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:f4b019bc2c60a1a117b7764af1468f4a26966993d26e11b24715645e6e8bfd38
+oid sha256:23062520a12d5e1e00eddfc67dc8e0cc7e9ecbed9d3fd44280cbfb4ef049f700
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:783ea7b92cdbce3da4492609631c00fcecbc5693dbff363f5876fa5942b74c5c
+oid sha256:90117a9401eb1308758e8bc0871dbe30fae2be413099f29b1caa961e81d1b86b
 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 sha256:3ae0a5f636e3b7efad4ad765d67a451cd40f8f2e24e01c5d42929e454a337257
+oid sha256:4f23fa0ef01cbb776456cad40209cd1c0c6a02d9fdf8c0632982552f2f542168
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0729554891586304,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.31424581005586594,
+  "best_metric": 1.0723166465759277,
+  "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": 11.654,
       "eval_steps_per_second": 2.918,
       "step": 450
+    },
+    {
+      "epoch": 0.32122905027932963,
+      "grad_norm": 0.3964717388153076,
+      "learning_rate": 4.067521926476516e-06,
+      "loss": 0.8386,
+      "step": 460
+    },
+    {
+      "epoch": 0.32821229050279327,
+      "grad_norm": 0.3847760558128357,
+      "learning_rate": 2.294501922950403e-06,
+      "loss": 0.7781,
+      "step": 470
+    },
+    {
+      "epoch": 0.33519553072625696,
+      "grad_norm": 0.4073781669139862,
+      "learning_rate": 1.021852782135112e-06,
+      "loss": 0.752,
+      "step": 480
+    },
+    {
+      "epoch": 0.34217877094972066,
+      "grad_norm": 0.47937291860580444,
+      "learning_rate": 2.5577472271845927e-07,
+      "loss": 0.8182,
+      "step": 490
+    },
+    {
+      "epoch": 0.34916201117318435,
+      "grad_norm": 1.1718170642852783,
+      "learning_rate": 0.0,
+      "loss": 2.1401,
+      "step": 500
+    },
+    {
+      "epoch": 0.34916201117318435,
+      "eval_loss": 1.0723166465759277,
+      "eval_runtime": 52.1413,
+      "eval_samples_per_second": 11.565,
+      "eval_steps_per_second": 2.896,
+      "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