Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15b573fcd60d1aa809d4dec3ce1f1d637d08914a00346cfe658bce64f7af0cbd
+oid sha256:66a12bb2083fe3e4071f4aeea1dd2969a464653144af305c28e914631854287d
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fba58a756a546466aae43c16acdbe4b160bdbb50807f816f835cf69cd018d20d
+oid sha256:b7bf5cd3a36172a5988b2e7dfe0155c3e6245117d95b3301ed62401b68427a24
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c708afc9328576d184f0c43e0ecb742e075685c032d9fcd6d43852f28faedca
+oid sha256:cee8e84e28165d7f799e3ca6bb8d8c99a917144fb3dd996803826f2c5bb0c056
 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": 11.887412071228027,
   "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.36496350364963503,
+  "epoch": 0.40551500405515006,
   "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": 75.239,
       "eval_steps_per_second": 18.846,
       "step": 450
+    },
+    {
+      "epoch": 0.37307380373073806,
+      "grad_norm": 0.07813820987939835,
+      "learning_rate": 3.912568710229791e-06,
+      "loss": 11.8972,
+      "step": 460
+    },
+    {
+      "epoch": 0.38118410381184104,
+      "grad_norm": 0.1135927066206932,
+      "learning_rate": 2.2070923258856255e-06,
+      "loss": 11.8932,
+      "step": 470
+    },
+    {
+      "epoch": 0.38929440389294406,
+      "grad_norm": 0.1418009102344513,
+      "learning_rate": 9.829250571013935e-07,
+      "loss": 11.8895,
+      "step": 480
+    },
+    {
+      "epoch": 0.39740470397404704,
+      "grad_norm": 0.07481211423873901,
+      "learning_rate": 2.4603092375775605e-07,
+      "loss": 11.89,
+      "step": 490
+    },
+    {
+      "epoch": 0.40551500405515006,
+      "grad_norm": 0.1311364620923996,
+      "learning_rate": 0.0,
+      "loss": 11.8847,
+      "step": 500
+    },
+    {
+      "epoch": 0.40551500405515006,
+      "eval_loss": 11.887540817260742,
+      "eval_runtime": 6.8924,
+      "eval_samples_per_second": 75.3,
+      "eval_steps_per_second": 18.861,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "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": 283524956160.0,
+  "total_flos": 314860339200.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null