Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0d9e7c6cc0b09c24f21c0e65c470639048c0e7c7d83ceb5351797f378cc9f7
+oid sha256:a38185a60a1504ce268afd0ab41fb778a2eed967eb142ded6d9a12efb1aeae4c
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efbed2a83d794625186cfe55a85a3e3992794a85bc09b2ff54fdeef500d6b974
+oid sha256:5b1a83bc57d62812dece30b606a42e83392a104f052ebd545dddc03821e3633e
 size 509177556

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cc463bc6a591b06ca2cb3f06961a217df71f23c357566ef37a962e37c0b1714
+oid sha256:e7a05634e3e275423c3e9d79988215306eb482758bcb550a37efcfece02000d7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c579f5f648f371ddcf6d84448bace40e1d46168d2f7b5fae9b6105a9c79d201
+oid sha256:2c9718e38efb2d48aaa61791c4fc8b4a7f9cfd08f355dda43ae7de9f2cb195d8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.407829225063324,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.10792660990526443,
+  "best_metric": 0.4035276770591736,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.1199184554502938,
   "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": 10.068,
       "eval_steps_per_second": 2.517,
       "step": 450
+    },
+    {
+      "epoch": 0.1103249790142703,
+      "grad_norm": 1.040457844734192,
+      "learning_rate": 4.125629382569038e-06,
+      "loss": 0.4633,
+      "step": 460
+    },
+    {
+      "epoch": 0.11272334812327617,
+      "grad_norm": 0.9297060370445251,
+      "learning_rate": 2.327280521849694e-06,
+      "loss": 0.4546,
+      "step": 470
+    },
+    {
+      "epoch": 0.11512171723228205,
+      "grad_norm": 1.2702484130859375,
+      "learning_rate": 1.0364506790227565e-06,
+      "loss": 0.3864,
+      "step": 480
+    },
+    {
+      "epoch": 0.11752008634128792,
+      "grad_norm": 2.7662715911865234,
+      "learning_rate": 2.5942864732872295e-07,
+      "loss": 1.3183,
+      "step": 490
+    },
+    {
+      "epoch": 0.1199184554502938,
+      "grad_norm": 2.1641576290130615,
+      "learning_rate": 0.0,
+      "loss": 1.0251,
+      "step": 500
+    },
+    {
+      "epoch": 0.1199184554502938,
+      "eval_loss": 0.4035276770591736,
+      "eval_runtime": 174.4062,
+      "eval_samples_per_second": 10.068,
+      "eval_steps_per_second": 2.517,
+      "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": 1.44902656622592e+17,
+  "total_flos": 1.6100295180288e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null