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:a59db3e4434ebdb2c055739fbfc497d4193984e94417e1ef056752ba70a184f8
+oid sha256:79ccc0918a040ee5d5f9428efddab81ddb07c4563f28f6f5aea364b08caadf38
 size 100690184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:993e389f1929284472f2ab7229af0004eae130c9ad6011c0583f2498ca66eb93
+oid sha256:910362c0337ce8ea6619d37d6bc18e317171653032707461545e52b5dcb93d25
 size 51345082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3e77348693ab93014486e58318571069128adf081adfe643fc83e768d147faf
+oid sha256:c8e6e9bb919f94c48a5b66d0e0fe837587212fca84bac551dc783e7eb4c6bbb2
 size 14308

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": 0.8030063509941101,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.21500238891543239,
+  "best_metric": 0.8017581105232239,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.23889154323936931,
   "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": 74.874,
       "eval_steps_per_second": 18.761,
       "step": 450
+    },
+    {
+      "epoch": 0.21978021978021978,
+      "grad_norm": 7.895440578460693,
+      "learning_rate": 3.912568710229791e-06,
+      "loss": 1.0214,
+      "step": 460
+    },
+    {
+      "epoch": 0.22455805064500717,
+      "grad_norm": 7.843092918395996,
+      "learning_rate": 2.2070923258856255e-06,
+      "loss": 1.2448,
+      "step": 470
+    },
+    {
+      "epoch": 0.22933588150979456,
+      "grad_norm": 7.881674766540527,
+      "learning_rate": 9.829250571013935e-07,
+      "loss": 1.603,
+      "step": 480
+    },
+    {
+      "epoch": 0.23411371237458195,
+      "grad_norm": 11.434523582458496,
+      "learning_rate": 2.4603092375775605e-07,
+      "loss": 1.8552,
+      "step": 490
+    },
+    {
+      "epoch": 0.23889154323936931,
+      "grad_norm": 9.036798477172852,
+      "learning_rate": 0.0,
+      "loss": 2.0245,
+      "step": 500
+    },
+    {
+      "epoch": 0.23889154323936931,
+      "eval_loss": 0.8017581105232239,
+      "eval_runtime": 11.7902,
+      "eval_samples_per_second": 74.808,
+      "eval_steps_per_second": 18.744,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4191310105804800.0,
+  "total_flos": 4657011228672000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null