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:f673175238ee1eb071892c5a3d9407fc2604fab40fdecd6028a24ec3acfe3cc4
+oid sha256:5d3f7fa966296efeef40be0a2690bee07cfd42c6ef9fae0ce6e5d79bf2b2a3d4
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:872b3653e5582b54a191d0c3aa20b01cb7c3760d8d37c7980f43da22f864f3a7
+oid sha256:a6efe47c644041ddde8767308d37ad11faf6234b871bc1e17d1e902e229e3e8c
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d3ec42086752f8599b93092daaf5186d63dc1f99fb4939cb628060589a5e48b
+oid sha256:9ab43582069a5f502d6313af2ea603268eb8a5461c6171e24d0488f793e4b167
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f47f6fd97a856343780028ccfaed8e5641a3a980e3597ef52b4019307ae01e5
+oid sha256:6a2dfa9dcdb3fc187f28da300ef3fe13e5352f326a4d02f24bd99cfc1f6355cc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b69eb670c3cb2e8990bd44fdbb9d85b0dfe744c6edeb960f8aca64da872d92bb
+oid sha256:55aa7457fe16eba2e2195248c13b63a89c64da497a183a5427725abd2a6993f5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9b4d415aecd3bccace0aa6492df85716dadf0f18230661a1f683f94f8b89436
+oid sha256:3f95664b3c0cb11ccfe12cfbcef006f4db96821b67097f19e3f0c67e0ac73444
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd8b969ce6a3f06e5c06504065f43d471f4f8e360f2eb91a5068e5fed0b0d9dc
+oid sha256:344fc18df9c84f214bc47e69d1bbde70d66cf3ec6caeac9cd529dfb5814c4b9a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.0,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.0739506995336443,
+  "epoch": 1.6069287141905395,
   "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": 31.832,
       "eval_steps_per_second": 8.276,
       "step": 50
+    },
+    {
+      "epoch": 1.09526982011992,
+      "grad_norm": 1.4509647927596347e-09,
+      "learning_rate": 5.7231268960295e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 1.116588940706196,
+      "grad_norm": 1.2944647576063062e-09,
+      "learning_rate": 5.574402751448614e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 1.1379080612924717,
+      "grad_norm": 1.404435456819897e-09,
+      "learning_rate": 5.425597248551387e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 1.1592271818787476,
+      "grad_norm": 1.8385311051360986e-09,
+      "learning_rate": 5.2768731039705e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 1.1805463024650233,
+      "grad_norm": 2.188858427842888e-09,
+      "learning_rate": 5.128392945374505e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 1.201865423051299,
+      "grad_norm": 2.473932170232729e-09,
+      "learning_rate": 4.980319133636863e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 1.223184543637575,
+      "grad_norm": 2.957512679202523e-09,
+      "learning_rate": 4.83281358529671e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 1.2445036642238507,
+      "grad_norm": 4.090505267839717e-09,
+      "learning_rate": 4.686037595505507e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 1.2658227848101267,
+      "grad_norm": 0.028839975595474243,
+      "learning_rate": 4.54015166165314e-05,
+      "loss": 0.0001,
+      "step": 59
+    },
+    {
+      "epoch": 1.2871419053964024,
+      "grad_norm": 3.436689599567444e-09,
+      "learning_rate": 4.395315307866405e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 1.308461025982678,
+      "grad_norm": 3.736273512799926e-09,
+      "learning_rate": 4.2516869105717004e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 1.329780146568954,
+      "grad_norm": 4.177445500630483e-09,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 1.3510992671552298,
+      "grad_norm": 4.131688324804372e-09,
+      "learning_rate": 3.968680715012606e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 1.3724183877415057,
+      "grad_norm": 4.780627449463282e-09,
+      "learning_rate": 3.829612379868006e-05,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 1.3937375083277814,
+      "grad_norm": 5.516650247727739e-09,
+      "learning_rate": 3.692370589061639e-05,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 1.4150566289140574,
+      "grad_norm": 6.456162715551272e-09,
+      "learning_rate": 3.557105414476782e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 1.436375749500333,
+      "grad_norm": 6.741116553854454e-09,
+      "learning_rate": 3.423964766595906e-05,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 1.457694870086609,
+      "grad_norm": 7.689346936956554e-09,
+      "learning_rate": 3.293094232762715e-05,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 1.4790139906728847,
+      "grad_norm": 7.789759060017332e-09,
+      "learning_rate": 3.164636917984534e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 1.5003331112591605,
+      "grad_norm": 0.00078203045995906,
+      "learning_rate": 3.0387332884490805e-05,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 1.5216522318454364,
+      "grad_norm": 5.782083700722751e-09,
+      "learning_rate": 2.9155210179267546e-05,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 1.5429713524317124,
+      "grad_norm": 6.204281532973255e-09,
+      "learning_rate": 2.7951348372263875e-05,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 1.564290473017988,
+      "grad_norm": 7.148269087764447e-09,
+      "learning_rate": 2.677706386869083e-05,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 1.5856095936042638,
+      "grad_norm": 6.854582679238774e-09,
+      "learning_rate": 2.5633640731412412e-05,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 1.6069287141905395,
+      "grad_norm": 7.026794257569691e-09,
+      "learning_rate": 2.4522329276841663e-05,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 1.6069287141905395,
+      "eval_loss": 0.0,
+      "eval_runtime": 1.5715,
+      "eval_samples_per_second": 31.817,
+      "eval_steps_per_second": 8.272,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,7 +578,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -404,12 +587,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.024966926541783e+17,
+  "total_flos": 9.031389058160394e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null