Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d34827106dd42929d55bb92e4754f1a51a1debab16f6829c86757fdb34704034
+oid sha256:11947fa14753725b5067c536dcca8a8f57c8d274e3c89a826b290c8ac4c6c1d2
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:054c01a291fe45e9663cabd244f4ad63c9fb9d76511c7d17941f7feab1bf926c
+oid sha256:face7d1771049228a48d433f75d0e1774f2f72da44cf6d549b122804bbe3360d
 size 37134740

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:527a19b2cd156d8f5430ede1cef4cd294e554f6adaedbd14fe4b8d674afd12ab
+oid sha256:c839c46404502cef15f9f24c2e5a7b32a0c79f743c5bfaf1cfe3b184511154bb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f03fffc232f1b8a6305d6fa9076c1e1bca28e4d7666df088caa1812431cf9135
+oid sha256:b3488300cc890b0bf0becbfdd6a3cc8770e6656a66feed4ec387a72a2b445721
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.9057368040084839,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.013872832369942197,
+  "epoch": 0.015414258188824663,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 39.261,
       "eval_steps_per_second": 9.817,
       "step": 450
+    },
+    {
+      "epoch": 0.014181117533718689,
+      "grad_norm": 0.26937440037727356,
+      "learning_rate": 3.931937862260632e-06,
+      "loss": 1.8069,
+      "step": 460
+    },
+    {
+      "epoch": 0.014489402697495183,
+      "grad_norm": 0.29797518253326416,
+      "learning_rate": 2.2180185255187225e-06,
+      "loss": 1.8405,
+      "step": 470
+    },
+    {
+      "epoch": 0.014797687861271676,
+      "grad_norm": 0.2863852381706238,
+      "learning_rate": 9.877910227306082e-07,
+      "loss": 1.8969,
+      "step": 480
+    },
+    {
+      "epoch": 0.01510597302504817,
+      "grad_norm": 0.28537192940711975,
+      "learning_rate": 2.472488986278439e-07,
+      "loss": 1.871,
+      "step": 490
+    },
+    {
+      "epoch": 0.015414258188824663,
+      "grad_norm": 0.46400362253189087,
+      "learning_rate": 0.0,
+      "loss": 1.8561,
+      "step": 500
+    },
+    {
+      "epoch": 0.015414258188824663,
+      "eval_loss": 1.9071128368377686,
+      "eval_runtime": 347.3877,
+      "eval_samples_per_second": 39.316,
+      "eval_steps_per_second": 9.831,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.019483934575821e+16,
+  "total_flos": 2.243648652784435e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null