Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8abb9249bd133bc3af9fe522a990c44d839f9cd6d94dca0f33af0120516330e
+oid sha256:75fe246123afaa4e61ff09e077c81cdcfbce5fb2c7e59d7b75732b6f0315f800
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b78706f901803099042ef77b1381f78e73e21eed686b03cbfa54a25aaa71f909
+oid sha256:8cce6f59fa7f16d56d8f0469e71dd0b41ea79371537940cf3e9f49bff4aaa8e0
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68c46241dbd3d99f0378633dfb4810640e66f03e1679e20cd9efdbafe1809fbd
+oid sha256:91dba13b0528571b7fa9c5f0550128e1d0f8989120275e9ec731c4187b74ab8f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0f69d9f90a0d5ce8ac61f1f875459a761943b0c4252d8391ecd4046776d8753
+oid sha256:cb0db0205cf37887636e31665ab1051856b2efe4ed0485b1a8cad32db1f6dfbb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7006033062934875,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.02858776443682104,
+  "best_metric": 0.6950636506080627,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.03216123499142367,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 9.93,
       "eval_steps_per_second": 2.483,
       "step": 400
+    },
+    {
+      "epoch": 0.029302458547741567,
+      "grad_norm": 0.5984488129615784,
+      "learning_rate": 1.9480266573755372e-05,
+      "loss": 1.308,
+      "step": 410
+    },
+    {
+      "epoch": 0.030017152658662092,
+      "grad_norm": 0.6418554782867432,
+      "learning_rate": 1.5499094192044554e-05,
+      "loss": 1.2611,
+      "step": 420
+    },
+    {
+      "epoch": 0.03073184676958262,
+      "grad_norm": 0.7937597632408142,
+      "learning_rate": 1.1939345528389446e-05,
+      "loss": 1.4339,
+      "step": 430
+    },
+    {
+      "epoch": 0.031446540880503145,
+      "grad_norm": 1.0111737251281738,
+      "learning_rate": 8.818363320454701e-06,
+      "loss": 1.4374,
+      "step": 440
+    },
+    {
+      "epoch": 0.03216123499142367,
+      "grad_norm": 1.7831614017486572,
+      "learning_rate": 6.1513526798373514e-06,
+      "loss": 1.5577,
+      "step": 450
+    },
+    {
+      "epoch": 0.03216123499142367,
+      "eval_loss": 0.6950636506080627,
+      "eval_runtime": 593.0731,
+      "eval_samples_per_second": 9.935,
+      "eval_steps_per_second": 2.484,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.330508659163136e+17,
+  "total_flos": 1.496822241558528e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null