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:c4b694e97f12ba0d9b80936d6bca813b6ce7af19d72d9a807f8b927879c1e5ce
+oid sha256:d3a5a313afb3fda6452ee104799899de7a9cd8c93891581e47ef1f221be58c2b
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac9f2e903bbf84f3f99839f1d4f0bfde2eed106e8182b31e802c69d07bca5e69
+oid sha256:ec5f73ad12647f34ffee766f8a6207c0c091c573d79793857d6e1c07e1929e15
 size 82461044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97ba33e881ebfe096fa15ecb254e8f1a02b8bcbe89cb30588c4574966da54992
+oid sha256:1ac83c1df159bd712af17d8be240ed3dac742b59e9671e5ea3b9715f7a9aeb5f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30565d7b1986ad1c3966f0f9b850f0ae7d4cfe76be60a78deb1442c25c9c950e
+oid sha256:693af3889e4633c932ce337b10348752049de987b4153b6619512b489850fe7b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.5509848594665527,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.10240072818295597,
+  "best_metric": 2.550354242324829,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.11377858686995107,
   "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": 10.032,
       "eval_steps_per_second": 2.509,
       "step": 450
+    },
+    {
+      "epoch": 0.10467629992035499,
+      "grad_norm": 0.542321503162384,
+      "learning_rate": 4.028783622414835e-06,
+      "loss": 2.6094,
+      "step": 460
+    },
+    {
+      "epoch": 0.10695187165775401,
+      "grad_norm": 0.5314146280288696,
+      "learning_rate": 2.272649523684208e-06,
+      "loss": 2.6186,
+      "step": 470
+    },
+    {
+      "epoch": 0.10922744339515303,
+      "grad_norm": 0.523740828037262,
+      "learning_rate": 1.0121208508766823e-06,
+      "loss": 2.5175,
+      "step": 480
+    },
+    {
+      "epoch": 0.11150301513255205,
+      "grad_norm": 0.53782719373703,
+      "learning_rate": 2.533387729782834e-07,
+      "loss": 2.3776,
+      "step": 490
+    },
+    {
+      "epoch": 0.11377858686995107,
+      "grad_norm": 1.0320826768875122,
+      "learning_rate": 0.0,
+      "loss": 2.5147,
+      "step": 500
+    },
+    {
+      "epoch": 0.11377858686995107,
+      "eval_loss": 2.550354242324829,
+      "eval_runtime": 184.627,
+      "eval_samples_per_second": 10.026,
+      "eval_steps_per_second": 2.508,
+      "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": 1.4819620298529178e+17,
+  "total_flos": 1.6471099211513856e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null