Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ae269a91547154375b3fc58ab1fd0eb8cc0784550c8cfb628a9b4ddf25350b3
+oid sha256:f88680748b7bd964a795d97731a14ba11632f4d08259c2ef318463363c3097bb
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:778992d43e1892dd0cad28babc9b5363417d5c3ad4bdc6316ccfa7043b93a906
+oid sha256:c03fb1108b9df4e3935f628f3cadb31f75f2c86104a73d90eccc79f506121127
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4a0d4560ed0f7a94e1dd4c7c15bf6bee0552022392775a46cf04f39c4f926a2
+oid sha256:cdf1dfdef095e920a6111c0af8961845861411f1290bafdec71880ce8cf16384
 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": 0.6681258082389832,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05151983513652756,
+  "epoch": 0.10303967027305512,
   "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": 13.807,
       "eval_steps_per_second": 6.937,
       "step": 25
+    },
+    {
+      "epoch": 0.05358062854198867,
+      "grad_norm": 15.42173957824707,
+      "learning_rate": 0.0001,
+      "loss": 0.4441,
+      "step": 26
+    },
+    {
+      "epoch": 0.05564142194744977,
+      "grad_norm": 1.8112399578094482,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.0552,
+      "step": 27
+    },
+    {
+      "epoch": 0.05770221535291087,
+      "grad_norm": 0.7334427833557129,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.0083,
+      "step": 28
+    },
+    {
+      "epoch": 0.059763008758371976,
+      "grad_norm": 9.213266372680664,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.2998,
+      "step": 29
+    },
+    {
+      "epoch": 0.061823802163833076,
+      "grad_norm": 3.4060914516448975,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.0579,
+      "step": 30
+    },
+    {
+      "epoch": 0.06388459556929418,
+      "grad_norm": 0.07256096601486206,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.001,
+      "step": 31
+    },
+    {
+      "epoch": 0.06594538897475528,
+      "grad_norm": 0.05080750212073326,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0008,
+      "step": 32
+    },
+    {
+      "epoch": 0.06800618238021638,
+      "grad_norm": 4.680781841278076,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.0752,
+      "step": 33
+    },
+    {
+      "epoch": 0.07006697578567748,
+      "grad_norm": 1.9387208223342896,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0059,
+      "step": 34
+    },
+    {
+      "epoch": 0.07212776919113859,
+      "grad_norm": 0.2535548806190491,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.002,
+      "step": 35
+    },
+    {
+      "epoch": 0.07418856259659969,
+      "grad_norm": 0.1797764152288437,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.0015,
+      "step": 36
+    },
+    {
+      "epoch": 0.0762493560020608,
+      "grad_norm": 0.1363029181957245,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.0014,
+      "step": 37
+    },
+    {
+      "epoch": 0.0783101494075219,
+      "grad_norm": 0.08102747797966003,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0009,
+      "step": 38
+    },
+    {
+      "epoch": 0.080370942812983,
+      "grad_norm": 0.08120626956224442,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.0009,
+      "step": 39
+    },
+    {
+      "epoch": 0.0824317362184441,
+      "grad_norm": 0.06320202350616455,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.0007,
+      "step": 40
+    },
+    {
+      "epoch": 0.0844925296239052,
+      "grad_norm": 0.06635958701372147,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.0007,
+      "step": 41
+    },
+    {
+      "epoch": 0.0865533230293663,
+      "grad_norm": 0.04807131737470627,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.0006,
+      "step": 42
+    },
+    {
+      "epoch": 0.0886141164348274,
+      "grad_norm": 0.06771901249885559,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.0007,
+      "step": 43
+    },
+    {
+      "epoch": 0.09067490984028852,
+      "grad_norm": 0.046476930379867554,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0005,
+      "step": 44
+    },
+    {
+      "epoch": 0.09273570324574962,
+      "grad_norm": 13.438279151916504,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0353,
+      "step": 45
+    },
+    {
+      "epoch": 0.09479649665121072,
+      "grad_norm": 20.22861099243164,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.05,
+      "step": 46
+    },
+    {
+      "epoch": 0.09685729005667182,
+      "grad_norm": 26.98645782470703,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.0715,
+      "step": 47
+    },
+    {
+      "epoch": 0.09891808346213292,
+      "grad_norm": 26.829103469848633,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.0614,
+      "step": 48
+    },
+    {
+      "epoch": 0.10097887686759402,
+      "grad_norm": 35.39474868774414,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.0936,
+      "step": 49
+    },
+    {
+      "epoch": 0.10303967027305512,
+      "grad_norm": 19.681806564331055,
+      "learning_rate": 0.0,
+      "loss": 0.041,
+      "step": 50
+    },
+    {
+      "epoch": 0.10303967027305512,
+      "eval_loss": 1.1938879489898682,
+      "eval_runtime": 14.8623,
+      "eval_samples_per_second": 13.793,
+      "eval_steps_per_second": 6.93,
+      "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": 1802385752064000.0,
+  "total_flos": 3604771504128000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null