Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19d28c2dd2fde93a119ba64d22f4ec55235b9c2081eb70e680f3f272dd1d7833
+oid sha256:4055eef871415ac14d295f29521207063c3707fa165a63ab5d54b2b70d2dcb8e
 size 4731640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1c5ad0c63716da679e34f14e2699fee656df61e43dffcbe69ce34b4107de369
+oid sha256:db02afab52ffb35bdc7c4db5db9405ab93fa65e93f5ae56b504ddae610189e77
 size 2505722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa0d1881f14943199f0fdddc429f486d93b6cbc0202ab758802d8022a31a2d62
+oid sha256:3e7a5ecabca45bfb641df7b779adfba6edbeb53593782226104d39636c8b819b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 3.094447374343872,
   "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.052321778940483975,
+  "epoch": 0.06540222367560497,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 30.811,
       "eval_steps_per_second": 15.501,
       "step": 20
+    },
+    {
+      "epoch": 0.05493786788750817,
+      "grad_norm": 348.24462890625,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 12.0762,
+      "step": 21
+    },
+    {
+      "epoch": 0.05755395683453238,
+      "grad_norm": 337.1204833984375,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 12.4519,
+      "step": 22
+    },
+    {
+      "epoch": 0.060170045781556575,
+      "grad_norm": 433.0714416503906,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 13.5538,
+      "step": 23
+    },
+    {
+      "epoch": 0.06278613472858077,
+      "grad_norm": 328.62322998046875,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 12.2419,
+      "step": 24
+    },
+    {
+      "epoch": 0.06540222367560497,
+      "grad_norm": 420.27734375,
+      "learning_rate": 0.0,
+      "loss": 11.0996,
+      "step": 25
+    },
+    {
+      "epoch": 0.06540222367560497,
+      "eval_loss": 3.1058640480041504,
+      "eval_runtime": 5.3551,
+      "eval_samples_per_second": 30.065,
+      "eval_steps_per_second": 15.126,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -201,7 +244,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 73650803834880.0,
+  "total_flos": 93597896540160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null