Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff21da8b71bcc544044dfeb58bc1a2db0b902c4525be7778603504fc7e60e7af
+oid sha256:525eea3f2c93217aef6f42d2b143a65e63d7ab0ec67ae2667a54acc1c89b2a45
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46139fa872045ec625780a9afcfc568fc5271e916530520a6889d480ee052eae
+oid sha256:a119d6761d4a53c7777ebe6af48109b36c740bc207a47858a068048ae26b4643
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a244050d59b77afc534052cb310c398c2fc1c91e22095bd7d72556c0374e0a54
+oid sha256:34f8c1634877b7d4e3c74a0e50d2917fe957a0d933a5540aa6509d62f047bd85
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9567f2f3182e832808fd621212e0dd5e8f1a88bd24ddda3ea0d289496073738c
+oid sha256:67bdc1680e75e7cf9661cc84482edc217f841c56aca5f9a3979c1c72a436f392
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.4786899089813232,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0007193131997568721,
+  "best_metric": 3.277400493621826,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.0010789697996353082,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 2.892,
       "eval_steps_per_second": 1.446,
       "step": 50
+    },
+    {
+      "epoch": 0.0007336994637520095,
+      "grad_norm": 8.999927520751953,
+      "learning_rate": 0.00010495837546732224,
+      "loss": 2.9427,
+      "step": 51
+    },
+    {
+      "epoch": 0.000748085727747147,
+      "grad_norm": 12.779885292053223,
+      "learning_rate": 0.00010165339447663587,
+      "loss": 3.1953,
+      "step": 52
+    },
+    {
+      "epoch": 0.0007624719917422845,
+      "grad_norm": 7.076213836669922,
+      "learning_rate": 9.834660552336415e-05,
+      "loss": 3.3286,
+      "step": 53
+    },
+    {
+      "epoch": 0.0007768582557374219,
+      "grad_norm": 8.078849792480469,
+      "learning_rate": 9.504162453267777e-05,
+      "loss": 3.7154,
+      "step": 54
+    },
+    {
+      "epoch": 0.0007912445197325594,
+      "grad_norm": 12.962296485900879,
+      "learning_rate": 9.174206545276677e-05,
+      "loss": 3.3829,
+      "step": 55
+    },
+    {
+      "epoch": 0.0008056307837276968,
+      "grad_norm": 6.32912015914917,
+      "learning_rate": 8.845153630304139e-05,
+      "loss": 2.8261,
+      "step": 56
+    },
+    {
+      "epoch": 0.0008200170477228343,
+      "grad_norm": 6.619338035583496,
+      "learning_rate": 8.517363522881579e-05,
+      "loss": 3.0182,
+      "step": 57
+    },
+    {
+      "epoch": 0.0008344033117179717,
+      "grad_norm": 6.766091346740723,
+      "learning_rate": 8.191194656678904e-05,
+      "loss": 3.5953,
+      "step": 58
+    },
+    {
+      "epoch": 0.0008487895757131091,
+      "grad_norm": 5.642858505249023,
+      "learning_rate": 7.867003692562534e-05,
+      "loss": 2.6085,
+      "step": 59
+    },
+    {
+      "epoch": 0.0008631758397082466,
+      "grad_norm": 5.088937759399414,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 3.0031,
+      "step": 60
+    },
+    {
+      "epoch": 0.000877562103703384,
+      "grad_norm": 6.179854869842529,
+      "learning_rate": 7.225970912381556e-05,
+      "loss": 3.0115,
+      "step": 61
+    },
+    {
+      "epoch": 0.0008919483676985214,
+      "grad_norm": 6.379157543182373,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.9728,
+      "step": 62
+    },
+    {
+      "epoch": 0.0009063346316936589,
+      "grad_norm": 6.963946342468262,
+      "learning_rate": 6.59706825558357e-05,
+      "loss": 3.1727,
+      "step": 63
+    },
+    {
+      "epoch": 0.0009207208956887963,
+      "grad_norm": 5.228279113769531,
+      "learning_rate": 6.28802751081779e-05,
+      "loss": 3.2701,
+      "step": 64
+    },
+    {
+      "epoch": 0.0009351071596839337,
+      "grad_norm": 6.0718488693237305,
+      "learning_rate": 5.983045753470308e-05,
+      "loss": 3.1534,
+      "step": 65
+    },
+    {
+      "epoch": 0.0009494934236790712,
+      "grad_norm": 5.688898086547852,
+      "learning_rate": 5.6824564766150726e-05,
+      "loss": 3.2423,
+      "step": 66
+    },
+    {
+      "epoch": 0.0009638796876742087,
+      "grad_norm": 6.626285076141357,
+      "learning_rate": 5.386588370213124e-05,
+      "loss": 2.8435,
+      "step": 67
+    },
+    {
+      "epoch": 0.000978265951669346,
+      "grad_norm": 5.733967304229736,
+      "learning_rate": 5.095764961694922e-05,
+      "loss": 3.2189,
+      "step": 68
+    },
+    {
+      "epoch": 0.0009926522156644836,
+      "grad_norm": 8.272422790527344,
+      "learning_rate": 4.810304262187852e-05,
+      "loss": 4.0563,
+      "step": 69
+    },
+    {
+      "epoch": 0.001007038479659621,
+      "grad_norm": 5.926618576049805,
+      "learning_rate": 4.530518418775733e-05,
+      "loss": 3.0186,
+      "step": 70
+    },
+    {
+      "epoch": 0.0010214247436547584,
+      "grad_norm": 5.379611015319824,
+      "learning_rate": 4.256713373170564e-05,
+      "loss": 3.0911,
+      "step": 71
+    },
+    {
+      "epoch": 0.0010358110076498959,
+      "grad_norm": 6.168915748596191,
+      "learning_rate": 3.9891885271697496e-05,
+      "loss": 2.9903,
+      "step": 72
+    },
+    {
+      "epoch": 0.0010501972716450334,
+      "grad_norm": 8.017834663391113,
+      "learning_rate": 3.7282364152646297e-05,
+      "loss": 3.4968,
+      "step": 73
+    },
+    {
+      "epoch": 0.0010645835356401707,
+      "grad_norm": 6.804283142089844,
+      "learning_rate": 3.4741423847583134e-05,
+      "loss": 3.0869,
+      "step": 74
+    },
+    {
+      "epoch": 0.0010789697996353082,
+      "grad_norm": 5.8104658126831055,
+      "learning_rate": 3.227184283742591e-05,
+      "loss": 3.1871,
+      "step": 75
+    },
+    {
+      "epoch": 0.0010789697996353082,
+      "eval_loss": 3.277400493621826,
+      "eval_runtime": 10118.7756,
+      "eval_samples_per_second": 2.892,
+      "eval_steps_per_second": 1.446,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.01789468884992e+16,
+  "total_flos": 1.052684203327488e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null