Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b1149dd9a6283afe62fd6a5435ee2e45e45334cc32625902c52b02e76811a99
+oid sha256:a2ad69abcf582af5963477d3f8275092be215cdd47a2ea582bd60f8c186ad6a6
 size 58680

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:821aeba1618a4c6ea1f02f73ae01dfffb923411fd07e313df87fa264da97423b
+oid sha256:22538b08b14bb81b9c8d2cd359cafd851dfbbb4acb203c99b72e83d7860ffdda
 size 127270

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f9214c7106f65d75a1a0e44277060eea7ca60dc6107b276ad73b95692d7abf5
+oid sha256:a70d32ecc22f55e473cbc8ba8e5688f1822894ad2808843160bb86eb84df3325
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f03fffc232f1b8a6305d6fa9076c1e1bca28e4d7666df088caa1812431cf9135
+oid sha256:b3488300cc890b0bf0becbfdd6a3cc8770e6656a66feed4ec387a72a2b445721
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.30145263671875,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.0126441787605895,
+  "best_metric": 10.301432609558105,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.01404908751176611,
   "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": 248.982,
       "eval_steps_per_second": 62.258,
       "step": 450
+    },
+    {
+      "epoch": 0.012925160510824821,
+      "grad_norm": 0.16703709959983826,
+      "learning_rate": 3.931937862260632e-06,
+      "loss": 20.6069,
+      "step": 460
+    },
+    {
+      "epoch": 0.013206142261060145,
+      "grad_norm": 0.19127300381660461,
+      "learning_rate": 2.2180185255187225e-06,
+      "loss": 20.6087,
+      "step": 470
+    },
+    {
+      "epoch": 0.013487124011295466,
+      "grad_norm": 0.19735532999038696,
+      "learning_rate": 9.877910227306082e-07,
+      "loss": 20.6209,
+      "step": 480
+    },
+    {
+      "epoch": 0.013768105761530789,
+      "grad_norm": 0.1791822463274002,
+      "learning_rate": 2.472488986278439e-07,
+      "loss": 20.5952,
+      "step": 490
+    },
+    {
+      "epoch": 0.01404908751176611,
+      "grad_norm": 0.20496730506420135,
+      "learning_rate": 0.0,
+      "loss": 20.5889,
+      "step": 500
+    },
+    {
+      "epoch": 0.01404908751176611,
+      "eval_loss": 10.301432609558105,
+      "eval_runtime": 60.1498,
+      "eval_samples_per_second": 249.128,
+      "eval_steps_per_second": 62.294,
+      "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": 19336966963200.0,
+  "total_flos": 21494130278400.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null