": 34
+    },
+    {
+      "epoch": 0.5785123966942148,
+      "grad_norm": 9.296069145202637,
+      "learning_rate": 4.1910900172361764e-05,
+      "loss": 2.3771,
+      "step": 35
+    },
+    {
+      "epoch": 0.5950413223140496,
+      "grad_norm": 8.15500259399414,
+      "learning_rate": 3.92514779894488e-05,
+      "loss": 2.4083,
+      "step": 36
+    },
+    {
+      "epoch": 0.6115702479338843,
+      "grad_norm": 9.642007827758789,
+      "learning_rate": 3.6623583073538966e-05,
+      "loss": 2.2474,
+      "step": 37
+    },
+    {
+      "epoch": 0.628099173553719,
+      "grad_norm": 6.308684825897217,
+      "learning_rate": 3.403492349320101e-05,
+      "loss": 2.4492,
+      "step": 38
+    },
+    {
+      "epoch": 0.6446280991735537,
+      "grad_norm": 6.576019763946533,
+      "learning_rate": 3.149309223300428e-05,
+      "loss": 2.3185,
+      "step": 39
+    },
+    {
+      "epoch": 0.6611570247933884,
+      "grad_norm": 9.71943187713623,
+      "learning_rate": 2.900554492198677e-05,
+      "loss": 2.6858,
+      "step": 40
+    },
+    {
+      "epoch": 0.6776859504132231,
+      "grad_norm": 11.457530975341797,
+      "learning_rate": 2.65795779650105e-05,
+      "loss": 3.1241,
+      "step": 41
+    },
+    {
+      "epoch": 0.6942148760330579,
+      "grad_norm": 9.567526817321777,
+      "learning_rate": 2.422230714114891e-05,
+      "loss": 2.3865,
+      "step": 42
+    },
+    {
+      "epoch": 0.7107438016528925,
+      "grad_norm": 6.879986763000488,
+      "learning_rate": 2.194064673188089e-05,
+      "loss": 2.2602,
+      "step": 43
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 7.776947498321533,
+      "learning_rate": 1.9741289240311755e-05,
+      "loss": 2.0642,
+      "step": 44
+    },
+    {
+      "epoch": 0.743801652892562,
+      "grad_norm": 7.914689540863037,
+      "learning_rate": 1.7630685760908622e-05,
+      "loss": 2.3686,
+      "step": 45
+    },
+    {
+      "epoch": 0.7603305785123967,
+      "grad_norm": 8.547547340393066,
+      "learning_rate": 1.561502705732883e-05,
+      "loss": 2.9245,
+      "step": 46
+    },
+    {
+      "epoch": 0.7768595041322314,
+      "grad_norm": 7.577058792114258,
+      "learning_rate": 1.3700225403843469e-05,
+      "loss": 2.2968,
+      "step": 47
+    },
+    {
+      "epoch": 0.7933884297520661,
+      "grad_norm": 7.617032527923584,
+      "learning_rate": 1.1891897243618182e-05,
+      "loss": 2.1618,
+      "step": 48
+    },
+    {
+      "epoch": 0.8099173553719008,
+      "grad_norm": 6.652332782745361,
+      "learning_rate": 1.0195346714717813e-05,
+      "loss": 1.725,
+      "step": 49
+    },
+    {
+      "epoch": 0.8264462809917356,
+      "grad_norm": 7.552050590515137,
+      "learning_rate": 8.615550092155478e-06,
+      "loss": 2.0762,
+      "step": 50
+    },
+    {
+      "epoch": 0.8264462809917356,
+      "eval_loss": 2.21439266204834,
+      "eval_runtime": 4.4905,
+      "eval_samples_per_second": 5.79,
+      "eval_steps_per_second": 2.895,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.91723590385664e+16,
+  "total_flos": 3.83447180771328e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null