Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:322e4b4ab218ed9826dab774f3ac52057e47c6d79efcad7591afdf78512e6d25
+oid sha256:da197a7ca9c9b39665459f9d6eee72b31950a0722038cf2ecd3b39fc77e52705
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ea58b196173dae06101680ad3497db2a11c2c448b1dfc5f5af8885059ff069a
+oid sha256:ec6d55c039c3d9066c7e45953b695ea88b5511f0a34465ca6329854398a085b6
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e635b9f00660a29ee53707109db999c5b735cf86540794d5fbc23678811636ee
+oid sha256:0f2972dc0a554cc4f245654263bcb104bf57c588a6fe212f549fce377a1cf5a2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3012fb121cd84e6e41f718fd33de9e34ed33145ada7b055f7e25e49408431d
+oid sha256:71a96715f430c2eb0d6104363f54769b2c1bdb005671dc81f0d67833a84ba743
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0022566579282283783,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.018126158060098284,
+  "best_metric": 0.0022082594223320484,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.020140175622331426,
   "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": 16.471,
       "eval_steps_per_second": 4.119,
       "step": 450
+    },
+    {
+      "epoch": 0.018528961572544914,
+      "grad_norm": 0.007461088243871927,
+      "learning_rate": 4.22247514272324e-06,
+      "loss": 0.0006,
+      "step": 460
+    },
+    {
+      "epoch": 0.01893176508499154,
+      "grad_norm": 0.14012055099010468,
+      "learning_rate": 2.38191152001518e-06,
+      "loss": 0.0031,
+      "step": 470
+    },
+    {
+      "epoch": 0.01933456859743817,
+      "grad_norm": 0.002362759318202734,
+      "learning_rate": 1.0607805071688306e-06,
+      "loss": 0.0033,
+      "step": 480
+    },
+    {
+      "epoch": 0.0197373721098848,
+      "grad_norm": 0.050466276705265045,
+      "learning_rate": 2.655185216791625e-07,
+      "loss": 0.0005,
+      "step": 490
+    },
+    {
+      "epoch": 0.020140175622331426,
+      "grad_norm": 0.0015239582862704992,
+      "learning_rate": 0.0,
+      "loss": 0.0026,
+      "step": 500
+    },
+    {
+      "epoch": 0.020140175622331426,
+      "eval_loss": 0.0022082594223320484,
+      "eval_runtime": 634.7,
+      "eval_samples_per_second": 16.471,
+      "eval_steps_per_second": 4.118,
+      "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": 8.504245300179763e+16,
+  "total_flos": 9.447066286895923e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null