Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1673a59aa80734e604ec8a2a909c57c22eeaa9fdb08ddbd65418fe8f1bdc2c63
+oid sha256:86e1fd7a58064dbe8b98981562c633d44378856f69d9cdf17665f4c6cd725ce2
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e168dc348a0189903a82803b34b1e8dee9ee0a5c01fd3c85395db0b7095826
+oid sha256:575516cac8ffdfc386a685b9bc166c8e68de48e1c1c09d7fa35e84d8233b2539
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82a3bf93d0cde0007296f6c1996ef6cc1fdfe6c8c52c3f1ccc292be711797010
+oid sha256:a783cee426f7cdbd93a2b1b7b897b261a793b816a6b2c3688ac92ab1af3ae8cf
 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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6060606060606061,
+  "epoch": 1.2121212121212122,
   "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": 8.052,
       "eval_steps_per_second": 4.026,
       "step": 25
+    },
+    {
+      "epoch": 0.6303030303030303,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.6545454545454545,
+      "grad_norm": 13.499174118041992,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 1.0393,
+      "step": 27
+    },
+    {
+      "epoch": 0.6787878787878788,
+      "grad_norm": 6.368555068969727,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.3086,
+      "step": 28
+    },
+    {
+      "epoch": 0.703030303030303,
+      "grad_norm": 13.0841064453125,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.9051,
+      "step": 29
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 13.383321762084961,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 1.1452,
+      "step": 30
+    },
+    {
+      "epoch": 0.7515151515151515,
+      "grad_norm": 0.0,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.7757575757575758,
+      "grad_norm": 0.0,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 8.7849702835083,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.8124,
+      "step": 33
+    },
+    {
+      "epoch": 0.8242424242424242,
+      "grad_norm": 16.79686737060547,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.5349,
+      "step": 34
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 0.0,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.8727272727272727,
+      "grad_norm": 14.058218002319336,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.8506,
+      "step": 36
+    },
+    {
+      "epoch": 0.896969696969697,
+      "grad_norm": 11.131260871887207,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 1.0009,
+      "step": 37
+    },
+    {
+      "epoch": 0.9212121212121213,
+      "grad_norm": 16.038894653320312,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.6914,
+      "step": 38
+    },
+    {
+      "epoch": 0.9454545454545454,
+      "grad_norm": 15.095179557800293,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.6247,
+      "step": 39
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 11.539749145507812,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.8336,
+      "step": 40
+    },
+    {
+      "epoch": 0.9939393939393939,
+      "grad_norm": 13.128904342651367,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 1.1426,
+      "step": 41
+    },
+    {
+      "epoch": 1.018181818181818,
+      "grad_norm": 10.853378295898438,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 6.4015,
+      "step": 42
+    },
+    {
+      "epoch": 1.0424242424242425,
+      "grad_norm": 9.659259796142578,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.4573,
+      "step": 43
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.0,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 1.1151515151515152,
+      "grad_norm": 4.810526371002197,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 1.6521,
+      "step": 46
+    },
+    {
+      "epoch": 1.1393939393939394,
+      "grad_norm": 0.0,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 1.1636363636363636,
+      "grad_norm": 13.763459205627441,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.7686,
+      "step": 48
+    },
+    {
+      "epoch": 1.187878787878788,
+      "grad_norm": 10.437994003295898,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.7031,
+      "step": 49
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 7.7976579666137695,
+      "learning_rate": 0.0,
+      "loss": 0.4385,
+      "step": 50
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "eval_loss": NaN,
+      "eval_runtime": 2.2391,
+      "eval_samples_per_second": 8.039,
+      "eval_steps_per_second": 4.019,
+      "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": 6531344184115200.0,
+  "total_flos": 1.30626883682304e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null