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:e31e7d76a9b2780f3e1ceea686944be8fe6a551a6ffafb45b3d9f15bacc71ab7
+oid sha256:dfd8204117bdd69bcc3184cdffe05dca387d19dc06c5167fc23ec89f925b684b
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa070af73b8bd0a34d4d834d8602c8c8d71c638b4984263d2638b10564aa027e
+oid sha256:325cf199abb966ac0e070e8e77f9d049e71daf18abcac15318347ad2b7ef8924
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a5c6aa2884b0b3ab3eea503865660bbaa2e49a678110098485e78de4b178340
+oid sha256:c519cdd57aa1b544ccb5c1eb065ecb6e7fe3b7757c3883210ecc3ef70431233e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56d2b9cd8b76db862d8f36c96267d64ff69a21d07ce7f6eb4a0887810e44a8eb
+oid sha256:043092824777602976966449c2a2a96527a878ad10507a3b4d0f461ea2b8d14e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.13189151883125305,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.4893964110929853,
+  "epoch": 0.5437737901033171,
   "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": 17.206,
       "eval_steps_per_second": 4.301,
       "step": 450
+    },
+    {
+      "epoch": 0.5002718868950516,
+      "grad_norm": 0.4370393455028534,
+      "learning_rate": 3.912568710229791e-06,
+      "loss": 0.1239,
+      "step": 460
+    },
+    {
+      "epoch": 0.511147362697118,
+      "grad_norm": 0.5538854002952576,
+      "learning_rate": 2.2070923258856255e-06,
+      "loss": 0.0938,
+      "step": 470
+    },
+    {
+      "epoch": 0.5220228384991843,
+      "grad_norm": 1.1034691333770752,
+      "learning_rate": 9.829250571013935e-07,
+      "loss": 0.1054,
+      "step": 480
+    },
+    {
+      "epoch": 0.5328983143012507,
+      "grad_norm": 1.444915533065796,
+      "learning_rate": 2.4603092375775605e-07,
+      "loss": 0.1426,
+      "step": 490
+    },
+    {
+      "epoch": 0.5437737901033171,
+      "grad_norm": 3.916834831237793,
+      "learning_rate": 0.0,
+      "loss": 0.2352,
+      "step": 500
+    },
+    {
+      "epoch": 0.5437737901033171,
+      "eval_loss": 0.13204382359981537,
+      "eval_runtime": 22.7776,
+      "eval_samples_per_second": 17.034,
+      "eval_steps_per_second": 4.259,
+      "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": 8.104765506453504e+16,
+  "total_flos": 9.002332739076096e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null