Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e408bc190a9673e8ef47ea156a69a548facc4232b8a3a64aede83859170f212
+oid sha256:4e4fa93ba026f24dd7441a824c695d7df8b386e353560a82684d41c4f0ccb67f
 size 332316480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2df00d780924862a637e48ffd60be3177c20b3102960109a2e2cc65b17a22d2a
+oid sha256:f2a87ce9c4e183a0005ae44abb5adea4d5c1f07deea5d24db98ce366a3dcf194
 size 169158276

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:748680862c97abcd5a57b1e60cef9082d9a22be5c48011dace8358d6adb3806c
+oid sha256:d01d0530a896c1669c524e1bb54cb02a86378f308d3332754a7bfd082390ef33
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0db0205cf37887636e31665ab1051856b2efe4ed0485b1a8cad32db1f6dfbb
+oid sha256:1173c3cbf86b725051d7e94252382f4f9be9dc9f6afe0d4b01afed08d5bf2028
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.426518440246582,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.028873917228103944,
+  "best_metric": 2.425506353378296,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.03208213025344883,
   "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": 26.42,
       "eval_steps_per_second": 6.606,
       "step": 450
+    },
+    {
+      "epoch": 0.029515559833172923,
+      "grad_norm": 1.2081670761108398,
+      "learning_rate": 3.9513070142914725e-06,
+      "loss": 2.4222,
+      "step": 460
+    },
+    {
+      "epoch": 0.0301572024382419,
+      "grad_norm": 1.6027675867080688,
+      "learning_rate": 2.2289447251518195e-06,
+      "loss": 2.4569,
+      "step": 470
+    },
+    {
+      "epoch": 0.030798845043310877,
+      "grad_norm": 2.0222573280334473,
+      "learning_rate": 9.92656988359823e-07,
+      "loss": 2.4387,
+      "step": 480
+    },
+    {
+      "epoch": 0.03144048764837985,
+      "grad_norm": 2.331239700317383,
+      "learning_rate": 2.4846687349793185e-07,
+      "loss": 2.4296,
+      "step": 490
+    },
+    {
+      "epoch": 0.03208213025344883,
+      "grad_norm": 3.7559499740600586,
+      "learning_rate": 0.0,
+      "loss": 2.5162,
+      "step": 500
+    },
+    {
+      "epoch": 0.03208213025344883,
+      "eval_loss": 2.425506353378296,
+      "eval_runtime": 248.6079,
+      "eval_samples_per_second": 26.399,
+      "eval_steps_per_second": 6.601,
+      "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": 2.569081761615053e+16,
+  "total_flos": 2.8513699793731584e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null