Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:544ec3c81baa0939e589bd5c9db1c331a7848cb0fa27183c956f3d50b902b0e7
+oid sha256:5cbc7a49709e9542b20fff8a8f59756c28115101e94fb4b8bd2ec2fde6b8e564
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d9c5bd6359a5cc032069d9d32f9c7ae1d8fd2a15719e117e8b1bd584af27f06
+oid sha256:5ed7b26d7e96385d1af34bcc7e0bf79e5a76779452b1836915858d6897ebdf39
 size 111412820

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b38c318cc0bbed882a1d1a6a0e872b3052845a17efc867d6760318c2b7f41d9
+oid sha256:eb4a2f681cf5e977b9bfcb6e4dd4cbb7858b14001ef3a7b3c46244d4d03bf8cb
 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": 1.085567831993103,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.29397354238118567,
+  "best_metric": 1.0833667516708374,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.32663726931242854,
   "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": 18.854,
       "eval_steps_per_second": 4.717,
       "step": 450
+    },
+    {
+      "epoch": 0.30050628776743427,
+      "grad_norm": 0.19558390974998474,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 0.89,
+      "step": 460
+    },
+    {
+      "epoch": 0.30703903315368286,
+      "grad_norm": 0.3003573715686798,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 0.9225,
+      "step": 470
+    },
+    {
+      "epoch": 0.3135717785399314,
+      "grad_norm": 0.584018886089325,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 1.0287,
+      "step": 480
+    },
+    {
+      "epoch": 0.32010452392618,
+      "grad_norm": 0.8156113624572754,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 1.0906,
+      "step": 490
+    },
+    {
+      "epoch": 0.32663726931242854,
+      "grad_norm": 2.664822816848755,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 1.5452,
+      "step": 500
+    },
+    {
+      "epoch": 0.32663726931242854,
+      "eval_loss": 1.0833667516708374,
+      "eval_runtime": 136.7852,
+      "eval_samples_per_second": 18.847,
+      "eval_steps_per_second": 4.715,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -430,7 +473,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.9220372617088205e+17,
+  "total_flos": 4.356406596473979e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null