Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802f5ec4ef5b5e2308993257def8f00762bc1b26499fb2039a2d92242e039162
+oid sha256:6103b793da4daa0f6b8b3044c3fe92ad1287cf0740f230f390a9ee01144ce9fc
 size 34456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf62384c309ec39ededc152a1c8b7b5449408f7ccc782ed98b21bf43536bb731
+oid sha256:a776016bd019cb68daca0905079c65f9393fa241f431dc90bf1b3b8f824034be
 size 73222

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6153d0669f2facd86c6d761b00823f43129c08fa123aa09f0d804b16277e0362
+oid sha256:bb731434e3a241ca3588fc4eb107238b7ab6141d781e5dae076447d4b76ad583
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0050558673340411545,
+  "epoch": 0.010111734668082309,
   "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": 302.166,
       "eval_steps_per_second": 37.771,
       "step": 25
+    },
+    {
+      "epoch": 0.005258102027402801,
+      "grad_norm": 0.00018002571596298367,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 46.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.005460336720764447,
+      "grad_norm": 0.0002462012926116586,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 46.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.005662571414126094,
+      "grad_norm": 0.00029739696765318513,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 46.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.005864806107487739,
+      "grad_norm": 0.0003964843926951289,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 46.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.006067040800849386,
+      "grad_norm": 0.0004054371966049075,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 46.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.006269275494211032,
+      "grad_norm": 0.00019075242744293064,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 46.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.0064715101875726785,
+      "grad_norm": 0.0004364342021290213,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 46.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.006673744880934324,
+      "grad_norm": 0.0003642778901848942,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 46.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.00687597957429597,
+      "grad_norm": 0.00036662680213339627,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 46.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.007078214267657617,
+      "grad_norm": 0.0002541069407016039,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 46.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.0072804489610192626,
+      "grad_norm": 0.0003552269481588155,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 46.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.007482683654380909,
+      "grad_norm": 0.0002922409912571311,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 46.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.007684918347742555,
+      "grad_norm": 0.000310244329739362,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 46.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.0078871530411042,
+      "grad_norm": 0.0001724491303320974,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 46.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.008089387734465847,
+      "grad_norm": 7.884677324909717e-05,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 46.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.008291622427827494,
+      "grad_norm": 7.308423664653674e-05,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 46.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.00849385712118914,
+      "grad_norm": 0.00012783825513906777,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 46.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.008696091814550786,
+      "grad_norm": 0.00034225135459564626,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 46.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.008898326507912432,
+      "grad_norm": 0.0005108854384161532,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 46.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.009100561201274079,
+      "grad_norm": 0.0004680280981119722,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 46.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.009302795894635724,
+      "grad_norm": 0.0004146777791902423,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 46.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.00950503058799737,
+      "grad_norm": 0.0003186096728313714,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 46.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.009707265281359017,
+      "grad_norm": 0.0003894997644238174,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 46.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.009909499974720664,
+      "grad_norm": 0.00041468587005510926,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 46.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.010111734668082309,
+      "grad_norm": 0.0004269829369150102,
+      "learning_rate": 0.0,
+      "loss": 46.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.010111734668082309,
+      "eval_loss": 11.5,
+      "eval_runtime": 27.5269,
+      "eval_samples_per_second": 302.54,
+      "eval_steps_per_second": 37.818,
+      "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": 4019807846400.0,
+  "total_flos": 6371395436544.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null