Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f147fd2d4daf4632bb9fdf29d617019084b5284c568613dd597773fdff4901da
+oid sha256:8b2819f9465a207fe085343291204ae6ca6df162ffd7be3a508d5b992e265ee0
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcbdba99b34caf538cdd330838bef22d617e9f47539acdd8e8bcb08ea40ff46e
+oid sha256:5764596ead973bae41f6c9076ece431ef1539335f26bd48cd45722b904666c0d
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf4edccebbc69cd5a7d67b6fb128ea8405dd99d3ea114f7f7b9f353128a6c14
+oid sha256:a77e38119dfe5541b23a95a42296803c9e2f140a52fe01cd605f5bd7305ce6c6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.122968316078186,
   "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.10217113665389528,
+  "epoch": 0.1532567049808429,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 3.697,
       "eval_steps_per_second": 0.941,
       "step": 20
+    },
+    {
+      "epoch": 0.10727969348659004,
+      "grad_norm": 0.13435852527618408,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.968,
+      "step": 21
+    },
+    {
+      "epoch": 0.12260536398467432,
+      "grad_norm": 0.1441923826932907,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.1093,
+      "step": 24
+    },
+    {
+      "epoch": 0.1277139208173691,
+      "eval_loss": 1.1210970878601074,
+      "eval_runtime": 41.9413,
+      "eval_samples_per_second": 3.934,
+      "eval_steps_per_second": 1.001,
+      "step": 25
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.1330297738313675,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.9727,
+      "step": 27
+    },
+    {
+      "epoch": 0.1532567049808429,
+      "grad_norm": 0.16263821721076965,
+      "learning_rate": 0.0,
+      "loss": 1.1974,
+      "step": 30
+    },
+    {
+      "epoch": 0.1532567049808429,
+      "eval_loss": 1.126773476600647,
+      "eval_runtime": 41.973,
+      "eval_samples_per_second": 3.931,
+      "eval_steps_per_second": 1.001,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,7 +147,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.715327779995648e+16,
+  "total_flos": 2.368785981898752e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null