Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b87838ab46e211a9364c206d56dfc2df0cbbbf444ca62e5042fc8dea9acd111
+oid sha256:3121242772bba1bee6f2961b73e21f3021f9bf790691c2a397a7ecfb7a24b122
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ae06ffed850e83e81a647a4b735b7360bbf29bf7798597ba78f2a845de118b7
+oid sha256:b25fd793717e787556f65beeb12fb56afdd644a84be5880c65032b81c7048393
 size 91850618

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ddea9620e5ab305ca70284a15aa87abe524ac823dc5104cc438345f4cfdfc5a
+oid sha256:971e44e13c43914faeff374459b25c51d385962f61817ebc0e218593892c7244
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e959ae44ed59e1d9df727fe405a413d7ba7165046402e1b6aa379cddd545297
+oid sha256:dc6d7a4e5542db8278bbb08501029d28a2952cf2860b91c35fe25fb2510ba81c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8625227808952332,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.1532436574152903,
+  "best_metric": 0.8617475032806396,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.17027073046143368,
   "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": 46.602,
       "eval_steps_per_second": 11.679,
       "step": 450
+    },
+    {
+      "epoch": 0.156649072024519,
+      "grad_norm": 0.7241954207420349,
+      "learning_rate": 4.0868910785073565e-06,
+      "loss": 0.7643,
+      "step": 460
+    },
+    {
+      "epoch": 0.16005448663374766,
+      "grad_norm": 1.0439797639846802,
+      "learning_rate": 2.3054281225835e-06,
+      "loss": 0.7719,
+      "step": 470
+    },
+    {
+      "epoch": 0.16345990124297632,
+      "grad_norm": 1.5047202110290527,
+      "learning_rate": 1.026718747764327e-06,
+      "loss": 0.8146,
+      "step": 480
+    },
+    {
+      "epoch": 0.16686531585220502,
+      "grad_norm": 2.1545448303222656,
+      "learning_rate": 2.5699269758854715e-07,
+      "loss": 1.007,
+      "step": 490
+    },
+    {
+      "epoch": 0.17027073046143368,
+      "grad_norm": 4.2632155418396,
+      "learning_rate": 0.0,
+      "loss": 0.8951,
+      "step": 500
+    },
+    {
+      "epoch": 0.17027073046143368,
+      "eval_loss": 0.8617475032806396,
+      "eval_runtime": 26.8638,
+      "eval_samples_per_second": 46.047,
+      "eval_steps_per_second": 11.54,
+      "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": 1.343796340064256e+16,
+  "total_flos": 1.485182733385728e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null