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:be8a396ac79da5c6fe9496c8c539cb4b943c0f59bb95f9c0e5397419ef9c3670
+oid sha256:7e8eed084a58403bde1e33e583af0547981a2300766cfc1a676afaf2e983a1d9
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91c945e29e7ba612739f657c6dc7652e88550736cd10e69b0701d46db9261f5b
+oid sha256:52c144f70052b174434702e96eff91f63cecb4b39f7dbfe7c99db7627c5831e5
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcd474099de92dc845d40d5927f170b424592df7fa8ed3e362e00c4d62a05861
+oid sha256:d49593ae7e22d09a07a09f52967b7e9139e11dc8b7b2354bdf8719302bca62c7
 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": 1.0726971626281738,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.31424581005586594,
+  "best_metric": 1.0719058513641357,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.34916201117318435,
   "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": 11.394,
       "eval_steps_per_second": 2.853,
       "step": 450
+    },
+    {
+      "epoch": 0.32122905027932963,
+      "grad_norm": 0.39169561862945557,
+      "learning_rate": 4.0868910785073565e-06,
+      "loss": 0.8389,
+      "step": 460
+    },
+    {
+      "epoch": 0.32821229050279327,
+      "grad_norm": 0.38382428884506226,
+      "learning_rate": 2.3054281225835e-06,
+      "loss": 0.7781,
+      "step": 470
+    },
+    {
+      "epoch": 0.33519553072625696,
+      "grad_norm": 0.4115770161151886,
+      "learning_rate": 1.026718747764327e-06,
+      "loss": 0.7531,
+      "step": 480
+    },
+    {
+      "epoch": 0.34217877094972066,
+      "grad_norm": 0.47876521944999695,
+      "learning_rate": 2.5699269758854715e-07,
+      "loss": 0.8186,
+      "step": 490
+    },
+    {
+      "epoch": 0.34916201117318435,
+      "grad_norm": 1.236006259918213,
+      "learning_rate": 0.0,
+      "loss": 2.1411,
+      "step": 500
+    },
+    {
+      "epoch": 0.34916201117318435,
+      "eval_loss": 1.0719058513641357,
+      "eval_runtime": 52.6183,
+      "eval_samples_per_second": 11.46,
+      "eval_steps_per_second": 2.87,
+      "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": 1.2681469712400384e+17,
+  "total_flos": 1.408558478917632e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null