Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95242ee5a4640342ba6725c9447e1225b255be13af9bf4e75c4cf177493e09c4
+oid sha256:eef5d577fa270ac45c4ae1836c04e0b5941e07fa9bad3d925b9c1b55b4345b62
 size 2269195160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4a49ba6e6235503e71ad17d675f89b53fcd208fc98336bc4ba998629443cb78
+oid sha256:d3918eb538ba25d432e89a0eb34ef7d73bf9e47f653f9dc271701ac399d192d1
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:865ce51008d7a83b34996e6d27c77f865e6f16681ebbc319aefe04ef3f1e1cab
+oid sha256:38ee6c95372ce4cb3d8136f58cece038ecbd986fc5848b8fd3f3ba533ae3ed81
 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": 0.0007504465156768277,
+  "epoch": 0.0015008930313536555,
   "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": 2.984,
       "eval_steps_per_second": 1.492,
       "step": 25
+    },
+    {
+      "epoch": 0.0007804643763039008,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.0008104822369309739,
+      "grad_norm": 11.411437034606934,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.4422,
+      "step": 27
+    },
+    {
+      "epoch": 0.000840500097558047,
+      "grad_norm": 0.0016927358228713274,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.0001,
+      "step": 28
+    },
+    {
+      "epoch": 0.0008705179581851201,
+      "grad_norm": 0.3806565999984741,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.0083,
+      "step": 29
+    },
+    {
+      "epoch": 0.0009005358188121932,
+      "grad_norm": 2.338160753250122,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.0228,
+      "step": 30
+    },
+    {
+      "epoch": 0.0009305536794392663,
+      "grad_norm": 3.414599895477295,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.0331,
+      "step": 31
+    },
+    {
+      "epoch": 0.0009605715400663394,
+      "grad_norm": 0.022703867405653,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0003,
+      "step": 32
+    },
+    {
+      "epoch": 0.0009905894006934125,
+      "grad_norm": 0.0,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.0010206072613204856,
+      "grad_norm": 0.0,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.0010506251219475587,
+      "grad_norm": 0.0,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.0010806429825746318,
+      "grad_norm": 0.19225087761878967,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.0021,
+      "step": 36
+    },
+    {
+      "epoch": 0.001110660843201705,
+      "grad_norm": 0.0,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.001140678703828778,
+      "grad_norm": 3.7654895782470703,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0465,
+      "step": 38
+    },
+    {
+      "epoch": 0.0011706965644558511,
+      "grad_norm": 11.871513366699219,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.2006,
+      "step": 39
+    },
+    {
+      "epoch": 0.0012007144250829242,
+      "grad_norm": 1.8782795667648315,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.0129,
+      "step": 40
+    },
+    {
+      "epoch": 0.0012307322857099976,
+      "grad_norm": 10.00529670715332,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.5964,
+      "step": 41
+    },
+    {
+      "epoch": 0.0012607501463370707,
+      "grad_norm": 0.6463675498962402,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.0065,
+      "step": 42
+    },
+    {
+      "epoch": 0.0012907680069641438,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.0013207858675912169,
+      "grad_norm": 0.0,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.00135080372821829,
+      "grad_norm": 0.0,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.001380821588845363,
+      "grad_norm": 0.0,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.0014108394494724362,
+      "grad_norm": 0.0,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.0014408573100995093,
+      "grad_norm": 0.0,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.0014708751707265824,
+      "grad_norm": 0.0,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.0015008930313536555,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.0015008930313536555,
+      "eval_loss": NaN,
+      "eval_runtime": 4703.3313,
+      "eval_samples_per_second": 2.982,
+      "eval_steps_per_second": 1.491,
+      "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": 3.746532815378842e+16,
+  "total_flos": 7.455971246447002e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null