Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b7873364f3410f4af99da464d511f21aef75807900703dae421d1fb12077e9
+oid sha256:d126b2cc12f1984d3d84c1f722101ed21bd3a7802cd896fc5a4add73401547ba
 size 47724600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5461573286fe4da3531012e694d534afe7ac250fe59618ce3c053b97de07955
+oid sha256:8b6b1e5615193bca02e8c22c94e811c4c282693ce461ab1de9566646d2b14e90
 size 25331516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da3329a9a938e0a70d74db80282f79c37243b0daed5fdeaa4d0a706888969746
+oid sha256:b4fa36fc2c7b6f6446672275992d497a7520d4fd55470671d747f810101b39e8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.8055723905563354,
   "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0016332530317259401,
+  "epoch": 0.0032665060634518802,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 3.729,
       "eval_steps_per_second": 1.864,
       "step": 10
+    },
+    {
+      "epoch": 0.001796578334898534,
+      "grad_norm": 18.369661331176758,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 16.7498,
+      "step": 11
+    },
+    {
+      "epoch": 0.0019599036380711283,
+      "grad_norm": 141.58885192871094,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 14.3132,
+      "step": 12
+    },
+    {
+      "epoch": 0.0021232289412437223,
+      "grad_norm": 21.435638427734375,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 17.8755,
+      "step": 13
+    },
+    {
+      "epoch": 0.0022865542444163163,
+      "grad_norm": 32.77855682373047,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 14.8908,
+      "step": 14
+    },
+    {
+      "epoch": 0.0024498795475889103,
+      "grad_norm": 13.740817070007324,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 12.916,
+      "step": 15
+    },
+    {
+      "epoch": 0.0024498795475889103,
+      "eval_loss": 1.8550177812576294,
+      "eval_runtime": 685.077,
+      "eval_samples_per_second": 3.763,
+      "eval_steps_per_second": 1.882,
+      "step": 15
+    },
+    {
+      "epoch": 0.0026132048507615043,
+      "grad_norm": 17.10791778564453,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 16.5775,
+      "step": 16
+    },
+    {
+      "epoch": 0.0027765301539340983,
+      "grad_norm": 24.963502883911133,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 11.7159,
+      "step": 17
+    },
+    {
+      "epoch": 0.0029398554571066922,
+      "grad_norm": 15.869377136230469,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 13.8917,
+      "step": 18
+    },
+    {
+      "epoch": 0.0031031807602792862,
+      "grad_norm": 71.64442443847656,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 16.4648,
+      "step": 19
+    },
+    {
+      "epoch": 0.0032665060634518802,
+      "grad_norm": 15.940417289733887,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 11.6998,
+      "step": 20
+    },
+    {
+      "epoch": 0.0032665060634518802,
+      "eval_loss": 1.8210992813110352,
+      "eval_runtime": 667.8863,
+      "eval_samples_per_second": 3.86,
+      "eval_steps_per_second": 1.93,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -115,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -124,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1065847263068160.0,
+  "total_flos": 2167222768238592.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null