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:f102ef4698d844c875d5184ec21fdef167f3894ab597ca91eb5bfb5b1f373288
+oid sha256:073b880d632e6cdd73a0457b3b4aedf212cd2f5344f1b4e455d2b5165382a541
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b53848587dfe277e48929e52a15d6390d7b8bc10f9b2fb66d77d90c58b235f32
+oid sha256:7469d82f677ff9e4d23cf8bf6fe9850c7ec1a8b3920ff36dd9e92bbe406ce630
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b595a1a30382cad6f3fc5fb34e88c6303ea1b74b49c015e453cf170c4be45bad
+oid sha256:5ca3dcefd2f837582ea005f759a169a4db7b0941472cde6d941ec6012bccc282
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.1002987623214722,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0004880072225068931,
+  "epoch": 0.0009760144450137862,
   "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": 3.578,
       "eval_steps_per_second": 1.789,
       "step": 25
+    },
+    {
+      "epoch": 0.0005075275114071688,
+      "grad_norm": 5.981378078460693,
+      "learning_rate": 0.0001,
+      "loss": 4.6663,
+      "step": 26
+    },
+    {
+      "epoch": 0.0005270478003074446,
+      "grad_norm": 6.813650131225586,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 4.4858,
+      "step": 27
+    },
+    {
+      "epoch": 0.0005465680892077203,
+      "grad_norm": 5.694484710693359,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 3.8496,
+      "step": 28
+    },
+    {
+      "epoch": 0.000566088378107996,
+      "grad_norm": 5.858161449432373,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 4.4739,
+      "step": 29
+    },
+    {
+      "epoch": 0.0005856086670082717,
+      "grad_norm": 6.250691890716553,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 4.0139,
+      "step": 30
+    },
+    {
+      "epoch": 0.0006051289559085474,
+      "grad_norm": 5.8988752365112305,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 4.0186,
+      "step": 31
+    },
+    {
+      "epoch": 0.0006246492448088232,
+      "grad_norm": 6.843201637268066,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 4.3718,
+      "step": 32
+    },
+    {
+      "epoch": 0.0006441695337090989,
+      "grad_norm": 7.384850025177002,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 4.5045,
+      "step": 33
+    },
+    {
+      "epoch": 0.0006636898226093746,
+      "grad_norm": 7.434286594390869,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 4.2881,
+      "step": 34
+    },
+    {
+      "epoch": 0.0006832101115096503,
+      "grad_norm": 7.059499740600586,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 4.4589,
+      "step": 35
+    },
+    {
+      "epoch": 0.0007027304004099261,
+      "grad_norm": 7.253593444824219,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 4.148,
+      "step": 36
+    },
+    {
+      "epoch": 0.0007222506893102018,
+      "grad_norm": 7.907142639160156,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 4.2299,
+      "step": 37
+    },
+    {
+      "epoch": 0.0007417709782104776,
+      "grad_norm": 7.825556755065918,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 4.2046,
+      "step": 38
+    },
+    {
+      "epoch": 0.0007612912671107532,
+      "grad_norm": 7.069599628448486,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 3.8814,
+      "step": 39
+    },
+    {
+      "epoch": 0.000780811556011029,
+      "grad_norm": 7.556497097015381,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 4.1689,
+      "step": 40
+    },
+    {
+      "epoch": 0.0008003318449113047,
+      "grad_norm": 8.259849548339844,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 3.7389,
+      "step": 41
+    },
+    {
+      "epoch": 0.0008198521338115805,
+      "grad_norm": 8.705476760864258,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 4.6672,
+      "step": 42
+    },
+    {
+      "epoch": 0.0008393724227118561,
+      "grad_norm": 7.974400043487549,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 3.6511,
+      "step": 43
+    },
+    {
+      "epoch": 0.0008588927116121318,
+      "grad_norm": 7.9710540771484375,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 3.8957,
+      "step": 44
+    },
+    {
+      "epoch": 0.0008784130005124076,
+      "grad_norm": 9.321637153625488,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 3.827,
+      "step": 45
+    },
+    {
+      "epoch": 0.0008979332894126833,
+      "grad_norm": 9.066277503967285,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 4.1383,
+      "step": 46
+    },
+    {
+      "epoch": 0.0009174535783129591,
+      "grad_norm": 10.388931274414062,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 4.7694,
+      "step": 47
+    },
+    {
+      "epoch": 0.0009369738672132347,
+      "grad_norm": 11.57152271270752,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 4.068,
+      "step": 48
+    },
+    {
+      "epoch": 0.0009564941561135105,
+      "grad_norm": 10.462427139282227,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 4.6273,
+      "step": 49
+    },
+    {
+      "epoch": 0.0009760144450137862,
+      "grad_norm": 12.40966510772705,
+      "learning_rate": 0.0,
+      "loss": 5.1242,
+      "step": 50
+    },
+    {
+      "epoch": 0.0009760144450137862,
+      "eval_loss": 1.1065218448638916,
+      "eval_runtime": 6027.0265,
+      "eval_samples_per_second": 3.579,
+      "eval_steps_per_second": 1.789,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.5508080351379456e+16,
+  "total_flos": 7.066459555076506e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null