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:bea408bee92d56e6e10dd66b1022433f1a020ce3c8f307d3d39b037aa96a1c4e
+oid sha256:156f79d9d2a088dacaa1528b970cdc9812b62dd113d4f3c0fee58d8ec80586e0
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b412f3b1951d17ac8ae88b5821599182640f8e978fea0494972d8483947de2b1
+oid sha256:1e379ca099be724d74a63fbc1cf6b3102b5e5587da085cf79691c84a7d4383eb
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbc745c9c1c891b528c4bc43acca5683d7c2b2f8d02a3b49911a8e0a63034a9b
+oid sha256:0057f81d6fb413d17eb7fd106b72832ac1dd0fe44d33531d88d739c1a7f21ccc
 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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.011025358324145534,
+  "epoch": 0.022050716648291068,
   "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": 7.114,
       "eval_steps_per_second": 3.557,
       "step": 10
+    },
+    {
+      "epoch": 0.012127894156560088,
+      "grad_norm": 1.2060033082962036,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.7359,
+      "step": 11
+    },
+    {
+      "epoch": 0.013230429988974642,
+      "grad_norm": 1.1315321922302246,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.5669,
+      "step": 12
+    },
+    {
+      "epoch": 0.014332965821389196,
+      "grad_norm": 1.1741143465042114,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.606,
+      "step": 13
+    },
+    {
+      "epoch": 0.015435501653803748,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.3572,
+      "step": 14
+    },
+    {
+      "epoch": 0.016538037486218304,
+      "grad_norm": 0.6324079036712646,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.4557,
+      "step": 15
+    },
+    {
+      "epoch": 0.016538037486218304,
+      "eval_loss": NaN,
+      "eval_runtime": 53.6318,
+      "eval_samples_per_second": 7.123,
+      "eval_steps_per_second": 3.561,
+      "step": 15
+    },
+    {
+      "epoch": 0.017640573318632856,
+      "grad_norm": 0.648357093334198,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.5305,
+      "step": 16
+    },
+    {
+      "epoch": 0.018743109151047408,
+      "grad_norm": 0.5638170838356018,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.386,
+      "step": 17
+    },
+    {
+      "epoch": 0.019845644983461964,
+      "grad_norm": 0.7388977408409119,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.3905,
+      "step": 18
+    },
+    {
+      "epoch": 0.020948180815876516,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.1132,
+      "step": 19
+    },
+    {
+      "epoch": 0.022050716648291068,
+      "grad_norm": 0.5183130502700806,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.3396,
+      "step": 20
+    },
+    {
+      "epoch": 0.022050716648291068,
+      "eval_loss": NaN,
+      "eval_runtime": 53.1373,
+      "eval_samples_per_second": 7.189,
+      "eval_steps_per_second": 3.594,
+      "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": 1391446091366400.0,
+  "total_flos": 2782892182732800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null