Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfe2cbf9677fb6aa10f1669a2a99f087378cb1ac9d724b57b5f472df00fff23a
+oid sha256:72772774dd83f1e3f05c69b453d4df59660debc4bc8dd9ef3a9dcc4dabf428f3
 size 9047632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62a3ca6703e728c4266299b7f4a719dc8f0e3ebdfab843a9a60e4181a5f21fe3
+oid sha256:939fc0aa7fb58d52418c782ffc94b029c4571e271359b4d0de9752d13a74ddcf
 size 4628218

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd9e8cf707aa5af47b78871671eda38069f38f45787ed0bbd9ca3e81ded08e0a
+oid sha256:06bfc3389cb4a6d3908bf6bc42b75fdbea0f533a3706e669cf66e968104a2a50
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d63688a697a579ea602c9246c5261e5aa082fc650a107f52a0a175ef1d7c1f
+oid sha256:7b91b1b9f6f06d1788c3dcf4d0729b3ed9c063c44851d2809ea5eccdca91d117
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.432068347930908,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.7874015748031497,
+  "best_metric": 2.386683225631714,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.984251968503937,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 256.306,
       "eval_steps_per_second": 64.675,
       "step": 200
+    },
+    {
+      "epoch": 0.8267716535433071,
+      "grad_norm": 2.2410874366760254,
+      "learning_rate": 2.3527918813016095e-05,
+      "loss": 2.4958,
+      "step": 210
+    },
+    {
+      "epoch": 0.8661417322834646,
+      "grad_norm": 2.906589984893799,
+      "learning_rate": 1.4268294496957278e-05,
+      "loss": 2.3526,
+      "step": 220
+    },
+    {
+      "epoch": 0.905511811023622,
+      "grad_norm": 2.744379758834839,
+      "learning_rate": 7.191707568436117e-06,
+      "loss": 2.3691,
+      "step": 230
+    },
+    {
+      "epoch": 0.9448818897637795,
+      "grad_norm": 3.0293545722961426,
+      "learning_rate": 2.4656541586025275e-06,
+      "loss": 2.3613,
+      "step": 240
+    },
+    {
+      "epoch": 0.984251968503937,
+      "grad_norm": 4.734268665313721,
+      "learning_rate": 2.019954895048029e-07,
+      "loss": 2.1728,
+      "step": 250
+    },
+    {
+      "epoch": 0.984251968503937,
+      "eval_loss": 2.386683225631714,
+      "eval_runtime": 0.3984,
+      "eval_samples_per_second": 268.576,
+      "eval_steps_per_second": 67.771,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 233125576704000.0,
+  "total_flos": 290985659596800.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null