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:d4707bf8702d2133ba1aca6b974a93acf5f29ff7f05c5ac125e5ccbea5f38e27
+oid sha256:36ba02a350e967436dfaf92527f5a24639795bbeae59e9dae336ed2c8064f307
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20bdd0883adbcda2562412511c3f9ffffd9f55e86b63d880ebf0163b313be846
+oid sha256:247cc39e41461764fc68f8a793d6d29cd944907b3deb83437d125133d059b9fa
 size 418094

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:554cb9097b11ef7c9c06b04f0aef03158f22f9ae295e3f92eb5e7713b2751306
+oid sha256:7a48bec28384c3e333ccf1b3e7ed393daa25f74ae54e0f7b04bda8d516f161fa
 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": 6.646402835845947,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.010208479843923686,
+  "best_metric": 6.645919322967529,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.011342755382137429,
   "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": 378.179,
       "eval_steps_per_second": 94.56,
       "step": 450
+    },
+    {
+      "epoch": 0.010435334951566434,
+      "grad_norm": 0.2037954330444336,
+      "learning_rate": 4.22247514272324e-06,
+      "loss": 6.8519,
+      "step": 460
+    },
+    {
+      "epoch": 0.010662190059209183,
+      "grad_norm": 0.2961488366127014,
+      "learning_rate": 2.38191152001518e-06,
+      "loss": 6.8155,
+      "step": 470
+    },
+    {
+      "epoch": 0.010889045166851932,
+      "grad_norm": 0.538969874382019,
+      "learning_rate": 1.0607805071688306e-06,
+      "loss": 6.5301,
+      "step": 480
+    },
+    {
+      "epoch": 0.01111590027449468,
+      "grad_norm": 0.36002838611602783,
+      "learning_rate": 2.655185216791625e-07,
+      "loss": 6.6116,
+      "step": 490
+    },
+    {
+      "epoch": 0.011342755382137429,
+      "grad_norm": 0.7732294201850891,
+      "learning_rate": 0.0,
+      "loss": 6.4791,
+      "step": 500
+    },
+    {
+      "epoch": 0.011342755382137429,
+      "eval_loss": 6.645919322967529,
+      "eval_runtime": 48.3918,
+      "eval_samples_per_second": 383.557,
+      "eval_steps_per_second": 95.905,
+      "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": 1817733402624.0,
+  "total_flos": 2021973110784.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null