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:ab85fd8c9e83827e2020628051d1186460602715355e54931d17c7e92f724258
+oid sha256:96d9e4b3c61254cfc57e368c6f71823d458e34b3639ddebab4c70aac704e3bc2
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8095e92a64097461a47f9a82a8b00f77310f7e64f30e5cae3564d924f080137c
+oid sha256:6dbcfacfb7e15343bdc5c413df6a75a0c2141d6c32e20fcc5f2cab114acf85fd
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:596120eea124c4b91e435e0bda7c8f9851d8ffa3b83bd733b15a68f36f1e807e
+oid sha256:4d4afce41700577459a3a96f1f7dd39fdc7a825134c7ffea0db76cc1c1c3d163
 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": 0.00499966973438859,
   "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0098015192354815,
+  "epoch": 0.019603038470963,
   "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": 3.081,
       "eval_steps_per_second": 1.54,
       "step": 10
+    },
+    {
+      "epoch": 0.01078167115902965,
+      "grad_norm": 0.06610959768295288,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.0013,
+      "step": 11
+    },
+    {
+      "epoch": 0.0117618230825778,
+      "grad_norm": 0.026695387437939644,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.0005,
+      "step": 12
+    },
+    {
+      "epoch": 0.01274197500612595,
+      "grad_norm": 0.27281925082206726,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0023,
+      "step": 13
+    },
+    {
+      "epoch": 0.0137221269296741,
+      "grad_norm": 0.16124923527240753,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.0007,
+      "step": 14
+    },
+    {
+      "epoch": 0.014702278853222249,
+      "grad_norm": 0.294295072555542,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0025,
+      "step": 15
+    },
+    {
+      "epoch": 0.014702278853222249,
+      "eval_loss": 0.0067756325006484985,
+      "eval_runtime": 140.2529,
+      "eval_samples_per_second": 3.066,
+      "eval_steps_per_second": 1.533,
+      "step": 15
+    },
+    {
+      "epoch": 0.0156824307767704,
+      "grad_norm": 0.03048100881278515,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0002,
+      "step": 16
+    },
+    {
+      "epoch": 0.01666258270031855,
+      "grad_norm": 0.052780840545892715,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.0001,
+      "step": 17
+    },
+    {
+      "epoch": 0.017642734623866698,
+      "grad_norm": 0.0012328748125582933,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.018622886547414848,
+      "grad_norm": 0.0009590290137566626,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.019603038470963,
+      "grad_norm": 0.005971523933112621,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.019603038470963,
+      "eval_loss": 0.0067951129749417305,
+      "eval_runtime": 140.4107,
+      "eval_samples_per_second": 3.062,
+      "eval_steps_per_second": 1.531,
+      "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": 2484418841149440.0,
+  "total_flos": 4968837682298880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null