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:fc6b1f112c7d5c2a6062dedfa06d50e867284bcea11b4d78694d64b760610273
+oid sha256:2effdf9b8d485f5ac991e7909825151191feb311529300ddef56ec988d2b0eaa
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33743c7dc351e949c4a02c988cd1f00083ba10e628bb76d8abce297ba03195b5
+oid sha256:bcb2fbbdcabbfc16daa7dfb4e039a22fa4b42d59acf0e7fef80fce8b916031d5
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18e324aaaf374a495578455ed9405b7036f7c54a54cba362625bd233bfcd2b91
+oid sha256:677416775b136845b2ca673add0476771c4c9eda8ec3b17f0abe82dbba5b2714
 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": 0.9256044030189514,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06180469715698393,
+  "epoch": 0.12360939431396786,
   "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": 13.799,
       "eval_steps_per_second": 6.94,
       "step": 25
+    },
+    {
+      "epoch": 0.06427688504326329,
+      "grad_norm": 2.2261664867401123,
+      "learning_rate": 0.0001,
+      "loss": 0.6891,
+      "step": 26
+    },
+    {
+      "epoch": 0.06674907292954264,
+      "grad_norm": 1.6850603818893433,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.5721,
+      "step": 27
+    },
+    {
+      "epoch": 0.069221260815822,
+      "grad_norm": 1.8727993965148926,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.6303,
+      "step": 28
+    },
+    {
+      "epoch": 0.07169344870210136,
+      "grad_norm": 2.063399314880371,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.6771,
+      "step": 29
+    },
+    {
+      "epoch": 0.07416563658838071,
+      "grad_norm": 2.0754222869873047,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.6502,
+      "step": 30
+    },
+    {
+      "epoch": 0.07663782447466007,
+      "grad_norm": 2.234769821166992,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.6757,
+      "step": 31
+    },
+    {
+      "epoch": 0.07911001236093942,
+      "grad_norm": 3.158531427383423,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.5525,
+      "step": 32
+    },
+    {
+      "epoch": 0.0815822002472188,
+      "grad_norm": 2.121997117996216,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.7501,
+      "step": 33
+    },
+    {
+      "epoch": 0.08405438813349815,
+      "grad_norm": 1.9423466920852661,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.5491,
+      "step": 34
+    },
+    {
+      "epoch": 0.0865265760197775,
+      "grad_norm": 1.9268449544906616,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.5777,
+      "step": 35
+    },
+    {
+      "epoch": 0.08899876390605686,
+      "grad_norm": 2.129122734069824,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.6474,
+      "step": 36
+    },
+    {
+      "epoch": 0.09147095179233622,
+      "grad_norm": 2.023771286010742,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.6191,
+      "step": 37
+    },
+    {
+      "epoch": 0.09394313967861558,
+      "grad_norm": 2.6497044563293457,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.6296,
+      "step": 38
+    },
+    {
+      "epoch": 0.09641532756489493,
+      "grad_norm": 3.2890775203704834,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.5254,
+      "step": 39
+    },
+    {
+      "epoch": 0.09888751545117429,
+      "grad_norm": 2.1858644485473633,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.6739,
+      "step": 40
+    },
+    {
+      "epoch": 0.10135970333745364,
+      "grad_norm": 3.5748488903045654,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.7215,
+      "step": 41
+    },
+    {
+      "epoch": 0.103831891223733,
+      "grad_norm": 2.7620849609375,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.6759,
+      "step": 42
+    },
+    {
+      "epoch": 0.10630407911001236,
+      "grad_norm": 2.5980374813079834,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.7247,
+      "step": 43
+    },
+    {
+      "epoch": 0.10877626699629171,
+      "grad_norm": 2.363985061645508,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.704,
+      "step": 44
+    },
+    {
+      "epoch": 0.11124845488257108,
+      "grad_norm": 3.290933609008789,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.7793,
+      "step": 45
+    },
+    {
+      "epoch": 0.11372064276885044,
+      "grad_norm": 7.270810127258301,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.92,
+      "step": 46
+    },
+    {
+      "epoch": 0.1161928306551298,
+      "grad_norm": 7.295011043548584,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.7803,
+      "step": 47
+    },
+    {
+      "epoch": 0.11866501854140915,
+      "grad_norm": 9.162553787231445,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.8926,
+      "step": 48
+    },
+    {
+      "epoch": 0.1211372064276885,
+      "grad_norm": 7.822823524475098,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.9028,
+      "step": 49
+    },
+    {
+      "epoch": 0.12360939431396786,
+      "grad_norm": 13.31362533569336,
+      "learning_rate": 0.0,
+      "loss": 1.5714,
+      "step": 50
+    },
+    {
+      "epoch": 0.12360939431396786,
+      "eval_loss": 1.020422101020813,
+      "eval_runtime": 12.3847,
+      "eval_samples_per_second": 13.807,
+      "eval_steps_per_second": 6.944,
+      "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