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:e1170f3fa1896e7d4ebf2f945caa9865d4e2c7cf6c41cd2db87a09b6674ca7c4
+oid sha256:35e6d08e728c53d723a8ab3e110d36c840c433f18d2a9b62149a4d47e68ee84f
 size 34456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b20ec3ee215bdbb19290103b8995c90ddd4f62dfcd6955b6f53739bc4724db7
+oid sha256:f1dde0f8e53382780988a883e210916c9ed6f1e2a277c56638d445d2be85943b
 size 73222

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec4a050e84f2386a3ffcdc3fce95dcf3731233db1b9ab90aa550c0a97724aea0
+oid sha256:50ddff5f59a501c6bc33abfbda2a7a3ecca6037689918567f821342e10a25f02
 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": 0.014116318464144552,
+  "epoch": 0.028232636928289104,
   "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": 270.322,
       "eval_steps_per_second": 33.802,
       "step": 25
+    },
+    {
+      "epoch": 0.014680971202710334,
+      "grad_norm": 2.2867512598168105e-05,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 46.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.015245623941276116,
+      "grad_norm": 4.6477565774694085e-05,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 46.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.015810276679841896,
+      "grad_norm": 3.423292946536094e-05,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 46.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.01637492941840768,
+      "grad_norm": 3.5890931030735373e-05,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 46.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.01693958215697346,
+      "grad_norm": 4.4407599489204586e-05,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 46.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.017504234895539244,
+      "grad_norm": 3.465132976998575e-05,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 46.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.018068887634105024,
+      "grad_norm": 4.70224731543567e-05,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 46.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.018633540372670808,
+      "grad_norm": 3.505837594275363e-05,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 46.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.019198193111236588,
+      "grad_norm": 3.5714987461688e-05,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 46.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.019762845849802372,
+      "grad_norm": 5.084039003122598e-05,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 46.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.020327498588368152,
+      "grad_norm": 4.46678459411487e-05,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 46.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.020892151326933936,
+      "grad_norm": 6.067987851565704e-05,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 46.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.021456804065499716,
+      "grad_norm": 3.688631841214374e-05,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 46.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.0220214568040655,
+      "grad_norm": 6.034424222889356e-05,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 46.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.02258610954263128,
+      "grad_norm": 4.5887103624409065e-05,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 46.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.023150762281197064,
+      "grad_norm": 4.306920163799077e-05,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 46.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.023715415019762844,
+      "grad_norm": 3.5082059184787795e-05,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 46.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.024280067758328628,
+      "grad_norm": 4.288729542167857e-05,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 46.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.024844720496894408,
+      "grad_norm": 0.0001078369386959821,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 46.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.025409373235460192,
+      "grad_norm": 7.061719225021079e-05,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 46.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.025974025974025976,
+      "grad_norm": 7.406086660921574e-05,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 46.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.026538678712591756,
+      "grad_norm": 0.00016675041115377098,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 46.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.02710333145115754,
+      "grad_norm": 7.549115980509669e-05,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 46.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.02766798418972332,
+      "grad_norm": 7.31956897652708e-05,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 46.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.028232636928289104,
+      "grad_norm": 0.0001534127222839743,
+      "learning_rate": 0.0,
+      "loss": 46.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.028232636928289104,
+      "eval_loss": 11.5,
+      "eval_runtime": 10.9467,
+      "eval_samples_per_second": 272.503,
+      "eval_steps_per_second": 34.074,
+      "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": 7094960848896.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null