Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57d0e8bf9ccacc822b2d25f076d02efc0f3ed4e90428be6f10aef95760f90737
+oid sha256:638180b215b354adb672f0254f35cc40675b1abada1b4edb9c6454682cc64ad9
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e793e47aeffd3116f3f26b7d30f96e81a1340b699527c8c02de075c1ef8afb5f
+oid sha256:ce9eac54f816e146a36e5a80d35799dbc0a010dc01d217b9e54913c91177203b
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b8545b9f35fce90ba3b7d4932b740367734714927e9f56db82d1f995048af4d
+oid sha256:539d22757fa25fbe9b2a005be7a60121f8bda931d4bf486f25d11e1dc3c8973d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac6ee4c7143f9893927b533c972fc3aa0da9526c7e014b3849d291e400a8521c
+oid sha256:cc8fda128404f5cc7285a078c14dccabc8f3e7d949516ad102b12752c4b2742a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5632148385047913,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.2323180175529169,
+  "best_metric": 0.5627415180206299,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.2581311306143521,
   "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": 11.962,
       "eval_steps_per_second": 2.991,
       "step": 450
+    },
+    {
+      "epoch": 0.23748064016520393,
+      "grad_norm": 0.307348370552063,
+      "learning_rate": 4.144998534599878e-06,
+      "loss": 0.5093,
+      "step": 460
+    },
+    {
+      "epoch": 0.24264326277749096,
+      "grad_norm": 0.30287760496139526,
+      "learning_rate": 2.3382067214827915e-06,
+      "loss": 0.5933,
+      "step": 470
+    },
+    {
+      "epoch": 0.24780588538977802,
+      "grad_norm": 0.3055270314216614,
+      "learning_rate": 1.0413166446519713e-06,
+      "loss": 0.6079,
+      "step": 480
+    },
+    {
+      "epoch": 0.25296850800206505,
+      "grad_norm": 0.30271589756011963,
+      "learning_rate": 2.6064662219881083e-07,
+      "loss": 0.5536,
+      "step": 490
+    },
+    {
+      "epoch": 0.2581311306143521,
+      "grad_norm": 0.6881096363067627,
+      "learning_rate": 0.0,
+      "loss": 0.4496,
+      "step": 500
+    },
+    {
+      "epoch": 0.2581311306143521,
+      "eval_loss": 0.5627415180206299,
+      "eval_runtime": 68.0724,
+      "eval_samples_per_second": 11.987,
+      "eval_steps_per_second": 2.997,
+      "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": 1.17165892042752e+17,
+  "total_flos": 1.30287126183936e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null