Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72ae699a2fab588657f77f0c4ebb179a058cd312961cc320b0fda5843e682095
+oid sha256:be29528f71ba43ac07d12c9b108e8ed89a5b1624e8813b55f6fd169fa936c7da
 size 47724600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9f80c522e817642ee7859b5cc8096dd2dd08c8c2d0438b0c7d8c55a3deb98c5
+oid sha256:2a26d856b99478b33ebd9e1dcac017f63aacf10ac6d79dc872fa31d4eb1635fa
 size 25331516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36076598392afcf6f77d42a8cec151c6d4a952eeb4e794abf60d43794b231081
+oid sha256:19e933800afb0fd34bba88daa8a5cbb343b0ec6491c064b79d293b1dd3f0cd8d
 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": 1.115118145942688,
   "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0014316392269148174,
+  "epoch": 0.002863278453829635,
   "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": 6.589,
       "eval_steps_per_second": 3.294,
       "step": 10
+    },
+    {
+      "epoch": 0.0015748031496062992,
+      "grad_norm": 13.856171607971191,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 15.7511,
+      "step": 11
+    },
+    {
+      "epoch": 0.001717967072297781,
+      "grad_norm": 12.846494674682617,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 12.6877,
+      "step": 12
+    },
+    {
+      "epoch": 0.0018611309949892628,
+      "grad_norm": 18.605619430541992,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 10.9035,
+      "step": 13
+    },
+    {
+      "epoch": 0.0020042949176807445,
+      "grad_norm": 16.605167388916016,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 17.4268,
+      "step": 14
+    },
+    {
+      "epoch": 0.0021474588403722263,
+      "grad_norm": 9.639287948608398,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 9.6034,
+      "step": 15
+    },
+    {
+      "epoch": 0.0021474588403722263,
+      "eval_loss": 1.1374800205230713,
+      "eval_runtime": 445.0599,
+      "eval_samples_per_second": 6.61,
+      "eval_steps_per_second": 3.305,
+      "step": 15
+    },
+    {
+      "epoch": 0.002290622763063708,
+      "grad_norm": 14.398244857788086,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.8691,
+      "step": 16
+    },
+    {
+      "epoch": 0.00243378668575519,
+      "grad_norm": 12.246084213256836,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 9.336,
+      "step": 17
+    },
+    {
+      "epoch": 0.0025769506084466712,
+      "grad_norm": 11.735007286071777,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 11.1932,
+      "step": 18
+    },
+    {
+      "epoch": 0.002720114531138153,
+      "grad_norm": 9.10404109954834,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 10.207,
+      "step": 19
+    },
+    {
+      "epoch": 0.002863278453829635,
+      "grad_norm": 12.01398754119873,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 11.9392,
+      "step": 20
+    },
+    {
+      "epoch": 0.002863278453829635,
+      "eval_loss": 1.1486986875534058,
+      "eval_runtime": 449.1578,
+      "eval_samples_per_second": 6.55,
+      "eval_steps_per_second": 3.275,
+      "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": 1367837320937472.0,
+  "total_flos": 2753438762926080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null