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:e8b977e13640462c145593935ebd07d1e1c0cba1d24b7dba2bed4f7ca0163ab5
+oid sha256:fc839a9e8b66adc036d170039415f9e6d6c905b4192b4100c75ad960dcc08ecf
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eba062ed082a143c5cd605be51c039de0c792bb1453038a3c38eaae7ccd9f1d9
+oid sha256:f09cd9c12e6cebc52b7685fae1ebdcee1c6ceefef04c4a2bc0fce57cd8b761ad
 size 1324282

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09b51fd095a0c7ca6c336790baa3824799044fa55a32b278240357fa924a22e4
+oid sha256:c3843a064148c511095fd3523f9fd0e45794e49ae6a191111791271c98e5da20
 size 14308

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": 11.682252883911133,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.08982932428386066,
+  "best_metric": 11.681905746459961,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.09981036031540073,
   "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": 66.675,
       "eval_steps_per_second": 16.685,
       "step": 450
+    },
+    {
+      "epoch": 0.09182553149016869,
+      "grad_norm": 0.10584419965744019,
+      "learning_rate": 4.0868910785073565e-06,
+      "loss": 11.7384,
+      "step": 460
+    },
+    {
+      "epoch": 0.0938217386964767,
+      "grad_norm": 0.08683383464813232,
+      "learning_rate": 2.3054281225835e-06,
+      "loss": 11.7358,
+      "step": 470
+    },
+    {
+      "epoch": 0.09581794590278471,
+      "grad_norm": 0.08547329902648926,
+      "learning_rate": 1.026718747764327e-06,
+      "loss": 11.7267,
+      "step": 480
+    },
+    {
+      "epoch": 0.09781415310909272,
+      "grad_norm": 0.09161391854286194,
+      "learning_rate": 2.5699269758854715e-07,
+      "loss": 11.7112,
+      "step": 490
+    },
+    {
+      "epoch": 0.09981036031540073,
+      "grad_norm": 0.3164777159690857,
+      "learning_rate": 0.0,
+      "loss": 11.5407,
+      "step": 500
+    },
+    {
+      "epoch": 0.09981036031540073,
+      "eval_loss": 11.681905746459961,
+      "eval_runtime": 31.3449,
+      "eval_samples_per_second": 67.316,
+      "eval_steps_per_second": 16.845,
+      "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": 63856533307392.0,
+  "total_flos": 70902333702144.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null