Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cf2d746cf9c1bcb2d13ea94c2632bccb5f2b274e91f8cac38e63024aae99092
+oid sha256:14fad88eaff3f9e0c2b07260912cdc45c644bf5e4d95a34cb03df39e87f900f4
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30cf4209b1ecb2af9a25148698df44405d1d3663d9c64fbc4517055affd85545
+oid sha256:6210a6ec10ebc2458aa9ffa49429f2af3dd7b19351ec74512b739af0e8579f01
 size 51418452

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18c7bf7a082fa3558d497f2e3ffae21e2ac8e74eeecff79cda5124ee33566210
+oid sha256:8f28831b96af77035c2ded7be2a068154d942395539af092e0feeb6dcde701bc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f0f789b56065211b8c0b1a5e2a97dd0b5b08a816bbbe288fb6f9c677282af9
+oid sha256:5b782a524e5b57eb023365370accae538ac5e68454bafa53a6dd8b2c51cead56
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7452362179756165,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.529567519858782,
+  "best_metric": 0.7421861290931702,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.5884083553986467,
   "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": 22.053,
       "eval_steps_per_second": 5.513,
       "step": 450
+    },
+    {
+      "epoch": 0.5413356869667549,
+      "grad_norm": 0.7531328201293945,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 5.4884,
+      "step": 460
+    },
+    {
+      "epoch": 0.5531038540747278,
+      "grad_norm": 0.7240074872970581,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 4.6025,
+      "step": 470
+    },
+    {
+      "epoch": 0.5648720211827007,
+      "grad_norm": 1.1110539436340332,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 2.8274,
+      "step": 480
+    },
+    {
+      "epoch": 0.5766401882906738,
+      "grad_norm": 1.0983327627182007,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 1.2374,
+      "step": 490
+    },
+    {
+      "epoch": 0.5884083553986467,
+      "grad_norm": 1.2942715883255005,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 1.221,
+      "step": 500
+    },
+    {
+      "epoch": 0.5884083553986467,
+      "eval_loss": 0.7421861290931702,
+      "eval_runtime": 64.9523,
+      "eval_samples_per_second": 22.047,
+      "eval_steps_per_second": 5.512,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -430,7 +473,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.030240531264307e+17,
+  "total_flos": 3.3691853688039014e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null